Pub Date : 2024-03-02DOI: 10.58346/jisis.2024.i1.011
P. Lavanya, Dr.I.V. Subba Reddy, Dr.V. Selvakumar, Shreesh V Deshpande
In several nations, the majority of heart attacks lead to fatality prior to patients receiving any kind of medical intervention. The traditional healthcare system is mostly passive, requiring patients to initiate contact with healthcare services independently. People often do not request the treatment if they are unconscious during a heart disease episode. The use of Internet of Medical Things (IoMT) methods offers significant advantages in addressing the issue of caring for patients with cardiac problems. These techniques may transform service delivery into ubiquitous and activate healthcare services. Low-cost remote monitoring systems are essential to implementing a widespread healthcare service. In this article, we proposed a cost-effective Personal Health Care Device(PHCD) based on the Internet of Things (IoT). The PHCD transmits user somatic signals to data acquisition devices using a LoRa (Long-range and low-power) wireless communication network. The received data is uploaded to the cloud using IoT platforms like Adafruit IO. Further, various Machine learning (ML) algorithms, Naïve Bayes, ANN, CNN, and LSTM, were applied to collected data to predict heart rate and SpO2 behavior. The performance results of different forecast models were compared to identify precise modeling and reliable forecasts to prevent emergency cardiovascular conditions.
{"title":"An Intelligent Health Surveillance System: Predictive Modeling of Cardiovascular Parameters through Machine Learning Algorithms Using LoRa Communication and Internet of Medical Things (IoMT)","authors":"P. Lavanya, Dr.I.V. Subba Reddy, Dr.V. Selvakumar, Shreesh V Deshpande","doi":"10.58346/jisis.2024.i1.011","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.011","url":null,"abstract":"In several nations, the majority of heart attacks lead to fatality prior to patients receiving any kind of medical intervention. The traditional healthcare system is mostly passive, requiring patients to initiate contact with healthcare services independently. People often do not request the treatment if they are unconscious during a heart disease episode. The use of Internet of Medical Things (IoMT) methods offers significant advantages in addressing the issue of caring for patients with cardiac problems. These techniques may transform service delivery into ubiquitous and activate healthcare services. Low-cost remote monitoring systems are essential to implementing a widespread healthcare service. In this article, we proposed a cost-effective Personal Health Care Device(PHCD) based on the Internet of Things (IoT). The PHCD transmits user somatic signals to data acquisition devices using a LoRa (Long-range and low-power) wireless communication network. The received data is uploaded to the cloud using IoT platforms like Adafruit IO. Further, various Machine learning (ML) algorithms, Naïve Bayes, ANN, CNN, and LSTM, were applied to collected data to predict heart rate and SpO2 behavior. The performance results of different forecast models were compared to identify precise modeling and reliable forecasts to prevent emergency cardiovascular conditions.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081595","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.003
Dr.V. Jyothi, Dr. Tammineni Sreelatha, Dr.T.M. Thiyagu, R. Sowndharya, N. Arvinth
Smart cities are metropolitan areas that use sophisticated technology to increase efficiency, sustainability, and overall quality of life. The potential for transformation is tremendous, with applications ranging from Internet of Things (IoT)-driven infrastructure to data-driven governance. Effectively handling the abundant data produced in smart cities requires stringent security and privacy protocols. This research aims to tackle these difficulties by introducing the suggested Artificial Intelligence-based Data Management System (AI-DMS) for Smart Cities. AI-DMS seeks to optimize the data processing pipeline, guaranteeing effectiveness throughout the process, from data extraction to publication. Implementing a Multi-Level Sensitive Model is a notable addition, as it classifies data into three categories: sensitive, quasi-sensitive, and public. This allows for more nuanced sharing of data. Privacy preservation is accomplished using Principal Component Analysis (PCA), a comprehensive technique encompassing feature mapping, selection, normalization, and transformation. The simulation results demonstrate that AI-DMS outperforms other methods. It achieves a Data Quality Score of 95.12% (training) and 93.76% (testing), a Privacy Preservation Rate of 85.23% (training) and 82.76% (testing), a Processing Efficiency of 90.54% (training) and 88.76% (testing), a Sensitivity Model Accuracy of 80.12% (training) and 78.45% (testing), and a Data Access Time of 22.76 ms (training) and 21.32 ms (testing). The results highlight AI-DMS as a reliable and effective system, guaranteeing superior smart city data management that is secure and precise. This contribution aligns with the changing urban scene, offering improvements in decision-making based on data while still ensuring privacy and security.
{"title":"A Data Management System for Smart Cities Leveraging Artificial Intelligence Modeling Techniques to Enhance Privacy and Security","authors":"Dr.V. Jyothi, Dr. Tammineni Sreelatha, Dr.T.M. Thiyagu, R. Sowndharya, N. Arvinth","doi":"10.58346/jisis.2024.i1.003","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.003","url":null,"abstract":"Smart cities are metropolitan areas that use sophisticated technology to increase efficiency, sustainability, and overall quality of life. The potential for transformation is tremendous, with applications ranging from Internet of Things (IoT)-driven infrastructure to data-driven governance. Effectively handling the abundant data produced in smart cities requires stringent security and privacy protocols. This research aims to tackle these difficulties by introducing the suggested Artificial Intelligence-based Data Management System (AI-DMS) for Smart Cities. AI-DMS seeks to optimize the data processing pipeline, guaranteeing effectiveness throughout the process, from data extraction to publication. Implementing a Multi-Level Sensitive Model is a notable addition, as it classifies data into three categories: sensitive, quasi-sensitive, and public. This allows for more nuanced sharing of data. Privacy preservation is accomplished using Principal Component Analysis (PCA), a comprehensive technique encompassing feature mapping, selection, normalization, and transformation. The simulation results demonstrate that AI-DMS outperforms other methods. It achieves a Data Quality Score of 95.12% (training) and 93.76% (testing), a Privacy Preservation Rate of 85.23% (training) and 82.76% (testing), a Processing Efficiency of 90.54% (training) and 88.76% (testing), a Sensitivity Model Accuracy of 80.12% (training) and 78.45% (testing), and a Data Access Time of 22.76 ms (training) and 21.32 ms (testing). The results highlight AI-DMS as a reliable and effective system, guaranteeing superior smart city data management that is secure and precise. This contribution aligns with the changing urban scene, offering improvements in decision-making based on data while still ensuring privacy and security.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140082416","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.015
S. Parthasarathy, Arunraj Lakshminarayanan, A. Khan, K. J. Sathick
Child sexual abuse is a pervasive and distressing issue that poses serious threats to the well-being and development of children. Early identification and prevention of such incidents are crucial for ensuring child safety and protection. In this study, we investigate the application of stacked machine learning models for the forecasting of child sexual abuse cases. Data on child sexual abuse incidents were gathered from StatBank Denmark and used in this analysis. The geographical coordinates of the municipalities were incorporated as part of the descriptive analysis to examine the distribution and prevalence of child abuse cases. Our approach incorporates a stacked ensemble framework that combines the XGBoost, LSTM, and Random Forest algorithms. By leveraging the strength of individual models and capturing diverse patterns in the data, the stacked model aims to improve prediction performance. Our experimental results demonstrate that the CSA-Forecaster model outperforms individual models in forecasting child sexual abuse incidents. The proposed model achieved an RMSE of 0.094, MAE of 0.0712, MAPE of 0.1557, and R2 of 0.8028, indicating robust performance. The outcomes of this research have significant repercussions for the creation of proactive interventions and support systems. Child protection agencies and experts might be equipped to more effectively allocate resources and potentially prevent future abuse instances by employing machine learning models.
{"title":"CSA-Forecaster: Stacked Model for Forecasting Child Sexual Abuse","authors":"S. Parthasarathy, Arunraj Lakshminarayanan, A. Khan, K. J. Sathick","doi":"10.58346/jisis.2024.i1.015","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.015","url":null,"abstract":"Child sexual abuse is a pervasive and distressing issue that poses serious threats to the well-being and development of children. Early identification and prevention of such incidents are crucial for ensuring child safety and protection. In this study, we investigate the application of stacked machine learning models for the forecasting of child sexual abuse cases. Data on child sexual abuse incidents were gathered from StatBank Denmark and used in this analysis. The geographical coordinates of the municipalities were incorporated as part of the descriptive analysis to examine the distribution and prevalence of child abuse cases. Our approach incorporates a stacked ensemble framework that combines the XGBoost, LSTM, and Random Forest algorithms. By leveraging the strength of individual models and capturing diverse patterns in the data, the stacked model aims to improve prediction performance. Our experimental results demonstrate that the CSA-Forecaster model outperforms individual models in forecasting child sexual abuse incidents. The proposed model achieved an RMSE of 0.094, MAE of 0.0712, MAPE of 0.1557, and R2 of 0.8028, indicating robust performance. The outcomes of this research have significant repercussions for the creation of proactive interventions and support systems. Child protection agencies and experts might be equipped to more effectively allocate resources and potentially prevent future abuse instances by employing machine learning models.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081483","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.010
Dr. Fernando Escobedo, Dr. Henry Bernardo Garay Canales, Dr. Eddy Miguel Aguirre Reyes, Carlos Alberto Lamadrid Vela, Oscar Napoleón Montoya Perez, Grover Enrique Caballero Jimenez
As the user base expands, social network data becomes more intricate, making analyzing the interconnections between various entities challenging. Various graph visualization technologies are employed to analyze extensive and intricate network data. Network graphs inherently possess intricacy and may have overlapping elements. Graph clustering is a basic endeavor that aims to identify communities or groupings inside networks. Recent research has mostly concentrated on developing deep learning techniques to acquire a concise representation of graphs, which is then utilized with traditional clustering methods such as k-means or spectral clustering techniques. Multiplying these two-step architectures is challenging and sometimes results in unsatisfactory performance. This is mostly due to the lack of a goal-oriented graph encoding developed explicitly for the clustering job. This work introduces a novel Deep Learning (DL) method called Deep Attentional Implanted Graph Clustering (DAIGC), designed to achieve goal-oriented clustering. Our approach centers on associated graphs to thoroughly investigate both aspects of data in graphs. The proposed DAIGC technique utilizes a Graph Attention Autoencoder (GAA) to determine the significance of nearby nodes about a target node. This allows encoding a graph's topographical structure and node value into a concise representation. Based on this representation, an interior product decoder has been trained to rebuild the graph structure. The performance of the proposed approach has been evaluated on four distinct types and sizes of real-world intricate networks, varying in vertex count from 𝑁=102 𝑡𝑜 𝑁=107. The performance of the suggested methods is evaluated by comparing them with two established and commonly used graph clustering techniques. The testing findings demonstrate the effectiveness of the proposed method in terms of processing speed and visualization compared to the state-of-the-art algorithms.
{"title":"Deep Attentional Implanted Graph Clustering Algorithm for the Visualization and Analysis of Social Networks","authors":"Dr. Fernando Escobedo, Dr. Henry Bernardo Garay Canales, Dr. Eddy Miguel Aguirre Reyes, Carlos Alberto Lamadrid Vela, Oscar Napoleón Montoya Perez, Grover Enrique Caballero Jimenez","doi":"10.58346/jisis.2024.i1.010","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.010","url":null,"abstract":"As the user base expands, social network data becomes more intricate, making analyzing the interconnections between various entities challenging. Various graph visualization technologies are employed to analyze extensive and intricate network data. Network graphs inherently possess intricacy and may have overlapping elements. Graph clustering is a basic endeavor that aims to identify communities or groupings inside networks. Recent research has mostly concentrated on developing deep learning techniques to acquire a concise representation of graphs, which is then utilized with traditional clustering methods such as k-means or spectral clustering techniques. Multiplying these two-step architectures is challenging and sometimes results in unsatisfactory performance. This is mostly due to the lack of a goal-oriented graph encoding developed explicitly for the clustering job. This work introduces a novel Deep Learning (DL) method called Deep Attentional Implanted Graph Clustering (DAIGC), designed to achieve goal-oriented clustering. Our approach centers on associated graphs to thoroughly investigate both aspects of data in graphs. The proposed DAIGC technique utilizes a Graph Attention Autoencoder (GAA) to determine the significance of nearby nodes about a target node. This allows encoding a graph's topographical structure and node value into a concise representation. Based on this representation, an interior product decoder has been trained to rebuild the graph structure. The performance of the proposed approach has been evaluated on four distinct types and sizes of real-world intricate networks, varying in vertex count from 𝑁=102 𝑡𝑜 𝑁=107. The performance of the suggested methods is evaluated by comparing them with two established and commonly used graph clustering techniques. The testing findings demonstrate the effectiveness of the proposed method in terms of processing speed and visualization compared to the state-of-the-art algorithms.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081752","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.006
Wasin AlKishri, Dr. Setyawan Widyarto, Dr. Jabar H. Yousif
Deep neural networks are able to generate stunningly realistic images, making it easy to fool both technology and humans into distinguishing real images from fake ones. Generative Adversarial Networks (GANs) play a significant role in these successes (GANs). Various studies have shown that combining features from different domains can produce effective results. However, the challenges lie in detecting these fake images, especially when modifications or removal of GAN components are involved. In this research, we analyse the high-frequency Fourier modes of real and deep network-generated images and show that Images generated by deep networks share an observable, systematic shortcoming when it comes to reproducing their high-frequency features. We illustrate how eliminating the GAN fingerprint in modified pictures' frequency and spatial spectrum might affect deep-fake detection approaches. In-depth review of the latest research on the GAN-Based Artifacts Detection Method. We empirically assess our approach to the CNN detection model using style GAN structures 140k datasets of Real and Fake Faces. Our method has dramatically reduced the detection rate of fake images by 50%. In our study, we found that adversaries are able to remove the fingerprints of GANs, making it difficult to detect the generated images. This result confirms the lack of robustness of current algorithms and the need for further research in this area.
深度神经网络能够生成令人惊叹的逼真图像，让技术和人类轻松辨别真假图像。生成对抗网络（GAN）在这些成功中发挥了重要作用。各种研究表明，结合不同领域的特征可以产生有效的结果。然而，如何检测这些伪造图像，尤其是在涉及修改或删除 GAN 组件的情况下，是一项挑战。在这项研究中，我们分析了真实图像和深度网络生成图像的高频傅立叶模式，结果表明，深度网络生成的图像在再现其高频特征方面存在可观察到的系统性缺陷。我们说明了在修改后的图片频率和空间频谱中消除 GAN 指纹会如何影响深度防伪检测方法。深入回顾基于 GAN 的伪影检测方法的最新研究。我们使用样式 GAN 结构 140k 真实和虚假人脸数据集对 CNN 检测模型的方法进行了实证评估。我们的方法将假图像的检测率大幅降低了 50%。在我们的研究中，我们发现对手能够消除 GAN 的指纹，从而难以检测生成的图像。这一结果证实了当前算法缺乏鲁棒性，需要在这一领域开展进一步研究。
{"title":"Evaluating the Effectiveness of a Gan Fingerprint Removal Approach in Fooling Deepfake Face Detection","authors":"Wasin AlKishri, Dr. Setyawan Widyarto, Dr. Jabar H. Yousif","doi":"10.58346/jisis.2024.i1.006","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.006","url":null,"abstract":"Deep neural networks are able to generate stunningly realistic images, making it easy to fool both technology and humans into distinguishing real images from fake ones. Generative Adversarial Networks (GANs) play a significant role in these successes (GANs). Various studies have shown that combining features from different domains can produce effective results. However, the challenges lie in detecting these fake images, especially when modifications or removal of GAN components are involved. In this research, we analyse the high-frequency Fourier modes of real and deep network-generated images and show that Images generated by deep networks share an observable, systematic shortcoming when it comes to reproducing their high-frequency features. We illustrate how eliminating the GAN fingerprint in modified pictures' frequency and spatial spectrum might affect deep-fake detection approaches. In-depth review of the latest research on the GAN-Based Artifacts Detection Method. We empirically assess our approach to the CNN detection model using style GAN structures 140k datasets of Real and Fake Faces. Our method has dramatically reduced the detection rate of fake images by 50%. In our study, we found that adversaries are able to remove the fingerprints of GANs, making it difficult to detect the generated images. This result confirms the lack of robustness of current algorithms and the need for further research in this area.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081408","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.014
Rosa Clavijo-López, Dr. Wayky Alfredo Luy Navarrete, Dr. Jesús Merino Velásquez, Dr. Carlos Miguel Aguilar Saldaña, Alcides Muñoz Ocas, Dr. César Augusto Flores Tananta
Database Management Systems (DBMS) advancement has been crucial to Information Technology (IT). Traditional DBMS needed help managing large and varied datasets under strict time constraints due to the emergence of Big Data and the widespread use of Internet of Things (IoT) devices. The growing intricacy of data and the need for instantaneous processing presented substantial obstacles. This research suggests a Machine Learning-based Intelligent Database Management Systems (ML-IDMS) technique. This invention combines the skills of Machine Learning with DBMS, improving flexibility and decision-making capacities. The ML-IDMS is specifically developed to tackle current obstacles by providing capabilities such as instantaneous data retrieval, intelligent heat measurement, and effective neural network initialization. The simulation results showcase the effectiveness of ML-IDMS, as shown by impressive metrics such as query execution time (19.27 sec), storage efficiency (83.78%), data accuracy (90%), redundancy reduction (66.42%), network throughput (7.93 Gbps), and end-to-end delay (14.4 ms). The results highlight the efficacy of ML-IDMS in managing various data circumstances. ML-IDMS addresses current obstacles and establishes a standard for future intelligent data management and analytics progress.
{"title":"Integrating Novel Machine Learning for Big Data Analytics and IoT Technology in Intelligent Database Management Systems","authors":"Rosa Clavijo-López, Dr. Wayky Alfredo Luy Navarrete, Dr. Jesús Merino Velásquez, Dr. Carlos Miguel Aguilar Saldaña, Alcides Muñoz Ocas, Dr. César Augusto Flores Tananta","doi":"10.58346/jisis.2024.i1.014","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.014","url":null,"abstract":"Database Management Systems (DBMS) advancement has been crucial to Information Technology (IT). Traditional DBMS needed help managing large and varied datasets under strict time constraints due to the emergence of Big Data and the widespread use of Internet of Things (IoT) devices. The growing intricacy of data and the need for instantaneous processing presented substantial obstacles. This research suggests a Machine Learning-based Intelligent Database Management Systems (ML-IDMS) technique. This invention combines the skills of Machine Learning with DBMS, improving flexibility and decision-making capacities. The ML-IDMS is specifically developed to tackle current obstacles by providing capabilities such as instantaneous data retrieval, intelligent heat measurement, and effective neural network initialization. The simulation results showcase the effectiveness of ML-IDMS, as shown by impressive metrics such as query execution time (19.27 sec), storage efficiency (83.78%), data accuracy (90%), redundancy reduction (66.42%), network throughput (7.93 Gbps), and end-to-end delay (14.4 ms). The results highlight the efficacy of ML-IDMS in managing various data circumstances. ML-IDMS addresses current obstacles and establishes a standard for future intelligent data management and analytics progress.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081906","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.012
Van Hoa Le
RFID Network Planning (RNP) is the problem of deploying RFID readers within a workspace so that each tag can be covered by at least one reader. The objective of RNP is to determine the optimal positions of readers while satisfying certain constraints, such as maximum coverage, minimal interference, load balance among readers, etc. However, most previous studies considered the workspace rectangular or square and assumed a fixed number of readers. They then employed some heuristic methods to find the optimal reader positions. This approach is not practical because the workspace can have any shape, and an approach adaptable to the actual shape of the workspace is needed. This paper proposed an improved adaptive model considering the workspace shape, called RNP-3P. The objectives of RNP-3P are to minimize the number of readers, maximize coverage area, minimize interference, and achieve load balance. RNP-3P optimizes the problem in three phases: Phase 1 involves modeling the workspace with grid cell size, Phase 2 determines the objective function, and Phase 3 proposes the iGAPO algorithm to optimize the number and positions of readers within the workspace. Simulation results demonstrate that the proposed model is more effective compared to other heuristic methods.
RFID 网络规划（RNP）是在工作区内部署 RFID 阅读器，使每个标签至少能被一个阅读器覆盖的问题。RNP 的目标是确定阅读器的最佳位置，同时满足某些约束条件，如最大覆盖率、最小干扰、阅读器之间的负载平衡等。然而，以往的大多数研究都认为工作空间是矩形或正方形的，并假设阅读器的数量是固定的。然后，他们采用一些启发式方法来找到最佳的阅读器位置。这种方法并不实用，因为工作区可以是任何形状，因此需要一种能适应工作区实际形状的方法。本文提出了一种考虑到工作空间形状的改进型自适应模型，称为 RNP-3P。RNP-3P 的目标是最小化阅读器数量、最大化覆盖区域、最小化干扰和实现负载平衡。RNP-3P 分三个阶段对问题进行优化：第一阶段是建立具有网格单元大小的工作区模型，第二阶段是确定目标函数，第三阶段是提出 iGAPO 算法，以优化工作区内阅读器的数量和位置。仿真结果表明，与其他启发式方法相比，所提出的模型更为有效。
{"title":"An Optimal Model for Allocation Readers with Grid Cell Size and Arbitrary Workspace Shapes in RFID Network Planning","authors":"Van Hoa Le","doi":"10.58346/jisis.2024.i1.012","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.012","url":null,"abstract":"RFID Network Planning (RNP) is the problem of deploying RFID readers within a workspace so that each tag can be covered by at least one reader. The objective of RNP is to determine the optimal positions of readers while satisfying certain constraints, such as maximum coverage, minimal interference, load balance among readers, etc. However, most previous studies considered the workspace rectangular or square and assumed a fixed number of readers. They then employed some heuristic methods to find the optimal reader positions. This approach is not practical because the workspace can have any shape, and an approach adaptable to the actual shape of the workspace is needed. This paper proposed an improved adaptive model considering the workspace shape, called RNP-3P. The objectives of RNP-3P are to minimize the number of readers, maximize coverage area, minimize interference, and achieve load balance. RNP-3P optimizes the problem in three phases: Phase 1 involves modeling the workspace with grid cell size, Phase 2 determines the objective function, and Phase 3 proposes the iGAPO algorithm to optimize the number and positions of readers within the workspace. Simulation results demonstrate that the proposed model is more effective compared to other heuristic methods.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140082140","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.013
Dr. Walaa Saber Ismail
Introduction: In an age of rapid technical innovation and a growing digital world, protecting sensitive data from cyberattacks is crucial. The dynamic and complicated nature of these attacks requires novel cybersecurity solutions. Methods: This study analyses how Artificial Intelligence (AI) and Natural Language Processing (NLP) strengthen cybersecurity. The qualitative research approach is followed to gather data through a literature review of relevant scholarly articles and conduct interviews with cybersecurity specialists. Results: Recent AI advances have greatly enhanced the detection of anomalous patterns and behaviors in huge datasets, a key threat identification tool. NLP has also excelled at detecting malevolent intent in textual data, such as phishing efforts. AI and NLP enable adaptive security policies, enabling agile responses to evolving security issues. Expert interviews confirm that AI and NLP reduce false positives, improve threat intelligence, streamline network security setups, and improve compliance checks. These technologies enable responsive security policies, which give a strategic edge against developing security threats. AI and NLP's predictive skills could revolutionize cybersecurity by preventing threats. Conclusion: This study shows that AI and NLP have improved cybersecurity threat detection, automated incident response, and adaptive security policies. Overcoming threat detection, aggressive attacks and data privacy issues is essential to properly leveraging these advances and strengthening cyber resilience in a changing digital landscape.
{"title":"Threat Detection and Response Using AI and NLP in Cybersecurity","authors":"Dr. Walaa Saber Ismail","doi":"10.58346/jisis.2024.i1.013","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.013","url":null,"abstract":"Introduction: In an age of rapid technical innovation and a growing digital world, protecting sensitive data from cyberattacks is crucial. The dynamic and complicated nature of these attacks requires novel cybersecurity solutions. Methods: This study analyses how Artificial Intelligence (AI) and Natural Language Processing (NLP) strengthen cybersecurity. The qualitative research approach is followed to gather data through a literature review of relevant scholarly articles and conduct interviews with cybersecurity specialists. Results: Recent AI advances have greatly enhanced the detection of anomalous patterns and behaviors in huge datasets, a key threat identification tool. NLP has also excelled at detecting malevolent intent in textual data, such as phishing efforts. AI and NLP enable adaptive security policies, enabling agile responses to evolving security issues. Expert interviews confirm that AI and NLP reduce false positives, improve threat intelligence, streamline network security setups, and improve compliance checks. These technologies enable responsive security policies, which give a strategic edge against developing security threats. AI and NLP's predictive skills could revolutionize cybersecurity by preventing threats. Conclusion: This study shows that AI and NLP have improved cybersecurity threat detection, automated incident response, and adaptive security policies. Overcoming threat detection, aggressive attacks and data privacy issues is essential to properly leveraging these advances and strengthening cyber resilience in a changing digital landscape.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081651","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.007
Seiba Alhassan, Dr. Gaddafi Abdul-Salaam, Asante Micheal, Y. Missah, Dr. Ernest D. Ganaa, Alimatu Sadia Shirazu
The major problem computer network users face concerning data – whether in storage, in transit, or being processed - is unauthorized access. This unauthorized access typically leads to the loss of confidentiality, integrity, and availability of data. Consequently, it is essential to implement an accurate Intrusion Detection System (IDS) for every information system. Many researchers have proposed machine learning and deep learning models, such as autoencoders, to enhance existing IDS. However, the accuracy of these models remains a significant research challenge. This paper proposes a Correlation-Based Feature Selection and Autoencoder (CFS-AE) to enhance detection accuracy and reduce the false alarms associated with the current anomaly-based IDS. The first step involves feature selection for the NSL-KDD and CIC-IDS2017 datasets which are used to train and test our model. Subsequently, an autoencoder is employed as a classifier to categorize data traffic into attack and normal categories. The results from our experimental study revealed an accuracy of 94.32% and 97.71% for the NSL-KDD and CIC-IDS2017 datasets, respectively. These results demonstrate improved performance over existing IDS systems.
{"title":"CFS-AE: Correlation-based Feature Selection and Autoencoder for Improved Intrusion Detection System Performance","authors":"Seiba Alhassan, Dr. Gaddafi Abdul-Salaam, Asante Micheal, Y. Missah, Dr. Ernest D. Ganaa, Alimatu Sadia Shirazu","doi":"10.58346/jisis.2024.i1.007","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.007","url":null,"abstract":"The major problem computer network users face concerning data – whether in storage, in transit, or being processed - is unauthorized access. This unauthorized access typically leads to the loss of confidentiality, integrity, and availability of data. Consequently, it is essential to implement an accurate Intrusion Detection System (IDS) for every information system. Many researchers have proposed machine learning and deep learning models, such as autoencoders, to enhance existing IDS. However, the accuracy of these models remains a significant research challenge. This paper proposes a Correlation-Based Feature Selection and Autoencoder (CFS-AE) to enhance detection accuracy and reduce the false alarms associated with the current anomaly-based IDS. The first step involves feature selection for the NSL-KDD and CIC-IDS2017 datasets which are used to train and test our model. Subsequently, an autoencoder is employed as a classifier to categorize data traffic into attack and normal categories. The results from our experimental study revealed an accuracy of 94.32% and 97.71% for the NSL-KDD and CIC-IDS2017 datasets, respectively. These results demonstrate improved performance over existing IDS systems.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140082438","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 : 2024-03-02DOI: 10.58346/jisis.2024.i1.005
Adán F. Guzmán-Castillo, Gabriela Suntaxi, Bryan N. Flores-Sarango, Denys A. Flores
Recent threat reports have warned researchers and security professionals about a shortage of cybersecurity skills to face devastating personal data breaches. As a response, governments have taken on the challenge of proposing specific legislation to protect citizens' privacy while holding information-processing companies accountable for any misuse. However, unauthorized access to such information, or possible negligent destruction of personal records are some issues that cannot be dealt with privacy laws alone. In this research, we introduce the functional requirements to deploy PriVARq, a novel privacy-oriented architecture to proactively manage any consensual submission of personal identifiable information (PII); i.e. during its collection, processing, verification and transference. PriVARq’s main contribution is the balance between legal frameworks and industry-leading security standards to mitigate the former’s shortage of practical solutions to tackle some privacy and security issues when dealing with PII. Consequently, for defining PriVARq’s functional requirements, a privacy-by-design approach is employed which not only considers legislation proposed in Europe and Latin America but also analyzes technical aspects outlined in international security standards. We aim to provide a proactive approach to reduce the shortage of skills and solutions to tackle privacy leakages in public repositories and devise future research venues to implement PriVARq in public and private organizations.
{"title":"Towards Designing a Privacy-Oriented Architecture for Managing Personal Identifiable Information","authors":"Adán F. Guzmán-Castillo, Gabriela Suntaxi, Bryan N. Flores-Sarango, Denys A. Flores","doi":"10.58346/jisis.2024.i1.005","DOIUrl":"https://doi.org/10.58346/jisis.2024.i1.005","url":null,"abstract":"Recent threat reports have warned researchers and security professionals about a shortage of cybersecurity skills to face devastating personal data breaches. As a response, governments have taken on the challenge of proposing specific legislation to protect citizens' privacy while holding information-processing companies accountable for any misuse. However, unauthorized access to such information, or possible negligent destruction of personal records are some issues that cannot be dealt with privacy laws alone. In this research, we introduce the functional requirements to deploy PriVARq, a novel privacy-oriented architecture to proactively manage any consensual submission of personal identifiable information (PII); i.e. during its collection, processing, verification and transference. PriVARq’s main contribution is the balance between legal frameworks and industry-leading security standards to mitigate the former’s shortage of practical solutions to tackle some privacy and security issues when dealing with PII. Consequently, for defining PriVARq’s functional requirements, a privacy-by-design approach is employed which not only considers legislation proposed in Europe and Latin America but also analyzes technical aspects outlined in international security standards. We aim to provide a proactive approach to reduce the shortage of skills and solutions to tackle privacy leakages in public repositories and devise future research venues to implement PriVARq in public and private organizations.","PeriodicalId":36718,"journal":{"name":"Journal of Internet Services and Information Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140082045","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：