Online pharmacies are a promising business model for promoting online sales of medicines. The purpose of this study is to investigate how technology acceptance model (TAM) variables (perceived ease of use and perceived usefulness), perceived trust, perceived performance risk, and perceived physical risk influence customers' intention to use online pharmacy. A questionnaire survey was used to collect data for the planned study. The results showed that perception of trust is a critical factor influencing costomers intention to use an online pharmacy. The reluctance of customers to buy medicines, categorized as risk, through online pharmacies which was originally thought to be a determining factor, has no impact if customer trust in online pharmacy has been formed. This study has several relevances for advancing online pharmacy promotion including the importances of user-friendly and benefits provided by online pharmacies provider. It is very important how online pharmacies providers can increase customers trust in terms of legality, quality and security of personal data.
{"title":"Factors affecting customers intention towards online pharmacies in Indonesian market","authors":"Ferawaty Ferawaty, Wakky Antonio, Adilla Anggraeni","doi":"10.11591/ijict.v13i1.pp91-100","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp91-100","url":null,"abstract":"Online pharmacies are a promising business model for promoting online sales of medicines. The purpose of this study is to investigate how technology acceptance model (TAM) variables (perceived ease of use and perceived usefulness), perceived trust, perceived performance risk, and perceived physical risk influence customers' intention to use online pharmacy. A questionnaire survey was used to collect data for the planned study. The results showed that perception of trust is a critical factor influencing costomers intention to use an online pharmacy. The reluctance of customers to buy medicines, categorized as risk, through online pharmacies which was originally thought to be a determining factor, has no impact if customer trust in online pharmacy has been formed. This study has several relevances for advancing online pharmacy promotion including the importances of user-friendly and benefits provided by online pharmacies provider. It is very important how online pharmacies providers can increase customers trust in terms of legality, quality and security of personal data.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140745098","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp9-26
Shehram Sikander Khan, A. Mailewa
Recent improvements in the internet of things (IoT), cloud services, and network data variety have increased the demand for complex anomaly detection algorithms in network intrusion detection systems (IDSs) capable of dealing with sophisticated network threats. Academics are interested in deep and machine learning (ML) breakthroughs because they have the potential to address complex challenges such as zero-day attacks. In comparison to firewalls, IDS are the initial line of network security. This study suggests merging supervised and unsupervised learning in identification systems IDS. Support vector machine (SVM) is an anomaly-based classification classifier. Deep autoencoder (DAE) lowers dimensionality. DAE are compared to principal component analysis (PCA) in this study, and hyper-parameters for F-1 micro score and balanced accuracy are specified. We have an uneven set of data classes. precision-recall curves, average precision (AP) score, train-test times, t-SNE, grid search, and L1/L2 regularization methods are used. KDDTrain+ and KDDTest+ datasets will be used in our model. For classification and performance, the DAE+SVM neural network technique is successful. Autoencoders outperformed linear PCA in terms of capturing valuable input attributes using t-SNE to embed high dimensional inputs on a two-dimensional plane. Our neural system outperforms solo SVM and PCA encoded SVM in multi-class scenarios.
{"title":"Predicting anomalies in computer networks using autoencoder-based representation learning","authors":"Shehram Sikander Khan, A. Mailewa","doi":"10.11591/ijict.v13i1.pp9-26","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp9-26","url":null,"abstract":"Recent improvements in the internet of things (IoT), cloud services, and network data variety have increased the demand for complex anomaly detection algorithms in network intrusion detection systems (IDSs) capable of dealing with sophisticated network threats. Academics are interested in deep and machine learning (ML) breakthroughs because they have the potential to address complex challenges such as zero-day attacks. In comparison to firewalls, IDS are the initial line of network security. This study suggests merging supervised and unsupervised learning in identification systems IDS. Support vector machine (SVM) is an anomaly-based classification classifier. Deep autoencoder (DAE) lowers dimensionality. DAE are compared to principal component analysis (PCA) in this study, and hyper-parameters for F-1 micro score and balanced accuracy are specified. We have an uneven set of data classes. precision-recall curves, average precision (AP) score, train-test times, t-SNE, grid search, and L1/L2 regularization methods are used. KDDTrain+ and KDDTest+ datasets will be used in our model. For classification and performance, the DAE+SVM neural network technique is successful. Autoencoders outperformed linear PCA in terms of capturing valuable input attributes using t-SNE to embed high dimensional inputs on a two-dimensional plane. Our neural system outperforms solo SVM and PCA encoded SVM in multi-class scenarios.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"21 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140742004","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp42-49
Muhammad Alwan Naufal, A. S. Girsang
Traffic accidents are a widespread concern globally, causing loss of life, injuries, and economic burdens. Efficiently classifying accident types is crucial for effective accident management and prevention. This study proposes a practical approach for traffic accident classification using IndoBERT, a language model specifically trained for Indonesian. The classification task involves sorting accidents into four classes: car accidents, motorcycle accidents, bus accidents, and others. The proposed model achieves a 94% accuracy in categorizing these accidents. To assess its performance, we compared IndoBERT with traditional methods, random forest (RF) and support vector machine (SVM), which achieved accuracy scores of 85% and 87%, respectively. The IndoBERT-based model demonstrates its effectiveness in handling the complexities of the Indonesian language, providing a useful tool for traffic accident classification and contributing to improved accident management and prevention strategies.
{"title":"Traffic accident classification using IndoBERT","authors":"Muhammad Alwan Naufal, A. S. Girsang","doi":"10.11591/ijict.v13i1.pp42-49","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp42-49","url":null,"abstract":"Traffic accidents are a widespread concern globally, causing loss of life, injuries, and economic burdens. Efficiently classifying accident types is crucial for effective accident management and prevention. This study proposes a practical approach for traffic accident classification using IndoBERT, a language model specifically trained for Indonesian. The classification task involves sorting accidents into four classes: car accidents, motorcycle accidents, bus accidents, and others. The proposed model achieves a 94% accuracy in categorizing these accidents. To assess its performance, we compared IndoBERT with traditional methods, random forest (RF) and support vector machine (SVM), which achieved accuracy scores of 85% and 87%, respectively. The IndoBERT-based model demonstrates its effectiveness in handling the complexities of the Indonesian language, providing a useful tool for traffic accident classification and contributing to improved accident management and prevention strategies.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"30 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140744987","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp1-8
Sabeena Yasmin Hera, Mohammad Amjad
Because of the explosion in data, it is now incredibly difficult for a single person to filter through all of the information and extract what they need. As a result, information filtering algorithms are necessary to uncover meaningful information from the massive amount of data already available online. Users can benefit from recommendation systems (RSs) since they simplify the process of identifying relevant information. User ratings are incredibly significant for creating recommendations. Previously, academics relied on historical user ratings to predict future ratings, but today, consumers are paying more attention to user reviews because they contain so much relevant information about the user's decision. The proposed approach uses written testimonials to overcome the issue of doubt in the ratings' pasts. Using two data sets, we performed experimental evaluations of the proposed framework. For prediction, clustering algorithms are used with natural language processing in this strategy. It also evaluates the findings of various methods, such as the K-mean, spectral, and hierarchical clustering algorithms, and offers conclusions on which strategy is optimal for the supplied use cases. In addition, we demonstrate that the proposed technique outperforms alternatives that do not involve clustering.
由于数据的爆炸式增长，现在一个人很难从所有信息中筛选出自己需要的信息。因此，有必要使用信息过滤算法，从网上已有的海量数据中挖掘出有意义的信息。用户可以从推荐系统（RS）中获益，因为它们简化了识别相关信息的过程。用户评级对于创建推荐具有难以置信的重要意义。以前，学术界依靠历史用户评分来预测未来评分，但如今，消费者更加关注用户评论，因为它们包含了大量与用户决策相关的信息。所提出的方法利用书面推荐来克服对过去评分的怀疑问题。我们使用两个数据集对所提出的框架进行了实验评估。在预测方面，该策略使用了聚类算法和自然语言处理技术。它还评估了各种方法（如 K 均值、光谱和分层聚类算法）的结果，并就哪种策略最适合所提供的使用案例给出了结论。此外，我们还证明了所提出的技术优于不涉及聚类的其他方法。
{"title":"Review-based analysis of clustering approaches in a recommendation system","authors":"Sabeena Yasmin Hera, Mohammad Amjad","doi":"10.11591/ijict.v13i1.pp1-8","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp1-8","url":null,"abstract":"Because of the explosion in data, it is now incredibly difficult for a single person to filter through all of the information and extract what they need. As a result, information filtering algorithms are necessary to uncover meaningful information from the massive amount of data already available online. Users can benefit from recommendation systems (RSs) since they simplify the process of identifying relevant information. User ratings are incredibly significant for creating recommendations. Previously, academics relied on historical user ratings to predict future ratings, but today, consumers are paying more attention to user reviews because they contain so much relevant information about the user's decision. The proposed approach uses written testimonials to overcome the issue of doubt in the ratings' pasts. Using two data sets, we performed experimental evaluations of the proposed framework. For prediction, clustering algorithms are used with natural language processing in this strategy. It also evaluates the findings of various methods, such as the K-mean, spectral, and hierarchical clustering algorithms, and offers conclusions on which strategy is optimal for the supplied use cases. In addition, we demonstrate that the proposed technique outperforms alternatives that do not involve clustering.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"26 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140741051","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp123-130
Narmadha Ganesamoorthy, B. Sakthivel, Deivasigamani Subbramania, K. Balasubadra
In the power grid, communication networks play an important role in exchanging smart grid-based information. In contrast to wired communication, wireless communication offers many benefits in terms of easy setup connections and low-cost high-speed links. Conversely, wireless communications are commonly more vulnerable to security threats than wired ones. All power equipment devices and appliances in the smart distribution grid (SDG) are communicated through wireless networks only. Most security research focuses on keeping the SDG network from different types of attacks. The denial-of-service (DoS) attack is consuming more energy in the network leads to a permanent breakdown of memory. This work proposes a new metaheuristic optimization inspired by maternal care of hen to their children called hen maternal care (HMCO) inspired optimization. The HMCO algorithm mimics the care shown by hen for their children in nature. The mother hen is always watchful and protects its chicks against predators. All chickens utilize different calls to designate flying predators like falcons and owls from ground seekers like foxes and coyotes, showing that they can both survey a danger and advise different chickens how to set themselves up. Our method shows greater performance among other standard algorithms.
{"title":"Hen maternal care inspired optimization framework for attack detection in wireless smart grid network","authors":"Narmadha Ganesamoorthy, B. Sakthivel, Deivasigamani Subbramania, K. Balasubadra","doi":"10.11591/ijict.v13i1.pp123-130","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp123-130","url":null,"abstract":"In the power grid, communication networks play an important role in exchanging smart grid-based information. In contrast to wired communication, wireless communication offers many benefits in terms of easy setup connections and low-cost high-speed links. Conversely, wireless communications are commonly more vulnerable to security threats than wired ones. All power equipment devices and appliances in the smart distribution grid (SDG) are communicated through wireless networks only. Most security research focuses on keeping the SDG network from different types of attacks. The denial-of-service (DoS) attack is consuming more energy in the network leads to a permanent breakdown of memory. This work proposes a new metaheuristic optimization inspired by maternal care of hen to their children called hen maternal care (HMCO) inspired optimization. The HMCO algorithm mimics the care shown by hen for their children in nature. The mother hen is always watchful and protects its chicks against predators. All chickens utilize different calls to designate flying predators like falcons and owls from ground seekers like foxes and coyotes, showing that they can both survey a danger and advise different chickens how to set themselves up. Our method shows greater performance among other standard algorithms.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"13 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140744552","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp34-41
Geerish Suddul, Jean Fabrice Laurent Seguin
Information found on an identity card is needed for different essential tasks and manually extracting this information is time consuming, resource exhaustive and may be prone to human error. In this study, an optical character recognition (OCR) approach using deep learning techniques is proposed to automatically extract text related information from the image of an identity card in view of developing an automated client onboarding system. The OCR problem is divided into two main parts. Firstly, a custom-built image segmentation model, based on the U-net architecture, is used to detect the location of the text to be extracted. Secondly, using the location of the identified text fields, a (CRNN) based on long short-term memory (LSTM) cells is trained to recognise the characters and build words. Experimental results, based on the national identity card of the Republic of Mauritius, demonstrate that our approach achieves higher accuracy compared to other studies. Our text detection module has an intersection over union (IOU) measure of 0.70 with a pixel accuracy of 98% for text detection and the text recognition module achieved a mean word recognition accuracy of around 97% on main fields of the identity card.
{"title":"A custom-built deep learning approach for text extraction from identity card images","authors":"Geerish Suddul, Jean Fabrice Laurent Seguin","doi":"10.11591/ijict.v13i1.pp34-41","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp34-41","url":null,"abstract":"Information found on an identity card is needed for different essential tasks and manually extracting this information is time consuming, resource exhaustive and may be prone to human error. In this study, an optical character recognition (OCR) approach using deep learning techniques is proposed to automatically extract text related information from the image of an identity card in view of developing an automated client onboarding system. The OCR problem is divided into two main parts. Firstly, a custom-built image segmentation model, based on the U-net architecture, is used to detect the location of the text to be extracted. Secondly, using the location of the identified text fields, a (CRNN) based on long short-term memory (LSTM) cells is trained to recognise the characters and build words. Experimental results, based on the national identity card of the Republic of Mauritius, demonstrate that our approach achieves higher accuracy compared to other studies. Our text detection module has an intersection over union (IOU) measure of 0.70 with a pixel accuracy of 98% for text detection and the text recognition module achieved a mean word recognition accuracy of around 97% on main fields of the identity card.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"40 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140743643","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp57-66
Nagaki Kentarou, Fujita Satoshi
This paper introduces a novel approach to remote coaching, specifically targeting the body movements of learners participating remotely. The proposed system employs a smartphone camera to capture the learner’s body and represent it as a 3D avatar. The instructor can then offer guidance and instruction by manipulating the 3D avatar’s shape, which is displayed on a web browser. The main challenge faced by the system is to enable the sharing and editing of 3D objects among users. Since the HTML5 drag-and-drop feature is inadequate for transforming virtual objects consisting of multiple interconnected rigid bodies, the system tracks the pivot point of the manipulated rigid body. It assigns attributes such as pivot points and action points to each object, extending beyond their 2D screen coordinates. To implement the system, an interactive web application framework following the model-view-view-model (MVVM) architecture is utilized, incorporating Vue.js, Three.js, and Google Firebase. The prototype system takes advantage of the data binding capability of the framework and successfully operates within the 3D space of a web browser. Experimental results demonstrate that it can effectively share transformation information with an average delay of 300 ms.
本文介绍了一种新颖的远程辅导方法，特别是针对远程参与学习者的肢体动作。所提议的系统利用智能手机摄像头捕捉学习者的身体，并将其表现为三维头像。然后，指导者可以通过操纵显示在网络浏览器上的三维头像的形状来提供指导和指示。该系统面临的主要挑战是如何在用户之间共享和编辑三维对象。由于 HTML5 的拖放功能不足以转换由多个相互连接的刚体组成的虚拟对象，因此系统会跟踪所操作刚体的支点。它为每个对象分配了支点和动作点等属性，超出了它们的二维屏幕坐标。为了实现该系统，我们使用了一个交互式网络应用框架，该框架采用了模型-视图-视图-模型（MVVM）架构，结合了 Vue.js、Three.js 和 Google Firebase。原型系统利用该框架的数据绑定功能，成功地在网络浏览器的三维空间中运行。实验结果表明，它能有效地共享变换信息，平均延迟为 300 毫秒。
{"title":"Remote practical instruction using web browsers","authors":"Nagaki Kentarou, Fujita Satoshi","doi":"10.11591/ijict.v13i1.pp57-66","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp57-66","url":null,"abstract":"This paper introduces a novel approach to remote coaching, specifically targeting the body movements of learners participating remotely. The proposed system employs a smartphone camera to capture the learner’s body and represent it as a 3D avatar. The instructor can then offer guidance and instruction by manipulating the 3D avatar’s shape, which is displayed on a web browser. The main challenge faced by the system is to enable the sharing and editing of 3D objects among users. Since the HTML5 drag-and-drop feature is inadequate for transforming virtual objects consisting of multiple interconnected rigid bodies, the system tracks the pivot point of the manipulated rigid body. It assigns attributes such as pivot points and action points to each object, extending beyond their 2D screen coordinates. To implement the system, an interactive web application framework following the model-view-view-model (MVVM) architecture is utilized, incorporating Vue.js, Three.js, and Google Firebase. The prototype system takes advantage of the data binding capability of the framework and successfully operates within the 3D space of a web browser. Experimental results demonstrate that it can effectively share transformation information with an average delay of 300 ms.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"6 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140745225","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp108-115
A. Ojugo, P. Ejeh, C. Odiakaose, Andrew Okonji Eboka, F. Emordi
Rainfall as an environmental feat can change fast and yield significant influence in downstream hydrology known as runoff with a variety of implications such as erosion, water quality, and infrastructures. These, in turn impact the quality of life, sewage systems, agriculture, and tourism of a nation to mention a few. It chaotic, complex, and dynamic nature has necessitated studies in the quest for future direction of such runoff via prediction models. With little successes in use of knowledge driven models, many studies have now turned to data-driven models. Dataset is retrieved from Metrological Center in Lagos, Nigeria for the period 1999-2019 for the Benin-Owena River Basin. Data is split: 70% for train and 30% for test. Our study adapts a spatial-temporal profile hidden Markov trained deep neural network. Result yields a sensitivity of 0.9, specificity 0.19, accuracy of 0.74, and improvement rate of classification of 0.12. Other ensembles underperformed when compared to proposed model. The study reveals annual rainfall is an effect of variation cycle. Models will help simulate future floods and provide lead time warnings in flood management.
{"title":"Predicting rainfall runoff in Southern Nigeria using a fused hybrid deep learning ensemble","authors":"A. Ojugo, P. Ejeh, C. Odiakaose, Andrew Okonji Eboka, F. Emordi","doi":"10.11591/ijict.v13i1.pp108-115","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp108-115","url":null,"abstract":"Rainfall as an environmental feat can change fast and yield significant influence in downstream hydrology known as runoff with a variety of implications such as erosion, water quality, and infrastructures. These, in turn impact the quality of life, sewage systems, agriculture, and tourism of a nation to mention a few. It chaotic, complex, and dynamic nature has necessitated studies in the quest for future direction of such runoff via prediction models. With little successes in use of knowledge driven models, many studies have now turned to data-driven models. Dataset is retrieved from Metrological Center in Lagos, Nigeria for the period 1999-2019 for the Benin-Owena River Basin. Data is split: 70% for train and 30% for test. Our study adapts a spatial-temporal profile hidden Markov trained deep neural network. Result yields a sensitivity of 0.9, specificity 0.19, accuracy of 0.74, and improvement rate of classification of 0.12. Other ensembles underperformed when compared to proposed model. The study reveals annual rainfall is an effect of variation cycle. Models will help simulate future floods and provide lead time warnings in flood management.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"12 42","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140745544","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp27-33
Gyana Ranjana Panigrahi, N. Barpanda, Dr. Prabira Kumar Sethy
The extensive relevance of digital forensics in today's data-driven environment has been emphasized in this article. The free software and the commercial software community are debatable, despite users and developers often differing views on important topics like software safety and usability. This article primarily uses pre-defined criteria and a platform-oriented approach to examine promising freeware (Magnet Forensics and Sleuth Kit) vs. profitable (ProDiscover and Oxygen Forensic Suite) mobile forensics tools. Under diverse settings, the tools' capacity to develop and analyze forensically sound digital forensic media sources is validated. After erasing data, each media type was tested again after formatting. The study concludes with a comparison matrix that may aid in determining the best-fit option for the investigation's requirements among the tools. The findings indicate the potential for freeware to supplant numerous proprietary applications, as users can opt for freeware instead of incurring costs associated with proprietary software. Furthermore, this perception can be put into practice.
{"title":"Navigating the cyber forensics landscape a review of recent innovations","authors":"Gyana Ranjana Panigrahi, N. Barpanda, Dr. Prabira Kumar Sethy","doi":"10.11591/ijict.v13i1.pp27-33","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp27-33","url":null,"abstract":"The extensive relevance of digital forensics in today's data-driven environment has been emphasized in this article. The free software and the commercial software community are debatable, despite users and developers often differing views on important topics like software safety and usability. This article primarily uses pre-defined criteria and a platform-oriented approach to examine promising freeware (Magnet Forensics and Sleuth Kit) vs. profitable (ProDiscover and Oxygen Forensic Suite) mobile forensics tools. Under diverse settings, the tools' capacity to develop and analyze forensically sound digital forensic media sources is validated. After erasing data, each media type was tested again after formatting. The study concludes with a comparison matrix that may aid in determining the best-fit option for the investigation's requirements among the tools. The findings indicate the potential for freeware to supplant numerous proprietary applications, as users can opt for freeware instead of incurring costs associated with proprietary software. Furthermore, this perception can be put into practice.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"15 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140741507","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}
Pub Date : 2024-04-04DOI: 10.11591/ijict.v13i1.pp50-56
Shania Priccilia, A. S. Girsang
The accessibility of academic information greatly impacts the satisfaction and loyalty of university students. However, limited university resources often hinder students from conveniently accessing information services. To address this challenge, this research proposes the digitization of the question-answering process between students and student service staff through the implementation of generative chatbot. A generative chatbot can provide students with human-like responses to academic inquiries at their convenience. This research developed generative chatbot using pre-trained GPT-2 architecture in three different sizes, specifically designed for addressing practicum-related questions in a private university in Indonesia. The experiment utilized 1288 question-answer pairs in Indonesian and demonstrated the best performance with a BLEU score of 0.753, signifying good performance accuracy in generating text despite dataset limitations.
{"title":"Indonesian generative chatbot model for student services using GPT","authors":"Shania Priccilia, A. S. Girsang","doi":"10.11591/ijict.v13i1.pp50-56","DOIUrl":"https://doi.org/10.11591/ijict.v13i1.pp50-56","url":null,"abstract":"The accessibility of academic information greatly impacts the satisfaction and loyalty of university students. However, limited university resources often hinder students from conveniently accessing information services. To address this challenge, this research proposes the digitization of the question-answering process between students and student service staff through the implementation of generative chatbot. A generative chatbot can provide students with human-like responses to academic inquiries at their convenience. This research developed generative chatbot using pre-trained GPT-2 architecture in three different sizes, specifically designed for addressing practicum-related questions in a private university in Indonesia. The experiment utilized 1288 question-answer pairs in Indonesian and demonstrated the best performance with a BLEU score of 0.753, signifying good performance accuracy in generating text despite dataset limitations.","PeriodicalId":245958,"journal":{"name":"International Journal of Informatics and Communication Technology (IJ-ICT)","volume":"24 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140743035","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：