To see the other types of publications on this topic, follow the link: Google collaboratory.
Journal articles on the topic 'Google collaboratory'
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 'Google collaboratory.'
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
Haana Udtari Anjani, Vitriani Vitriani, and Mulya Hastuti. "Pemanfaatan Media Google Colaboratory Pada Mata Pelajaran Informatika di SMA Negeri 5 Pekanbaru." SOKO GURU: Jurnal Ilmu Pendidikan 4, no. 1 (2024): 101–8. http://dx.doi.org/10.55606/sokoguru.v4i1.3613.
Full textAbstract:
This research aims to fill the knowledge gap by analyzing the utilization of Google Collaboratory learning media on utilization of Google Collaboratory learning media in informatics subjects in the high school environment. informatics in a secondary school environment. Through a deeper understanding about the experience of using this platform, it is expected to be identified benefits, constraints, and effective strategies in optimizing the utilization of Google Collaboratory as a learning media. Google Collaboratory as an effective and efficient learning media in informatics learning. This research will use a qualitative approach with a case study research design. with a case study research design. The qualitative approach is chosen to get an in-depth understanding of the experience of using Google Collaboratory in informatics learning. Collaboratory in informatics learning. The case study design was chosen because it allows researchers to investigate phenomena in a real context, such as the utilization of Google Collaboratory in a learning situation in a secondary school. secondary school. This research provides a deeper understanding of the potential and challenges in the utilization of Google Collaboratory as a medium for learning Informatics in secondary school. Informatics in secondary schools. The findings of this research can be the basis for the development of more innovative and effective learning practices in the future. context of information technology education in the future.
2
Kusuma Dewi, Karin, Ismi Kaniawulan, and Candra Dewi Lestari. "ANALISIS SENTIMEN PENGGUNA APLIKASI JAMSOSTEK MOBILE (JMO) PADA APPSTORE MENGGUNAKAN METODE NAIVE BAYES." Simtek : jurnal sistem informasi dan teknik komputer 8, no. 2 (2023): 333–38. http://dx.doi.org/10.51876/simtek.v8i2.286.
Full textAbstract:
The use of Jamsostek Mobile has problems that often occur, namely failure to update data on the JMO application, digital cards that do not appear on the JMO application, data update failures and access failures. To overcome this, BPJS participants are faced with BPJS branches or companies. This is an obstacle that should be overcome through optimizing regulations from the BPJS so that there are no complaints from the public regarding this matter.
 Jamsostek Mobile is an application implemented by BPJS Ketenagakerjaan to make it easier for users to carry out JHT simulations, check JHT balances, check details for JHT contributions and pension benefits, and make JHT claims. This application can be accessed on the App Store and Playstore. The implementation of the application turned out to generate several comments or reviews from users both in the App Store and Play Store.
 This study aims to analyze sentiment from user reviews on the App Store with the stages of Scraping, Labeling, Cleaning, Preprocessing Text, Class Naive Bayes, TF-IDF, Evaluation, Visualization using Google Collaboratory tools
 From the results of research on the sentiment analysis of users of the Jamsostek Mobile application on the AppStore platform, which totaled 2001 data and had passed the preprocessing text stage consisting of filtering, tokenization, transformation and classification using the Naïve Bayes algorithm and evaluation of data with a confusion matrix using Google Collaboratory, it can be interpreted that the results from reviews of the use of negative JMO applications with a proportion of 96% in accuracy (accuracy), 96% in value precision, and a success rate (recall) of 100%. This value indicates that the naïve Bayes classification algorithm is considered quite good in processing review data, because the proportion of accuracy is 96%. Based on this value, it proves that the sentiment or reviews of JMO application users on the App Store platform are negative.
 Keywords: Sentimen Analysis, Naive Bayes, App Store, Jamsostek Mobile, Google Collaboratory
3
Ayundyah, Kesumawati, Mifrahi Mustika Noor, and Primandari Arum Handini. "Optimalisasi Virtual Lab Dan Google Collaboratory Untuk Pembelajaran Daring Bersama Berbasis Collaborative Project Based Learning." Refleksi Pembelajaran Inovatif 4, no. 1 (2022): 507–19. https://doi.org/10.20885/rpi.vol4.iss1.art2.
Full textAbstract:
Metode pembelajaran tardisional saat ini dirasa memiliki banyak kekurangan bagi pembelajaran mandiri peserta didik. Penelitian ini bertujuan untuk melihat bagaimana penerapan proses pembelajaran dengan pendekatan PjBL kolaboratif. Proyek diberikan kepada mahasiswa dari dua prodi berbeda yaitu program studi Statistik dan Ilmu Ekonomi dimana isu yang diberikan mengenai isu ekonomi dengan pendekatan statistik. Observasi dilakukan pada dua kelas dengan total jumlah mahasiswa sebanyak 105. Hasil penerapan PjBL kolaboratif menunjukkan terdapat peningkatan perolehan capaian CPMK saat mahasiswa melakukan kegiatan PjBL kolaboratif yang diarahkan oleh dosen, daripada kolaboratif mandiri. Ketercapaian CPMK dengan menggunakan PjBL kolaboratif mencapai 100%. Selian itu, mayoritas mahasiswa (62.5%) kegiatan PjBL kolaboratif lintas prodi ini dilaksanakan dengan baik. Penelitian ini mendukung adanya penerapan kegiatan PjBL kolaboratif untuk diterapkan pada mata kuliah lintas prodi.
4
Moch Farryz Rizkilloh and Sri Widiyanesti. "Prediksi Harga Cryptocurrency Menggunakan Algoritma Long Short Term Memory (LSTM)." Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 6, no. 1 (2022): 25–31. http://dx.doi.org/10.29207/resti.v6i1.3630.
Full textAbstract:
Technological developments continue to encourage the creation of various innovations in almost all aspects of human life. One of the innovations that is becoming a worldwide phenomenon today is the presence of cryptocurrency as a digital currency that is able to replace the role of conventional currency as a means of payment. Currently, the number of cryptocurrency investors in Indonesia has reached 4.45 million people as of March 2021, an increase of 78% compared to the end of the previous year. Very volatile price movements make cryptocurrency investments considered speculative so the risks faced are also very high. The purpose of this study is to build a predictive model that is able to forecast prices on the cryptocurrency market. The algorithm used to build the prediction model is Long Short Term Memory (LSTM). LSTM is the development of the Recurrent Neural Network (RNN) algorithm to overcome problems in the RNN in managing data for a long period. LSTM is considered superior to other algorithms in managing time series data. The data in this study were taken from the Yahoo Finance website using the Pandas Datareader library through Google Collaboratory. The entire prediction model development process is carried out through Google Collaboratory tools. To improve the accuracy of the model, the Nadam optimization algorithm was used and three testing sessions were carried out with the number of Epochs of 1, 10, and 20 in each session. The final test results show that the best prediction performance occurs when testing the DOGE coin type with the number of Epoch 20 which gets an RMSE value of 0.0630.
5
Cárdenas Vargas, Freddy, and Jennifer Riveros Cepeda. "Simulación Hidrológica de la Cuenca del Rio Atrato Mediante Herramientas Computacionales." Revista de Tecnología 17, no. 2 (2020): 30–36. http://dx.doi.org/10.18270/rt.v17i2.3329.
Full textAbstract:
Reconocer la importancia del Río Atrato, tanto para el país, como específicamente a los alrededores de su cuenca; se realiza este estudio investigativo por medio de los recursos de información geográfica, con el fin de simular su hidrología para conocer su comportamiento. Además de resaltar la importancia y el buen uso de los diferentes recursos informáticos para realizar este estudio hidrológico (IDEAM, Google Earth, Collaboratory, Qgis e información satelital).[1] Todo esto, buscando realizar un estudio preciso y con calidad de información para realizar modelamientos necesarios en el campo de la ingeniería ambiental para el buen uso del recurso. Se denota que la zona de estudio tiene alta precipitación anual, y no se considera tan bimodal, como en otras regiones del territorio nacional.
6
Indrihapsari, Yuniar, Handaru Jati, N. Nurkhamid, et al. "A Comparison of OpenNMT Sequence Model for Indonesian Automatic Question Generation." Elinvo (Electronics, Informatics, and Vocational Education) 8, no. 1 (2023): 55–63. http://dx.doi.org/10.21831/elinvo.v8i1.56491.
Full textAbstract:
Evaluation of learners is a crucial aspect of the educational system. However, creating evaluation instruments is a process that demands teachers' time and energy. The researcher developed the Indonesia Automatic Question Generator in this study using an architecture modified from past studies. The primary goals of this project are (1) to construct an AQG tool utilizing the OpenNMT series and (2) to analyze and compare the model's performance. As a data source, this study employs the SQuAD 2.0 dataset and numerous sequence techniques, including BiGRU, BiLSTM, and Transformer. The researcher trained the models using OpenNMT-py and Google Collaboratory. This approach generates questions that are relevant to the context of the source. This study found that the model was acceptable.
7
Iskandar, Dadang Mulyana, Mesra Betty Yel, and Aldi Sitohang. "Detection of The Deaf Signal Language Using The Single Shot Detection (SSD) Method." Journal of Applied Engineering and Technological Science (JAETS) 4, no. 1 (2022): 215–22. http://dx.doi.org/10.37385/jaets.v4i1.966.
Full textAbstract:
Sign Language is a language that prioritizes manual communication, body language, and lip movements, instead of sound, to communicate. Deaf people are the main group who use this language, usually by combining hand shape, orientation and movement of the hands, arms, and body, and facial expressions to express their thoughts. Therefore, the researcher created an image recognition program in sign language using the Single Shot Detection (SSD) method, which is a convolution activity by combining several layers of preparation, by utilizing several components that move together and are motivated by a biological sensory system. The letters used in making sign language programs use the letters of the alphabet (az). This sign language detection programming that runs on the Google Collaboratory application
8
Lomeo, Davide, and Minerva Singh. "Cloud-Based Monitoring and Evaluation of the Spatial-Temporal Distribution of Southeast Asia’s Mangroves Using Deep Learning." Remote Sensing 14, no. 10 (2022): 2291. http://dx.doi.org/10.3390/rs14102291.
Full textAbstract:
This paper proposes a cloud-based mangrove monitoring framework that uses Google Collaboratory and Google Earth Engine to classify mangroves in Southeast Asia (SEA) using satellite remote sensing imagery (SRSI). Three multi-class classification convolutional neural network (CNN) models were generated, showing F1-score values as high as 0.9 in only six epochs of training. Mangrove forests are tropical and subtropical environments that provide essential ecosystem services to local biota and coastal communities and are considered the most efficient vegetative carbon stock globally. Despite their importance, mangrove forest cover continues to decline worldwide, especially in SEA. Scientists have produced monitoring tools based on SRSI and CNNs to identify deforestation hotspots and drive targeted interventions. Nevertheless, although CNNs excel in distinguishing between different landcover types, their greatest limitation remains the need for significant computing power to operate. This may not always be feasible, especially in developing countries. The proposed framework is believed to provide a robust, low-cost, cloud-based, near-real-time monitoring tool that could serve governments, environmental agencies, and researchers, to help map mangroves in SEA.
9
Ortiz Orozco, Maria Fernanda, and Juan Sebastian Pardo Florez. "Análisis hidrológico de la cuenca del río Sumapaz ubicada en Bogotá D.C entre los años 2011 al 2019." Revista de Tecnología 17, no. 2 (2020): 92–100. http://dx.doi.org/10.18270/rt.v17i2.3335.
Full textAbstract:
Se realizó la identificación y selección de la cuenca del Río Sumapaz cerca de su nacimiento en el municipio de Cabrera – Cundinamarca, seguidamente se reconocieron diferentes estaciones del IDEAM necesarias para la debida recolección de datos de precipitación y caudal , y con la descarga de datos de dichos datos de la cuenca se utilizaron distintas herramientas como lo son Qgis y Google Collaboratory a través de estas se realizó la simulación del comportamiento del río y así se obtuvieron resultados como el perfil del río, los puntos máximos, mínimos y medios de caudal y precipitación y su relación entre sí, asimismo se hicieron los debidos análisis a los resultados obtenidos con el objetivo de conocer los diversos factores que intervienen en la conducta natural de la cuenca y como se puede mejorar ésta.
10
Wiratama, Ari Satria, Muhammad Rifqi, and Siti Maesaroh. "EFEKTIVITAS TRANSFER LEARNING DALAM PENDETEKSIAN PENYAKIT PNEUMONIA MELALUI CITRA X-RAY PARU MANUSIA." Jurnal Ilmiah Sains dan Teknologi 7, no. 1 (2023): 43–52. http://dx.doi.org/10.47080/saintek.v7i1.2551.
Full textAbstract:
Pneumonia is a disease that attacks the human lung system. This disease causes serious problems not only in Indonesia but is a serious problem for people around the world. By doing early detection of pneumonia can reduce mortality. X-ray imaging of the human chest is one of the most widely used to diagnose pneumonia. The X-ray method is a fast and easy method of detecting a disease. In this study, the Transfer Learning method was used to classify chest X-ray images labeled as non-pneumonia and pneumonia lungs. To classify this image recognition, the Google Collaboratory application uses the ResNet50V2 Architecture model. The dataset used for this study was 5863 training data by testing 30 times, the results obtained were an accuracy of 97% and a loss value of 0.4.
11
Rizqy, Muhammad Enricco, Ahmad Faqih, and Gifthera Dwilestari. "Naïve Bayes Optimization by Implementing Genetic Algorithm in Sentiment Analysis of BCA Mobile Reviews." Journal of Artificial Intelligence and Engineering Applications (JAIEA) 4, no. 2 (2025): 771–77. https://doi.org/10.59934/jaiea.v4i2.750.
Full textAbstract:
The development of the digital era has encouraged the adoption of mobile banking applications that facilitate banking transactions, including the BCA Mobile application which is simple but still adheres to a slightly outdated, user-friendly appearance but to provide the best service, it is necessary to evaluate the various problems that arise through review analysis. This study aims to conduct sentiment analysis of BCA Mobile application reviews taken from the Google Play Store, with data totaling 1,200 reviews scraping results using Google Collaboratory python programming language, to categorize negative and positive reviews used manual labeling for more accurate results, the Naïve Bayes approach is used in classifying positive and negative category reviews due to the ability of this algorithm to handle text data. However, the weakness of Naïve Bayes which is sensitive to irrelevant features can cause a decrease in accuracy. This research implements Genetic algorithm to improve the performance of Naïve Bayes. The results showed that the application of Genetic algorithm successfully increased the accuracy, precision of Naïve Bayes classification 95%, precision 92% to accuracy 98%, precision 99%, which proved the effectiveness of Genetic algorithm in optimizing the model and improving the quality of sentiment analysis.
12
Sari, Nofita, Hanny Hikmayanti Handayani, and Amril Mutoi Siregar. "Implementasi Clustering Data Kasus Covid 19 Di Indonesia Menggunakan Algoritma K-Means." Bianglala Informatika 11, no. 1 (2023): 7–12. http://dx.doi.org/10.31294/bi.v11i1.14762.
Full textAbstract:
Covid19 adalah virus pertama kali terdeteksi di Wuhan, Cina pada akhir Desember 2019. Kasus Covid-19 masuk di Indonesia pada Maret 2020, tercatat mencapai 1.511.712 dengan jumlah kematian 40,858 dan sembuh 1.348.330 kasus. Di Indonesia terdapat 34 provinsi yang menjadi persebaran kasus Covid19. Penelitian ini bertujuan untuk mengelompokkan setiap provinsi di Indonesia ke dalam beberapa cluster tertentu agar mengetahui daerah dengan jumlah kasus yang tergolong tinggi, sedang, rendah. Mengelompokan data kasus Covid19 di provinsi Indonesia menggunakan teknik clustering dengan menggunakan algoritma K-means. Data yang digunakan sebanyak 7098 data dari tanggal 1 Maret hingga 11 Oktober 2020. Dataset yang digunakan dari website AtapData (atapdata.ai). Mengolah data tersebut menggunakan Google Collaboratory dengan bahasa pemrograman python. Pada penelitian dilakukan optimasi menggunakan metode elbow yang menghasilkan jumlah cluster sebanyak 3 cluster. Pengujian dilakukan untuk mendapatkan nilai K yang optimal. Melakukan evaluasi menggunakan Sum of Square Error (SSE). Dari hasil evaluasi memiliki jumlah optimal K: 3 yaitu 228913736548657.56.Kata Kunci : Covid19, algoritma K means, Clustering, Metode ElbowCovid19 is a virus that was first detected in Wuhan, China at the end of December 2019. Covid-19 cases entered Indonesia in March 2020, it was recorded that it had reached 1,511,712 with 40,858 deaths and 1,348,330 cases of recovery. In Indonesia there are 34 provinces where the spread of Covid19 cases. This study aims to classify each province in Indonesia into certain clusters in order to identify areas with high, medium, low number of cases. The grouping of Covid19 case data in the Indonesian province uses a clustering technique using the K-means algorithm. The data used is 7098 data from March 1 to October 11 2020. The dataset used is from the AtapData website (atapdata.ai). Processing the data using Google Collaboratory with the python programming language. In this research, optimization was carried out using the elbow method which resulted in a total of 3 clusters. Tests are carried out to obtain optimal K values. Evaluation using Sum of Square Error (SSE). From the evaluation results, it has an optimal number of K: 3, namely 228913736548657.56.Keywords: Covid19, K mean algorithm, Clustering, Elbow Method
13
Rizky, A., A. Fadhillah, Irzaman, and Irmansyah. "Python-based Program for Analysing Lattice Parameter of Cubic and Tetragonal Crystal Structure." Journal of Physics: Conference Series 2019, no. 1 (2021): 012070. http://dx.doi.org/10.1088/1742-6596/2019/1/012070.
Full textAbstract:
Abstract A program for analysing lattice parameter of a crystal structure has been successfully created based on Python programming language using the Google Collaboratory service, so it can be accessed through a PC or smartphone as long as internet access is available. This program can be used to calculate lattice parameter of a crystal structure with x-ray diffraction data as the input. Crystal structures that can be calculated for its lattice parameter are cubic and tetragonal. The program will ask for the type of crystal structure of the data, along with diffraction angles and miller indices. The input will be processed using the Cramer-Cohen method according to the previously entered crystal structure. By also entering the wavelength used, the output of this program is the lattice parameter in the angstrom unit. The percentage of error of this program’s output is extremely low.
14
Penny and Kharisma Austin Makaba. "PENGARUH INFLUENCER MARKETING DAN ONLINE CUSTOMER REVIEW TERHADAP MINAT BELI PRODUK SKINCARE SKINTIFIC DI SHOPEE." Jurnal Manajemen & Bisnis Jayakarta 6, no. 01 (2024): 26–42. http://dx.doi.org/10.53825/jmbjayakarta.v6i01.282.
Full textAbstract:
Dampak transformasi digital yang dirasakan saat ini menyebabkan adanya perubahan dalam pergeseran pola hidup khususnya di dalam kehidupan bisnis yang beralih menggunakan online. Melalui kehadiran bisnis secara online menyebabkan strategi pemasaran kepada calon konsumen dilakukan dengan metode yang berbeda pula dengan bisnis konvensional lainnya. Berdasarkan pemanfaatan strategi pemasaran di era digitalisasi saat ini, penelitian ini dilakukan untuk mengetahui pengaruh dari Influencer Marketing dan Online Customer Review terhadap Minat Beli pada produk Skintific dengan studi kasus pada mahasiswa Universitas Universal dengan metode pengambilan sampel Purposive sampling dan jumlah sampel sebanyak 90 responden. Pendekatan penelitian ini adalah kuantitatif dengan menggunakan kuesioner sebagai instrumen pengumpulan data primer. Metode analisis data menggunakan Partial Least Square Path Modeling (PLS-PM) dengan pemanfaatan bahasa pemrograman R dalam Google Collaboratory. Hasil penelitian ini mengungkapkan bahwa Influencer Marketing dan Online Customer Review berpengaruh terhadap Minat Beli pada produk skincare Skintific di Shopee.
15
Leonardi, Veronica Hertensia, Ali Ibrahim, Rizka Dhini Kurnia, and Mira Afrina. "Analisis Sentimen Ulasan Aplikasi Pembelajaran Bahasa Menggunakan Metode VADER." Jurnal Algoritma 22, no. 1 (2025): 767–76. https://doi.org/10.33364/algoritma/v.22-1.2285.
Full textAbstract:
Perkembangan teknologi saat ini mempermudah proses belajar bahasa melalui aplikasi seperti Duolingo. Penelitian ini bertujuan untuk memahami persepsi pengguna terhadap Duolingo dengan menggunakan analisis sentimen berbasis VADER (Valence Aware Dictionary and Sentiment Reasoner). Ulasan pengguna dari Google Play Store diproses menggunakan Google Collaboratory, menghasilkan 1.831 data yang dikelompokkan sebagai netral, negatif, dan positif. Hasil analisis menunjukkan akurasi keseluruhan sebesar 98 persen. Model ini efektif dalam mengidentifikasi sentimen netral (presisi 100 persen, recall 97 persen, F1-score 99 persen) dan positif (presisi 99 persen, recall 82 persen, F1-score 99 persen). Namun, model kurang efektif dalam mendeteksi emosi negatif, dengan F1-score 74 persen, recall 82 persen, dan presisi 67 persen, yang menunjukkan adanya kesalahan klasifikasi pada beberapa emosi negatif. Awan kata menunjukkan kata-kata positif seperti "good," "helpful", dan "fun," serta kata-kata negatif seperti "technical problems" dan "learning limitations." Tantangan dalam penggunaan VADER termasuk ketidakmampuan menangani konteks bahasa yang kompleks dan nuansa emosional yang mendalam. Untuk meningkatkan klasifikasi sentimen, penelitian ini merekomendasikan penggunaan VADER bersama Deep-Translator. Kombinasi ini dapat membantu mengidentifikasi sentimen negatif dengan lebih baik dan menangani data dengan berbagai bahasa secara lebih efisien. Tujuan penelitian ini adalah untuk memahami sudut pandang pengguna dan meningkatkan akurasi analisis sentimen, sehingga berkontribusi pada pengembangan aplikasi pembelajaran bahasa yang lebih baik.
16
Hermawan, Tri Ramadhani Putra, and Akhmad Rizal Dzikrillah. "Penerapan Metode Naïve Bayes untuk Analisis Sentimen pada Ulasan Pengguna Aplikasi ChatGPT di Google Play Store." Building of Informatics, Technology and Science (BITS) 6, no. 1 (2024): 430–39. https://doi.org/10.47065/bits.v6i1.5400.
Full textAbstract:
ChatGPT is a chatbot application developed by OpenAI. It has attracted a large number of users in a short period of time. User comments are categorized into positive and negative, indicating their sentiments on using this app. Although ChatGPT provides convenience from its various features, it also has its downside if misused. Some people think that people will depend on the information provided by this chatbot and reduce the desire to find out the information themselves, because the information from ChatGPT still uses the old generation model. From this concern, a deeper research on sentiment analysis of people who have used the ChatGPT application is made. It is hoped that this research will be able to collect data on public responses to ChatGPT, both pros and cons. Research data will be taken from reviews of ChatGPT application users in the Play Store. Google Collaboratory with Google Play Scraper will be used during the data collection process. The data that has been obtained will go through a preprocessing stage to be cleaned. After the data is successfully cleaned, the data will go through the process of labeling positive and negative data, and will be classified through the Naïve Bayes method. The study results show that the application of the Naïve Bayes method is able to classify user sentiment using Confusion Matrix with a percentage accuracy value of 94.05%, a percentage precision value of 95% for positive and 81.25% for negative. Then the percentage of recall value for positive is 98.84%, and for negative is 48%.
17
Rachmadi, Chaeru. "The Implementation of Deep Learning Method for Disease Detection in Tomato Plants Based on Leaf Images via Web." Fidelity : Jurnal Teknik Elektro 7, no. 1 (2025): 33–45. https://doi.org/10.52005/fidelity.v7i1.269.
Full textAbstract:
Agriculture plays a vital role in supporting the economy. Optimally and wisely managed agricultural development can encourage sustainable economic growth and equity. One example is tomato production, which has great potential to be developed. In 2021, the production of tomatoes in all Indonesian provinces reached a total of 1,114,401 tons. However, tomato production often decreases due to disease attacks on plants. Therefore, this research aimed to identify plant diseases by utilizing deep learning methods applied to web applications, so that they can be easily accessed by farmers. Its use only requires uploading images of plants to be identified into the web application. Based on the results of training and testing conducted at Google Collaboratory using two model architectures, the findings highlight that VGG16 and DenseNet121, the DenseNet121 architecture provides higher accuracy reaching 100%, while VGG16 reaches 98.58%. In addition, in web application implementation and testing with primary data, the DenseNet121 model also showed high accuracy of 92%.
18
Nazrul, Effendy, Ruhyadi Didi, Pratama Rizky, Fatadilla Rabba Dana, Fathunnisa Aulia Ananda, and Yuwan Atmadja Anugrah. "Forest quality assessment based on bird sound recognition using convolutional neural networks." International Journal of Electrical and Computer Engineering (IJECE) 12, no. 4 (2022): 4235–42. https://doi.org/10.11591/ijece.v12i4.pp4235-4242.
Full textAbstract:
Deforestation in Indonesia is in a status that is quite alarming. From year to year, deforestation is still happening. The decline in fauna and the diminishing biodiversity are greatly affected by deforestation. This paper proposes a bioacoustics-based forest quality assessment tool using Nvidia Jetson Nano and convolutional neural networks (CNN). The device, named GamaDet, is a portable physical product based on the microprocessor and equipped with a microphone to record the sounds of birds in the forest and display the results of their analysis. In addition, a Google Collaboratory-based GamaNet digital product is also proposed. GamaNet requires forest recording audio files to be further analyzed into a forest quality index. Testing the forest recording for 60 seconds at an arboretum forest showed that both products could work well. The GamaDet takes 370 seconds, while the GamaNet takes 70 seconds to process the audio data into a forest quality index and a list of detected birds.
19
Nana, Nana, Dadang Iskandar Mulyana, Ali Akbar, and Muhammad Zikri. "Optimasi Klasifikasi Buah Anggur Menggunakan Data Augmentasi dan Convolutional Neural Network." Smart Comp: Jurnalnya Orang Pintar Komputer 11, no. 2 (2022): 148–61. http://dx.doi.org/10.30591/smartcomp.v11i2.3527.
Full textAbstract:
Anggur adalah buah yang populer dan dapat dengan mudah ditemukan hampir di mana saja di dunia. Banyak yang akan terkagum-kagum dengan rasa manis dan nikmat dari buah anggur ini. Anggur tidak hanya membawa kelezatan yang luar biasa untuk kita semua, tetapi juga membawa manfaat khusus bagi kesehatan manusia. Oleh karena itu, peneliti mencoba membuat program pengenalan citra buah anggur yang menggunakan algoritma Data Augmentation dan Convolutional Neural Network. Ini adalah aktivitas konvolusi yang menggabungkan beberapa pemrosesan persiapan dengan beberapa komponen yang bergerak bersama melalui sistem sensor biologis. Anggur yang digunakan adalah Champagne, Concord, Cotton Candy, Chris Monceedless, Gewürztraminer, Grenora, Kyoho, Moondrops, Pinot Noir, Riesling, Sultana, Sweet Jubilee dan Valiant. Optimalisasi klasifikasi dilakukan pada citra buah anggur menggunakan dua model pengujian yaitu model Sequential dan model on-top VGG16 yang beroperasi pada website aplikasi Google Collaboratory dan Keras. Data pengujian untuk observasi ini pada data latih sebanyak 2400 citra dan data uji sebanyak 480 citra yang menghasilkan nilai untuk model sequential dengan akurasi sebesar 98,54% dan loss sebesar 0,027%, untuk model on-top VGG16 nilai akurasinya adalah 99,37% dan nilai loss hanya 0,029%.
20
Santiastry, Sany, Asriyanik Asriyanik, and Winda Apriandari. "PENERAPAN ALGORITMA NAIVE BAYES DAN METODE CRISP-DM DALAM PREDIKSI HASIL TES KEMAMPUAN BAHASA INGGRIS MAHASISWA." JATI (Jurnal Mahasiswa Teknik Informatika) 8, no. 5 (2024): 10432–39. http://dx.doi.org/10.36040/jati.v8i5.11069.
Full textAbstract:
Bahasa Inggris memiliki peran penting dalam sistem pendidikan di Indonesia, terutama karena fungsinya sebagai bahasa internasional. Pentingnya hal ini terlihat dari banyaknya informasi ilmiah dan teknologi di berbagai bidang yang ditulis dalam bahasa Inggris. Meskipun demikian, belum ada penelitian di Universitas Muhammadiyah Sukabumi yang berfokus pada memprediksi tingkat keberhasilan mahasiswa dalam tes kecakapan bahasa Inggris. Penelitian ini bertujuan untuk membangun model prediksi menggunakan algoritma Naive Bayes di platform Google Collaboratory untuk memperkirakan hasil tes kecakapan bahasa Inggris mahasiswa di Universitas Muhammadiyah Sukabumi. Naïve Bayes adalah salah satu algoritma machine learning yang banyak digunakan dalam klasifikasi dan prediksi. Penelitian ini menghasilkan model prediktif serta situs web sederhana yang dapat mencatat nilai mata kuliah bahasa Inggris mahasiswa dan memprediksi keberhasilan mereka dalam tes kemahiran bahasa Inggris. Evaluasi model ini menggunakan metrik akurasi, presisi, recall, dan nilai F1. Model yang dibuat menunjukkan akurasi sebesar 87,94%, dengan rata-rata presisi makro 0,82, recall 0,91, dan nilai F1 0,84, serta rata-rata presisi berbobot 0,89, recall 0,88, dan nilai F1 0,88. Model ini dapat secara akurat memprediksi hasil kelulusan mahasiswa berdasarkan nilai mereka.
21
Rinanto, Rayhan, and Aditya Mulya. "COMPARISON OF RAINFALL ESTIMATION VALUE CAUSED FLOOD USING CST AND MCST METHODS." JURNAL SWARNABHUMI : Jurnal Geografi dan Pembelajaran Geografi 7, no. 1 (2022): 50–57. http://dx.doi.org/10.31851/swarnabhumi.v7i1.7225.
Full textAbstract:
Hydrometeorological disasters such as general flooding have occurred in the BMI (Indonesian Maritime Continent) area. One of the cases occurred in 2 sub-districts in Kudus Regency on February 1, 2021. However, limited tools were an obstacle to measuring the falling rainfall and it was very difficult to detect the clouds that caused the rain. Therefore, the rainfall estimation method using the CST and mCST methods is used to find out the results of the rainfall estimation and how to compare the two methods. The data used is Himawari-8 Satellite data along with supporting data from the BMKG Rain Post around the research location. The data is then processed using Google Collaboratory and analyzed quantitatively. The results of this study indicate that the correlation of the value of the estimated rainfall using the CST and mCST methods to the rainfall value of the observation data in the three research areas has a very low value. In addition, the precipitation that occurs tends to be caused by stratiform clouds (Dense Cirrus).
22
Winarta, Andre, and Wahyu Joni Kurniawan. "OPTIMASI CLUSTER K-MEANS MENGGUNAKAN METODE ELBOW PADA DATA PENGGUNA NARKOBA DENGAN PEMROGRAMAN PYTHON." JTIK (Jurnal Teknik Informatika Kaputama) 5, no. 1 (2021): 113–19. http://dx.doi.org/10.59697/jtik.v5i1.593.
Full textAbstract:
As we know, drugs are very illegal in Indonesia because drug abuse can have very dangerous effects. Drugs are substances that have side effects such as hallucinations, reduced awareness and arousal of the user. Technological advances continue to change over time so that information needs are very much needed in life. Currently, data on drug users is very extensive, so that adequate information presentation techniques are needed so that the information received is very accurate and in accordance with the user's needs. Therefore, it is necessary to carry out a data mining process on drug user data to obtain useful information for users. This study aims to prove Elbow's performance to produce optimal clusters of drug user data using the K-Means algorithm as a data grouping method. Cluster optimization is obtained from the Elbow method, which is executed with Google Collaboratory using the Python programming language. The test results show that the Elbow method works very well in producing the optimal cluster, which is found at k = 3 with the SSE difference value of 1257.862 with k test = 5.
23
Moustakim, Mohammed Amine, Tamou Nasser, Najib Elkamoun, and Ahmed Essadki. "Prediction of electric power and load forcasting using LSTM technique for EMS." EPJ Web of Conferences 330 (2025): 03005. https://doi.org/10.1051/epjconf/202533003005.
Full textAbstract:
A designed electric load and energy forecasting is proposed for buildings. Two different forecasting models, one for electricity consumption (medium-term load forecasting MTLF) and another for electrical en- ergy (very short-term) are proposed, compared, and interpreted. To feed those prediction models, and depending on dataset quality, two available online websites are chosen. Forecasting models are developed by PYTHON programming language, using various libraries dedicated to machine learning projects, such as ’TensorFlow’, ’Kiras’ and ’Scikit-learn’, and others for the visualization of results and data visualization like ’MatPlotLib’ and ’Seaborn’, and many other libraries. Because of the type of prediction based on time series, we used Long Short Term Memory (LSTM-type) neural network models. The load forecasting model proposed in this study outperformed a previous engineering work on the same dataset. The proposed model achieved a minimal MAPE of 3.74% and a minimal RMSE that was approximately 20% lower than the engineer’s work. This article presents the proposed work and its results. Simulation results are presented using Google collaboratory the hosted Jupyter Notebook service.
24
Praseeda, B. Nair, Maria Johnson Ann, Mary Alex Ann, Sebastian Anshu, and Sunil Devika. "Android App for Handwriting Analysis Using Deep Learning." Journal of Communication Engineering and Its Innovations 5, no. 3 (2019): 16–21. https://doi.org/10.5281/zenodo.3564162.
Full textAbstract:
In this project, we aim to develop an android app to predict if a person is an extrovert or introvert by analyzing their handwriting in an offline manner using deep learning. Graphology is the analysis of physical characteristics and patterns of handwriting which has many applications in the field of employment profiling, marital compatibility, graphotherapy, psychological analysis, medical diagnosis, etc. Graphology is an effective tool used in employment profiling. According to an article published in 1988 in The Wall Street Journal around 80% of the fastest growing companies in Western Europe used handwriting analysis as part of their HR procedures hiring full time graphology experts. Model training is done on Google colaboratory and the model is then compressed using Tensorflow Lite to run on a mobile device. This can reduce human effort and handwriting analysis can be done without the supervision of a graphologist.
25
Satria Maheswara, Eka, Ahmad Bustomi Zuhri, and Dadang Iskandar Maulana. "Optimation Image Classification Pada Ikan Hiu Dengan Metode Convolutional Neural Network Dan Data Augmentasi." JURNAL TIKA 7, no. 1 (2022): 1–11. http://dx.doi.org/10.51179/tika.v7i1.993.
Full textAbstract:
Ikan Hiu merupakan ikan bertulang rawan yang banyak diburu karena mempunyai nilai ekonomi yang tinggi. Penangkapan dan perdagangan secara berlebihan mengakibatkan spesies ini terancam kepunahan dan sudah masuk pada beberapa kategori IUCN Red List. informasi tentang jenis-jenis hiu yang didaratkan di PPN Sungai liat Bangka masih sangat terbatas dikarenakan sulitnya identifikasi secara morfologi sehingga perlu dilakukan identifikasi menggunakan metode molekuler. oleh karena itu, peneliti menghasilkan program pengenalan citra pada ikan hiu menggunakan algoritma Convolutional Neural Network, yang merupakan kegiatan konvolusi dengan menggabungkan beberapa lapisan persiapan, dengan memanfaatkan beberapa komponen yang bergerak sama dan dimotivasi oleh sistem sensorik biologis. Gambar ikan hiu yang digunakan adalah basking, blacktip, blue, bull, hammerhead, lemon, mako, nurse, sand tiger, dan thresher. Implementasi pengenalan citra ikan hiu dilakukan dengan memakai 2 model pengujian yaitu model Sequential dan model on top VGG16 yang berjalan di aplikasi Google Collaboratory, dan Keras. Data pengujian pada penelitian ini adalah 1089 citra data latih dan 1073 citra data uji yang menghasilkan nilai evaluasi dengan nilai akurasi 86,58% dan nilai loss 0,701 pada model Sequential dan nilai akurasi 91,80% dan nilai loss 0,0355 pada model on top VGG16.
26
HR. Wibi Bagas N, Evang Mailoa, and Hindriyanto Dwi Purnomo. "Fruit Detection for Classification by Type with YNOv3-Based CNN Algorithm." Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 4, no. 3 (2020): 476–81. http://dx.doi.org/10.29207/resti.v4i3.1868.
Full textAbstract:
The fruit is part of the flowers in plants that are produced from pollination of the pistils and stamens. The shape and color of many fruits with a variety, with the type of single fruit, double fruit and compound fruit. This study asks for the development of 10 pieces detection applications to help the sensor agriculture sector for 10 pieces detection. The data in this study used the image of 10 fruits namely Mangosteen, Delicious, Star Fruit, Water Guava, Kiwi, Pear, Pineapple, Salak, Dragon Fruit, and Strawberry. Training and testing using CNN algorithms and YOLOv3 machine learning methods with the support of the work of the Darknet53 neural network. The analysis was conducted using 2,333 images of data from 10 classes. The training process is carried out up to 5,000 iterations stored in checkpoints. The implementation of the detection of 10 pieces was carried out on Google Collaboratory through imagery with two tests. Accuracy in the detection of 10 pieces can reach more than 90% in the first test of each fruit and an average of 70% in the second test for images outside the test data.
27
Sutomo, Febri, Daffa Ammar Muaafii, Daffa Naufaldi Al Rasyid, et al. "OPTIMIZATION OF THE K-NEAREST NEIGHBORS ALGORITHM USING THE ELBOW METHOD ON STROKE PREDICTION." Jurnal Teknik Informatika (Jutif) 4, no. 1 (2023): 125–30. http://dx.doi.org/10.52436/1.jutif.2023.4.1.839.
Full textAbstract:
Stroke is the second most deadly disease in the world according to WHO. The sufferer has an injury to the nervous system. Because of this, health experts, especially in the field of nursing, need special attention. Technological advances continue to change over time so that information needs are needed in life. Currently the data on stroke sufferers is extensive enough so that adequate information presentation techniques are needed so that the information received is very accurate and in accordance with user needs. Therefore, it is necessary to process data mining on stroke patient data to obtain useful information for users. This study aims to prove the performance of the Elbow Method to produce the optimum k value in the stroke prediction data using the K-Nearest Neighbors (KNN) algorithm. The optimum k value is generated from the Elbow Method which is executed with the Google Collaboratory using the Python programming language. The test results show that the Elbow Method produces the optimum k value at k = 7. The KNN model that uses the optimum k value from the Elbow Method can increase the accuracy and precision values reaching 6% and 0.12, respectively.
28
Iskandar, Dadang, and Marjuki Marjuki. "Classification of Melinjo Fruit Levels Using Skin Color Detection With RGB and HSV." Journal of Applied Engineering and Technological Science (JAETS) 4, no. 1 (2022): 123–30. http://dx.doi.org/10.37385/jaets.v4i1.958.
Full textAbstract:
This study aims to detect the ripeness of melinjo fruit using digital image method. Structured identification or division using image processing and computer vision requires the socialization of patterns based on training datasets. Melinjo (Gnetum gnemon L.) is a plant that can grow anywhere, such as yards, gardens, or on the sidelines of residential areas, as a result, produces melinjo into a plant that has relatively large potential to be developed. The process of image processing and pattern socialization is a highly developed research study. Starting based on the process of socializing an object, or a structured division of the object and about detecting the level of fruit maturity. The structured division process regarding ripeness into 3 classes, namely: raw, half-cooked and ripe where the process is carried out using Google Collaboratory which processes the RGB color space to HSV. In this study, the testing method for the system that will be used is a functional test where the test is carried out only by observing the execution results through test data and checking the functionality of the system being developed. The level of accuracy obtained from this study is 98.0% correct.
29
Zebua, Yakub Anuyuta, Daniel Ryan Hamonangan Sitompul, Stiven Hamonangan Sinurat, et al. "PREDIKSI PENETAPAN TARIF PENERBANGAN MENGGUNAKAN AUTO-ML DENGAN ALGORITMA RANDOM FOREST." Jurnal Teknik Informasi dan Komputer (Tekinkom) 5, no. 1 (2022): 115. http://dx.doi.org/10.37600/tekinkom.v5i1.508.
Full textAbstract:
With so many airlines competing with each other, airlines are competing to become the consumer/market's main choice, but to achieve this, there is no airline strategy that can predict the price of airline tickets according to market needs. To meet the needs of airlines, we need a way to determine the price of airline tickets according to market needs with the help of the influence of technology and information. This research method was carried out using Google Collaboratory as a media to create a data model automated machine learning (AutoML) with the Random Forest, Logistic Regression and Gradient Boosting Regressor algorithms. In this study, the model that produced the highest R2 value and the lowest RMSE was a random forest with an R2 value of 83.91% and an RMSE of $175.9. However, from the three models, Random Forest got a change in accuracy of 1.96% to 85.87. To assist in predicting the determination of flight fares, airline companies can more easily and be alert to determine flight fares that are in accordance with the market. Therefore, Random Forest can be declared better than Logistic Regression and Gradient Boosting models. The Random Forest model that has been created can be used to predict in real-time using Machine Learning.
30
Sampathila, Niranjana, Krishnaraj Chadaga, Neelankit Goswami, et al. "Customized Deep Learning Classifier for Detection of Acute Lymphoblastic Leukemia Using Blood Smear Images." Healthcare 10, no. 10 (2022): 1812. http://dx.doi.org/10.3390/healthcare10101812.
Full textAbstract:
Acute lymphoblastic leukemia (ALL) is a rare type of blood cancer caused due to the overproduction of lymphocytes by the bone marrow in the human body. It is one of the common types of cancer in children, which has a fair chance of being cured. However, this may even occur in adults, and the chances of a cure are slim if diagnosed at a later stage. To aid in the early detection of this deadly disease, an intelligent method to screen the white blood cells is proposed in this study. The proposed intelligent deep learning algorithm uses the microscopic images of blood smears as the input data. This algorithm is implemented with a convolutional neural network (CNN) to predict the leukemic cells from the healthy blood cells. The custom ALLNET model was trained and tested using the microscopic images available as open-source data. The model training was carried out on Google Collaboratory using the Nvidia Tesla P-100 GPU method. Maximum accuracy of 95.54%, specificity of 95.81%, sensitivity of 95.91%, F1-score of 95.43%, and precision of 96% were obtained by this accurate classifier. The proposed technique may be used during the pre-screening to detect the leukemia cells during complete blood count (CBC) and peripheral blood tests.
31
Guzmán Rincón, Alfredo, and Lira Isis Valencia Quecano. "Modelo de Monte Carlo para la predicción de la deserción: herramienta para la retroalimentación de las políticas públicas en la educación superio." Razón Crítica, no. 17 (May 24, 2024): 1–19. http://dx.doi.org/10.21789/25007807.2024.
Full textAbstract:
La deserción en la educación superior es un problema global en aumento que afecta los beneficios individuales y sociales asociados a un mayor nivel educativo. A pesar de las investigaciones existentes sobre los factores que contribuyen a la deserción, se ha prestado poca atención al desarrollo de modelos predictivos que puedan informar las políticas públicas en esta área. Este artículo se propuso determinar la tendencia de la deserción en Colombia mediante un modelo de Monte Carlo, con el objetivo de proporcionar una retroalimentación para la toma de decisiones sobre las políticas públicas de prevención y mitigación de la deserción. El modelo utilizado se basó en datos históricos y se implementó en Python utilizando la Suite de Google Collaboratory. Los resultados mostraron que, si se mantienen las políticas actuales de financiamiento estudiantil en Colombia, se espera que la tasa promedio de deserción para el período 2022-1 y 2024-1 sea del 11,65 %, con una desviación estándar del 2,82 %. Este modelo ofrece una herramienta novedosa para predecir la deserción estudiantil y respaldar el diseño de políticas públicas. Sin embargo, es importante tener en cuenta las limitaciones del modelo y complementar los resultados con análisis adicionales para tomar decisiones informadas en la prevención y mitigación de la deserción.
32
Sianturi, Ismail M., and Diko Harinto. "PREDIKSI PENETAPAN TARIF PENERBANGAN MENGGUNAKAN AUTO-ML DENGAN ALGORITMA RANDOM FOREST." Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan 2, no. 1 (2022): 40–48. http://dx.doi.org/10.55338/justikpen.v2i1.37.
Full textAbstract:
With so many airlines competing with each other, airlines are competing to become the consumer/market's main choice, but to achieve this, there is no airline strategy that can predict the price of airline tickets according to market needs. To meet the needs of airlines, we need a way to determine the price of airline tickets according to market needs with the help of the influence of technology and information. This research method was carried out using Google Collaboratory as a media to create a data model with the Random Forest, Logistic Regression and Gradient Boosting Regressor algorithms. In this study, the model that produced the highest R2 value and the lowest RMSE was a random forest with an R2 value of 83.91% and an RMSE of $175.9. However, from the three models, Random Forest got a change in accuracy of 1.96% to 85.87. To assist in predicting the determination of flight fares, airline companies can more easily and be alert to determine flight fares that are in accordance with the market. Therefore, Random Forest can be declared better than Logistic Regression and Gradient Boosting models. The Random Forest model that has been created can be used to predict in real-time using Machine Learning.
33
Custodio, Paul Michael. "Improving MRI Classification through Layered Convolutional Neural Networks Configuration." Smart Techno (Smart Technology, Informatics and Technopreneurship) 7, no. 1 (2025): 38–44. https://doi.org/10.59356/smart-techno.v7i1.154.
Full textAbstract:
Timely and accurate classification of brain tumors using Magnetic Resonance Imaging (MRI) is critical for effective treatment planning. This study proposes a layered Convolutional Neural Network (CNN) configuration to enhance the classification of brain tumors, addressing the limitations of traditional machine learning approaches that rely heavily on manual feature extraction. Utilizing a dataset sourced from Kaggle, comprising 7023 MRI images categorized into glioma, meningioma, no tumor, and pituitary tumor classes, the research implements data augmentation techniques such as rotation and flipping to increase the dataset size by 20%. Images were standardized to 128x128 pixels and normalized for model compatibility. The core model architecture was built using 2D CNNs with configurations ranging from one to three layers. The models were trained and tested using TensorFlow and Keras on Google Collaboratory, and evaluated based on accuracy, loss, and computational efficiency. The findings revealed that among all the configurations tested, the three-layered CNN model delivered the best performance. It achieved an accuracy value of 89.79% with a corresponding loss of 0.469. In terms of processing time, the model completed training in 59.8894 seconds and performed inference in 5.1099 seconds, highlighting its suitability for real-time diagnostic applications despite the longer training duration.
34
Nurhadi AS, Yusril, Dadang Iskandar Mulyana, and Yuma Akbar. "Klasifikasi Rumput Liar Menggunakan Deep Learning Dengan Dense Convolutional Neural Network." Progresif: Jurnal Ilmiah Komputer 19, no. 1 (2023): 347. https://doi.org/10.35889/progresif.v19i1.1166.
Full textAbstract:
<p>Weed control research using robots increases productivity in agriculture. Most of the work focused on developing robotics for farmland, ignoring the weed management issues facing pasture farmers. In developing a weed control robot, it takes a lot of hardware and software components and devices. In software requirements, there is a need for a system that can help the robot to recognize weeds that it will take care of for land management. The biggest obstacle to the expansion of robotic weed control is the robust classification of weed species in their natural environment. This work contributes to the method of classifying weed species using Deep Learning with Dense Convolutional Neural Network. The wild grass images used are Chinee apple, Snake weed, Lantana, Prickly acacia, Siam weed, Parthenium, Rubber vine and Parkinsonia. This image recognition implementation is done by using Resnet50 on Tensorflow at Google Collaboratory. The dataset used in the test is the DeepWeeds dataset which consists of 17,509 images labeled with 10,505 training data and 3,502 test data used to produce evaluation values with 78% precision, 78% recall, 78% f1-score, 77.73% accuracy and loss. 0.6676.</p><p><strong><em>Kata kunci</em></strong><strong><em>:</em></strong><em> ResNet50; Convolutional Neural Network; Image Classification</em><em>.</em></p><p align="center"><strong>Abstrak</strong></p><p>Penelitian kontrol gulma menggunakan robot meningkatkan produktivitas di bidang agrikultur. Sebagian besar pekerjaan fokus pada pengembangan robotika untuk lahan pertanian, mengabaikan masalah pengelolaan gulma yang dihadapi peternak padang rumput. Dalam mengembangkan robot pengendali gulma dibutuhkan banyak perangkat dan komponen hardware maupun software. Pada kebutuhan software perlu adanya sistem yang dapat membantu robot untuk mengenali tanaman gulma yang akan diurusnya untuk pengelolaan lahan. Kendala terbesar untuk peluasan pengendalian gulma dengan robot adalah klasifikasi kuat species gulma di lingkungan alami mereka. Karya ini berkontribusi pada metode pengklasifikasian species gulma menggunakan Deep Learning dengan Dense Convolutional Neural Network. Citra tanaman rumput liar yang digunakan adalah Chinee apple, Snake weed, Lantana, Prickly acacia, Siam weed, Parthenium, Rubber vine dan Parkinsonia. Implementasi pengenalan citra ini dilakukan dengan memanfaatkan Resnet50 pada Tensorflow di Google Collaboratory. Dataset yang digunakan dalam pengujian adalah dataset DeepWeeds yang terdiri dari 17.509 gambar berlabel sebanyak 10.505 data training dan 3.502 data test yang digunakan menghasilkan nilai evaluasi dengan nilai precision 78%, recall 78%, f1-score 78%, akurasi 77,73% dan loss 0.6676.</p><p><strong><em>Kata kunci</em></strong><strong><em>:</em></strong><em> ResNet50; Convolutional Neural Network; Image Classification</em><em>.</em></p>
35
Permana, Raga, Handrianus Saldu, and Dadang Iskandar Maulana. "OPTIMASI IMAGE CLASSIFICATION PADA JENIS SAMPAH DENGAN DATA AUGMENTATION DAN CONVOLUTIONAL NEURAL NETWORK." Jurnal Sistem Informasi dan Informatika (Simika) 5, no. 2 (2022): 111–20. http://dx.doi.org/10.47080/simika.v5i2.1913.
Full textAbstract:
Garbage is useless goods/materials used normally or specifically in production, goods damaged during production or useless materials which mainly come from households. Moreover, inorganic waste is very difficult and takes a longer time to be decomposed by the soil. The lack of public knowledge about the classification of types of waste and how to process it causes a very serious problem in Indonesia. Therefore, this research creates a waste type recognition program using the Convolutional Neural Network (CNN) algorithm, which can be used to detect and recognize objects in an image. CNN is a technique inspired by the way mammals, humans, produce visual perception. CNN is included in the type of deep neural network because of its high network depth and widely applied to imagery. 2 Types of waste classification, namely inorganic waste and organic waste. The implementation of garbage image recognition uses 2 test models, Sequential and on top VGG16 which runs on the Google Collaboratory application, and Keras. After carrying out the Augmentation process, the number of test data in this study was 1489 images on the training data and 182 on the testing data resulting in an evaluation value with an accuracy of 90.97% and a loss value of 0.307 on the Sequential model, and an accuracy value of 97.99% with a loss value of 0.069 on the on top model. VGG16.
36
Forero Peña, Juliana, and Javier Palacios Puentes. "Propuesta de optimización de la cuenca del Río Anil El mediante herramientas computacionales." INVENTUM 16, no. 31 (2021): 40–49. http://dx.doi.org/10.26620/uniminuto.inventum.16.31.2021.40-49.
Full textAbstract:
Esta investigación se realizó con el objetivo de crear una propuesta para la optimización de la cuenca del Río Anil, a partir de una simulación de la hidrología, utilizando herramientas computacionales como Google Collaboratory, Sistemas de Información Geográfica (QGIS) y VAC Systems, proponiendo un diseño sostenible. Por medio de la información suministrada por el IDEAM se diagnosticó el estado de la cuenca del Río Anil El, donde se encontraron diferentes estaciones de monitoreo, las cuales permiten tener datos constantes sobre las épocas lluviosas y secas dentro de las zonas de estudio junto con los caudales correspondientes. Al analizar los resultados obtenidos del estudio de los datos por medio de la herramienta Solver y la correlación de la cuenca con las estaciones cercanas, se observó el comportamiento hidrometeorológico, indicando que el Río Anil es una zona trópico seco, manteniendo precipitaciones altas en los meses de julio, agosto, septiembre y bajas en los primeros meses del año, percibiendo que es constante durante casi todo el año; la cuenca presenta inundaciones en las épocas de lluvia, en las que se evidencia que sufre de precipitaciones altas provocando inundaciones en el municipio de Uramita y veredas cercanas. Finalmente se propuso un diseño sostenible para el aprovechamiento de los recursos hídricos generados por la capacidad de infiltración de la cuenca del Río Anil El, beneficiando las necesidades de la población.
37
Solihin, Amat, Dadang Iskandar Mulyana, and Mesra Betty Yel. "Klasifikasi Jenis Alat Musik Tradisional Papua menggunakan Metode Transfer Learning dan Data Augmentasi." Jurnal SISKOM-KB (Sistem Komputer dan Kecerdasan Buatan) 5, no. 2 (2022): 36–44. http://dx.doi.org/10.47970/siskom-kb.v5i2.279.
Full textAbstract:
Papua merupakan sebuah pulau yang terletak di sebelah utara Australia dan merupakan bagian dari wilayah timur Indonesia yang sebagian besar daratannya masih berupa hutan belantara dan merupakan pulau terbesar kedua di dunia setelah Greenland. Papua terkenal akan aneka budayanya, termasuk kekayaan alat musik. Ada berbagai jenis alat musik tradisional Papua yang menawan dan memiliki sejarah musik tradisional mendalam dibaliknya. Alat musik ini biasa digunakan untuk mengiringi acara adat maupun pesta. Perkembangan teknologi saat ini dan di tengah perkembangan musik kontemporer di Papua, ada kegelisahaan akan hilangnya musik-musik tradisi yang sangat kaya beragam sesuai kebudayaan masing-masing wilayah di Papua. Oleh karena itu, peneliti membuat program pengenalan citra alat musik tradisional Papua menggunakan metode Transfer Learning, yang merupakan metode dari Convolutional Neural Network yang merupakan operasi konvolusi dengan melatih terlebih dahulu pada model sebelumnya yang kemudian menggabungkan beberapa lapisan pemrosesan, menggunakan beberapa elemen yang bergerak secara paralel dan terinspirasi oleh sistem saraf biologis. Citra alat musik Papua yang digunakan adalah Fue, Pikon, Triton, Yi dan Tifa. Implementasi pengenalan citra ini dilakukan dengan memanfaatkan Pre-Trained model dari DenseNet201 yang berjalan pada aplikasi Google Collaboratory dan Tensorflow. Dataset yang digunakan dalam pengujian sebanyak 979 data training dan 143 data testing yang mengahasilkan nilai evaluasi dengan nilai precision 98%, recall 98%, f1-score 98%, accuracy 98,46% dan loss 0.051.
38
Saputra, Okta, Dadang Iskandar Mulyana, and Mesra Betty Yel. "Implementasi Algoritma Convolutional Neural Network (CNN) Untuk Klasifikasi Senjata Tradisional Di Jawa Tengah Dengan Metode Transfer Learning." Jurnal SISKOM-KB (Sistem Komputer dan Kecerdasan Buatan) 5, no. 2 (2022): 45–52. http://dx.doi.org/10.47970/siskom-kb.v5i2.282.
Full textAbstract:
Indonesia merupakan bangsa yang terdiri dari berbagai etnik dan memiliki keberagaman kesenian dan kebudayaan yang unik. Perkembangan zaman telah membawa perubahan sejarah budaya, salah satunya adalah senjata tradisional. Senjata tradisional merupakan salah satu kekayaan budaya, seperti yang ada di Indonesia, Senjata ini memiliki berbagai ciri khas dan cerita tersendiri, masyarakat di Indonesia sudah cukup mengenal berbagai jenis senjata tradisional dari daerah masing-masing namun untuk mengenal senjata tradisional dari daerah lain dapat dibilang kurang memahami, Banyaknya jenis senjata tradisonal yang ada di Indonesia khususnya di pulau Jawa membuat peneliti tertarik untuk membuat suatu program pengenalan jenis senjata tradisional khususnya untuk senjata tradisional yang ada di Jawa Tengah berdasarkan dataset foto atau citra senjata tradisional menggunakan metode Transfer Learning, yang merupakan metode dari Convolutional Neural Network dengan memanfaatkan pre-trained model yang mampu meningkatkan nilai akurasi cukup tinggi dan jumlah training parameters yang kecil. Citra senjata tradisional Jawa Tengah yang digunakan adalah Keris, Tombak, Khudi, Wedhung dan Plintheng. Implementasi pengenalan citra ini dilakukan dengan memanfaatkan Pre-Trained model dari MobileNetV2 yang berjalan pada aplikasi Google Collaboratory dan Tensorflow. Dataset yang digunakan dalam pegujian sebanyak 638 data training atau sebesar 81% dan 147 data validasi atau sebesar 19% dengan melakukan pengujian sebanyak 50 kali dan batch size sebesar 32, maka diperoleh hasil akurasi sebesar 98,64% namun memiliki nilai loss sebesar 0.16
39
Khaw, Li Wen, and Shahrum Shah Abdullah. "MRI Brain Image Classification Using Convolutional Neural Networks And Transfer Learning." Journal of Advanced Research in Computing and Applications 31, no. 1 (2024): 20–26. http://dx.doi.org/10.37934/arca.31.1.2026.
Full textAbstract:
Alzheimer's disease (AD) is a neurodegenerative disorder. There is no particular cure for Alzheimer's disease. Accurate and early diagnosis of AD could assist patients in receiving appropriate care. However, diagnosing AD in brain MRI images is a difficult task that depends on the presence of experienced radiologists or medical professionals. As one MRI exam might generate thousands of images, it typically takes several weeks for the results to be obtained. Many researchers use statistical and machine learning methods to diagnose Alzheimer's disease. Deep Learning algorithms have demonstrated human-level competence in a variety of fields. Deep learning, especially convolutional neural networks (CNN), is becoming popular because of its state-of-the-art performance in many computer vision tasks such as visual object classification, object detection, and segmentation. Transfer learning is a technique that can be used with CNNs to improve their performance. The purpose of this project is to develop a model of brain MRI image classification for Alzheimer's disease diagnosis by using CNN and transfer learning. In this project, the modified VGG16 model with fine-tuning was proposed, and MRI data from the OASIS database was used to classify Alzheimer's disease into three (3) different classes, which are AD, MCI and NC. The model is developed using Google Collaboratory and Adam's optimization algorithm. The proposed model has achieved a training accuracy of 98.56% and the validation accuracy of 90.24%.
40
Usen, Yolan Anjani, and Cynthia Hayat. "DESIGN AND BUILD VEHICLE PLATE DETECTION SYSTEM USING YOU ONLY LOOK ONCE METHOD BASED ON ANDROID." Jurnal Teknik Informatika (Jutif) 4, no. 4 (2023): 807–18. http://dx.doi.org/10.52436/1.jutif.2023.4.4.791.
Full textAbstract:
The method of collecting the vehicle data is conducted conventionally by gathering data from each region to be converted into single, raw information in the form of vehicle plates for all regions, to be processed on a computer and sent to the Central Bureau of Statistics. It is then transformed into a form of national data file that provides information on vehicle plates for the Indonesian people. This kind of data gathering method requires a lot of time and effort. Therefore, it is a concern for researchers to detect vehicle plates using image processing by utilizing the Android-based You Only Look Once method. The YOLOv4 technique is used because it processes image data directly with optimal performance in order to produce faster predictions. In its application, the researchers use Google Collaboratory to create models and Android Studio for android applications. At the same time, the parameters studied were precision, recall, F1 score, average IoU, and mAP. By using the "Vehicle Registration Plate" dataset, the ratio of which is 70% in training data and 30% in data validation, an accuracy of 77% is obtained with a detection time of 0.05 seconds, whereas the average accuracy value is 86.82%. Therefore, it can be concluded that this study has an optimized performance for detecting vehicle plates using the Android application.
41
OLIVEIRA, Daniel Ferreira de, Vivian de Oliveira FERNANDES, Elias Nasr NAIM ELIAS, Vinícius Emmel MARTINS, and Mauro José ALIXANDRINI JÚNIOR. "AVALIAÇÃO INTRÍNSECA DOS DADOS DO OPENSTREETMAP E OS ASPECTOS ESPAÇO-TEMPORAIS NO ESTUDO DE CASO DO ROMPIMENTO DA BARRAGEM DE BRUMADINHO." Geosciences = Geociências 41, no. 3 (2023): 797–810. http://dx.doi.org/10.5016/geociencias.v41i3.16786.
Full textAbstract:
O presente estudo consistiu na avaliação intrínseca dos dados do OSM e dos aspectos espaço-temporais no estudo de caso do rompimento da barragem de Brumadinho em Minas Gerais. Partindo da premissa de que os dados colaborativos do Openstreetmap (OSM) podem ser utilizados no gerenciamento de crises humanitárias. A utilização da plataforma do OSM, como base para aquisição de dados geoespaciais se deu pelo elevado número de contribuidores e dados gerados. A partir do recorte da área afetada pelo desastre, foi realizada uma análise quantitativa das edições ao longo do tempo, o que permitiu avaliar um dos potenciais do OSM, considerando os impactos das ações do Humanitarian OpenStreetMap Team (HOT), que através de Mapatonas gerou uma quantidade significativa de dados em um curto intervalo de tempo. A metodologia utilizada consistiu em uma análise de regressão realizada no ambiente do Google Collaboratory que por meio de código em Python que mostrou a quantidade de edições naquela região e uma análise dos vetores gerados, adquiridos por meio de um plugin do QGIS chamado QuickOSM. Os resultados mostraram que foram gerados, aproximadamente 8000 registros em um intervalo de uma semana após o desastre, sendo 5000 em um único dia. A partir daí pode-se concluir que as ações de mapeamento do Humanitarian OpenStreetMap Team possuem potencial para o fornecimento de uma resposta rápida acerca das dinâmicas de alteração do solo causadas por desastres ambientais.
42
Widyanto, Tetrian, Ina Ristiana, and Arief Wibowo. "Komparasi Naïve Bayes dan SVM Analisis Sentimen RUU Kesehatan di Twitter." SINTECH (Science and Information Technology) Journal 6, no. 3 (2023): 147–61. http://dx.doi.org/10.31598/sintechjournal.v6i3.1433.
Full textAbstract:
This research focuses on sentiment analysis regarding the plan to ratify the Health Bill which has become a hot topic of conversation on social media, especially Twitter. This research aims to classify tweets that reflect various opinions regarding the Health Bill, including support, rejection and neutrality. In this research, the author uses two types of classification algorithms, namely the Multinomial Naïve Bayes Algorithm and the Support Vector Machine (SVM) Algorithm. Previously, tweets were labelled using the Lexicon InSet dictionary. The research was conducted in the Python programming language and using Google Collaboratory. Data validation was carried out using the K-fold cross-validation method. The research results indicate that both algorithms predominantly produce positive sentiments over negative ones. However, SVM with a linear kernel achieves a higher accuracy rate of 0.87, compared to Multinomial Naïve Bayes, which has an accuracy of 0.82. SVM also records a precision of 0.87, recall of 0.97, and an F1-score of 0.91, while Multinomial Naïve Bayes shows a precision of 0.81, recall of 0.98, and an F1-score of 0.89. Overall, this research confirms that SVM excels in text sentiment classification, while Multinomial Naïve Bayes also provides good results in recognising positive and negative sentiment. These results have important implications for understanding public sentiment regarding the Health Bill on the Twitter platform.
43
Wantoro, Agus, Dani Saputra, Damayanti, Permatan, and Rusliyawati. "Perbandingan Metode Naive Bayes Dan Support Vector Machine (SVM) Pada Analisis Kendaraan Listrik Pada Media Sosial “X”." Jurnal Informatika Polinema 11, no. 2 (2025): 227–34. https://doi.org/10.33795/jip.v11i2.6458.
Full textAbstract:
Kendaraan listrik merupakan kendaraan yang menggunakan satu atau lebih motor listrik atau motor traksi sebagai tenaga penggeraknya. Kendaraan listrik saat ini menjadi tren global sebagai alternatif kendaraan berbahan bakar fosil atau bahan bakar minyak (BBM). Peralihan dari kendaraan berbahan bakar minyak ke kendaraan listrik menjadi salah satu solusi efektif karena kendaraan listrik memiliki beberapa keunggulan dibanding kendaraan BBM. Penelitian ini bertujuan untuk menganalisis sentimen publik terhadap kemunculan kendaraan listrik pada media “X” dan melakukan perbandingan kinerja algoritma klasifikasi. Data sentimen selanjutnya akan dilakukan klasifikasi menggunakan metode Naïve Bayes dan Support Vector Machine (SVM). Pengelolaan data menggunakan bahasa pemrograman python dan google Collaboratory. Tahapan penelitian ini meliputi crawling, labelling, pre-processing, klasifikasi metode, dan visualisasi. Berdasarkan 2615 data yang telah dikumpulkan, selanjutnya dilakukan preprocessing, dan cleaning data sehingga. Hasil cleaning didapatkan 1245 data yang akan dilakukan klasifikasi. Dataset dibagi menjadi dua, yaitu data latih dan data uji. Berdasarkan data latih, selanjutnya dilakukan pelabelan data menghasilkan 57,16% data positif sebanyak 30,02 data netral, dan 17,83 data negatif. Hasil perbandingan klasifikasi menunjukkan bahwa metode Naïve Bayes memiliki akurasi sebesar 66%, sedangkan metode Support Vector Machine (SVM) sebesar 93%. Metode Support Vector Machine (SVM) terbukti lebih unggul untuk analisis data dibandingkan dengan metode Naïve Bayes. Selain itu berdasarkan data pengguna “X” lebih banyak yang memberikan respon positif terhadap kendaraan listrik
44
Kaloshina, T. Yu, and D. A. Sevostyanov. "Digital competencies as the basis of professional competitiveness (on the example of training management specialists)." Professional education in the modern world 12, no. 1 (2022): 105–13. http://dx.doi.org/10.20913/2618-7515-2022-1-13.
Full textAbstract:
Introduction. The digitalization of the economy and the digitalization of society are occurring at a rapid pace. The Russian Federation has approved a strategy for the development of the information society for the period up to 2030. The implementation of this strategy provides for improving the quality of life, creating conditions for the development of knowledge, the use of digital technologies, increasing the degree of digital literacy, digital security, etc. The formation of a global digital environment has affected all spheres of life, and especially education. Currently, the digitalization of education is seen as a turning point in history and the formation of a new paradigm for it’s development. Purpose setting. The article studies and discusses the problem of the formation and development of digital competencies of management specialists.Methodology of the study. The methodology of the research includes a socio-philosophical analysis of current trends in the digitalization of education and the use of a sociological survey of students.Results. The paper presents the results of a study on the use of information technologies by students in education (the viewing and searching for information and digital content, evaluating and analyzing information and digital content, using the functionality of social networks in education, reading educational and scientific literature, professional development, working with a text editor, working with electronic tables, information visualization). According to the authors, management specialists should confidently use “smart” gadgets (smartphones, tablets, etc.). In the digital environment, management professionals need to be able to use data analysis programs such as Jupyter Notebook, JupyterLab, PyCharm, RStudio, Stata, SPSS, Microsoft Excel and others, and use Google Sheets. Also, in their professional activities, they must be able to use cloud technologies and programs for data analysis with the ability to simultaneously edit a document (Google Collaboratory, for example).Conclusion. The authors believe that digital literacy and digital competencies are necessary for the competitiveness of a future management specialists and for their success in the modern labor market.
45
Fernandi, Arya, Sofia Sa'idah, and Rita Magdalena. "Handwritten Hiragana Letter Detection Using CNN." JOIV : International Journal on Informatics Visualization 8, no. 3-2 (2024): 1916. https://doi.org/10.62527/joiv.8.3-2.3035.
Full textAbstract:
Hiragana is one of the primary alphabets used in Japanese. Hiragana is a phonetic symbol; each letter represents one syllable. Hiragana letters are formed from curved lines and strokes. However, detecting Hiragana letters causes many errors because people still rely on their vision to detect the letters, especially people familiar with them for the first time. It will be difficult and not very clear to read the letters. Therefore, a Convolutional Neural Network (CNN) method is used to detect handwritten Hiragana letters and help people who first get to know Hiragana letters when the letters are too complicated for human eyes to detect. This research uses the YOLOv8 model as a handwritten Hiragana letter detection algorithm. The Hiragana letters to be detected are basic letters with 46 characters. This research uses the YOLOv8 model run on Google Collaboratory with the Ultralytics library version 8.0.20 using the Python programming language. The dataset is collected from the internet and annotated using the Roboflow framework and dataset 4600 Hiragana letters. From the test results, the best model is YOLOv8l using SGD optimizer and learning rate 0.01 with a precision value of 98.5%, recall value of 95.7%, f1-score value of 97.1%, and mAP value of 95.5%. In the future, we aim to expand the number of datasets and employ a broader range of hyperparameter values to optimize the classification precision and accuracy of the Hiragana Letter Detection system.
46
Arischo, Ray Shandy, and Damayanti Damayanti. "Analisis Sentimen Pinjaman Online di Twitter dengan Metode Naive Bayes Classifier dan SVM." JURNAL MEDIA INFORMATIKA BUDIDARMA 8, no. 2 (2024): 1120. http://dx.doi.org/10.30865/mib.v8i2.7406.
Full textAbstract:
Online loans are a form of financial service that occurs online or online, where online loans are available in applications or information technology. Online loans can also be a place to develop small and medium enterprises, because they provide easy access to loans and are also relatively safe. The social media platform twitter is one of the platforms that discusses illegal and legal online loans. Twitter has a trending topic feature that displays topics of conversation that are being discussed at a certain time. This research uses sentiment analysis which is useful as access to track public responses to an object of interest. In this study using a comparison of algorithms, namely naïve bayes classifier with support vector machine (SVM), where from the two methods will be sought who is better at analyzing data with which value of accuracy, precision, recall, f1-score is better. The data used in as many as 2725 tweets obtained through the crawling process with the python programming language and google collaboratory tools. Sentiment analysis is divided into 3 categories, namely positive, negative, and neutral, with data calculations divided into 70% training data and 20% test data. The naïve bayes classifier algorithm has an accuracy value of 55%, with a support of 404 data. Meanwhile, the support vector machine (SVM) accuracy is 77% with a support of 818 data. The results of the accuracy value of the SVM method are better than the naïve bayes classifier method in this study.
47
Hidayat, Sidiq Syamsul, Dwi Rahmawati, Muhamad Cahyo Ardi Prabowo, Liliek Triyono, and Farika Tono Putri. "Determining the Rice Seeds Quality Using Convolutional Neural Network." JOIV : International Journal on Informatics Visualization 7, no. 2 (2023): 527. http://dx.doi.org/10.30630/joiv.7.2.1175.
Full textAbstract:
Seed inspection is crucial for plant nurseries and farmers as it ensures seed quality when growing seedlings. It is traditionally accomplished by expert inspectors filtering samples manually, but there are some challenges, such as cost, accuracy, and large numbers. Speed and accuracy were the main conditions for increasing agricultural productivity. Machine learning is a sub-science of Artificial Intelligence that can be applied in research on the classification of rice seed quality. The pipeline of a machine learning system is dataset collection, training, validation, and testing. Model making begins with taking data on the characteristics of rice seeds based on physical parameters in the form of seed shape and color. The dataset used is two thousand images divided into two categories, namely superior seeds and non-superior seeds. Training and Validation was conducted using the Convolutional Neural Network (CNN) algorithm with the concept of cross-validation on Google Collaboratory notebooks. The ratio split of train data and validation data in modeling from a dataset is 80:20. The result of the model formed is a model with the development of a Deep Convolutional Neural Network (Deep CNN) that can classify the digital image data of rice seeds from the results of data calls uploaded into the system. The results of the experiment conducted on 30 test data can be analyzed so that the system can classify superior and non-superior seeds with a precision value of 93% and a recall of 95%.
48
Nuraeni, Dini, and Masita Dwi Mandini Manessa. "SPATIAL MACHINE LEARNING FOR MONITORING TEA LEAVES AND CROP YIELD ESTIMATION USING SENTINEL-2 IMAGERY, (A Case of Gunung Mas Plantation, Bogor)." International Journal of Remote Sensing and Earth Sciences (IJReSES) 19, no. 2 (2023): 133. http://dx.doi.org/10.30536/j.ijreses.2022.v19.a3830.
Full textAbstract:
Indonesia's tea production and export volume have fluctuated with a downward trend in the last five years, partly due to the increasingly competitive world tea quality. Crop yield estimation is part of the management of tea plucking, affecting tea quality and quantity. The constraint in estimating crop yields requires technology that can make the process more effective and efficient. Remote sensing technology and machine learning have been widely used in precision agriculture. Recently, big data processing, especially remote sensing data, machine learning, and deep learning have been carried out using a cloud computing platform. Therefore, we propose using GeoAI, a combination of Sentinel-2A imagery, machine learning, and Google Collaboratory, to predict ready for plucking tea leaves at optimal plucking time at Gunung Mas Plantation Bogor. We used selected bands of Sentinel-2A and extracted more features (i.e., NDVI) as a training set. Then we utilized the tea blocks boundary and tea plucking data to generate labels using Random Forest (RF) and Support Vector Machine (SVM). The classification results were further used to estimate the production of crop tea yield. The RF classifier is able to achieve overall accuracy at 51% and SVM at 54%. Meanwhile, accuracy at optimally aged tea blocks is able to achieve at 75.62% for RF and 52.88% for SVM. Thus, the SVM classifier is better in terms of overall accuracy. Meanwhile, the RF classifier is superior in predicting ready for plucking tea at optimally aged tea blocks.
49
Singh, Sanjeev, Sudhakar Kancharla, Prachetha Kolli, Gowtham Mandadapu, and Manoj Kumar Jena. "In Silico Exploration of Phytochemicals as Potential Drug Candidates against Dipeptidyl Peptidase-4 Target for the Treatment of Type 2 Diabetes." Biomedical and Biotechnology Research Journal (BBRJ) 7, no. 4 (2023): 598–607. http://dx.doi.org/10.4103/bbrj.bbrj_205_23.
Full textAbstract:
Abstract Background: The objective of the study was to use docking and pharmacological research to explore phytochemicals as therapeutic candidates for the treatment of type 2 Diabetes Mellitus. Methods: The 100 plant compounds for the study were selected after a thorough review of the most recent literature using PubMed and Google Scholar. Three-dimensional structure in Structure-Data File Format of all phytochemicals was downloaded and collected from the PubChem platform. In parallel, the three-dimensional structure of the target protein dipeptidyl peptidase-4 in Protein Data Bank (PDB) format was obtained from the website of the Research Collaboratory for Structural Bioinformatics-PDB. AutoDock Vina software was used for the docking purpose. SwissADME and the admetSAR web server were used to further examine the top docked compounds for the pharmacological investigation. Results: Out of 100 phytochemicals, only 15 have shown better or comparable binding affinity above the benchmark medication, sitagliptin (−7.9 kcal/mol). All of these compounds were assessed to determine their viability as potential drugs by predicting their Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties. Two of these phytochemicals have proven their potential as medication candidates by passing the ADMET requirements. Conclusions: In silico studies help explore and find drug candidates among the enormous pool of phytochemicals and narrow down the screening process, saving time and money on experiments. In vitro and in vivo testing can be used in the future to further validate drug candidature.
50
Kollmann, Stephan A., Martin Kleppmann, and Alastair R. Beresford. "Snapdoc: Authenticated snapshots with history privacy in peer-to-peer collaborative editing." Proceedings on Privacy Enhancing Technologies 2019, no. 3 (2019): 210–32. http://dx.doi.org/10.2478/popets-2019-0044.
Full textAbstract:
Abstract Document collaboration applications, such as Google Docs or Microsoft Office Online, need to ensure that all collaborators have a consistent view of the shared document, and usually achieve this by relying on a trusted server. Other existing approaches that do not rely on a trusted third party assume that all collaborating devices are trusted. In particular, when inviting a new collaborator to a group, one needs to choose between a) keeping past edits private and sending only the latest state (a snapshot) of the document; or b) allowing the new collaborator to verify her view of the document is consistent with other honest devices by sending the full history of (signed) edits. We present a new protocol which allows an authenticated snapshot to be sent to new collaborators while both hiding the past editing history, and allowing them to verify consistency. We evaluate the costs of the protocol by emulating the editing history of 270 Wikipedia pages; 99% of insert operations were processed within 11.0 ms; 64.9 ms for delete operations. An additional benefit of authenticated snapshots is a median 84% reduction in the amount of data sent to a new collaborator compared to a basic protocol that transfers a full edit history.