Relevant bibliographies by topics / F1-score

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Book chapters
  4. Conference papers
  5. Reports

Academic literature on the topic 'F1-score'

Author: Grafiati
Published: 4 June 2021
Last updated: 16 January 2024

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources 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.

Journal articles on the topic "F1-score"

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 text
Abstract:
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.
APA, Harvard, Vancouver, ISO, and other styles
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 text
Abstract:
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.
APA, Harvard, Vancouver, ISO, and other styles
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 text
Abstract:
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.
APA, Harvard, Vancouver, ISO, and other styles
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 text
Abstract:
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.
APA, Harvard, Vancouver, ISO, and other styles
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 text
Abstract:
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.
APA, Harvard, Vancouver, ISO, and other styles
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 text
Abstract:
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.
APA, Harvard, Vancouver, ISO, and other styles
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
APA, Harvard, Vancouver, ISO, and other styles
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 text
Abstract:
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%).
APA, Harvard, Vancouver, ISO, and other styles
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 text
Abstract:
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.
APA, Harvard, Vancouver, ISO, and other styles
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 text
Abstract:
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.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "F1-score"

1

Svedberg, Jonatan, and George Shmas. "Effekten av textaugmenteringsstrategier på träffsäkerhet, F1-värde och viktat F1-värde." Thesis, KTH, Hälsoinformatik och logistik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-296550.

Full text
Abstract:
Att utveckla en sofistikerad chatbotlösning kräver stora mängder textdata för att kunna anpassalösningen till en specifik domän. Att manuellt skapa en komplett uppsättning textdata, specialanpassat för den givna domänen och innehållandes ett stort antal varierande meningar som en människa kan tänkas yttra, är ett enormt tidskrävande arbete. För att kringgå detta tillämpas dataaugmentering för att generera mer data utifrån en mindre uppsättning redan existerande textdata. Softronic AB vill undersöka alternativa strategier för dataaugmentering med målet att eventuellt ersätta den nuvarande lösningen med en mer vetenskapligt underbyggd sådan. I detta examensarbete har prototypmodeller utvecklats för att jämföra och utvärdera effekten av olika textaugmenteringsstrategier. Resultatet av genomförda experiment med prototypmodellerna visar att augmentering genom synonymutbyten med en domänanpassad synonymordlista, presenterade märkbart förbättrade effekter på förmågan hos en NLU-modell att korrekt klassificera data, gentemot övriga utvärderade strategier. Vidare indikerar resultatet att ett samband föreligger mellan den strukturella variationsgraden av det augmenterade datat och de tillämpade språkparens semantiska likhetsgrad under tillbakaöversättningar.
Developing a sophisticated chatbot solution requires large amounts of text data to be able to adapt the solution to a specific domain. Manually creating a complete set of text data, specially adapted for the given domain, and containing a large number of varying sentences that a human conceivably can express, is an exceptionally time-consuming task. To circumvent this, data augmentation is applied to generate more data based on a smaller set of already existing text data. Softronic AB wants to investigate alternative strategies for data augmentation with the aim of possibly replacing the current solution with a more scientifically substantiated one. In this thesis, prototype models have been developed to compare and evaluate the effect of different text augmentation strategies. The results of conducted experiments with the prototype models show that augmentation through synonym swaps with a domain-adapted thesaurus, presented noticeably improved effects on the ability of an NLU-model to correctly classify data, compared to other evaluated strategies. Furthermore, the result indicates that there is a relationship between the structural degree of variation of the augmented data and the applied language pair's semantic degree of similarity during back-translations.
APA, Harvard, Vancouver, ISO, and other styles
2

Makki, Sara. "An Efficient Classification Model for Analyzing Skewed Data to Detect Frauds in the Financial Sector." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSE1339/document.

Full text
Abstract:
Différents types de risques existent dans le domaine financier, tels que le financement du terrorisme, le blanchiment d’argent, la fraude de cartes de crédit, la fraude d’assurance, les risques de crédit, etc. Tout type de fraude peut entraîner des conséquences catastrophiques pour des entités telles que les banques ou les compagnies d’assurances. Ces risques financiers sont généralement détectés à l'aide des algorithmes de classification. Dans les problèmes de classification, la distribution asymétrique des classes, également connue sous le nom de déséquilibre de classe (class imbalance), est un défi très commun pour la détection des fraudes. Des approches spéciales d'exploration de données sont utilisées avec les algorithmes de classification traditionnels pour résoudre ce problème. Le problème de classes déséquilibrées se produit lorsque l'une des classes dans les données a beaucoup plus d'observations que l’autre classe. Ce problème est plus vulnérable lorsque l'on considère dans le contexte des données massives (Big Data). Les données qui sont utilisées pour construire les modèles contiennent une très petite partie de groupe minoritaire qu’on considère positifs par rapport à la classe majoritaire connue sous le nom de négatifs. Dans la plupart des cas, il est plus délicat et crucial de classer correctement le groupe minoritaire plutôt que l'autre groupe, comme la détection de la fraude, le diagnostic d’une maladie, etc. Dans ces exemples, la fraude et la maladie sont les groupes minoritaires et il est plus délicat de détecter un cas de fraude en raison de ses conséquences dangereuses qu'une situation normale. Ces proportions de classes dans les données rendent très difficile à l'algorithme d'apprentissage automatique d'apprendre les caractéristiques et les modèles du groupe minoritaire. Ces algorithmes seront biaisés vers le groupe majoritaire en raison de leurs nombreux exemples dans l'ensemble de données et apprendront à les classer beaucoup plus rapidement que l'autre groupe. Dans ce travail, nous avons développé deux approches : Une première approche ou classifieur unique basée sur les k plus proches voisins et utilise le cosinus comme mesure de similarité (Cost Sensitive Cosine Similarity K-Nearest Neighbors : CoSKNN) et une deuxième approche ou approche hybride qui combine plusieurs classifieurs uniques et fondu sur l'algorithme k-modes (K-modes Imbalanced Classification Hybrid Approach : K-MICHA). Dans l'algorithme CoSKNN, notre objectif était de résoudre le problème du déséquilibre en utilisant la mesure de cosinus et en introduisant un score sensible au coût pour la classification basée sur l'algorithme de KNN. Nous avons mené une expérience de validation comparative au cours de laquelle nous avons prouvé l'efficacité de CoSKNN en termes de taux de classification correcte et de détection des fraudes. D’autre part, K-MICHA a pour objectif de regrouper des points de données similaires en termes des résultats de classifieurs. Ensuite, calculez les probabilités de fraude dans les groupes obtenus afin de les utiliser pour détecter les fraudes de nouvelles observations. Cette approche peut être utilisée pour détecter tout type de fraude financière, lorsque des données étiquetées sont disponibles. La méthode K-MICHA est appliquée dans 3 cas : données concernant la fraude par carte de crédit, paiement mobile et assurance automobile. Dans les trois études de cas, nous comparons K-MICHA au stacking en utilisant le vote, le vote pondéré, la régression logistique et l’algorithme CART. Nous avons également comparé avec Adaboost et la forêt aléatoire. Nous prouvons l'efficacité de K-MICHA sur la base de ces expériences. Nous avons également appliqué K-MICHA dans un cadre Big Data en utilisant H2O et R. Nous avons pu traiter et analyser des ensembles de données plus volumineux en très peu de temps
There are different types of risks in financial domain such as, terrorist financing, money laundering, credit card fraudulence and insurance fraudulence that may result in catastrophic consequences for entities such as banks or insurance companies. These financial risks are usually detected using classification algorithms. In classification problems, the skewed distribution of classes also known as class imbalance, is a very common challenge in financial fraud detection, where special data mining approaches are used along with the traditional classification algorithms to tackle this issue. Imbalance class problem occurs when one of the classes have more instances than another class. This problem is more vulnerable when we consider big data context. The datasets that are used to build and train the models contain an extremely small portion of minority group also known as positives in comparison to the majority class known as negatives. In most of the cases, it’s more delicate and crucial to correctly classify the minority group rather than the other group, like fraud detection, disease diagnosis, etc. In these examples, the fraud and the disease are the minority groups and it’s more delicate to detect a fraud record because of its dangerous consequences, than a normal one. These class data proportions make it very difficult to the machine learning classifier to learn the characteristics and patterns of the minority group. These classifiers will be biased towards the majority group because of their many examples in the dataset and will learn to classify them much faster than the other group. After conducting a thorough study to investigate the challenges faced in the class imbalance cases, we found that we still can’t reach an acceptable sensitivity (i.e. good classification of minority group) without a significant decrease of accuracy. This leads to another challenge which is the choice of performance measures used to evaluate models. In these cases, this choice is not straightforward, the accuracy or sensitivity alone are misleading. We use other measures like precision-recall curve or F1 - score to evaluate this trade-off between accuracy and sensitivity. Our objective is to build an imbalanced classification model that considers the extreme class imbalance and the false alarms, in a big data framework. We developed two approaches: A Cost-Sensitive Cosine Similarity K-Nearest Neighbor (CoSKNN) as a single classifier, and a K-modes Imbalance Classification Hybrid Approach (K-MICHA) as an ensemble learning methodology. In CoSKNN, our aim was to tackle the imbalance problem by using cosine similarity as a distance metric and by introducing a cost sensitive score for the classification using the KNN algorithm. We conducted a comparative validation experiment where we prove the effectiveness of CoSKNN in terms of accuracy and fraud detection. On the other hand, the aim of K-MICHA is to cluster similar data points in terms of the classifiers outputs. Then, calculating the fraud probabilities in the obtained clusters in order to use them for detecting frauds of new transactions. This approach can be used to the detection of any type of financial fraud, where labelled data are available. At the end, we applied K-MICHA to a credit card, mobile payment and auto insurance fraud data sets. In all three case studies, we compare K-MICHA with stacking using voting, weighted voting, logistic regression and CART. We also compared with Adaboost and random forest. We prove the efficiency of K-MICHA based on these experiments
APA, Harvard, Vancouver, ISO, and other styles
3

Wahab, Nor-Ul. "Evaluation of Supervised Machine LearningAlgorithms for Detecting Anomalies in Vehicle’s Off-Board Sensor Data." Thesis, Högskolan Dalarna, Mikrodataanalys, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:du-28962.

Full text
Abstract:
A diesel particulate filter (DPF) is designed to physically remove diesel particulate matter or soot from the exhaust gas of a diesel engine. Frequently replacing DPF is a waste of resource and waiting for full utilization is risky and very costly, so, what is the optimal time/milage to change DPF? Answering this question is very difficult without knowing when the DPF is changed in a vehicle. We are finding the answer with supervised machine learning algorithms for detecting anomalies in vehicles off-board sensor data (operational data of vehicles). Filter change is considered an anomaly because it is rare as compared to normal data. Non-sequential machine learning algorithms for anomaly detection like oneclass support vector machine (OC-SVM), k-nearest neighbor (K-NN), and random forest (RF) are applied for the first time on DPF dataset. The dataset is unbalanced, and accuracy is found misleading as a performance measure for the algorithms. Precision, recall, and F1-score are found good measure for the performance of the machine learning algorithms when the data is unbalanced. RF gave highest F1-score of 0.55 than K-NN (0.52) and OCSVM (0.51). It means that RF perform better than K-NN and OC-SVM but after further investigation it is concluded that the results are not satisfactory. However, a sequential approach should have been tried which could yield better result.
APA, Harvard, Vancouver, ISO, and other styles
4

Piják, Marek. "Klasifikace emailové komunikace." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2018. http://www.nusl.cz/ntk/nusl-385889.

Full text
Abstract:
This diploma's thesis is based around creating a classifier, which will be able to recognize an email communication received by Topefekt.s.r.o on daily basis and assigning it into classification class. This project will implement some of the most commonly used classification methods including machine learning. Thesis will also include evaluation comparing all used methods.
APA, Harvard, Vancouver, ISO, and other styles
5

BORA, NILUTPOL. "SECURING INDUSTRIAL IOT: GCN-BASED IDS IMPLEMENTATION AND A REVIEW OF TESTING FRAMEWORKS." Thesis, 2023. http://dspace.dtu.ac.in:8080/jspui/handle/repository/20410.

Full text
Abstract:
Cyber-attacks on Industrial IoT systems can result in severe consequences such as production loss, equipment damage, and even human casualties and hence security is of utmost concern in this application of IoT. This thesis, presents an approach for network security, intrusion detection that utilizes the spatial attributes of a network in attempt overcome the limitations discovered through literature review of various studies in Intrusion Detection and testing frameworks. For this graph-based neural network have been used that was seen promising in modelling complex relationships between graphical entities, making them a suitable approach for IDS in interconnected systems. Our approach leverages a graph representation of network traffic, that is used as an input for neural network through the use of convolution operation. Our approach makes use of flow features of the network in relation with the neighbouring flows in contrast to other machine learning models that uses flow features independent to each other. This work has been evaluated primarily on Edge-IIoT 2022, dataset and compared with existing well-known datasets and machine learning methods. The results show that our approach achieved average 5.49% improved F1-score, compared with other standard existing methods with our model having highest F1-Score of 0.996. Further research and development in this area will advance the field of IIoT security and enhance the resilience of industrial systems in the face of evolving threats.
APA, Harvard, Vancouver, ISO, and other styles
6

Iffat, Naz Syeda. "Machine Learning Classification of Facial Affect Recognition Deficits after Traumatic Brain Injury for Informing Rehabilitation Needs and Progress." Thesis, 2020. http://hdl.handle.net/1805/24774.

Full text
Abstract:
Indiana University-Purdue University Indianapolis (IUPUI)
A common impairment after a traumatic brain injury (TBI) is a deficit in emotional recognition, such as inferences of others’ intentions. Some researchers have found these impairments in 39\% of the TBI population. Our research information needed to make inferences about emotions and mental states comes from visually presented, nonverbal cues (e.g., facial expressions or gestures). Theory of mind (ToM) deficits after TBI are partially explained by impaired visual attention and the processing of these important cues. This research found that patients with deficits in visual processing differ from healthy controls (HCs). Furthermore, we found visual processing problems can be determined by looking at the eye tracking data developed from industry standard eye tracking hardware and software. We predicted that the eye tracking data of the overall population is correlated to the TASIT test. The visual processing of impaired (who got at least one answer wrong from TASIT questions) and unimpaired (who got all answer correctly from TASIT questions) differs significantly. We have divided the eye-tracking data into 3 second time blocks of time series data to detect the most salient individual blocks to the TASIT score. Our preliminary results suggest that we can predict the whole population's impairment using eye-tracking data with an improved f1 score from 0.54 to 0.73. For this, we developed optimized support vector machine (SVM) and random forest (RF) classifier.
APA, Harvard, Vancouver, ISO, and other styles
7

(9746081), Syeda Iffat Naz. "Machine Learning Classification of Facial Affect Recognition Deficits after Traumatic Brain Injury for Informing Rehabilitation Needs and Progress." Thesis, 2021.

Find full text
Abstract:
A common impairment after a traumatic brain injury (TBI) is a deficit in emotional recognition, such as inferences of others’ intentions. Some researchers have found these impairments in 39\% of the TBI population. Our research information needed to make inferences about emotions and mental states comes from visually presented, nonverbal cues (e.g., facial expressions or gestures). Theory of mind (ToM) deficits after TBI are partially explained by impaired visual attention and the processing of these important cues. This research found that patients with deficits in visual processing differ from healthy controls (HCs). Furthermore, we found visual processing problems can be determined by looking at the eye tracking data developed from industry standard eye tracking hardware and software. We predicted that the eye tracking data of the overall population is correlated to the TASIT test. The visual processing of impaired (who got at least one answer wrong from TASIT questions) and unimpaired (who got all answer correctly from TASIT questions) differs significantly. We have divided the eye-tracking data into 3 second time blocks of time series data to detect the most salient individual blocks to the TASIT score. Our preliminary results suggest that we can predict the whole population's impairment using eye-tracking data with an improved f1 score from 0.54 to 0.73. For this, we developed optimized support vector machine (SVM) and random forest (RF) classifier.
APA, Harvard, Vancouver, ISO, and other styles
8

(8771429), Ashley S. Dale. "3D OBJECT DETECTION USING VIRTUAL ENVIRONMENT ASSISTED DEEP NETWORK TRAINING." Thesis, 2021.

Find full text
Abstract:

An RGBZ synthetic dataset consisting of five object classes in a variety of virtual environments and orientations was combined with a small sample of real-world image data and used to train the Mask R-CNN (MR-CNN) architecture in a variety of configurations. When the MR-CNN architecture was initialized with MS COCO weights and the heads were trained with a mix of synthetic data and real world data, F1 scores improved in four of the five classes: The average maximum F1-score of all classes and all epochs for the networks trained with synthetic data is F1∗ = 0.91, compared to F1 = 0.89 for the networks trained exclusively with real data, and the standard deviation of the maximum mean F1-score for synthetically trained networks is σ∗ F1 = 0.015, compared to σF 1 = 0.020 for the networks trained exclusively with real data. Various backgrounds in synthetic data were shown to have negligible impact on F1 scores, opening the door to abstract backgrounds and minimizing the need for intensive synthetic data fabrication. When the MR-CNN architecture was initialized with MS COCO weights and depth data was included in the training data, the net- work was shown to rely heavily on the initial convolutional input to feed features into the network, the image depth channel was shown to influence mask generation, and the image color channels were shown to influence object classification. A set of latent variables for a subset of the synthetic datatset was generated with a Variational Autoencoder then analyzed using Principle Component Analysis and Uniform Manifold Projection and Approximation (UMAP). The UMAP analysis showed no meaningful distinction between real-world and synthetic data, and a small bias towards clustering based on image background.

APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "F1-score"

1

Cai, Hua, Qing Xu, and Weilin Shen. "Complex Relative Position Encoding for Improving Joint Extraction of Entities and Relations." In Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications, 644–55. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-2456-9_66.

Full text
Abstract:
AbstractRelative position encoding (RPE) is important for transformer based pretrained language model to capture sequence ordering of input tokens. Transformer based model can detect entity pairs along with their relation for joint extraction of entities and relations. However, prior works suffer from the redundant entity pairs, or ignore the important inner structure in the process of extracting entities and relations. To address these limitations, in this paper, we first use BERT with complex relative position encoding (cRPE) to encode the input text information, then decompose the joint extraction task into two interrelated subtasks, namely head entity extraction and tail entity relation extraction. Owing to the excellent feature representation and reasonable decomposition strategy, our model can fully capture the semantic interdependence between different steps, as well as reduce noise from irrelevant entity pairs. Experimental results show that the F1 score of our method outperforms previous baseline work, achieving a better result on NYT-multi dataset with F1 score of 0.935.
APA, Harvard, Vancouver, ISO, and other styles
2

Dsouza, Alishiba, Ran Yu, Moritz Windoffer, and Elena Demidova. "Iterative Geographic Entity Alignment with Cross-Attention." In The Semantic Web – ISWC 2023, 216–33. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-47240-4_12.

Full text
Abstract:
AbstractAligning schemas and entities of community-created geographic data sources with ontologies and knowledge graphs is a promising research direction for making this data widely accessible and reusable for semantic applications. However, such alignment is challenging due to the substantial differences in entity representations and sparse interlinking across sources, as well as high heterogeneity of schema elements and sparse entity annotations in community-created geographic data. To address these challenges, we propose a novel cross-attention-based iterative alignment approach called IGEA in this paper. IGEA adopts cross-attention to align heterogeneous context representations across geographic data sources and knowledge graphs. Moreover, IGEA employs an iterative approach for schema and entity alignment to overcome annotation and interlinking sparsity. Experiments on real-world datasets from several countries demonstrate that our proposed approach increases entity alignment performance compared to baseline methods by up to 18% points in F1-score. IGEA increases the performance of the entity and tag-to-class alignment by 7 and 8% points in terms of F1-score, respectively, by employing the iterative method.
APA, Harvard, Vancouver, ISO, and other styles
3

Góra, Grzegorz, and Andrzej Skowron. "On kNN Class Weights for Optimising G-Mean and F1-Score." In Rough Sets, 414–30. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-50959-9_29.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Fourure, Damien, Muhammad Usama Javaid, Nicolas Posocco, and Simon Tihon. "Anomaly Detection: How to Artificially Increase Your F1-Score with a Biased Evaluation Protocol." In Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track, 3–18. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-86514-6_1.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Sharma, Surbhi, and Alka Singhal. "A Comprehensive Investigation of Machine Learning Algorithms with SMOTE Integration to Maximize F1 Score." In Communication and Intelligent Systems, 187–99. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-2100-3_16.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Zhong, Ziyuan, Yuchi Tian, and Baishakhi Ray. "Understanding Local Robustness of Deep Neural Networks under Natural Variations." In Fundamental Approaches to Software Engineering, 313–37. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-71500-7_16.

Full text
Abstract:
AbstractDeep Neural Networks (DNNs) are being deployed in a wide range of settings today, from safety-critical applications like autonomous driving to commercial applications involving image classifications. However, recent research has shown that DNNs can be brittle to even slight variations of the input data. Therefore, rigorous testing of DNNs has gained widespread attention.While DNN robustness under norm-bound perturbation got significant attention over the past few years, our knowledge is still limited when natural variants of the input images come. These natural variants, e.g., a rotated or a rainy version of the original input, are especially concerning as they can occur naturally in the field without any active adversary and may lead to undesirable consequences. Thus, it is important to identify the inputs whose small variations may lead to erroneous DNN behaviors. The very few studies that looked at DNN’s robustness under natural variants, however, focus on estimating the overall robustness of DNNs across all the test data rather than localizing such error-producing points. This work aims to bridge this gap.To this end, we study the local per-input robustness properties of the DNNs and leverage those properties to build a white-box (DeepRobust-W) and a black-box (DeepRobust-B) tool to automatically identify the non-robust points. Our evaluation of these methods on three DNN models spanning three widely used image classification datasets shows that they are effective in flagging points of poor robustness. In particular, DeepRobust-W and DeepRobust-B are able to achieve an F1 score of up to 91.4% and 99.1%, respectively. We further show that DeepRobust-W can be applied to a regression problem in a domain beyond image classification. Our evaluation on three self-driving car models demonstrates that DeepRobust-W is effective in identifying points of poor robustness with F1 score up to 78.9%.
APA, Harvard, Vancouver, ISO, and other styles
7

Liu, Lei, Zheng Pei, Peng Chen, Zhisheng Gao, Zhihao Gan, and Kang Feng. "An Effective GAN-Based Multi-classification Approach for Financial Time Series." In Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications, 1100–1107. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-2456-9_110.

Full text
Abstract:
AbstractDeep learning has achieved significant success in various applications due to its powerful feature representations of complex data. Financial time series forecasting is no exception. In this work we leverage Generative Adversarial Nets (GAN), which has been extensively studied recently, for the end-to-end multi-classification of financial time series. An improved generative model based on Convolutional Long Short-Term Memory (ConvLSTM) and Multi-Layer Perceptron (MLP) is proposed to effectively capture temporal features and mine the data distribution of volatility trends (short, neutral, and long) from given financial time series data. We empirically compare the proposed approach with state-of-the-art multi-classification methods on real-world stock dataset. The results show that the proposed GAN-based method outperforms its competitors in precision and F1 score.
APA, Harvard, Vancouver, ISO, and other styles
8

Fan, Xiangyu, Jilong Yang, Wei Zhao, Jincheng Deng, and Fangming Liu. "Webpage Tampering Detection Method Based on BiGRU-CRF-RCNN." In Communications in Computer and Information Science, 113–26. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-8285-9_8.

Full text
Abstract:
AbstractWith the development of the Internet, cyber security events occur frequently, especially webpage tampering events account for a high proportion. In response to this phenomenon, this paper constructs a webpage tampering detection framework BCR. Based on the webpage to be detected, the webpage text data is segmented and extracted according to the webpage structure, the text features are extracted by using BiGRU model combined with context dependence, and then combined with the CRF to learn sequence state labeling named entities, the word vector is constructed by the extracted named entity and brought into the RCNN model for tampering detection. The experiment results show that the framework has achieved 95.37% precision, 95.35% recall and 95.34% F1-Score in webpage tampering detection, which is better than Textrank RCNN framework in webpage tampering detection. In practical application, it also achieved 95.13% precision and 93.25% recall.
APA, Harvard, Vancouver, ISO, and other styles
9

Montassar, Imen, Belkacem Chikhaoui, and Shengrui Wang. "Agitated Behaviors Detection in Children with ASD Using Wearable Data." In Digital Health Transformation, Smart Ageing, and Managing Disability, 92–103. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-43950-6_8.

Full text
Abstract:
AbstractChildren diagnosed with Autism Spectrum Disorder (ASD) often exhibit agitated behaviors that can isolate them from their peers. This study aims to examine if wearable data, collected during everyday activities, could effectively detect such behaviors. First, we used the Empatica E4 device to collect real data including Blood Volume Pulse (BVP), Electrodermal Activity (EDA), and Acceleration (ACC), from a 9-years-old male child with autism over 6 months. Second, we analyzed and extracted numerous features from each signal, and employed different classifiers including Support Vector Machine (SVM), Random Forest (FR), eXtreme Gradient Boosting (XGBoost), and TabNet. Our preliminary findings showed good performance in comparison with the state of the art. Notably, XGBoost demonstrated the highest performance in terms of accuracy, precision, recall, and F1-score. The accuracy achieved in this paper using XGBoost is equal to $$80\%$$ 80 % which exceeds previous research.
APA, Harvard, Vancouver, ISO, and other styles
10

Röchert, Daniel, German Neubaum, and Stefan Stieglitz. "Identifying Political Sentiments on YouTube: A Systematic Comparison Regarding the Accuracy of Recurrent Neural Network and Machine Learning Models." In Disinformation in Open Online Media, 107–21. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-61841-4_8.

Full text
Abstract:
Abstract Since social media have increasingly become forums to exchange personal opinions, more and more approaches have been suggested to analyze those sentiments automatically. Neural networks and traditional machine learning methods allow individual adaption by training the data, tailoring the algorithm to the particular topic that is discussed. Still, a great number of methodological combinations involving algorithms (e.g., recurrent neural networks (RNN)), techniques (e.g., word2vec), and methods (e.g., Skip-Gram) are possible. This work offers a systematic comparison of sentiment analytical approaches using different word embeddings with RNN architectures and traditional machine learning techniques. Using German comments of controversial political discussions on YouTube, this study uses metrics such as F1-score, precision and recall to compare the quality of performance of different approaches. First results show that deep neural networks outperform multiclass prediction with small datasets in contrast to traditional machine learning models with word embeddings.
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "F1-score"

1

Alibekov, M. R. "Diagnosis of Plant Biotic Stress by Methods of Explainable Artificial Intelligence." In 32nd International Conference on Computer Graphics and Vision. Keldysh Institute of Applied Mathematics, 2022. http://dx.doi.org/10.20948/graphicon-2022-728-739.

Full text
Abstract:
Methods for digital image preprocessing, which significantly increase the efficiency of ML methods, and also a number of ML methods and models as a basis for constructing simple and efficient XAI networks for diagnosing plant biotic stresses, have been studied. A complex solution has been built, which includes the following stages: automatic segmentation; feature extraction; classification by ML models. The best classifiers and feature vectors are selected. The study was carried out on the open dataset PlantVillage Dataset. The single-layer perceptron (SLP) trained on a full vector of 92 features (20 statistical, 72 textural) became the best according to the F1- score=93% criterion. The training time on a PC with an Intel Core i5-8300H CPU took 189 minutes. According to the criterion “F1-score/number of features”, SLP trained on 7 principal components with F1-score=85% also became the best. Training time - 29 minutes. The criterion “F1- score/number+interpretability of features” favors the selected 9 features and the random forest model, F1-score=83%. The research software package is made in a modern version of Python using the OpenCV and deep learning model libraries, and is able for using in precision farming.
APA, Harvard, Vancouver, ISO, and other styles
2

Saini, Pratik, Samiran Pal, Tapas Nayak, and Indrajit Bhattacharya. "90% F1 Score in Relation Triple Extraction: Is it Real?" In Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP. Stroudsburg, PA, USA: Association for Computational Linguistics, 2023. http://dx.doi.org/10.18653/v1/2023.genbench-1.1.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Avola, Danilo, Luigi Cinque, Gian Luca Foresti, Francesco Lamacchia, Marco Raoul Marini, Luca Perini, Kristjana Qorraj, and Gabriele Telesca. "A Shape Comparison Reinforcement Method Based on Feature Extractors and F1-Score." In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC). IEEE, 2019. http://dx.doi.org/10.1109/smc.2019.8914601.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Sepúlveda, J., and S. A. Velastin. "F1 Score Assesment of Gaussian Mixture Background Subtraction Algorithms Using the MuHAVi Dataset." In 6th International Conference on Imaging for Crime Prevention and Detection (ICDP-15). Institution of Engineering and Technology, 2015. http://dx.doi.org/10.1049/ic.2015.0106.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Hougaz, Ana Beatriz, David Lima, Bernardo Peters, Patricia Cury, and Luciano Oliveira. "Sex estimation on panoramic dental radiographs: A methodological approach." In Simpósio Brasileiro de Computação Aplicada à Saúde. Sociedade Brasileira de Computação - SBC, 2023. http://dx.doi.org/10.5753/sbcas.2023.229563.

Full text
Abstract:
Estimating sex using tooth radiographs requires knowledge of a comprehensive spectrum of maxillar anatomy, which ultimately demands specialization on the anatomical structures in the oral cavity. In this paper, we propose a more effective methodological study than others present in the literature for the problem of automatic sex estimation. Our methodology uses the largest publicly available data set in the literature, raises statistical significance in the performance assessment, and explains which part of the images influences the classification. Our findings showed that although EfficientNetV2-Large reached an average F1-score of 91,43% +- 0,67, an EfficientNet-B0 could be more beneficial with a very close F1-score and a much lighter architecture.
APA, Harvard, Vancouver, ISO, and other styles
6

Souza, Daniel Abella C. M. de, Danyllo Albuquerque, Emanuel Dantas Filho, Mirko Perkusich, and Angelo Perkusich. "Using Machine Learning for Non-Functional Requirements Classification: A Practical Study." In Workshop Brasileiro de Engenharia de Software Inteligente. Sociedade Brasileira de Computação, 2023. http://dx.doi.org/10.5753/ise.2023.235829.

Full text
Abstract:
Non-Functional Requirements (NFR) are used to describe a set of software quality attributes such as reliability, maintainability, and performance. Since the functional and non-functional requirements are mixed together in software documentation, it requires a lot of effort to distinguish them. This study proposed automatic NFR classification by using machine learning classification techniques. An empirical study with three machine learning algorithms was applied to classify NFR automatically. Precision, recall, F1-score, and accuracy were calculated for the classification results through all techniques. The results showed that the SGD SVM classifier achieves the best results where precision, recall, F1-score, and accuracy reported were 0.66, 0.61, and 0.61.
APA, Harvard, Vancouver, ISO, and other styles
7

Oliveira, Amanda S., Thiago C. Cecote, Pedro H. L. Silva, Jadson C. Gertrudes, Vander L. S. Freitas, and Eduardo J. S. Luz. "How Good Is ChatGPT For Detecting Hate Speech In Portuguese?" In Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana. Sociedade Brasileira de Computação, 2023. http://dx.doi.org/10.5753/stil.2023.233943.

Full text
Abstract:
This study evaluates OpenAI’s ChatGPT, a large language model, for its efficacy in detecting hate speech in Portuguese tweets, comparing it with purpose-trained models. Despite incurring considerable computational costs, ChatGPT as a zero-shot classifier demonstrated commendable performance, even superior to or on par with state-of-the-art methods, with an F1-score of 73.0% on the ToLD-BR. In a cross-dataset evaluation on the HLPHSP dataset, it secured a superior F1-score of 73%. The choice of prompt significantly impacts the outcome, with a wider scope prompt balancing precision and recall metrics. ChatGPT, due to its interpretability and resilience against data distribution shifts, could be a preferred choice for tasks prioritizing these factors.
APA, Harvard, Vancouver, ISO, and other styles
8

Huang, Hao, Jianming Wang, and Halidan Abudureyimu. "Maximum F1-score discriminative training for automatic mispronunciation detection in computer-assisted language learning." In Interspeech 2012. ISCA: ISCA, 2012. http://dx.doi.org/10.21437/interspeech.2012-248.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Freitas, Pedro V. A. de, Antonio J. G. Busson, Álan L. V. Guedes, and Sérgio Colcher. "A Deep Learning Approach to Detect Pornography Videos in Educational Repositories." In Simpósio Brasileiro de Informática na Educação. Sociedade Brasileira de Computação, 2020. http://dx.doi.org/10.5753/cbie.sbie.2020.1253.

Full text
Abstract:
A large number of videos are uploaded on educational platforms every minute. Those platforms are responsible for any sensitive media uploaded by their users. An automated detection system to identify pornographic content could assist human workers by pre-selecting suspicious videos. In this paper, we propose a multimodal approach to adult content detection. We use two Deep Convolutional Neural Networks to extract high-level features from both image and audio sources of a video. Then, we concatenate those features and evaluate the performance of classifiers on a set of mixed educational and pornographic videos. We achieve an F1-score of 95.67% on the educational and adult videos set and an F1-score of 94% on our test subset for the pornographic class.
APA, Harvard, Vancouver, ISO, and other styles
10

Yajnik, Archit, and Sabu Lama Tamang. "Chunker Based Sentiment Analysis for Nepali Text." In 4th International Conference on NLP Trends & Technologies. Academy & Industry Research Collaboration, 2023. http://dx.doi.org/10.5121/csit.2023.131406.

Full text
Abstract:
The article represents the Sentiment Analysis (SA) of a Nepali sentence. Skip-gram model is used for the word to vector encoding. In the first experiment the vector representation of each sentence is generated by using Skip-gram model followed by the Multi-Layer Perceptron (MLP) classification and it is observed that the F1 score of 0.6486 is achieved for positive-negative classification with overall accuracy of 68%. Whereas in the second experiment the verb chunks are extracted using Nepali parser and carried out the similar experiment on the verb chunks. F1 score of 0.6779 is observedfor positive -negative classification with overall accuracy of 85%. Hence, Chunker based sentiment analysis is proven to be better than sentiment analysis using sentences.
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "F1-score"

1

Griffin, Andrew, Sean Griffin, Kristofer Lasko, Megan Maloney, S. Blundell, Michael Collins, and Nicole Wayant. Evaluation of automated feature extraction algorithms using high-resolution satellite imagery across a rural-urban gradient in two unique cities in developing countries. Engineer Research and Development Center (U.S.), April 2021. http://dx.doi.org/10.21079/11681/40182.

Full text
Abstract:
Feature extraction algorithms are routinely leveraged to extract building footprints and road networks into vector format. When used in conjunction with high resolution remotely sensed imagery, machine learning enables the automation of such feature extraction workflows. However, many of the feature extraction algorithms currently available have not been thoroughly evaluated in a scientific manner within complex terrain such as the cities of developing countries. This report details the performance of three automated feature extraction (AFE) datasets: Ecopia, Tier 1, and Tier 2, at extracting building footprints and roads from high resolution satellite imagery as compared to manual digitization of the same areas. To avoid environmental bias, this assessment was done in two different regions of the world: Maracay, Venezuela and Niamey, Niger. High, medium, and low urban density sites are compared between regions. We quantify the accuracy of the data and time needed to correct the three AFE datasets against hand digitized reference data across ninety tiles in each city, selected by stratified random sampling. Within each tile, the reference data was compared against the three AFE datasets, both before and after analyst editing, using the accuracy assessment metrics of Intersection over Union and F1 Score for buildings and roads, as well as Average Path Length Similarity (APLS) to measure road network connectivity. It was found that of the three AFE tested, the Ecopia data most frequently outperformed the other AFE in accuracy and reduced the time needed for editing.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'F1-score' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography