To see the other types of publications on this topic, follow the link: F1-score.
Journal articles on the topic 'F1-score'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'F1-score.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Sushkov, A. I., M. V. Popov, V. S. Rudakov, D. S. Svetlakova, A. N. Pashkov, A. S. Lukianchikova, M. Muktarzhan, et al. "Comparative analysis of models predicting the risks of early poor outcome of deceased-donor liver transplantation: a retrospective single-center study." Transplantologiya. The Russian Journal of Transplantation 15, no. 3 (September 14, 2023): 312–33. http://dx.doi.org/10.23873/2074-0506-2023-15-3-312-333.
Full textAbstract:
Rationale. The risk of early graft loss determines the specifics and plan of anesthesiological assistance, intensive therapy, and overall the feasibility of liver transplantation. Various prognostic models and criteria have become widespread abroad; however, Russian transplant centers have not yet validated them.Objective. To evaluate the applicability and accuracy of the most common models predicting the risks of early adverse outcomes in liver transplantation from deceased donors.Material and methods. A retrospective single-center study included data on 131 liver transplantations from deceased donors performed between May 2012 and January 2023. For each observation, DRI, SOFT, D-MELD, BAR, MEAF, L-GrAFT, and EASE indices were calculated, and compliance with an early allograft dysfunction criteria was verified. Depending on the possibility of calculating the indicators and their values relative to known cutoff points, the study groups were formed, and 1-, 3-, 6-, and 12-month graft survival rates were calculated. The forecast was compared with the actual outcomes, and sensitivity, specificity, F1-score, and C-index were calculated.Results. When assessing the risk of 1- and 3-month graft loss, models using only preoperative parameters demonstrated relatively low prognostic significance: DRI (F1-score: 0.16; C-index: 0.54), SOFT (F1-score: 0.42; C-index: 0.64), D-MELD (F1-score: 0.30; C-index: 0.58), and BAR (F1-score: 0.23; C-index: 0.57). Postoperative indices of MEAF (F1- score: 0.44; C-index: 0.74) and L-GrAFT (F1-score: 0.32; C-index: 0.65) were applicable in 96%, those of ABC (F1-score: 0.29; C-index: 0.71) in 91%, and EASE (F1-score: 0.26; C-index: 0.80) in 89% of cases. The relative risk of 30-days graft loss in case of EAD was 5.2 (95% CI: 3.4-8.1; p<0.0001), F1-score: 0.64, and C-index: 0.84. Using locally established cutoff values for SOFT (11 points) and L-GrAFT (-0.87) scores increased their prognostic significance: F1-score: 0.46 and 0.63, C-index: 0.69 and 0.87, respectively.Conclusion. The analyzed models can be used to assess the risks of early liver graft loss; however, their prognostic significance is not high. Developing a new model in a multicenter Russian study, as well as searching for new objective methods to assess the state of the donor liver are promising directions for future work.
2
Nealma, Samuyus, and Nurkholis. "FORMULASI DAN EVALUASI FISIK KRIM KOSMETIK DENGAN VARIASI EKSTRAK KAYU SECANG (Caesalpinia sappan) DAN BEESWAX SUMBAWA." Jurnal TAMBORA 4, no. 2 (July 23, 2020): 8–15. http://dx.doi.org/10.36761/jt.v4i2.634.
Full textAbstract:
In this research, secang wood will be used as a cream using Sumbawa beeswax base. The purpose of this study was to obtain the best cream formulation with secang wood extract and beeswax. Cream formula is based on the concentration of secang extract 0.5-2.5 grams and beeswax 0.2-4 grams in 20 grams of the preparation. Determination of physical evaluation will be carried out several tests, namely organoleptic test, pH, adhesion, dispersal power and protective power. The results showed that all three formulas, Formulation 1 (F1) and F3 were homogeneous, while F2 was not homogeneous. In pH testing, all formulations 1,2 and 3 have an average pH of 6. And in organoleptic testing, F3 shows a score of 3.9 in form and is the highest compared to the two other formulations, F1 has a score of 2.8, F2 scores 2.2. Whereas in color organoleptic, the highest score is F3 with a score of 3.8, F1 score 2.8 and F3 score 2.2. And in odorless organoleptics, F1 has the highest score of 3.6, F3 score of 3.3 and F2 score of 2.7. In the scatter power test, F1 has an average value of 11.8, F2 with a value of 53.52 and F3 with a value of 11.68. F1, F2 and F3 adhesion tests have values ??of 2.3 seconds, 2.3 and 3.67, respectively. And in KOH protection testing all formulas show changes.
3
Mangalik, Yanche Kurniawan, Triando Hamonangan Saragih, Dodon Turianto Nugrahadi, Muliadi Muliadi, and Muhammad Itqan Mazdadi. "Analisis Seleksi Fitur Binary PSO Pada Klasifikasi Kanker Berdasarkan Data Microarray Menggunakan DWKNN." Jurnal Informatika Polinema 9, no. 2 (February 27, 2023): 133–42. http://dx.doi.org/10.33795/jip.v9i2.1128.
Full textAbstract:
Salah satu penyakit mematikan penyebab kematian terbesar secara global adalah kanker. Kematian akibat kanker dapat diredam melalui deteksi dini terhadap kanker dengan memanfaatkan teknologi microarray. Namun teknologi ini memiliki kekurangan, yaitu jumlah gen (fitur) yang terlalu banyak. Kekurangan tersebut dapat diatasi dengan melakukan seleksi fitur terhadap data microarray. Salah satu algoritma seleksi fitur yang dapat digunakan adalah Binary Particle Swarm Optimizationi (BPSO). Pada penelitian ini, dilakukan seleksi fitur dengan BPSO pada data microarray dan klasifikasi menggunakan Distance Weighted KNN (DWKNN). Kemudian akan dilihat perbandingan hasil akurasi, presisi, recall, dan f1-score antara DWKNN dan BPSO-DWKNN. Seleksi fitur dan klasifikasi (BPSO-DWKNN) pada dataset Leukemia menghasilkan akurasi, presisi, recall, dan f1-score tertinggi beturut-turut sebesar 93,12%, 94,39%, 95,92%, dan 94,8%. Pada dataset Lung Cancer diperoleh akurasi, presisi, recall, dan f1-score tertinggi beturut-turut sebesar 98,36%, 98,77%, 99,35%, dan 99,03%. Pada dataset Prostate Cancer diperoleh akurasi, presisi, recall, dan f1-score tertinggi beturut-turut sebesar 86,81%, 89,13%, 88,04%, dan 88,07%. Pada dataset Diffuse Large B-Cell Lymphome diperoleh akurasi, presisi, recall, dan f1-score tertinggi beturut-turut sebesar 85,8%, 93,21%, 88,1%, dan 89,76%. Hasil perbandingan menunjukkan peningkatan akurasi, presisi, recall, dan f1-score pada algoritma DWKNN dengan seleksi fitur BPSO dibandingkan dengan algoritma DWKNN tanpa seleksi fitur BPSO.
4
Metlek, Sedat, and Halit Çetiner. "Classification of Poisonous and Edible Mushrooms with Optimized Classification Algorithms." International Conference on Applied Engineering and Natural Sciences 1, no. 1 (July 20, 2023): 408–15. http://dx.doi.org/10.59287/icaens.1030.
Full textAbstract:
Within the scope of this study, it is aimed to classify the mushroom species consumed as a staple food. For this purpose, 8124 mushroom data with 22 different mushroom feature information were used. 5686 of these data were used for training and 2438 for testing. In the study, poisonous and edible mushroom species were classified by random forest, decision tree, and logistic regression classification methods. The parameters used in the random forest and decision tree classification algorithms used in the study were optimized with the GridSearchCV optimization method. With the random forest algorithm, the highest precision, recall, and F1 score values are 0.93, 0.98, and 0.95, respectively. When these values are examined on a class basis, the highest distinctiveness results were obtained in the poisonous class. In the edible class, the highest performance results were measured as 0.97, 0.92, and 0.95 for precision, recall, and F1 score values, respectively. With the decision Tree algorithm, the highest precision, recall, and F1 score values are 0.98, 0.98, and 0.92, respectively. The highest precision, recall, and F1 score values of the best poisonous class are 0.90, 0.98, and 0.92, respectively. The best performance results of the edible class were obtained with the highest precision, recall, and F1 score values of 0.98, 0.89, and 0.90, respectively. The average accuracy rate was 0.9028 with the Logistic Regression algorithm, and the precision, recall, and F1 score values of the poisonous class were obtained as 0.86, 0.97, and 0.91, respectively. Precision, recall, and F1 score values of the Edible class were obtained as 0.96, 0.83, and 0.89, respectively.
5
Yadav, Siddharth, and Tanmoy Chakraborty. "Zera-Shot Sentiment Analysis for Code-Mixed Data." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 18 (May 18, 2021): 15941–42. http://dx.doi.org/10.1609/aaai.v35i18.17967.
Full textAbstract:
Code-mixing is the practice of alternating between two or more languages. A major part of sentiment analysis research has been monolingual and they perform poorly on the code-mixed text. We introduce methods that use multilingual and cross-lingual embeddings to transfer knowledge from monolingual text to code-mixed text for code-mixed sentiment analysis. Our methods handle code-mixed text through zero-shot learning and beat state-of-the-art English-Spanish code-mixed sentiment analysis by an absolute 3% F1-score. We are able to achieve 0.58 F1-score (without a parallel corpus) and 0.62 F1-score (with the parallel corpus) on the same benchmark in a zero-shot way as compared to 0.68 F1-score in supervised settings. Our code is publicly available on github.com/sedflix/unsacmt.
6
Kasthurirathne, Suranga N., Shaun Grannis, Paul K. Halverson, Justin Morea, Nir Menachemi, and Joshua R. Vest. "Precision Health–Enabled Machine Learning to Identify Need for Wraparound Social Services Using Patient- and Population-Level Data Sets: Algorithm Development and Validation." JMIR Medical Informatics 8, no. 7 (July 9, 2020): e16129. http://dx.doi.org/10.2196/16129.
Full textAbstract:
Background Emerging interest in precision health and the increasing availability of patient- and population-level data sets present considerable potential to enable analytical approaches to identify and mitigate the negative effects of social factors on health. These issues are not satisfactorily addressed in typical medical care encounters, and thus, opportunities to improve health outcomes, reduce costs, and improve coordination of care are not realized. Furthermore, methodological expertise on the use of varied patient- and population-level data sets and machine learning to predict need for supplemental services is limited. Objective The objective of this study was to leverage a comprehensive range of clinical, behavioral, social risk, and social determinants of health factors in order to develop decision models capable of identifying patients in need of various wraparound social services. Methods We used comprehensive patient- and population-level data sets to build decision models capable of predicting need for behavioral health, dietitian, social work, or other social service referrals within a safety-net health system using area under the receiver operating characteristic curve (AUROC), sensitivity, precision, F1 score, and specificity. We also evaluated the value of population-level social determinants of health data sets in improving machine learning performance of the models. Results Decision models for each wraparound service demonstrated performance measures ranging between 59.2%% and 99.3%. These results were statistically superior to the performance measures demonstrated by our previous models which used a limited data set and whose performance measures ranged from 38.2% to 88.3% (behavioural health: F1 score P<.001, AUROC P=.01; social work: F1 score P<.001, AUROC P=.03; dietitian: F1 score P=.001, AUROC P=.001; other: F1 score P=.01, AUROC P=.02); however, inclusion of additional population-level social determinants of health did not contribute to any performance improvements (behavioural health: F1 score P=.08, AUROC P=.09; social work: F1 score P=.16, AUROC P=.09; dietitian: F1 score P=.08, AUROC P=.14; other: F1 score P=.33, AUROC P=.21) in predicting the need for referral in our population of vulnerable patients seeking care at a safety-net provider. Conclusions Precision health–enabled decision models that leverage a wide range of patient- and population-level data sets and advanced machine learning methods are capable of predicting need for various wraparound social services with good performance.
7
Huang, Hao, Haihua Xu, Xianhui Wang, and Wushour Silamu. "Maximum F1-Score Discriminative Training Criterion for Automatic Mispronunciation Detection." IEEE/ACM Transactions on Audio, Speech, and Language Processing 23, no. 4 (April 2015): 787–97. http://dx.doi.org/10.1109/taslp.2015.2409733.
Full text
8
Song, Ikhwan, and Sungho Kim. "AVILNet: A New Pliable Network with a Novel Metric for Small-Object Segmentation and Detection in Infrared Images." Remote Sensing 13, no. 4 (February 4, 2021): 555. http://dx.doi.org/10.3390/rs13040555.
Full textAbstract:
Infrared small-object segmentation (ISOS) has a persistent trade-off problem—that is, which came first, recall or precision? Constructing a fine balance between of them is, au fond, of vital importance to obtain the best performance in real applications, such as surveillance, tracking, and many fields related to infrared searching and tracking. F1-score may be a good evaluation metric for this problem. However, since the F1-score only depends upon a specific threshold value, it cannot reflect the user’s requirements according to the various application environment. Therefore, several metrics are commonly used together. Now we introduce F-area, a novel metric for a panoptic evaluation of average precision and F1-score. It can simultaneously consider the performance in terms of real application and the potential capability of a model. Furthermore, we propose a new network, called the Amorphous Variable Inter-located Network (AVILNet), which is of pliable structure based on GridNet, and it is also an ensemble network consisting of the main and its sub-network. Compared with the state-of-the-art ISOS methods, our model achieved an AP of 51.69%, F1-score of 63.03%, and F-area of 32.58% on the International Conference on Computer Vision 2019 ISOS Single dataset by using one generator. In addition, an AP of 53.6%, an F1-score of 60.99%, and F-area of 32.69% by using dual generators, with beating the existing best record (AP, 51.42%; F1-score, 57.04%; and F-area, 29.33%).
9
Denize, Julien, Laurence Hubert-Moy, and Eric Pottier. "Polarimetric SAR Time-Series for Identification of Winter Land Use." Sensors 19, no. 24 (December 17, 2019): 5574. http://dx.doi.org/10.3390/s19245574.
Full textAbstract:
In the past decade, high spatial resolution Synthetic Aperture Radar (SAR) sensors have provided information that contributed significantly to cropland monitoring. However, the specific configurations of SAR sensors (e.g., band frequency, polarization mode) used to identify land-use types remains underexplored. This study investigates the contribution of C/L-Band frequency, dual/quad polarization and the density of image time-series to winter land-use identification in an agricultural area of approximately 130 km² located in northwestern France. First, SAR parameters were derived from RADARSAT-2, Sentinel-1 and Advanced Land Observing Satellite 2 (ALOS-2) time-series, and one quad-pol and six dual-pol datasets with different spatial resolutions and densities were calculated. Then, land use was classified using the Random Forest algorithm with each of these seven SAR datasets to determine the most suitable SAR configuration for identifying winter land-use. Results highlighted that (i) the C-Band (F1-score 0.70) outperformed the L-Band (F1-score 0.57), (ii) quad polarization (F1-score 0.69) outperformed dual polarization (F1-score 0.59) and (iii) a dense Sentinel-1 time-series (F1-score 0.70) outperformed RADARSAT-2 and ALOS-2 time-series (F1-score 0.69 and 0.29, respectively). In addition, Shannon Entropy and SPAN were the SAR parameters most important for discriminating winter land-use. Thus, the results of this study emphasize the interest of using Sentinel-1 time-series data for identifying winter land-use.
10
Adhitya, Rahmat Ryan, Wina Witanti, and Rezki Yuniarti. "PERBANDINGAN METODE CART DAN NAÏVE BAYES UNTUK KLASIFIKASI CUSTOMER CHURN." INFOTECH journal 9, no. 2 (July 4, 2023): 307–18. http://dx.doi.org/10.31949/infotech.v9i2.5641.
Full textAbstract:
Classification is the process of identifying and grouping an object into the same group or category Classification can be used to group a large-sized dataset, and some commonly used classification methods are CART (Classification And Regression Tree) and Naïve Bayes. This study discusses the comparison of CART and Naïve Bayes methods by measuring accuracy, precision, recall, and f1-score values with 3 scenarios of training and testing dataset distribution. Accuracy, precision, recall, and f1-score measurements are performed using a confusion matrix. The scenarios for training and testing dataset division are 70%, 80%, and 90% of the training dataset. From the results of the study, CART has the highest average accuracy and f1-score of 79.616% and 57.636% respectively, while the highest average accuracy and f1-score of Naïve Bayes are 75.104% and 62.004% respectively.
11
Ari, Tugba, Hande Sağlam, Hasan Öksüzoğlu, Orhan Kazan, İbrahim Şevki Bayrakdar, Suayip Burak Duman, Özer Çelik, et al. "Automatic Feature Segmentation in Dental Periapical Radiographs." Diagnostics 12, no. 12 (December 7, 2022): 3081. http://dx.doi.org/10.3390/diagnostics12123081.
Full textAbstract:
While a large number of archived digital images make it easy for radiology to provide data for Artificial Intelligence (AI) evaluation; AI algorithms are more and more applied in detecting diseases. The aim of the study is to perform a diagnostic evaluation on periapical radiographs with an AI model based on Convoluted Neural Networks (CNNs). The dataset includes 1169 adult periapical radiographs, which were labelled in CranioCatch annotation software. Deep learning was performed using the U-Net model implemented with the PyTorch library. The AI models based on deep learning models improved the success rate of carious lesion, crown, dental pulp, dental filling, periapical lesion, and root canal filling segmentation in periapical images. Sensitivity, precision and F1 scores for carious lesion were 0.82, 0.82, and 0.82, respectively; sensitivity, precision and F1 score for crown were 1, 1, and 1, respectively; sensitivity, precision and F1 score for dental pulp, were 0.97, 0.87 and 0.92, respectively; sensitivity, precision and F1 score for filling were 0.95, 0.95, and 0.95, respectively; sensitivity, precision and F1 score for the periapical lesion were 0.92, 0.85, and 0.88, respectively; sensitivity, precision and F1 score for root canal filling, were found to be 1, 0.96, and 0.98, respectively. The success of AI algorithms in evaluating periapical radiographs is encouraging and promising for their use in routine clinical processes as a clinical decision support system.
12
Bohnet, Bernd, Chris Alberti, and Michael Collins. "Coreference Resolution through a seq2seq Transition-Based System." Transactions of the Association for Computational Linguistics 11 (2023): 212–26. http://dx.doi.org/10.1162/tacl_a_00543.
Full textAbstract:
Abstract Most recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution system that uses a text-to-text (seq2seq) paradigm to predict mentions and links jointly. We implement the coreference system as a transition system and use multilingual T5 as an underlying language model. We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83.3 F1-score for English (a 2.3 higher F1-score than previous work [Dobrovolskii, 2021]) using only CoNLL data for training, 68.5 F1-score for Arabic (+4.1 higher than previous work), and 74.3 F1-score for Chinese (+5.3). In addition we use the SemEval-2010 data sets for experiments in the zero-shot setting, a few-shot setting, and supervised setting using all available training data. We obtain substantially higher zero-shot F1-scores for 3 out of 4 languages than previous approaches and significantly exceed previous supervised state-of-the-art results for all five tested languages. We provide the code and models as open source.1
13
Misnati, Misnati, Anna Y. Pomalingo, Irza Nanda Ranti, and Nuryani Nuryani. "The Effect of Substitution of Snakehead Fish and Purple Eggplant Flour on The Acceptability of Biscuits for Stunting Prevention." Media Gizi Indonesia 18, no. 2SP (October 23, 2023): 37–42. http://dx.doi.org/10.20473/mgi.v18i2sp.37-42.
Full textAbstract:
The development of supplementary food formulas for toddlers made from local foods can be an alternative in handling child nutritional problems. Purpose of study was to observe the acceptability of biscuits substitution of snakehead fish meal and purple eggplant flour. Design of study was an quasi experimental using postest only control group design with four treatments namely substitution of snakehead fish meal and purple eggplant flour. The ratio of wheat flour, fish meal and purple eggplant flour is 100%: 0 : 0,85% : 10% : 5%, 70% : 20% : 10%, and 55% : 30% : 15%. The results of the study based in the color characteristic the highest score after control was F1 (score = 2.47), the taste aspect F1 (score = 2.7), the aroma aspect F1 (score = 2.41), thetexture/crunch F1 (score = 2.65). There was an effect of substitution of snakehead fish meal and purple eggplant flour on color acceptability (p = 0.000) and taste (p = 0.003), there is no effect of substitution of snakehead fish meal and purple eggplant flour on aroma receptivity (p = 0.306) and crispness (p = 0.155). In conclusion, there are significant differences in the color and taste characteristics of cookies substitution of snakehead fish flour and purple eggplant flour between F0, F1, F2 and F3.
14
Julia Triani, Yovi Pratama, and Elvi Yanti. "Komparasi Dalam Prediksi Gagal Jantung Dengan Menggunakan Metode C4.5 dan Naïve Bayes." Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) 3, no. 1 (April 30, 2023): 394–402. http://dx.doi.org/10.33998/jakakom.2023.3.1.759.
Full textAbstract:
Industri kesehatan memiliki data kesehatan yang cukup besar, seperti dataset penyakit gagal jantung. Pada penelitian ini penulis memutuskan untuk memprediksi penyakit gagal jantung menggunakan metode C4.5 dan Naïve Bayes. Data yang dipakai diambil dari website kaggle.com yang berjumlah 918 data dengan 12 atribut. Adapun tujuan dari penelitian ini adalah untuk mengetahui perbandingan antara metode C4.5 dan Naïve Bayes dalam mengukur tingkat akurasi. Manfaat dari penelitian ini adalah dapat membantu pihak tenaga kesehatan dalam memprediksi pasien yang berkemungkinan terkena penyakit gagal jantung sehingga dapat menjadi informasi bagi pembaca untuk mengetahui resiko pasien terkena penyakit gagal jantung dengan tingkat akurasi yang tinggi. Proses implementasi metode C4.5 dan yang digunakan meraih tingkat akurasi sebesar 83.67%, presisi sebesar 85.01%, recall sebesar 86.04% dan f1-score sebesar 85.02%. untuk metode C4.5 dengan outlier. Kemudian metode C4.5 tanpa outlier meraih tingkat akurasi sebesar 85.02%, presisi sebesar 86.02%, recall sebesar 87.02% dan f1-score sebesar 86.52%. Dan metode Naïve Bayes yang digunakan meraih tingkat akurasi sebesar 85.30%, presisi sebesar 86.31%, recall sebesar 87.40% dan f1-score sebesar 86.85% untuk metode Naïve Bayes dengan outlier. Kemudian metode Naïve Bayes tanpa outlier meraih tingkat akurasi tertinggi yaitu sebesar 85.57%, presisi sebesar 86.54%, recall sebesar 87.57% dan f1-score sebesar 87.05%. Sehingga dapat disimpulkan bahwa nilai perhitungan akurasi, presisi, recall dan f1-score tertinggi yaitu metode Naïve Bayes tanpa outlier.
15
Lee, Geun Hyeong, and Soo-Yong Shin. "Federated Learning on Clinical Benchmark Data: Performance Assessment." Journal of Medical Internet Research 22, no. 10 (October 26, 2020): e20891. http://dx.doi.org/10.2196/20891.
Full textAbstract:
Background Federated learning (FL) is a newly proposed machine-learning method that uses a decentralized dataset. Since data transfer is not necessary for the learning process in FL, there is a significant advantage in protecting personal privacy. Therefore, many studies are being actively conducted in the applications of FL for diverse areas. Objective The aim of this study was to evaluate the reliability and performance of FL using three benchmark datasets, including a clinical benchmark dataset. Methods To evaluate FL in a realistic setting, we implemented FL using a client-server architecture with Python. The implemented client-server version of the FL software was deployed to Amazon Web Services. Modified National Institute of Standards and Technology (MNIST), Medical Information Mart for Intensive Care-III (MIMIC-III), and electrocardiogram (ECG) datasets were used to evaluate the performance of FL. To test FL in a realistic setting, the MNIST dataset was split into 10 different clients, with one digit for each client. In addition, we conducted four different experiments according to basic, imbalanced, skewed, and a combination of imbalanced and skewed data distributions. We also compared the performance of FL to that of the state-of-the-art method with respect to in-hospital mortality using the MIMIC-III dataset. Likewise, we conducted experiments comparing basic and imbalanced data distributions using MIMIC-III and ECG data. Results FL on the basic MNIST dataset with 10 clients achieved an area under the receiver operating characteristic curve (AUROC) of 0.997 and an F1-score of 0.946. The experiment with the imbalanced MNIST dataset achieved an AUROC of 0.995 and an F1-score of 0.921. The experiment with the skewed MNIST dataset achieved an AUROC of 0.992 and an F1-score of 0.905. Finally, the combined imbalanced and skewed experiment achieved an AUROC of 0.990 and an F1-score of 0.891. The basic FL on in-hospital mortality using MIMIC-III data achieved an AUROC of 0.850 and an F1-score of 0.944, while the experiment with the imbalanced MIMIC-III dataset achieved an AUROC of 0.850 and an F1-score of 0.943. For ECG classification, the basic FL achieved an AUROC of 0.938 and an F1-score of 0.807, and the imbalanced ECG dataset achieved an AUROC of 0.943 and an F1-score of 0.807. Conclusions FL demonstrated comparative performance on different benchmark datasets. In addition, FL demonstrated reliable performance in cases where the distribution was imbalanced, skewed, and extreme, reflecting the real-life scenario in which data distributions from various hospitals are different. FL can achieve high performance while maintaining privacy protection because there is no requirement to centralize the data.
16
Munsch, Nicolas, Alistair Martin, Stefanie Gruarin, Jama Nateqi, Isselmou Abdarahmane, Rafael Weingartner-Ortner, and Bernhard Knapp. "Diagnostic Accuracy of Web-Based COVID-19 Symptom Checkers: Comparison Study." Journal of Medical Internet Research 22, no. 10 (October 6, 2020): e21299. http://dx.doi.org/10.2196/21299.
Full textAbstract:
Background A large number of web-based COVID-19 symptom checkers and chatbots have been developed; however, anecdotal evidence suggests that their conclusions are highly variable. To our knowledge, no study has evaluated the accuracy of COVID-19 symptom checkers in a statistically rigorous manner. Objective The aim of this study is to evaluate and compare the diagnostic accuracies of web-based COVID-19 symptom checkers. Methods We identified 10 web-based COVID-19 symptom checkers, all of which were included in the study. We evaluated the COVID-19 symptom checkers by assessing 50 COVID-19 case reports alongside 410 non–COVID-19 control cases. A bootstrapping method was used to counter the unbalanced sample sizes and obtain confidence intervals (CIs). Results are reported as sensitivity, specificity, F1 score, and Matthews correlation coefficient (MCC). Results The classification task between COVID-19–positive and COVID-19–negative for “high risk” cases among the 460 test cases yielded (sorted by F1 score): Symptoma (F1=0.92, MCC=0.85), Infermedica (F1=0.80, MCC=0.61), US Centers for Disease Control and Prevention (CDC) (F1=0.71, MCC=0.30), Babylon (F1=0.70, MCC=0.29), Cleveland Clinic (F1=0.40, MCC=0.07), Providence (F1=0.40, MCC=0.05), Apple (F1=0.29, MCC=-0.10), Docyet (F1=0.27, MCC=0.29), Ada (F1=0.24, MCC=0.27) and Your.MD (F1=0.24, MCC=0.27). For “high risk” and “medium risk” combined the performance was: Symptoma (F1=0.91, MCC=0.83) Infermedica (F1=0.80, MCC=0.61), Cleveland Clinic (F1=0.76, MCC=0.47), Providence (F1=0.75, MCC=0.45), Your.MD (F1=0.72, MCC=0.33), CDC (F1=0.71, MCC=0.30), Babylon (F1=0.70, MCC=0.29), Apple (F1=0.70, MCC=0.25), Ada (F1=0.42, MCC=0.03), and Docyet (F1=0.27, MCC=0.29). Conclusions We found that the number of correctly assessed COVID-19 and control cases varies considerably between symptom checkers, with different symptom checkers showing different strengths with respect to sensitivity and specificity. A good balance between sensitivity and specificity was only achieved by two symptom checkers.
17
Susilayasa, I. Made Adi, Anak Agung Istri Eka Karyawati, Luh Gede Astuti, Luh Arida Ayu Rahning Putri, I. Gede Arta Wibawa, and I. Komang Ari Mogi. "Analisis Sentimen Ulasan E-Commerce Pakaian Berdasarkan Kategori dengan Algoritma Convolutional Neural Network." JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) 11, no. 1 (July 8, 2022): 1. http://dx.doi.org/10.24843/jlk.2022.v11.i01.p01.
Full textAbstract:
Almost everyone looks at reviews before deciding to buy an item in e-commerce. Consumers say that online reviews influence their purchasing decisions. Based on these data, consumers need sentiment reviews to make a decision to choose a product/service. However, the results of the sentiment analysis are still less specific, so the review classification process is carried out based on the review category. Sentiment classification process based on clothing category is carried out using the Convolutional neural network method. The amount of data used is 3384 data with 3 categories. The category classification model shows good performance. When evaluated with testing data (unseen data), the accuracy value is 88%, the precision value is 88%, recall is 88% and the f1-score is 88%. For the sentiment classification model with the bottoms category, the resulting accuracy value is 80%, precision is 81%, recall is 80%, and f1-score is 79%. For the sentiment classification model with the dresses category, the accuracy value is 81%, precision is 81%, recall is 81%, and f1-score is 81%. For sentiment classification with the tops category the resulting accuracy value is 77%, precision is 77%, recall is 77%, and f1-score is 77%.
18
Yasir, Muhammad, Asad Karim, Sumera Malik, Amal A. Bajaffer, and Esam I. Azhar. "Application of Decision-Tree-Based Machine Learning Algorithms for Prediction of Antimicrobial Resistance." Antibiotics 11, no. 11 (November 10, 2022): 1593. http://dx.doi.org/10.3390/antibiotics11111593.
Full textAbstract:
Timely and efficacious antibiotic treatment depends on precise and quick in silico antimicrobial-resistance predictions. Limited treatment choices due to antimicrobial resistance (AMR) highlight the necessity to optimize the available diagnostics. AMR can be explicitly anticipated on the basis of genome sequence. In this study, we used transcriptomes of 410 multidrug-resistant isolates of Pseudomonas aeruginosa. We trained 10 machine learning (ML) classifiers on the basis of data on gene expression (GEXP) information and generated predictive models for meropenem, ciprofloxacin, and ceftazidime drugs. Among all the used ML models, four models showed high F1-score, accuracy, precision, and specificity compared with the other models. However, RandomForestClassifier showed a moderate F1-score (0.6), precision (0.61), and specificity (0.625) for ciprofloxacin. In the case of ceftazidime, RidgeClassifier performed well and showed F1-score (0.652), precision (0.654), and specificity (0.652) values. For meropenem, KNeighborsClassifier exhibited moderate F1-score (0.629), precision (0.629), and specificity (0.629). Among these three antibiotics, GEXP data on meropenem and ceftazidime improved diagnostic performance. The findings will pave the way for the establishment of a resistance profiling tool that can predict AMR on the basis of transcriptomic markers.
19
Putra Negara, Arif Bijaksana. "The Influence Of Applying Stopword Removal And Smote On Indonesian Sentiment Classification." Lontar Komputer : Jurnal Ilmiah Teknologi Informasi 14, no. 3 (December 5, 2023): 172. http://dx.doi.org/10.24843/lkjiti.2023.v14.i03.p05.
Full textAbstract:
Information, like public opinions or responses, can be obtained through Twitter tweets. These opinions can expressed as a sentiment. Sentiments can be positive, neutral, or negative. Sentiment analysis (opinion mining) on a text can performed through text classification. This research aims to determine the influence of implementing Stopword Removal and SMOTE on the sentiment classification model for Indonesian tweets. The algorithms used in this research are Logistic Regression and Random Forest. Based on the evaluation, the best classification model in this research was achieved by implementing the Random Forest algorithm along with SMOTE, with an f1-score value of 75.03%. Meanwhile, implementing the Random Forest algorithm and Stopword Removal achieved the worst classification model, with an f1-score value of 68.09%. Implementing Stopword Removal in both algorithms has a negative impact in the form of a decrease in the resulting f1-score. Meanwhile, the performance of SMOTE provides a positive impact in the form of an increase in the resulting f1-score. This happened since Stopword Removal could reduce information and alter the meaning of processed tweets, causing the tweet to lose its sentiment.
20
A.M., Oyelakin, Alimi O. M, Mustapha I. O, and Ajiboye I. K. "Analysis of Single and Ensemble Machine Learning Classifiers for Phishing Attacks Detection." International Journal of Software Engineering and Computer Systems 7, no. 2 (August 30, 2021): 44–49. http://dx.doi.org/10.15282/ijsecs.7.2.2021.5.0088.
Full textAbstract:
Phishing attacks have been used in different ways to harvest the confidential information of unsuspecting internet users. To stem the tide of phishing-based attacks, several machine learning techniques have been proposed in the past. However, fewer studies have considered investigating single and ensemble machine learning-based models for the classification of phishing attacks. This study carried out performance analysis of selected single and ensemble machine learning (ML) classifiers in phishing classification. The focus is to investigate how these algorithms behave in the classification of phishing attacks in the chosen dataset. Logistic Regression and Decision Trees were chosen as single learning classifiers while simple voting techniques and Random Forest were used as the ensemble machine learning algorithms. Accuracy, Precision, Recall and F1-score were used as performance metrics. Logistic Regression algorithm recorded 0.86 as accuracy, 0.89 as precision, 0.87 as recall and 0.81 as F1-score. Similarly, the Decision Trees classifier achieved an accuracy of 0.87, 0.83 for precision, 0.88 for recall and 0.81 for F1-score. In the voting ensemble, accuracy of 0.92 was achieved. 0.90 was obtained for precision, 0.92 for recall and 0.92 for F1-score. Random Forest algorithm recorded 0.98, 0.97, 0.98 and 0.97 as accuracy, precision, recall and F1-score respectively. From the experimental analyses, Random Forest algorithm outperformed simple averaging classifier and the two single algorithms used for phishing URL detection. The study established that the ensemble techniques that were used for the experimentations are more efficient for phishing URL identification compared to the single classifiers.
21
Zhang, Zhining, Liang Wan, Kun Chu, Shusheng Li, Haodong Wei, and Lu Tang. "JACLNet:Application of adaptive code length network in JavaScript malicious code detection." PLOS ONE 17, no. 12 (December 14, 2022): e0277891. http://dx.doi.org/10.1371/journal.pone.0277891.
Full textAbstract:
Currently, JavaScript malicious code detection methods are becoming more and more effective. Still, the existing methods based on deep learning are poor at detecting too long or too short JavaScript code. Based on this, this paper proposes an adaptive code length deep learning network JACLNet, composed of convolutional block RDCNet, BiLSTM and Transfrom, to capture the association features of the variable distance between codes. Firstly, an abstract syntax tree recombination algorithm is designed to provide rich syntax information for feature extraction. Secondly, a deep residual convolution block network (RDCNet) is designed to capture short-distance association features between codes. Finally, this paper proposes a JACLNet network for JavaScript malicious code detection. To verify that the model presented in this paper can effectively detect variable JavaScript code, we divide the datasets used in this paper into long text dataset DB_Long; short text dataset DB_Short, original dataset DB_Or and enhanced dataset DB_Re. In DB_Long, our method’s F1 − score is 98.87%, higher than that of JSContana by 2.52%. In DB_Short, our method’s F1-score is 97.32%, higher than that of JSContana by 7.79%. To verify that the abstract syntax tree recombination algorithm proposed in this paper can provide rich syntax information for subsequent models, we conduct comparative experiments on DB_Or and DB_Re. In DPCNN+BiLSTM, F1-score with abstract syntax tree recombination increased by 1.72%, and in JSContana, F1-score with abstract syntax tree recombination increased by 1.50%. F1-score with abstract syntax tree recombination in JACNet improved by 1.00% otherwise unused.
22
Alsabry, Ayman, and Malek Algabri. "Iterative Tuning of Tree-Ensemble-Based Models' parameters Using Bayesian Optimization for Breast Cancer Prediction." Informatics and Automation 23, no. 1 (January 11, 2024): 129–68. http://dx.doi.org/10.15622/ia.23.1.5.
Full textAbstract:
The study presents a method for iterative parameter tuning of tree ensemble-based models using Bayesian hyperparameter tuning for states prediction, using breast cancer as an example. The proposed method utilizes three different datasets, including the Wisconsin Diagnostic Breast Cancer (WDBC) dataset, the Surveillance, Epidemiology, and End Results (SEER) breast cancer dataset, and the Breast Cancer Coimbra dataset (BCCD), and implements tree ensemble-based models, specifically AdaBoost, Gentle-Boost, LogitBoost, Bag, and RUSBoost, for breast cancer prediction. Bayesian optimization was used to tune the hyperparameters of the models iteratively, and the performance of the models was evaluated using several metrics, including accuracy, precision, recall, and f1-score. Our results show that the proposed method significantly improves the performance of tree ensemble-based models, resulting in higher accuracy, precision, recall, and f1-score. Compared to other state-of-the-art models, the proposed method is more efficient. It achieved perfect scores of 100% for Accuracy, Precision, Recall, and F1-Score on the WDBC dataset. On the SEER BC dataset, the method achieved an accuracy of 95.9%, a precision of 97.6%, a recall of 94.2%, and an F1-Score of 95.9%. For the BCCD dataset, the method achieved an accuracy of 94.7%, a precision of 90%, a recall of 100%, and an F1-Score of 94.7%. The outcomes of this study have important implications for medical professionals, as early detection of breast cancer can significantly increase the chances of survival. Overall, this study provides a valuable contribution to the field of breast cancer prediction using machine learning.
23
Steven, Steven, Arif Bijaksana Putra Negara, and Yulianti Yulianti. "Implementasi Algoritma K-Nearest Neighbor Untuk Mengklasifikasi Masa Studi Mahasiswa Informatika Universitas Tanjungpura." Jurnal Sistem dan Teknologi Informasi (JustIN) 10, no. 3 (November 22, 2022): 319. http://dx.doi.org/10.26418/justin.v10i3.56724.
Full textAbstract:
Setiap perguruan tinggi memiliki waktu maksimal yang diberikan kepada mahasiswa dalam menyelesaikan studinya, jika mahasiswa tersebut sudah melewati batas waktu yang telah ditentukan maka mahasiswa tersebut akan dikeluarkan dari perguruan tinggi. Dengan memanfaatkan data akademik mahasiswa yang tersimpan dalam database perguruan tinggi, maka data akademik mahasiswa dapat digunakan untuk mengklasifikasi masa studi mahasiswa. Tujuan penelitian ini adalah untuk mengklasifikasi masa studi mahasiswa serta mengetahui performa algoritma yang digunakan dalam proses klasifikasi. Algoritma yang digunakan untuk penelitian ini adalah K-Nearest Neighbor dan Naive Bayes. Pada penelitian ini juga, algoritma klasifikasi akan ditambahkan Feature Selection Information Gain untuk melihat pengaruh akurasi pada algoritma. Data akademik akan diklasifikasikan kedalam 2 kelas, yaitu kelas lulus tepat waktu dan lulus tidak tepat waktu. Hasil evaluasi menunjukkan bahwa algoritma K-Nearest Neighbor dengan menambahkan Feature Selection Information Gain memberikan hasil performa klasifikasi yang paling baik dengan nilai akurasi sebesar 70.41% dan f1-score sebesar 80.68% dengan nilai k (jarak antar data)=17 pada evaluasi nilai akademik 4 semester dan nilai akurasi sebesar 70.14% dan f1-score sebesar 80.68% dengan nilai k (jarak antar data)=21 pada evaluasi nilai akademik 7 semester. Sedangkan dengan menggunakan algoritma Naive Bayes dengan menambahkan Feature Selection Information Gain mendapatkan nilai akurasi sebesar 67.95% dan f1-score sebesar 72.85.% pada evaluasi nilai akademik 4 semester dan nilai akurasi sebesar 69.32% dan f1-score sebesar 73.47% pada evaluasi nilai akademik 7 semester. Penggunaan Feature Selection Information Gain pada algoritma K-Nearest Neighbor memberikan nilai akurasi yang lebih baik dibandingkan algoritma Naive Bayes dengan perbandingan akurasi sebesar 2.46% dan f1-score sebesar 7.83% pada evaluasi nilai akademik 4 semester dan perbandingan akurasi sebesar 0.82% dan f1-score sebesar 7.21% pada evaluasi nilai akademik 7 semester. Setelah didapatkan performa algoritma terbaik yaitu algoritma K-Nearest Neighbor dengan menambahkan Feature Selection Information Gain, maka algoritma tersebut akan digunakan untuk mengklasifikasi masa studi mahasiswa Informatika Universitas Tanjungpura dengan sistem yang dibangun pada penelitian ini.
24
Yolanda, Nedya, Indyah Hartami Santi, and Dimas Fanny Hebrasianto Permadi. "Analisis Sentimen Analisis Sentimen Popularitas Aplikasi Moodle dan Edmodo Menggunakan Algoritma Support Vector Machine." Jurnal Algoritme 3, no. 1 (October 5, 2022): 48–59. http://dx.doi.org/10.35957/algoritme.v3i1.3313.
Full textAbstract:
Pandemi Covid-19 di Indonesia menyebabkan pembelajaran tatap muka diberhentikan sementara, sehingga keluar kebijakan pembelajaran berani. Secara tidak langsung mendorong sebuah aplikasi E-Learning memiliki tingkat penggunaan dan jumlah unduhan tinggi di Play Store. Aplikasi terbaik selalu diberikan kepada aplikasi dengan jumlah unduhan dan rating paling tinggi di Play Store. Sementara itu komentar dari pengguna perlu dipertimbangkan karena banyak aplikasi E-learning yang memilliki jumlah unduhan dan penilaian yang hampir sama seperti pada aplikasi Moodle dan Edmodo, oleh karena itu dilakukan analisis sentimen popularitas aplikasi Moodle dan Edmodo menggunakan Algoritma SVM. Komentar pengguna di Play Store digunakan sebagai sumber data. Dari 250 data hasil Scraping komentar pengguna lalu dilakukan proses preprocessing dan pembobotan ekstraksi TF IDF. Berdasarkan pengujian menggunakan matriks kebingungan dapat dipastikan bahwa sentimen pengguna terhadap aplikasi Edmodo memiliki proporsi yang lebih baik dibandingkan dengan aplikasi Moodle dapat didukung dengan munculnya sentimen positif 67% dengan keakuratan sebesar 84% dan pengujian presisi sebesar 93%, serta recall sebesar 82 % dan f1-score sebesar 87%. Sedangkan pada aplikasi Moodle memiliki persentase sentimen negatif sebesar 67% dengan keakuratan 82% dan presisi pengujian sebesar 79%, recall 100% dan f1-score 88%. Berdasarkan pengujian menggunakan matriks kebingungan dapat dipastikan bahwa sentimen pengguna terhadap aplikasi Edmodo memiliki proporsi yang lebih baik dibandingkan dengan aplikasi Moodle dapat didukung dengan munculnya sentimen positif 67% dengan keakuratan sebesar 84% dan pengujian presisi sebesar 93%, serta recall sebesar 82 % dan f1-score sebesar 87%. Sedangkan pada aplikasi Moodle memiliki persentase sentimen negatif sebesar 67% dengan keakuratan 82% dan presisi pengujian sebesar 79%, recall 100% dan f1-score 88%. Berdasarkan pengujian menggunakan matriks kebingungan dapat dipastikan bahwa sentimen pengguna terhadap aplikasi Edmodo memiliki proporsi yang lebih baik dibandingkan dengan aplikasi Moodle dapat didukung dengan munculnya sentimen positif 67% dengan keakuratan sebesar 84% dan pengujian presisi sebesar 93%, serta recall sebesar 82 % dan f1-score sebesar 87%. Sedangkan pada aplikasi Moodle memiliki persentase sentimen negatif sebesar 67% dengan keakuratan 82% dan presisi pengujian sebesar 79%, recall 100% dan f1-score 88%.
25
Banou, Z., S. Elfilali, and H. Benlahmar. "Towards a polynomial approximation of support vector machine accuracy applied to Arabic tweet sentiment analysis." Mathematical Modeling and Computing 10, no. 2 (2023): 511–17. http://dx.doi.org/10.23939/mmc2023.02.511.
Full textAbstract:
Machine learning algorithms have become very frequently used in natural language processing, notably sentiment analysis, which helps determine the general feeling carried within a text. Among these algorithms, Support Vector Machines have proven powerful classifiers especially in such a task, when their performance is assessed through accuracy score and f1-score. However, they remain slow in terms of training, thus making exhaustive grid-search experimentations very time-consuming. In this paper, we present an observed pattern in SVM's accuracy, and f1-score approximated with a Lagrange polynomial.
26
Putra, Andaru Pratama, Anggrarista Nusty Alivia, Maulidiya Meilani, Naura Jasmine Azzahra, and Nur Aini Rakhmawati. "ANALISIS SENTIMEN WARGA TWITTER TERHADAP GAME SHOPEE COCOKI DENGAN METODE NAIVE BAYES CLASSIFIER." Jurnal Ilmiah Informatika Komputer 28, no. 2 (2023): 137–48. http://dx.doi.org/10.35760/ik.2023.v28i2.9494.
Full textAbstract:
Di era digital saat ini, banyak platform e-commerce bersaing untuk menarik pelanggan. Shopee adalah salah satu platform yang populer dengan banyak fitur dan layanan yang menarik, termasuk game "Shopee Cocoki" yang telah menjadi tren di kalangan pengguna Shopee. Penelitian ini menggunakan metode analisis sentimen Naive Bayes, yang memanfaatkan kemungkinan untuk mengkategorikan tweet menjadi kategori sentimen positif, negatif, atau netral. Data yang digunakan adalah sejumlah tweet yang mengandung kata kunci terkait "Shopee Cocoki" yang diambil dari Twitter. Berdasarkan hasil eksperimen, diperoleh nilai akurasi keseluruhan sebesar 55%. Sentimen negatif memiliki nilai presisi sebesar 57%, recall sebesar 80%, dan f1-score sebesar 67%. Sentimen netral memiliki nilai presisi sebesar 33%, recall sebesar 17%, dan f1-score sebesar 22%. Sedangkan sentimen positif memiliki nilai presisi sebesar 33%, recall sebesar 25%, dan f1-score sebesar 29%.
27
Lee, Sang-Hyun. "A Study on the Performance Evaluation of the Convolutional Neural Network–Transformer Hybrid Model for Positional Analysis." Applied Sciences 13, no. 20 (October 13, 2023): 11258. http://dx.doi.org/10.3390/app132011258.
Full textAbstract:
In this study, we identified the different causes of odor problems and their associated discomfort. We also recognized the significance of public health and environmental concerns. To address odor issues, it is vital to conduct precise analysis and comprehend the root causes. We suggested a hybrid model of a Convolutional Neural Network (CNN) and Transformer called the CNN–Transformer to tackle this challenge and assessed its effectiveness. We utilized a dataset containing 120,000 samples of odor to compare the performance of CNN+LSTM, CNN, LSTM, and ELM models. The experimental results show that the CNN+LSTM hybrid model has an accuracy of 89.00%, precision of 89.41%, recall of 91.04%, F1-score of 90.22%, and RMSE of 0.28, with a large prediction error. The CNN+Transformer hybrid model had an accuracy of 96.21%, precision and recall of 94.53% and 94.16%, F1-score of 94.35%, and RMSE of 0.27, showing a low prediction error. The CNN model had an accuracy of 87.19%, precision and recall of 89.41% and 91.04%, F1-score of 90.22%, and RMSE of 0.23, showing a low prediction error. The LSTM model had an accuracy of 95.00%, precision and recall of 92.55% and 94.17%, F1-score of 92.33%, and RMSE of 0.03, indicating a very low prediction error. The ELM model performed poorly with an accuracy of 85.50%, precision and recall of 85.26% and 85.19%, respectively, and F1-score and RMSE of 85.19% and 0.31, respectively. This study confirms the suitability of the CNN–Transformer hybrid model for odor analysis and highlights its excellent predictive performance. The employment of this model is expected to be advantageous in addressing odor problems and mitigating associated public health and environmental concerns.
28
Nuha, Muhammad Syifa'un, and Reddy Alexandro H. "Pemanfaatan Yolo untuk Pengenalan Kesegaran Buah Mangga." Joutica 7, no. 1 (February 11, 2022): 513. http://dx.doi.org/10.30736/jti.v7i1.747.
Full textAbstract:
Buah merupakan salah satu kebutuhan selain makanan pokok, tidak hanya dikalangan tertentu saja, tapi disemua kalangan. Indonesia menjadi penghasil mangga terbesar keempat di dunia. Sehingga diperlukan suatu sistem yang dapat secara otomatis mengidentifikasi kebusukan dan kesegaran dari 3 jenis buah Mangga menggunakan pengolahan gambar, memperbaiki teknik penyortiran dan penilaian yang tidak ilmiah yang dilakukan secara manual, sehingga bisa meningkatkan kualitas jual mangga dengan menggunakan algoritma YOLO. Penelitian ini menggunakan 3 jenis mangga yang terdiri dari mangga golek, gedong, dan manalagi, dan melakukan uji coba dengan beberapa sekenario yaitu semua gambar mangga segar, semua gambar mangga busuk, dan semua gambar mangga segar dan busuk. Hasil dari penelitian menunjukkan beberapa uji coba yang dilakukan, maka didapatkan nilai rata-rata precision, recall, dan f1- score Skenario pertama yaitu mangga segar semua didapatkan tingkat akurasi 80%, precision 82%, dan recall 87%, didapatkan F1-score 84%. Kemudian sknario yang kedua yaitu mangga busuk semua didapatkan tingkat akurasi 76%, precision 76%, dan recall 87%, didapatkan F1-score 81%. Dan yang ketiga yaitu mangga segar dan busuk, didapatkan tingkat akurasi 73%, precision 66%, dan recall 81%, didapatkan F1-score 73%. dapat disimpulkan bahwa hasil penelitian ini masih tergolong underfitting. Hal ini dikarenakan masih butuh banyak dataset yang lebih banyak dan variannya yang mempunyai ciri-ciri yang ada kemiripan masing-masing kelasnya.
29
Lestari, Dewi Putrie, and Rifki Kosasih. "Comparison of two deep learning methods for detecting fire hotspots." International Journal of Electrical and Computer Engineering (IJECE) 12, no. 3 (June 1, 2022): 3118. http://dx.doi.org/10.11591/ijece.v12i3.pp3118-3128.
Full textAbstract:
Every high-rise building must meet construction requirements, i.e. it must have good safety to prevent unexpected events such as fire incident. To avoid the occurrence of a bigger fire, surveillance using closed circuit television (CCTV) videos is necessary. However, it is impossible for security forces to monitor for a full day. One of the methods that can be used to help security forces is deep learning method. In this study, we use two deep learning methods to detect fire hotspots, i.e. you only look once (YOLO) method and faster region-based convolutional neural network (faster R-CNN) method. The first stage, we collected 100 image data (70 training data and 30 test data). The next stage is model training which aims to make the model can recognize fire. Later, we calculate precision, recall, accuracy, and F1 score to measure performance of model. If the F1 score is close to 1, then the balance is optimal. In our experiment results, we found that YOLO has a precision is 100%, recall is 54.54%, accuracy is 66.67%, and F1 score is 0.70583667. While faster R-CNN has a precision is 87.5%, recall is 95.45%, accuracy is 86.67%, and F1 score is 0.913022.
30
Suh, Ji Won, Eli Anderson, William Ouimet, Katharine M. Johnson, and Chandi Witharana. "Mapping Relict Charcoal Hearths in New England Using Deep Convolutional Neural Networks and LiDAR Data." Remote Sensing 13, no. 22 (November 17, 2021): 4630. http://dx.doi.org/10.3390/rs13224630.
Full textAbstract:
Advanced deep learning methods combined with regional, open access, airborne Light Detection and Ranging (LiDAR) data have great potential to study the spatial extent of historic land use features preserved under the forest canopy throughout New England, a region in the northeastern United States. Mapping anthropogenic features plays a key role in understanding historic land use dynamics during the 17th to early 20th centuries, however previous studies have primarily used manual or semi-automated digitization methods, which are time consuming for broad-scale mapping. This study applies fully-automated deep convolutional neural networks (i.e., U-Net) with LiDAR derivatives to identify relict charcoal hearths (RCHs), a type of historical land use feature. Results show that slope, hillshade, and Visualization for Archaeological Topography (VAT) rasters work well in six localized test regions (spatial scale: <1.5 km2, best F1 score: 95.5%), but also at broader extents at the town level (spatial scale: 493 km2, best F1 score: 86%). The model performed best in areas with deciduous forest and high slope terrain (e.g., >15 degrees) (F1 score: 86.8%) compared to coniferous forest and low slope terrain (e.g., <15 degrees) (F1 score: 70.1%). Overall, our results contribute to current methodological discussions regarding automated extraction of historical cultural features using deep learning and LiDAR.
31
Agustyaningrum, Cucu Ika, Rizka Dahlia, and Omar Pahlevi. "Comparison of Conventional Machine Learning and Deep Neural Network Algorithms in the Prediction of Monkey-Pox." Jurnal Riset Informatika 5, no. 3 (June 6, 2023): 523–32. http://dx.doi.org/10.34288/jri.v5i2.522.
Full textAbstract:
Smallpox syndrome, also known as monkeypox, is an uncommon zoonotic viral infection brought on by the monkeypox virus, which belongs to the genus orthopoxvirus and family Poxviridae. Injury-related mortality in primates ranges from 1 to 10%. Data mining is a method for analyzing data. Deep neural networks and traditional machine learning methods are both used in the data analysis process. The Python programming language is used during the comparison procedure of this research algorithm to generate values for accuracy, f1 score, precision, recall, ROC, and AUC. The test results demonstrate that using sigmoid activation function parameters, the deep neural network algorithm's accuracy is 70.08%, F1 score is 79.18%, precision is 68.59%, recall is 62.65%, and AUC is 62.65%. In comparison to using conventional machine learning algorithms, the adagrad optimizer with learning rate 0.01 and 0.2 dropout has a higher value. The conventional machine learning model algorithm has the best xgboost, F1 score, precision, recall, and AUC scores when compared to other approaches: 64.40%, 64.45%, and 78.14%. According to these numbers, the average fairness disparity between deep neural network algorithms and traditional machine learning is 5.68%, F1 score is 13.79%, precision is 4.14%, recall is 1.75%, and AUC is 1.75%.
32
Zhang, Song, Frank Adjei-Kyeremeh, Hui Wang, Moritz Kolter, Iris Raffeis, Johannes Schleifenbaum, and Andreas Bührig-Polaczek. "Quantified Approach for Evaluation of Geometry Visibility of Optical-Based Process Monitoring System for Laser Powder Bed Fusion." Metals 13, no. 1 (December 21, 2022): 13. http://dx.doi.org/10.3390/met13010013.
Full textAbstract:
The long-term sustainability of the Additive Manufacturing (AM) industry not only depends on the ability to produce parts with reproducible quality and properties to a large extent but also on the standardization of the production processes. In that regard, online process monitoring and detection of defective parts during production become inevitable. Optical-based process monitoring techniques are popular; however, most work has been mainly focused on capturing images of print abnormalities without taking other influencing factors, such as camera and part position, chamber illumination, and print geometry on the resolution of the captured images, into account. In this work, we present a scenario to evaluate and quantify the performance of an optical-based monitoring system in a Laser Powder Bed Fusion (LPBF) machine using the F1 score, considering factors such as scan vector orientation, part geometry (size) and position in a built chamber with a fixed camera position. The quantified results confirm that the F1 score can be used as a reliable means of evaluating the performance of optical-based monitoring systems in the LPBF process for the purposes of standardization. The biggest line width of the test artifact (1000 µm) had the highest F1 score range of 0.714–0.876 compared to the smallest (200 µm) with a 0.158–0.649 F1 score.
33
Nurhaliza, Siti, Yusra Yusra, and Muhammad Fikry. "Klasifikasi Sentimen Masyarakat di Twitter Terhadap Kenaikan Harga BBM dengan Metode Support Vector Machine." Jurnal Sistem Komputer dan Informatika (JSON) 4, no. 4 (July 2, 2023): 586. http://dx.doi.org/10.30865/json.v4i4.6322.
Full textAbstract:
The increase in the price of fuel oil (BBM) in Indonesia has always been a controversy which can be seen from online media such as Twitter which has an effect on the Indonesian economy, with this problem it has a change in the impact of cost instability due to an increase in fuel prices which will also affect the rate of increase in transportation costs and the rate of inflation. The effect of these changes leads to many different public opinions so as to produce pros and cons of these changes, with the existence of the problems above, the classification process is needed. This study uses 3000 tweet data obtained from the crawling process. This study obtains an accuracy of 85% at a ratio of 90:10, for a precision value of 85%, 99% recall and 91% f1-score for negative sentiment, while 83% precision value, 19% recall, 30% f1-score for positive sentiment. Then in the 80:20 comparison experiment, an accuracy of 83% was obtained, for a precision value of 83%, a recall of 99% and an f1-score of 91% for negative sentiment, while a precision value of 82%, a recall of 16%, an f1-score of 26% for positive sentiment.
34
Aula, Nurul, Munirul Ula, and Lidya Rosnita. "ANALISIS SENTIMEN REVIEW CUSTOMER TERHADAP PERUSAHAAN EKSPEDISI JNE, J&T EXPRESS DAN POS INDONESIA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM)." JOURNAL OF INFORMATICS AND COMPUTER SCIENCE 9, no. 1 (April 29, 2023): 81. http://dx.doi.org/10.33143/jics.v9i1.2947.
Full textAbstract:
Abstrak— Kepuasan customer adalah masalah yang harus diamati pada sebuah perusahaan, karena customer adalah alasan mengapa suatu perusahaan masih berdiri dan sukses. Perusahaan ekspedisi JNE, J&T, dan Pos Indonesia mempunyai akun twitter layanan customer yaitu @Jnecare, @J&texpressid dan @Posindonesia. Akun ini digunakan untuk layanan customer secara online yang disediakan untuk menyampaikan pendapat, kritik, saran atau keluhan pelanggan. Agar dapat mengolah komentar yang banyak tentu membutuhkan waktu yang lebih besar jika hanya dilakukan secara sederhana. Penelitian ini bertujuan untuk menganalisis sentimen perusahaan ekpedisi mana yang lebih unggul dari beberapa layanan jasa ekspedisi, metode yang akan digunakan yaitu metode Support Vector Machine (SVM). Berdasarkan hasil penelitian diperoleh performa tertinggi yaitu pada ekpedisi J&T Express menggunakan algoritma Support Vector Machine menghasikan accuracy sebesar 85%, precision sebesar 59.35%, recall sebesar 58.67%, dan f1-score sebesar 58.01% selanjutnya pada ekpedisi JNE menghasikan accuracy sebesar 82.29%, precision sebesar 54.54%, recall sebesar 55.83%, dan f1-score sebesar 54.97% sedangkan pada Pos Indonesia menghasikan accuracy sebesar 77.78%, precision sebesar 35.9%, recall sebesar 58.67%, dan f1-score sebesar 33.85%. Dari hasil perbandingan ketiga jasa ekspedisi tersebut terbukti bahwa algoritma SVM mampu menghasilkan performa yang tinggi karena tidak memiliki satupun nilai yang tidak wajar baik pada performa accuracy, precision, recall dan F1-Score.Kata kunci: Sentimen, customer, ekspedisi, SVMAbstract—Customer satisfaction is a problem that must be observed in a company, because customers are the reason why a company is still standing and successful. JNE, J&T and Pos Indonesia expedition companies have customer service twitter accounts, namely @Jnecare, @J&texpressid and @Posindonesia. This account is used for online customer service provided to convey opinions, criticisms, suggestions or customer complaints. In order to be able to process a lot of comments, of course it takes more time if it's only done in a simple way. This study aims to analyze which shipping company sentiment is superior to some courier services, the method to be used is the Support Vector Machine (SVM) method. Based on the results of the study, the highest performance was obtained on the J&T Express expedition using the Support Vector Machine algorithm resulting in an accuracy of 85%, a precision of 59.35%, a recall of 58.67%, and an f1-score of 58.01% then on a JNE expedition it produced an accuracy of 82.29%, a precision of 54.54%, recall of 55.83%, and f1-score of 54.97% while Pos Indonesia produced an accuracy of 77.78%, precision of 35.9%, recall of 58.67%, and f1-score of 33.85%. From the results of the comparison of the three shipping services it is proven that the SVM algorithm is capable of producing high performance because it does not have any unreasonable values in terms of accuracy, precision, recall and F1-Score performance. Keywords: Sentiment, customer, expedition, SVM
35
Zhang, Weichun, Hongbin Liu, Wei Wu, Linqing Zhan, and Jing Wei. "Mapping Rice Paddy Based on Machine Learning with Sentinel-2 Multi-Temporal Data: Model Comparison and Transferability." Remote Sensing 12, no. 10 (May 19, 2020): 1620. http://dx.doi.org/10.3390/rs12101620.
Full textAbstract:
Rice is an important agricultural crop in the Southwest Hilly Area, China, but there has been a lack of efficient and accurate monitoring methods in the region. Recently, convolutional neural networks (CNNs) have obtained considerable achievements in the remote sensing community. However, it has not been widely used in mapping a rice paddy, and most studies lack the comparison of classification effectiveness and efficiency between CNNs and other classic machine learning models and their transferability. This study aims to develop various machine learning classification models with remote sensing data for comparing the local accuracy of classifiers and evaluating the transferability of pretrained classifiers. Therefore, two types of experiments were designed: local classification experiments and model transferability experiments. These experiments were conducted using cloud-free Sentinel-2 multi-temporal data in Banan District and Zhongxian County, typical hilly areas of Southwestern China. A pure pixel extraction algorithm was designed based on land-use vector data and a Google Earth Online image. Four convolutional neural network (CNN) algorithms (one-dimensional (Conv-1D), two-dimensional (Conv-2D) and three-dimensional (Conv-3D_1 and Conv-3D_2) convolutional neural networks) were developed and compared with four widely used classifiers (random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM) and multilayer perceptron (MLP)). Recall, precision, overall accuracy (OA) and F1 score were applied to evaluate classification accuracy. The results showed that Conv-2D performed best in local classification experiments with OA of 93.14% and F1 score of 0.8552 in Banan District, OA of 92.53% and F1 score of 0.8399 in Zhongxian County. CNN-based models except Conv-1D provided more desirable performance than non-CNN classifiers. Besides, among the non-CNN classifiers, XGBoost received the best result with OA of 89.73% and F1 score of 0.7742 in Banan District, SVM received the best result with OA of 88.57% and F1 score of 0.7538 in Zhongxian County. In model transferability experiments, almost all CNN classifiers had low transferability. RF and XGBoost models have achieved acceptable F1 scores for transfer (RF = 0.6673 and 0.6469, XGBoost = 0.7171 and 0.6709, respectively).
36
Dhingra, Om P., James Bernstein, Shaina D. Barnes, Hannah VanLaanen, Natasha Wadlington, and Jessica Chang. "Novel Oral Testosterone Formulation Improves Male Well Being Without Compromising International Prostate Symptom Scores." Journal of the Endocrine Society 5, Supplement_1 (May 1, 2021): A760. http://dx.doi.org/10.1210/jendso/bvab048.1546.
Full textAbstract:
Abstract Introduction: Male hypogonadism results from insufficient secretion of testosterone (T) and is characterized by low serum T concentrations. Common symptoms of hypogonadism include decreased libido, impotence, weakness, low energy, depression and/or loss of motivation, memory and concentrating issues, and sleep disturbances. Several forms of T replacement are available. Testosterone undecanoate (TU) is a testosterone prodrug available in oral formulations. A novel TU formulation, SOV2012-F1, has been submitted for FDA consideration under the name KYZATREX®. While TU efficacy is measured by serum total T, patientfocused endpoints such as Patient Reported Outcomes (PROs) are valuable indicators of well-being and psychosexual symptom abatement. Methods: A Phase 3, randomized, multicenter, open-label, active-controlled trial, comparing SOV2012F1 (testosterone undecanoate capsules) (n=214) with AndroGel® (1.62% topical testosterone gel) (n=100) enrolled males aged 18 to 65 years with hypogonadism (serum total T levels ≤281 ng/dL). A key exploratory endpoint was change from Baseline (ΔBL) after 52 weeks of treatment in the following PROs: International Prostate Symptom Score (IPSS), Psychosexual Daily Questionnaire (PDQ), Short Form Health Survey 36 item (SF-36), and the International Index of Erectile Function (IIEF). Results: Total or overall scores for all PROs (IPSS, PDQ, SF-36 and IIEF) showed increased improvement in the SOV2012-F1 group relative to the Androgel group, and all but IPSS demonstrated improvement relative to BL. For IPSS, due to the potential that T could worsen urinary symptoms, the ΔBL would ideally be small to reflect minimal impact. Change for the SOV2012-F1 and AndroGel groups was, respectively, 0.6 and 1.0. Further, the IPSS total score was not significantly different from BL in the patients receiving SOV20212-F1 (p = 0.5659). For PDQ, a clinically meaningful improvement of sexual desire in hypogonadal men age ≥65 years is ≥0.7; mean ΔBL was 1.6 in the SOV2012-F1 group versus 1.4 in the AndroGel group. In the SF-36, the mean ΔBL total score was 83.7 in the SOV2012-F1 group and 70.2 in the AndroGel group. Further, post hoc analysis of the Health Change category found a significant (p ≤ 0.05) improvement in patient perspectives on health over the course of the study. The overall satisfaction score of the IIEF trended towards significance for the SOV2012-F1 group with a mean ΔBL score of 2.3 versus and 1.6 in the AndroGel group. The ΔBL for the 4 domains of male sexual function were small and consistent between the SOV2012-F1 and AndroGel groups. Comparable results were noted for Early Withdrawals and All Subjects across all PROs. Conclusion: Treatment with SOV2012-F1 for 52 weeks exceeded AndroGel patient satisfaction as measured by PROs including IPSS, PDQ, SF-36 and IIEF, demonstrating clinical distinction. Further analysis of SOV2012-F1 will be forthcoming.
37
Pradhan, Biswajeet, Husam A. H. Al-Najjar, Maher Ibrahim Sameen, Ivor Tsang, and Abdullah M. Alamri. "Unseen Land Cover Classification from High-Resolution Orthophotos Using Integration of Zero-Shot Learning and Convolutional Neural Networks." Remote Sensing 12, no. 10 (May 23, 2020): 1676. http://dx.doi.org/10.3390/rs12101676.
Full textAbstract:
Zero-shot learning (ZSL) is an approach to classify objects unseen during the training phase and shown to be useful for real-world applications, especially when there is a lack of sufficient training data. Only a limited amount of works has been carried out on ZSL, especially in the field of remote sensing. This research investigates the use of a convolutional neural network (CNN) as a feature extraction and classification method for land cover mapping using high-resolution orthophotos. In the feature extraction phase, we used a CNN model with a single convolutional layer to extract discriminative features. In the second phase, we used class attributes learned from the Word2Vec model (pre-trained by Google News) to train a second CNN model that performed class signature prediction by using both the features extracted by the first CNN and class attributes during training and only the features during prediction. We trained and tested our models on datasets collected over two subareas in the Cameron Highlands (training dataset, first test dataset) and Ipoh (second test dataset) in Malaysia. Several experiments have been conducted on the feature extraction and classification models regarding the main parameters, such as the network’s layers and depth, number of filters, and the impact of Gaussian noise. As a result, the best models were selected using various accuracy metrics such as top-k categorical accuracy for k = [1,2,3], Recall, Precision, and F1-score. The best model for feature extraction achieved 0.953 F1-score, 0.941 precision, 0.882 recall for the training dataset and 0.904 F1-score, 0.869 precision, 0.949 recall for the first test dataset, and 0.898 F1-score, 0.870 precision, 0.838 recall for the second test dataset. The best model for classification achieved an average of 0.778 top-one, 0.890 top-two and 0.942 top-three accuracy, 0.798 F1-score, 0.766 recall and 0.838 precision for the first test dataset and 0.737 top-one, 0.906 top-two, 0.924 top-three, 0.729 F1-score, 0.676 recall and 0.790 precision for the second test dataset. The results demonstrated that the proposed ZSL is a promising tool for land cover mapping based on high-resolution photos.
38
AlBeladi, Ali A., and Ali H. Muqaibel. "Evaluating compressive sensing algorithms in through-the-wall radar via F1-score." International Journal of Signal and Imaging Systems Engineering 11, no. 3 (2018): 164. http://dx.doi.org/10.1504/ijsise.2018.093268.
Full text
39
AlBeladi, Ali A., and Ali H. Muqaibel. "Evaluating compressive sensing algorithms in through-the-wall radar via F1-score." International Journal of Signal and Imaging Systems Engineering 11, no. 3 (2018): 164. http://dx.doi.org/10.1504/ijsise.2018.10014297.
Full text
40
Syed, Khajamoinuddin, William Sleeman, Michael Hagan, Jatinder Palta, Rishabh Kapoor, and Preetam Ghosh. "Automatic Incident Triage in Radiation Oncology Incident Learning System." Healthcare 8, no. 3 (August 14, 2020): 272. http://dx.doi.org/10.3390/healthcare8030272.
Full textAbstract:
The Radiotherapy Incident Reporting and Analysis System (RIRAS) receives incident reports from Radiation Oncology facilities across the US Veterans Health Affairs (VHA) enterprise and Virginia Commonwealth University (VCU). In this work, we propose a computational pipeline for analysis of radiation oncology incident reports. Our pipeline uses machine learning (ML) and natural language processing (NLP) based methods to predict the severity of the incidents reported in the RIRAS platform using the textual description of the reported incidents. These incidents in RIRAS are reviewed by a radiation oncology subject matter expert (SME), who initially triages some incidents based on the salient elements in the incident report. To automate the triage process, we used the data from the VHA treatment centers and the VCU radiation oncology department. We used NLP combined with traditional ML algorithms, including support vector machine (SVM) with linear kernel, and compared it against the transfer learning approach with the universal language model fine-tuning (ULMFiT) algorithm. In RIRAS, severities are divided into four categories; A, B, C, and D, with A being the most severe to D being the least. In this work, we built models to predict High (A & B) vs. Low (C & D) severity instead of all the four categories. Models were evaluated with macro-averaged precision, recall, and F1-Score. The Traditional ML machine learning (SVM-linear) approach did well on the VHA dataset with 0.78 F1-Score but performed poorly on the VCU dataset with 0.5 F1-Score. The transfer learning approach did well on both datasets with 0.81 F1-Score on VHA dataset and 0.68 F1-Score on the VCU dataset. Overall, our methods show promise in automating the triage and severity determination process from radiotherapy incident reports.
41
Karayiğit, Habibe, Ali Akdagli, and Çiğdem İnan Aci. "Homophobic and Hate Speech Detection Using Multilingual-BERT Model on Turkish Social Media." Information Technology and Control 51, no. 2 (June 23, 2022): 356–75. http://dx.doi.org/10.5755/j01.itc.51.2.29988.
Full textAbstract:
Homophobic expressions are a form of insulting the sexual orientation or personality of people. Severe psychological traumas may occur in people who are exposed to this type of communication. It is important to develop automatic classification systems based on language models to examine social media content and distinguish homophobic discourse. This study aims to present a pre-trained Multilingual Bidirectional Encoder Representations from Transformers (M-BERT) model that can successfully detect whether Turkish comments on social media contain homophobic or related hate comments (i.e., sexist, severe humiliation, and defecation expressions). Comments in the Homophobic-Abusive Turkish Comments (HATC) dataset were collected from Instagram to train the detection models. The HATC dataset was manually labeled at the sentence level and combined with the Abusive Turkish Comments (ATC) dataset that has developed in our previous study. The HATC dataset has been balanced using the resampling method and two forms of the dataset (i.e., resHATC and original HATC) were used in the experiments. Afterward, the M-BERT model was compared with DL-based models (i.e., Long-Short Term Memory, Bidirectional Long-Short Term Memory (BiLSTM), Gated Recurrent Unit), Traditional Machine Learning (TML) classifiers (i.e., Support Vector Machine, Naive Bayes, Random Forest) and Ensemble Classifiers (i.e., Adaptive Boosting, eXtreme Gradient Boosting, Gradient Boosting) for the best model selection. The performance of the detection models was evaluated using F1-score, precision, and recall performance metrics. Results showed the best performance (homophobic F1-score: 82.64%, hateful F1-score: 91.75%, neutral F1-score: 96.08%, average F1-score: 90.15%) was achieved with the M-BERT model on the HATC dataset. The M-BERT detection model can increase the effectiveness of filters in detecting Turkish homophobic and related hate speech in social networks. It can be used to detect homophobic and related hate speech for different languages since the M-BERT model has multilingual pre-trained data.
42
Zhu, Xiaoya, Junfeng Wang, Zhiyang Fang, Xiaokang Yin, and Shengli Liu. "BBDetector: A Precise and Scalable Third-Party Library Detection in Binary Executables with Fine-Grained Function-Level Features." Applied Sciences 13, no. 1 (December 28, 2022): 413. http://dx.doi.org/10.3390/app13010413.
Full textAbstract:
Third-party library (TPL) reuse may introduce vulnerable or malicious code and expose the software, which exposes them to potential risks. Thus, it is essential to identify third-party dependencies and take immediate corrective action to fix critical vulnerabilities when a damaged reusable component is found or reported. However, most of the existing methods only rely on syntactic features, which results in low recognition accuracy and significantly discounts the detection performance by obfuscation techniques. In addition, a few semantic-based approaches face the efficiency problem. To resolve these problems, we propose and implement a more precise and scalable TPL detection method BBDetector . In addition to syntactic features, we consider the rich function-level semantic features and form a feature vector for each function. Moreover, we design a scalable function vector similarity search method to identify anchor functions and the candidate libraries, based upon which we carry out TPL detection. The experiment results demonstrate that BBDetector outperforms B2SFinder and ModX in terms of effectiveness, efficiency, and obfuscation-resilient capability. For the nix binaries, the F1-score of BBDetector is 1.11% and 11.21% higher than that of ModX and B2SFinder, respectively. Moreover, for the Ubuntu binaries, the F1-score of BBDetector is 1.32% and 14.93% is higher than that of ModX and B2SFinder, respectively. And in terms of efficiency, the detection time of BBDetector is only 30.02% of ModX. Besides, for the obfuscation-resilient capability, BBDetector is much stronger than B2SFinder. BBDetector achieves a F1-score of 71%, slightly lower than the F1-score of 77% achieved with the non-obfuscated binary programs. However, B2SFinder only achieves an F1-score of 28%, much lower than that of 67% achieved with the non-obfuscated binary programs.
43
Xu, Shiluo, Yingxu Song, and Xiulan Hao. "A Comparative Study of Shallow Machine Learning Models and Deep Learning Models for Landslide Susceptibility Assessment Based on Imbalanced Data." Forests 13, no. 11 (November 14, 2022): 1908. http://dx.doi.org/10.3390/f13111908.
Full textAbstract:
A landslide is a type of geological disaster that poses a threat to human lives and property. Landslide susceptibility assessment (LSA) is a crucial tool for landslide prevention. This paper’s primary objective is to compare the performances of conventional shallow machine learning methods and deep learning methods in LSA based on imbalanced data to evaluate the applicability of the two types of LSA models when class-weighted strategies are applied. In this article, logistic regression (LR), random forest (RF), deep fully connected neural network (DFCNN), and long short-term memory (LSTM) neural networks were employed for modeling in the Zigui-Badong area of the Three Gorges Reservoir area, China. Eighteen landslide influence factors were introduced to compare the performance of four models under a class balanced strategy versus a class imbalanced strategy. The Spearman rank correlation coefficient (SRCC) was applied for factor correlation analysis. The results reveal that the elevation and distance to rivers play a dominant role in LSA tasks. It was observed that DFCNN (AUC = 0.87, F1-score = 0.60) and LSTM (AUC = 0.89, F1-score = 0.61) significantly outperformed LR (AUC = 0.89, F1-score = 0.50) and RF (AUC = 0.88, F1-score = 0.50) under the class imbalanced strategy. The RF model achieved comparable outcomes (AUC = 0.90, F1-score = 0.61) to deep learning models under the class balanced strategy and ran at a faster training speed (up to 63 times faster than deep learning models). The LR model performance was inferior to that of the other three models under the balanced strategy. Meanwhile, the deep learning models and the shallow machine learning models showed significant differences in susceptibility spatial patterns. This paper’s findings will aid researchers in selecting appropriate LSA models. It is also valuable for land management policy making and disaster prevention and mitigation.
44
Khosa, Saima, Arif Mehmood, and Muhammad Rizwan. "Unifying Sentence Transformer Embedding and Softmax Voting Ensemble for Accurate News Category Prediction." Computers 12, no. 7 (July 8, 2023): 137. http://dx.doi.org/10.3390/computers12070137.
Full textAbstract:
The study focuses on news category prediction and investigates the performance of sentence embedding of four transformer models (BERT, RoBERTa, MPNet, and T5) and their variants as feature vectors when combined with Softmax and Random Forest using two accessible news datasets from Kaggle. The data are stratified into train and test sets to ensure equal representation of each category. Word embeddings are generated using transformer models, with the last hidden layer selected as the embedding. Mean pooling calculates a single vector representation called sentence embedding, capturing the overall meaning of the news article. The performance of Softmax and Random Forest, as well as the soft voting of both, is evaluated using evaluation measures such as accuracy, F1 score, precision, and recall. The study also contributes by evaluating the performance of Softmax and Random Forest individually. The macro-average F1 score is calculated to compare the performance of different transformer embeddings in the same experimental settings. The experiments reveal that MPNet versions v1 and v3 achieve the highest F1 score of 97.7% when combined with Random Forest, while T5 Large embedding achieves the highest F1 score of 98.2% when used with Softmax regression. MPNet v1 performs exceptionally well when used in the voting classifier, obtaining an impressive F1 score of 98.6%. In conclusion, the experiments validate the superiority of certain transformer models, such as MPNet v1, MPNet v3, and DistilRoBERTa, when used to calculate sentence embeddings within the Random Forest framework. The results also highlight the promising performance of T5 Large and RoBERTa Large in voting of Softmax regression and Random Forest. The voting classifier, employing transformer embeddings and ensemble learning techniques, consistently outperforms other baselines and individual algorithms. These findings emphasize the effectiveness of the voting classifier with transformer embeddings in achieving accurate and reliable predictions for news category classification tasks.
45
Baik, Seung-Min, Miae Lee, Kyung-Sook Hong, and Dong-Jin Park. "Development of Machine-Learning Model to Predict COVID-19 Mortality: Application of Ensemble Model and Regarding Feature Impacts." Diagnostics 12, no. 6 (June 14, 2022): 1464. http://dx.doi.org/10.3390/diagnostics12061464.
Full textAbstract:
This study was designed to develop machine-learning models to predict COVID-19 mortality and identify its key features based on clinical characteristics and laboratory tests. For this, deep-learning (DL) and machine-learning (ML) models were developed using receiver operating characteristic (ROC) area under the curve (AUC) and F1 score optimization of 87 parameters. Of the two, the DL model exhibited better performance (AUC 0.8721, accuracy 0.84, and F1 score 0.76). However, we also blended DL with ML, and the ensemble model performed the best (AUC 0.8811, accuracy 0.85, and F1 score 0.77). The DL model is generally unable to extract feature importance; however, we succeeded by using the Shapley Additive exPlanations method for each model. This study demonstrated both the applicability of DL and ML models for classifying COVID-19 mortality using hospital-structured data and that the ensemble model had the best predictive ability.
46
Yang, Jincheng, Shiwen Chen, Jinpeng Dong, and Xiao Han. "Binarization for time-frequency images of LPI radar signals based on K-means." Journal of Physics: Conference Series 2522, no. 1 (June 1, 2023): 012011. http://dx.doi.org/10.1088/1742-6596/2522/1/012011.
Full textAbstract:
Abstract Low probability of intercept radar signal is widely used because it is difficult to be intercepted by non-cooperative receivers in electronic warfare. We need to binarize the time-frequency images when analyzing LPI radar signals based on time-frequency distribution. However, the existing binarization algorithms cannot distinguish noise from the signal frequency at low signal-to-noise ratios. In this paper, we propose to use K-means algorithm to binarize the gray time-frequency images of LPI radar signals. We use F1-score to comprehensively consider the effect of binarization. Based on linear frequency modulation signals, the simulation experiments show that the F1-score of the proposed algorithm exceeds the F1-score of Otsu’s method by 40% to 80% when the signal-to-noise ratio is from -6 dB to 2 dB. The binarization effect of K-means is excellent and has great application prospects.
47
Hor Yan, Tan, Sazuan Nazrah Mohd Azam, Zamani Md. Sani, and Azizul Azizan. "Accuracy study of image classification for reverse vending machine waste segregation using convolutional neural network." International Journal of Electrical and Computer Engineering (IJECE) 14, no. 1 (February 1, 2024): 366. http://dx.doi.org/10.11591/ijece.v14i1.pp366-374.
Full textAbstract:
This study aims to create a sorting system with high accuracy that can classify various beverage containers based on types and separate them accordingly. This reverse vending machine (RVM) provides an image classification method and allows for recycling three types of beverage containers: drink carton boxes, polyethylene terephthalate (PET) bottles, and aluminium cans. The image classification method used in this project is transfer learning with convolutional neural networks (CNN). AlexNet, GoogLeNet, DenseNet201, InceptionResNetV2, InceptionV3, MobileNetV2, XceptionNet, ShuffleNet, ResNet 18, ResNet 50, and ResNet 101 are the neural networks that used in this project. This project will compare the F1-score and computational time among the eleven networks. The F1-score and computational time of image classification differs for each neural network. In this project, the AlexNet network gave the best F1-score, 97.50% with the shortest computational time, 2229.235 s among the eleven neural networks.
48
Pino, Rodney, Renier Mendoza, and Rachelle Sambayan. "Optical character recognition system for Baybayin scripts using support vector machine." PeerJ Computer Science 7 (February 15, 2021): e360. http://dx.doi.org/10.7717/peerj-cs.360.
Full textAbstract:
In 2018, the Philippine Congress signed House Bill 1022 declaring the Baybayin script as the Philippines’ national writing system. In this regard, it is highly probable that the Baybayin and Latin scripts would appear in a single document. In this work, we propose a system that discriminates the characters of both scripts. The proposed system considers the normalization of an individual character to identify if it belongs to Baybayin or Latin script and further classify them as to what unit they represent. This gives us four classification problems, namely: (1) Baybayin and Latin script recognition, (2) Baybayin character classification, (3) Latin character classification, and (4) Baybayin diacritical marks classification. To the best of our knowledge, this is the first study that makes use of Support Vector Machine (SVM) for Baybayin script recognition. This work also provides a new dataset for Baybayin, its diacritics, and Latin characters. Classification problems (1) and (4) use binary SVM while (2) and (3) apply the multiclass SVM classification. On average, our numerical experiments yield satisfactory results: (1) has 98.5% accuracy, 98.5% precision, 98.49% recall, and 98.5% F1 Score; (2) has 96.51% accuracy, 95.62% precision, 95.61% recall, and 95.62% F1 Score; (3) has 95.8% accuracy, 95.85% precision, 95.8% recall, and 95.83% F1 Score; and (4) has 100% accuracy, 100% precision, 100% recall, and 100% F1 Score.
49
Suprihanto, Suprihanto, Iwan Awaludin, Muhammad Fadhil, and M. Andhika Zaini Zulfikor. "Analisis Kinerja ResNet-50 dalam Klasifikasi Penyakit pada Daun Kopi Robusta." Jurnal Informatika 9, no. 2 (October 2, 2022): 116–22. http://dx.doi.org/10.31294/inf.v9i1.13049.
Full textAbstract:
Indonesia merupakan negara agraris yang banyak ditanami tumbuhan salah satunya yaitu tanaman kopi. Dalam budidaya tanaman kopi terdapat halangan seperti hama dan cuaca ekstrim yang bisa membuat tanaman layu atau terkena penyakit. Dengan kemajuan teknologi yang pesat di masa kini, banyak sistem yang membantu para petani untuk membantu mengidentifikasi penyakit pada daun kopi. Sistem ini menggunakan teknologi salah satu arsitektur Convolutional Neural Network, yaitu ResNet-50 untuk mengidentifikasi dan mengklasifikasi penyakit pada daun kopi robusta. Dalam melatih model ResNet-50 diperlukan proses pelatihan dan validasi model yang kemudian model yang telah dilatih akan dilakukan pengujian. Pengujian model akan digunakan untuk mengukur kinerja model yang akan dihitung dengan menggunakan Confusion Matrix yang variabel output nya akan digunakan untuk menghitung Akurasi, presisi, recall, Spesifisitas, dan F1 Score. Penelitian ini akan berfokus pada perhitungan nilai kinerja akurasi dan F1 Score dari model tersebut. Penelitian dilakukan dengan dua kasus yaitu binary class dan multiclass dimana binary class untuk mengklasifikasi gambar daun kopi robusta sehat dan sakit dan multiclass untuk mengklasifikasikan gambar daun kopi robusta pada setiap jenis kategori dari daun yang berpenyakit dan sehat. Hasil dari penelitian menunjukan pada kasus binary class mencapai akurasi 92,68% dan f1-score mencapai 92,88%, sedangkan pada kasus multiclass akurasi hanya mencapai 88,98% dan f1-score mencapai 88,44%. Kedua kasus tersebut diukur menggunakan data testing dengan model yang telah dilatih.
50
Amaliah Faradibah, Dewi Widyawati, A Ulfah Tenripada Syahar, and Sitti Rahmah Jabir. "Comparison Analysis of Random Forest Classifier, Support Vector Machine, and Artificial Neural Network Performance in Multiclass Brain Tumor Classification." Indonesian Journal of Data and Science 4, no. 2 (July 31, 2023): 54–63. http://dx.doi.org/10.56705/ijodas.v4i2.73.
Full textAbstract:
This study aims to analyze and compare the performance of three main classification models, namely Random Forest Classifier, Support Vector Machine, and Artificial Neural Network, in classifying Multiclass brain tumors based on MRI images. The research method includes exploratory data analysis (EDA), dataset preprocessing with image segmentation using the Canny method, and feature extraction using the Humoment method. The performance of the classification models is evaluated based on accuracy, precision, recall, and F1 score. The analysis results show variations in the performance of the three classification models, with Random Forest Classifier having an accuracy of 0.7, weighted precision of 0.55, weighted recall of 0.7, and weighted F1 score of 0.59; Support Vector Machine having an accuracy of 0.71, weighted precision of 0.5, weighted recall of 0.71, and weighted F1 score of 0.59; and Artificial Neural Network having an accuracy of 0.62, weighted precision of 0.6, weighted recall of 0.62, and weighted F1 score of 0.61. Visualization using box plots also reveals outliers in the performance of the three models. These findings indicate variations and outliers in the performance of the classification models for Multiclass brain tumor classification. Further analysis is needed to understand the factors that influence performance differences and identify ways to improve the classification model performance for brain tumor diagnosis based on MRI images