Journal of Computer Science and Technology Studies最新文献

{"title":"Advanced Cybercrime Detection: A Comprehensive Study on Supervised and Unsupervised Machine Learning Approaches Using Real-world Datasets","authors":"Duc M Cao, Md Abu Sayed, Md Tuhin Mia, Eftekhar Hossain Ayon, Bishnu Padh Ghosh, Rejon Kumar Ray, Aqib Raihan, Aslima Akter, Mamunur Rahman","doi":"10.32996/jcsts.2024.6.1.5","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.5","url":null,"abstract":"In the ever-evolving field of cybersecurity, sophisticated methods—which combine supervised and unsupervised approaches—are used to tackle cybercrime. Strong supervised tools include Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), while well-known unsupervised methods include the K-means clustering model. These techniques are used on the publicly available StatLine dataset from CBS, which is a large dataset that includes the individual attributes of one thousand crime victims. Performance analysis shows the remarkable 91% accuracy of SVM in supervised classification by examining the differences between training and testing data. K-Nearest Neighbors (KNN) models are quite good in the unsupervised arena; their accuracy in detecting criminal activity is impressive, at 79.56%. Strong assessment metrics, such as False Positive (FP), True Negative (TN), False Negative (FN), False Positive (TP), and False Alarm Rate (FAR), Detection Rate (DR), Accuracy (ACC), Recall, Precision, Specificity, Sensitivity, and Fowlkes–Mallow's scores, provide a comprehensive assessment.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"140 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139453265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revolutionizing Retail: A Hybrid Machine Learning Approach for Precision Demand Forecasting and Strategic Decision-Making in Global Commerce","authors":"MD Tanvir Islam, Eftekhar Hossain Ayon, Bishnu Padh Ghosh, MD, Salim Chowdhury, Rumana Shahid, Aisharyja Roy puja, Sanjida Rahman, Aslima Akter, Mamunur Rahman, Mohammad Shafiquzzaman Bhuiyan","doi":"10.32996/jcsts.2024.6.1.4","DOIUrl":"https://doi.org/10.32996/jcsts.2024.6.1.4","url":null,"abstract":"A thorough comparison of several machine learning methods is provided in this paper, including gradient boosting, AdaBoost, Random Forest (RF), XGBoost, Artificial Neural Network (ANN), and a unique hybrid framework (RF-XGBoost-LR). The assessment investigates their efficacy in real-time sales data analysis using key performance metrics like Mean Absolute Error (MAE), Mean Squared Error (MSE), and R2 score. The study introduces the hybrid model RF-XGBoost-LR, leveraging both bagging and boosting methodologies to address the limitations of individual models. Notably, Random Forest and XGBoost are scrutinized for their strengths and weaknesses, with the hybrid model strategically combining their merits. Results demonstrate the superior performance of the proposed hybrid model in terms of accuracy and robustness, showcasing potential applications in supply chain studies and demand forecasting. The findings highlight the significance of industry-specific customization and emphasize the potential for improved decision-making, marketing strategies, inventory management, and customer satisfaction through precise demand forecasting.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"4 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139536820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Analysis of Machine Learning Models for Data Classification: An In-Depth Exploration","authors":"Abdul Wajid Fazil, Musawer Hakimi, Rohullah Akbari, Mohammad Mustafa Quchi, Khudai Qul Khaliqyar","doi":"10.32996/jcsts.2023.5.4.16","DOIUrl":"https://doi.org/10.32996/jcsts.2023.5.4.16","url":null,"abstract":"This research delves into the realm of data classification using machine learning models, namely 'Random Forest', 'Support Vector Machine (SVM) ' and ‘Logistic Regression'. The dataset, derived from the Australian Government's Bureau of Meteorology, encompasses weather observations from 2008 to 2017, with additional columns like 'RainToday' and the target variable 'RainTomorrow.' The study employs various metrics, including Accuracy Score, 'Jaccard Index', F1-Score, Log Loss, Recall Score and Precision Score, for model evaluation. Utilizing libraries such as 'NumPy', Pandas, matplotlib and ‘sci-kit-learn', the data pre-processing involves one-hot encoding, balancing for class imbalance and creating training and test datasets. The research implements three models, Logistic Regression, SVM and Random Forest, for data classification. Results showcase the models' performance through metrics like ROC-AUC, log loss and Jaccard Score, revealing Random Forest's superior performance in terms of ROC-AUC (0.98), compared to SVM (0.89) and Logistic Regression (0.88). The analysis also includes a detailed examination of confusion matrices for each model, providing insights into their predictive accuracy. The study contributes valuable insights into the effectiveness of these models for weather prediction, with Random Forest emerging as a robust choice. The methodologies employed can be extended to other classification tasks, providing a foundation for leveraging machine learning in diverse domains.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"28 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138601742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of Nonalcoholic Fatty Liver Disease Using Deep Learning Algorithms","authors":"Sakib Rokoni, Sihab Sarar Chistee, Protik Kanu, Urmi Ghosh, Ashik Ahamed Raian, Labib Rokoni","doi":"10.32996/jcsts.2023.5.4.15","DOIUrl":"https://doi.org/10.32996/jcsts.2023.5.4.15","url":null,"abstract":"Some occasional drinkers develop Nonalcoholic Fatty Liver Disease (NAFLD). Hepatocytes are the key indication of NAFLD. Western nations are seeing rising non-alcoholic fatty liver disease (NAFLD). About 25% of Americans have this chronic liver condition. Recent research estimates that 33.66 percent of Bangladeshi adults have fatty liver disease, affecting over 45 million people. This illness is a major cause of liver-related deaths. Thus, minimizing fatty liver disease risk is crucial. Failure to diagnose fatty liver early may cause serious medical consequences. This study examines fatty liver signs and disorders to help diagnose diabetes early. This study shows the association between fatty liver symptoms and illness to help diagnose early. Deep learning categorization methods are widely utilized to build patient risk prediction models. In this study, “used” was utilized. This article uses numerous deep learning approaches to predict fatty liver disease. Convolutional, Long Short-Team Memory, Recurrent, and Multilayer perception neural network designs were mentioned. This study calculates AUC, shows correlation matrices, and visualizes features, and the optimum method. Deep learning achieved 71% accuracy in a highly categorized environment.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"37 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138605335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of Bangladeshi-Produced Plant Disease Using a Transfer Learning Based on Deep Neural Model","authors":"Tareq Hasan, Marjuk Ahmed Siddiki, Md. Naimul Hossain","doi":"10.32996/jcsts.2023.5.3.6","DOIUrl":"https://doi.org/10.32996/jcsts.2023.5.3.6","url":null,"abstract":"Plant diseases pose a significant threat to agricultural productivity and food security in Bangladesh. In this research, we address the challenge of timely and accurate plant disease detection through the application of transfer learning with deep neural models. We curated a diverse dataset comprising 18 categories of plant leaf images, including Bell pepper Bacterial spot, Bell pepper Healthy, Peach Healthy, Potato Early Blight, Rice Leaf Blast, Rice Healthy, Rice Brown Spot, Potato Healthy, Peach Bacterial spot, Corn Blight, Potato Late blight, Corn Healthy, Tomato Bacterial spot, Strawberry Leaf Scorch, Tomato Early blight, Tomato Early blight, Strawberry Healthy, and Tomato Healthy. The dataset represents the most prevalent plant diseases observed in the Bangladeshi context. We employed three state-of-the-art deep learning algorithms, EfficientNetV2M, VGG-19, and NASNetLarge, to develop robust plant disease detection models. Through transfer learning, these pre-trained models were fine-tuned on our specialized dataset to adapt them for the task at hand. The performance evaluation revealed impressive results, with EfficientNetV2M achieving an accuracy rate of 99%, VGG-19 achieving 93%, and NASNetLarge attaining 83% accuracy. The high accuracy of EfficientNetV2M showcases its exceptional capability in accurately classifying plant diseases prevalent in Bangladesh. The success of these deep neural models in detecting various plant diseases signifies their potential in revolutionizing plant disease management and enhancing agricultural practices. Our research contributes valuable insights into the effective use of transfer learning for plant disease detection and emphasizes the significance of dataset curation for improved model performance. The developed models hold promise in providing timely and precise disease diagnosis to farmers and agricultural professionals, thereby facilitating prompt interventions and minimizing crop losses. Future research can explore the integration of these deep neural models into practical agricultural tools, enabling real-time disease detection and offering substantial benefits to the agricultural industry in Bangladesh.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129889050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design of Error Code Guide System on Wincor Nixdorf ATM Machine for CMD Controller Part Based on Mobile Application","authors":"Usanto S","doi":"10.32996/jcsts.2023.5.3.5","DOIUrl":"https://doi.org/10.32996/jcsts.2023.5.3.5","url":null,"abstract":"The machines must have an identity to categorize these machines that are starting to circulate in the Indonesian market. The identity of these machines is determined by the Serial Number (SN) on the machine. For machines manufactured in 2015, the machine has the identity of \"Mesin dengan SN 56DW5.\" Moving on to 2016, the machine's identity changed to \"SN 56HG6,\" while the machine type remained the same, which is Procash 280. Given the various types of Procash 280 machines, engineers sometimes struggle to decipher the codes on Wincor Nixdorf ATM machines. The method employed by the author in analyzing the SSI Net system involves data collection through literature review and field studies, alongside Software System Development using the Waterfall Method. The author conducted a feasibility test, which included a Technology Feasibility Test for the error code application. The necessary facilities for creating the Error Code Application were available, such as a Toshiba Satellite C-40 Laptop with Windows 10 Pro, Intel Core ™) i3-3110 M CPU @ 2.40 GHz Processor, 4.00 GB RAM, and a 64-bit Operating System. The Operational Feasibility is evident in engineers being able to install the application whenever and wherever using the provided APK. Additionally, the application's instructions are in Indonesian to accommodate new engineers joining the company. The designed system consists of two components: the Master Data Error Code and the output produced. The Master Data Error Code employs a two-digit number to provide results within this application, both for CMD Error Codes and Screen Error Codes. The application's output features two displays: one in English and the other in Indonesian. The author suggests adding additional menu options to the application to further assist users in finding solutions.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122048168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Reading among Children in Saudi Arabia","authors":"Reima Al-Jarf","doi":"10.32996/jcsts.2023.5.3.4","DOIUrl":"https://doi.org/10.32996/jcsts.2023.5.3.4","url":null,"abstract":"A sample of parents in Saudi Arabia was surveyed to find out the reading technologies that children under the age of 12 use, children’s digital reading habits and interests, parents’ roles in encouraging the children to read digitally, the effects of digital reading on children’s reading ability, and to compare digital reading before, during and after the Pandemic. Survey results showed that all the children in the sample use a smart phone to access apps, games, cartoons, and YouTube videos. About 41% use an iPad or tablet and few use their parents or older siblings’ laptops. None of the children in the sample uses an e-reader such as Kindle. 5% do not like to use an iPad/tablet and prefer to use their parents’ smart phones. Children below the age of 6 use touch screen devices in reading the English and Arabic letters, numeracy and words. They  enjoy reading on touch screens. 36% of the children in grades 1-3 use touch screen devices in learning to read and 64% use them for games and entertainment. Children in grades 4-6 mainly use touch screen devices to play games, soccer, car races and watch movies mostly in English and do not use those devices for reading purposes. Older children feel that educational and language learning and reading apps are boring. During the pandemic, children used technology intensively due to remote teaching and learning, i.e., more than before and after the Pandemic. About half of the parents do not share, nor supervise reading from touch screen devices with their children whether during, before or after the pandemic. Despite the advancements in digital reading, most parents and children in Saudi Arabia still prefer print books and stories. Mobile audiobooks, electronic reading games, storybooks, picture books and glossy magazines, reading lessons with a digital, human-like character, WhatsApp remote reading, online book clubs, and children's digital libraries are not used. Therefore, this study recommends the integration of digital reading in the school curriculum, raising parents and teachers’ awareness of digital reading devices, reading apps and websites and designing mobile reading apps with interactive features to motivate older children to read Arabic fiction and short stories.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121572089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Epilepsy Seizures Classification with EEG Signals: A Machine Learning Approach","authors":"Sajad Ulhaq, Gul Zaman Khan, Imran Ulhaq, Inam Ullah, Fazal Rabbi, Gul Zaman, Khan","doi":"10.32996/jcsts.2023.5.3.3","DOIUrl":"https://doi.org/10.32996/jcsts.2023.5.3.3","url":null,"abstract":"Epilepsy is a neurological disorder characterized by recurrent seizures, which can significantly impact a person's life. Early and accurate diagnosis of epilepsy is crucial for effective management and treatment. The traditional methods for diagnosing epilepsy are deemed ineffective and costly. Epilepsy disease detection at an early stage is crucial. Machine learning techniques have shown promise in automating the classification of epilepsy based on various data sources, such as electroencephalogram (EEG) signals, clinical features, and imaging data. This paper presents a machine learning approach to epilepsy disease classification using EEG signal data. We have applied various machine learning models, including Random Forest, XGBoost, GradientBoost, Naive Bayes, Decision Tree, and Extra Tree, with some pre-processing and feature selection techniques. XGBoost achieved 98.93% training accuracy and 98.23% testing accuracy; Gradient Boost achieved 98.40% training and 98.20% testing accuracy; Extra Tree achieved 98.65% training and 97.85% testing accuracy; Random Forest achieved 97.42% training and 96.52% testing accuracy; Decision Tree achieved 92.6% training and 92.4% testing accuracy; Navies Bayes achieved 93.52% training and 92% testing accuracy. The XGBoost classifier achieved the highest accuracy among all other classifiers applied in the proposed research experiment.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114391426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Approach for Detection of Entities in Dynamic Media Contents","authors":"Mbongo Nzakiese, Ngombo Armando","doi":"10.32996/jcsts.2023.5.3.2","DOIUrl":"https://doi.org/10.32996/jcsts.2023.5.3.2","url":null,"abstract":"The notion of learning underlies almost every evolution of Intelligent Agents. In this paper, we present an approach for searching and detecting a given entity in a video sequence. Specifically, we study how the deep learning technique by artificial neural networks allows us to detect a character in a video sequence. The technique of detecting a character in a video is a complex field of study, considering the multitude of objects present in the data under analysis. From the results obtained, we highlight the following, compared to state of the art: In our approach, within the field of Computer Vision, the structuring of supervised learning algorithms allowed us to achieve several successes from simple characteristics of the target character. Our results demonstrate that is new approach allows us to locate, in an efficient way, wanted individuals from a private or public image base. For the case of Angola, the classifier we propose opens the possibility of reinforcing the national security system based on the database of target individuals (disappeared, criminals, etc.) and the video sequences of the Integrated Public Security Centre (CISP).","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128327504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Reading Among Educated Arabs: A Twitter-base Study","authors":"Reima Al-Jarf","doi":"10.32996/jcsts.2023.5.3.1","DOIUrl":"https://doi.org/10.32996/jcsts.2023.5.3.1","url":null,"abstract":"This study aimed to explore whether educated Arabs prefer to read paper or digital materials and which reading technologies and applications they use. The sample consisted of 272 educated Arabs (81% males and 19% females) who are Twitter users, who gave 437 responses to questions, hashtags and threads asking, “which digital media and digital devices do you use for reading, why, the advantages and disadvantages of digital reading vs reading from paper material”. Data analysis showed that 71.5% of educated Arabs in the sample read traditional printed books and 28.5% read digitally and use digital reading technologies as follows: 15% listen to audiobooks, 6.5% use Kindle, and 7% use e-Ink, Audible, Storytel, Feedly, text-to-speech software (Read Aloud, Natural Reader Pro and Kurzweil 1000), Instapaper, Evernote, Raindrop, Pocket, Siri, eBooks, Artificial Intelligence (AI), Tarteel, Wajeez, Sibawayh Reader, and Screen Readers  such as JAWS, Window Eyes, VoiceOver, Thunder,  and HAL by blind students. Digital readers in this study use smart phones, iPads, tablets, and computer screens and are familiar with digital document formats such as Pdf, Epub, Mobi, IPA and AZW. The percentage of educated Arabs who use digital reading and reading technologies and apps is small, taking into consideration that many Arab people have access to the Internet and have a smart phone, a desktop or laptop computer and should be able to access a plethora of reading apps, digital resources, and reading technologies. It seems that many educated Arabs are not familiar with digital reading, eBooks, e-libraries, online reading resources, reading technologies and applications. Digital readers gave some explanations for their preferences and how they use digital media reading, when and where. Some recommendations for familiarizing children, students and the public with digital reading and reading technologies are given.","PeriodicalId":417206,"journal":{"name":"Journal of Computer Science and Technology Studies","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127954484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}