Journal of Computing and Social Informatics最新文献

{"title":"A Comparative Study of YOLOv5 and YOLOv7 Object Detection Algorithms","authors":"Oluwaseyi Olorunshola, Martins E. Irhebhude, A. Evwiekpaefe","doi":"10.33736/jcsi.5070.2023","DOIUrl":"https://doi.org/10.33736/jcsi.5070.2023","url":null,"abstract":"This paper presents a comparative analysis of the widely accepted YOLOv5 and the latest version of YOLO which is YOLOv7. Experiments were carried out by training a custom model with both YOLOv5 and YOLOv7 independently in order to consider which one of the two performs better in terms of precision, recall, mAP@0.5 and mAP@0.5:0.95. The dataset used in the experiment is a custom dataset for Remote Weapon Station which consists of 9,779 images containing 21,561 annotations of four classes gotten from Google Open Images Dataset, Roboflow Public Dataset and locally sourced dataset. The four classes are Persons, Handguns, Rifles and Knives. The experimental results of YOLOv7 were precision score of 52.8%, recall value of 56.4%, mAP@0.5 of 51.5% and mAP@0.5:0.95 of 31.5% while that of YOLOv5 were precision score of 62.6%, recall value of 53.4%, mAP@0.5 of 55.3% and mAP@0.5:0.95 of 34.2%. It was observed from the experiment conducted that YOLOv5 gave a better result than YOLOv7 in terms of precision, mAP@0.5 and mAP@0.5:0.95 overall while YOLOv7 has a higher recall value during testing than YOLOv5. YOLOv5 records 4.0% increase in accuracy compared to YOLOv7.","PeriodicalId":177345,"journal":{"name":"Journal of Computing and Social Informatics","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129167082","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":"EEMDS: Efficient and Effective Malware Detection System with Hybrid Model based on XceptionCNN and LightGBM Algorithm","authors":"M. Onoja, Abayomi Jegede, N. Blamah, Abinbola Victor Olawale, T. O. Omotehinwa","doi":"10.33736/jcsi.4739.2022","DOIUrl":"https://doi.org/10.33736/jcsi.4739.2022","url":null,"abstract":"The security threats posed by malware make it imperative to build a model for efficient and effective classification of malware based on its family, irrespective of the variant. Preliminary experiments carried out demonstrate the suitability of the generic LightGBM algorithm for Windows malware as well as its effectiveness and efficiency in terms of detection accuracy, training accuracy, prediction time and training time. The prediction time of the generic LightGBM is 0.08s for binary class and 0.40s for multi-class on the Malimg dataset. The classification accuracy of the generic LightGBM is 99% True Positive Rate (TPR). Its training accuracy is 99.80% for binary class and 96.87% for multi-class, while the training time is 179.51s and 2224.77s for binary and multi classification respectively. The performance of the generic LightGBM leaves room for improvement, hence, the need to improve the classification accuracy and training accuracy of the model for effective decision making and to reduce the prediction time and training time for efficiency. It is also imperative to improve the performance and accuracy for effectiveness on larger samples. The goal is to enhance the detection accuracy and reduce the prediction time. The reduction in prediction time provides early detection of malware before it damages files stored in computer systems. Performance evaluation based on Malimg dataset demonstrates the effectiveness and efficiency of the hybrid model. The proposed model is a hybrid model which integrates XceptionCNN with LightGBM algorithm for Windows Malware classification on google colab environment. It uses the Malimg malware dataset which is a benchmark dataset for Windows malware image classification. It contains 9,339 Malware samples, structured as grayscale images, consisting of 25 families and 1,042 Windows benign executable files extracted from Windows environments. The proposed XceptionCNN-LightGBM technique provides improved classification accuracy of 100% TPR, with an overall reduction in the prediction time of 0.08s and 0.37s for binary and multi-class respectively. These are lower than the prediction time for the generic LightGBM which is 0.08s for binary class and 0.40s for multi-class, with an improved 100% classification accuracy. The training accuracy increased to 99.85% for binary classification and 97.40% for multi classification, with reduction in the training time of 29.97s for binary classification and 447.75s for multi classification. These are also lower than the training times for the generic LightGBM model, which are 179.51s and 2224.77s for the binary and multi classification respectively. This significant reduction in the training time makes it possible for the model to converge quickly and train a large sum of data within a relatively short period of time. Overall, the reduction in detection time and improvement in detection accuracy will minimize damages to files stored in computer systems in the event of malware atta","PeriodicalId":177345,"journal":{"name":"Journal of Computing and Social Informatics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114171499","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":"Trends and Future Directions in Automated Ransomware Detection","authors":"Abayomi Jegede, Ayotinde Fadele, M. Onoja, G. Aimufua, Ismaila Jesse Mazadu","doi":"10.33736/jcsi.4932.2022","DOIUrl":"https://doi.org/10.33736/jcsi.4932.2022","url":null,"abstract":"Ransomware attacks constitute major security threats to personal and corporate data and information. A successful ransomware attack results in significant security and privacy violations with attendant financial losses and reputational damages to owners of computer-based resources. This makes it imperative for accurate, timely and reliable detection of ransomware. Several techniques have been proposed for ransomware detection and each technique has its strengths and limitations. The aim of this paper is to discuss the current trends and future directions in automated ransomware detection. The paper provides a background discussion on ransomware as well as historical background and chronology of ransomware attacks. It also provides a detailed and critical review of recent approaches to ransomware detection, prevention, mitigation and recovery. A major strength of the paper is the presentation of the chronology of ransomware attacks from its inception in 1989 to the latest attacks occurring in 2021. Another strength of the study is that a large proportion of the studies reviewed were published between 2015 and 2022. This provides readers with an up-to-date knowledge of the state-of-the-art in ransomware detection. It also provides insights into advances in strategies for preventing, mitigating and recovering from ransomware attacks. Overall, this paper presents researchers with open issues and possible research problems in ransomware detection, prevention, mitigation and recovery.","PeriodicalId":177345,"journal":{"name":"Journal of Computing and Social Informatics","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133759285","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":"Credit Risk Prediction for Peer-To-Peer Lending Platforms: An Explainable Machine Learning Approach","authors":"Pei Swee Chong, J. Labadin, F. Meziane","doi":"10.33736/jcsi.4761.2022","DOIUrl":"https://doi.org/10.33736/jcsi.4761.2022","url":null,"abstract":"Small and medium enterprises face the challenge of obtaining start-up fund due to the strict rules and conditions set by banks and financial institutions. The plight yields to the growth in popularity of online peer-to-peer lending platforms which are an easier way to obtain loan as they have fewer rigid rules. However, high flexibility of loan funding in peer-to-peer lending comes with high default probability of loan funded to high-risk start-ups. An efficient model for evaluating credit risk of borrowers in peer-to-peer lending platforms is important to encourage investors to fund loans and justify the rejection of unsuccessful applications to satisfy financial regulators and increase transparency. This paper presents a supervised machine learning model with logistic regression to address this issue and predicts the probability of default of a loan funded to borrowers through peer-to-peer lending platforms. In addition, factors that affect the credit levels of borrowers are identified and discussed. The research shows that the most important features that affect probability of default are debt-to-income ratio, number of mortgage account, and Fair, Isaac and Company Score.","PeriodicalId":177345,"journal":{"name":"Journal of Computing and Social Informatics","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126590316","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":"Modified PRDG Model for Caregiver Segmentation Using Zarit Burden Interview Instrument","authors":"N. Rahmayanti, Retno Aulia Vinarti, A. Djunaidy, Anna Tjin, Jeng Liu","doi":"10.33736/jcsi.4317.2022","DOIUrl":"https://doi.org/10.33736/jcsi.4317.2022","url":null,"abstract":"The increasing demand for Indonesian workers in Taiwan has an impact on caregiver problems which can be triggered by the burden of caring for the elderly. Therefore, the aim of this study is to identify the characteristics of caregivers who are resilient to burdens based on Indonesian female caregivers who work in Taiwan data to be a guide for selecting prospective caregivers. The process includes analyzing the personal characteristics that have the most influence on the burden using multiple regression and then clustering caregiver data using K-Means with the Elbow Method and Silhouette Index. Then, segmentation in each cluster based on a comparison of the average values. The results of clustering accuracy on dimensions (PRDG) and modified dimensions (S+PRDG) were compared and the smallest error cluster was in case 4 in the S+PRDG dimension with the Elbow Method of 3.6%. Based on segmentation on that dimension, cluster 2 is a resilient caregiver cluster. Then the results of the multiple regression analysis (Number of Children, Education and Work Location) were studied further for each caregiver in cluster 2 and the conclusions are, their average number of children is 1, final education is in junior high school and their work location is in the capital of Taiwan.","PeriodicalId":177345,"journal":{"name":"Journal of Computing and Social Informatics","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114096210","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":"Open Government Data from the Perspective of SMEs: A Case Study in Indonesia","authors":"Amir Syarif, Mohamad Aizi Salamat, A. Mustapha, Supli Effendy Rahim","doi":"10.33736/jcsi.4070.2022","DOIUrl":"https://doi.org/10.33736/jcsi.4070.2022","url":null,"abstract":"The government of Indonesia carries out OGD by developing a data portal (data.go.id) under the name Satu Data Indonesia (SDI) as part of an open government initiative. Several studies on OGD and its effect on SME business in various countries have shown that it has a positive influence on SME business progress, so it can be said that OGD is very important and can bring goodness to implementing countries like Indonesia. One of the concerns that the government must address is the use and benefits of data made available to stakeholders. Micro Small and Medium Enterprises (MSMEs) employ approximately 97 percent of the total workforce, and 99.9 percent of all businesses in Indonesia are MSMEs. MSMEs account for approximately 60 percent of Indonesia's total GDP. As one of the pillars of the Indonesian economy, SMEs must be considered in terms of data availability that suits their needs. That is why this research is important in gaining their perspective. This paper investigates the perspectives of Indonesian SMEs on the open data provided by the Indonesian government. Based on the findings of the data analysis, it is possible to conclude that there is a demand for open data from the SMEs society in terms of the existence of agency mechanisms in place to receive and respond to data requests. And the Open Data Ecosystem, in terms of government promotion of data reuse, is critical for SMEs.","PeriodicalId":177345,"journal":{"name":"Journal of Computing and Social Informatics","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117236906","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}