Pub Date : 2024-01-08DOI: 10.30534/ijns/2024/101312024
Due to the increased risk of exposure to violent and harmful content brought about by the spread of online video content, robust systems for automatic detection and filtering have to be developed. This research suggests a novel method for deep learning-based violent content detection in videos. Our model examines both temporal and spatial characteristics in video frames by utilizing the power of recurrent neural networks (RNNs) and convolutional neural networks (CNNs).The suggested system uses a two-stream architecture, where one stream is used for temporal information using bidirectional LSTM (Long Short-Term Memory) networks to capture sequential dependencies, and the other stream is devoted to spatial analysis using 3D CNNs for frame-level understanding [1]. To ensure strong generalization, the model is additionally trained on a varied dataset that includes both violent and nonviolent content. Transfer learning is used with pre- trained deep learning models on large-scale datasets to improve the model's performance [5]. Comprehensive tests show how well the suggested method works to reliably identify violent content in videos of different genres and settings. The system demonstratesits potential for incorporation into online video platforms to give viewers a safer and more secure experience by achieving state-of-the-art outcomes in terms of precision, recall, and F1 score [4]. The suggested deep learning-based approach supports further initiatives to lessen the negative impacts of violent content in digital media and promote a safe and healthy online community [1]. Using Deep Learning to Address the Problem of Violent Video Detection: A Bright Future for Security and Safety. The proliferation of violent content is a key concern posed by the ever-increasing abundance of online video content. This puts personal safety, public safety, and platforms' capacity to properly filter information at risk. Presenting deep learning, a potent technique that presents a viable way to automatically identify violent content in videos [2]. To sum up, deep learning presents a potent and exciting way to address the pressing problem of violent video content. We can create a more secure online environment for everyone by utilizing this technology properly and resolving the issues it raises [5]. Further investigation into cross-modality learning and real-time detection shows promise for even higher efficiency and accuracy
由于网络视频内容的传播导致接触暴力和有害内容的风险增加,因此必须开发强大的自动检测和过滤系统。本研究提出了一种基于深度学习的视频暴力内容检测新方法。我们的模型利用递归神经网络(RNN)和卷积神经网络(CNN)的强大功能,对视频帧中的时间和空间特征进行检测。建议的系统采用双流架构,其中一个流使用双向 LSTM(长短期记忆)网络获取时间信息,以捕捉顺序依赖关系,另一个流则使用 3D CNN 进行空间分析,以实现帧级理解[1]。为确保强大的泛化能力,该模型还在包括暴力和非暴力内容的各种数据集上进行了额外训练。在大规模数据集上对预先训练好的深度学习模型进行迁移学习,以提高模型的性能[5]。综合测试表明,所建议的方法在可靠识别不同类型和环境视频中的暴力内容方面效果显著。该系统在精确度、召回率和 F1 分数方面都达到了最先进的水平[4],展示了其融入在线视频平台的潜力,从而为观众提供更安全可靠的体验。所建议的基于深度学习的方法有助于进一步减少数字媒体中暴力内容的负面影响,促进安全健康的网络社区[1]。利用深度学习解决暴力视频检测问题:安全保障的光明前景。暴力内容的泛滥是日益丰富的在线视频内容带来的主要问题。这使个人安全、公共安全和平台正确过滤信息的能力面临风险。深度学习是一种有效的技术,它为自动识别视频中的暴力内容提供了一种可行的方法[2]。总之,深度学习为解决暴力视频内容这一紧迫问题提供了一种有效且令人兴奋的方法。我们可以通过正确利用这项技术并解决它所带来的问题,为每个人创造一个更安全的网络环境[5]。对跨模态学习和实时检测的进一步研究有望实现更高的效率和准确性
{"title":"Violence Detection Using Deep Learning","authors":"","doi":"10.30534/ijns/2024/101312024","DOIUrl":"https://doi.org/10.30534/ijns/2024/101312024","url":null,"abstract":"Due to the increased risk of exposure to violent and harmful content brought about by the spread of online video content, robust systems for automatic detection and filtering have to be developed. This research suggests a novel method for deep learning-based violent content detection in videos. Our model examines both temporal and spatial characteristics in video frames by utilizing the power of recurrent neural networks (RNNs) and convolutional neural networks (CNNs).The suggested system uses a two-stream architecture, where one stream is used for temporal information using bidirectional LSTM (Long Short-Term Memory) networks to capture sequential dependencies, and the other stream is devoted to spatial analysis using 3D CNNs for frame-level understanding [1]. To ensure strong generalization, the model is additionally trained on a varied dataset that includes both violent and nonviolent content. Transfer learning is used with pre- trained deep learning models on large-scale datasets to improve the model's performance [5]. Comprehensive tests show how well the suggested method works to reliably identify violent content in videos of different genres and settings. The system demonstratesits potential for incorporation into online video platforms to give viewers a safer and more secure experience by achieving state-of-the-art outcomes in terms of precision, recall, and F1 score [4]. The suggested deep learning-based approach supports further initiatives to lessen the negative impacts of violent content in digital media and promote a safe and healthy online community [1]. Using Deep Learning to Address the Problem of Violent Video Detection: A Bright Future for Security and Safety. The proliferation of violent content is a key concern posed by the ever-increasing abundance of online video content. This puts personal safety, public safety, and platforms' capacity to properly filter information at risk. Presenting deep learning, a potent technique that presents a viable way to automatically identify violent content in videos [2]. To sum up, deep learning presents a potent and exciting way to address the pressing problem of violent video content. We can create a more secure online environment for everyone by utilizing this technology properly and resolving the issues it raises [5]. Further investigation into cross-modality learning and real-time detection shows promise for even higher efficiency and accuracy","PeriodicalId":516643,"journal":{"name":"International Journal of Networks and Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140512661","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 : 2024-01-08DOI: 10.30534/ijns/2024/051312024
An enormous amount of morbidity and mortality cases are caused by pneumonia, which is still a major global health concern. Pneumonia must be accurately and quickly detected in order to manage patients effectively and achieve better results. Machine learning (ML) algorithms have become effective instruments in recent years for automating the detection and diagnosis of pneumonia from medical imaging data. The goal of this review paper is to give a thorough overview of recent developments in ML-based pneumonia detection. It includes the various ML algorithms used, the training and testing datasets, and the evaluation metrics used to rate the effectiveness of these models. Additionally, this review highlights the difficulties encountered in the field and suggests possible directions for improvement in order to create a more reliable and robust pneumonia detection system. Healthcare professionals place a high value on pneumonia detection, and machine learning (ML)-based automation of There's been a lot of attention paid to this process. The importance of pneumonia detection and the part that ML techniques play in automating this process are highlighted in the introduction to this review paper. In the following section, it examines different machine learning (ML) The various system used for the discernment of pneumonia. Such include supervised understanding algorithms like logistic statistics, vector machine and randomization. forests, and convolutional neural networks. The review also discusses pneumonia detection using unsupervised learning techniques like clustering, dimensionality reduction, and autoencoders. In order to develop them, an assessment of pneumonia detection models is essential. The study has examined several appraisal metrics which are commonly used for that purpose, such as sensitivity, specificity, precision and the operational status of receivers. characteristic (ROC) curve, recall, precision, and F1-score. The selection of suitable metrics, which considers specific requirements for pneumonia detection, is main factor to be taken into consideration. The main obstacles is that there are no annotation data. to creating reliable pneumonia detection models. Accurate ML algorithms must be trained on high-quality labelled datasets. However, since chest X-ray images must be annotated by qualified radiologists, obtaining a sizable annotated dataset for pneumonia is frequently challenging. The creation of efficient ML models for pneumonia detection is hampered by the limited availability of annotated data.
肺炎造成了大量的发病和死亡病例,仍然是全球关注的主要健康问题。为了对患者进行有效管理并取得更好的效果,必须准确、快速地检测出肺炎。近年来,机器学习(ML)算法已成为从医学影像数据中自动检测和诊断肺炎的有效工具。本综述旨在全面介绍基于 ML 的肺炎检测的最新进展。其中包括所使用的各种 ML 算法、训练和测试数据集,以及用于评价这些模型有效性的评估指标。此外,本综述还强调了在该领域遇到的困难,并提出了可能的改进方向,以创建一个更可靠、更强大的肺炎检测系统。医疗保健专业人员非常重视肺炎检测,而基于机器学习(ML)的肺炎检测自动化一直备受关注。肺炎检测的重要性以及 ML 技术在这一过程自动化中发挥的作用在本综述论文的引言中得到了强调。在接下来的章节中,我们将探讨不同的机器学习 (ML) 技术。这些系统包括有监督的理解算法,如逻辑统计、向量机和随机化、森林和卷积神经网络。综述还讨论了使用聚类、降维和自动编码器等无监督学习技术进行肺炎检测的问题。为了开发这些技术,对肺炎检测模型进行评估至关重要。本研究研究了几种常用的评估指标,如灵敏度、特异性、精确度和接收器的运行状态、特征曲线(ROC)、召回率、精确度和 F1 分数。考虑到肺炎检测的具体要求,选择合适的指标是需要考虑的主要因素。创建可靠的肺炎检测模型的主要障碍是没有标注数据。准确的 ML 算法必须在高质量的标注数据集上进行训练。然而,由于胸部 X 光图像必须由合格的放射科医生进行标注,因此获得大量的肺炎标注数据集往往具有挑战性。注释数据的有限性阻碍了用于肺炎检测的高效 ML 模型的创建。
{"title":"Pneumonia Detection Using Machine Learning","authors":"","doi":"10.30534/ijns/2024/051312024","DOIUrl":"https://doi.org/10.30534/ijns/2024/051312024","url":null,"abstract":"An enormous amount of morbidity and mortality cases are caused by pneumonia, which is still a major global health concern. Pneumonia must be accurately and quickly detected in order to manage patients effectively and achieve better results. Machine learning (ML) algorithms have become effective instruments in recent years for automating the detection and diagnosis of pneumonia from medical imaging data. The goal of this review paper is to give a thorough overview of recent developments in ML-based pneumonia detection. It includes the various ML algorithms used, the training and testing datasets, and the evaluation metrics used to rate the effectiveness of these models. Additionally, this review highlights the difficulties encountered in the field and suggests possible directions for improvement in order to create a more reliable and robust pneumonia detection system. Healthcare professionals place a high value on pneumonia detection, and machine learning (ML)-based automation of There's been a lot of attention paid to this process. The importance of pneumonia detection and the part that ML techniques play in automating this process are highlighted in the introduction to this review paper. In the following section, it examines different machine learning (ML) The various system used for the discernment of pneumonia. Such include supervised understanding algorithms like logistic statistics, vector machine and randomization. forests, and convolutional neural networks. The review also discusses pneumonia detection using unsupervised learning techniques like clustering, dimensionality reduction, and autoencoders. In order to develop them, an assessment of pneumonia detection models is essential. The study has examined several appraisal metrics which are commonly used for that purpose, such as sensitivity, specificity, precision and the operational status of receivers. characteristic (ROC) curve, recall, precision, and F1-score. The selection of suitable metrics, which considers specific requirements for pneumonia detection, is main factor to be taken into consideration. The main obstacles is that there are no annotation data. to creating reliable pneumonia detection models. Accurate ML algorithms must be trained on high-quality labelled datasets. However, since chest X-ray images must be annotated by qualified radiologists, obtaining a sizable annotated dataset for pneumonia is frequently challenging. The creation of efficient ML models for pneumonia detection is hampered by the limited availability of annotated data.","PeriodicalId":516643,"journal":{"name":"International Journal of Networks and Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140512445","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 : 2024-01-08DOI: 10.30534/ijns/2024/041312024
The Internet of Things (IoT) includes connected devices that communicate over the Internet. This technology has the potential to change industries by increasing productivity, reducing costs and improving efficiency. In manufacturing, IoT devices improve machine maintenance, supply chain management and inventory management. Healthcare uses IoT for drug tracking and patient tracking. Transportation can benefit from improved visibility and streamlining of operations. In the energy sector, IoT optimizes use and reduces waste. New IoT applications can be used in a variety of industries to increase productivity, efficiency and effectiveness.
{"title":"IoT and its Potential for Transforming Industries","authors":"","doi":"10.30534/ijns/2024/041312024","DOIUrl":"https://doi.org/10.30534/ijns/2024/041312024","url":null,"abstract":"The Internet of Things (IoT) includes connected devices that communicate over the Internet. This technology has the potential to change industries by increasing productivity, reducing costs and improving efficiency. In manufacturing, IoT devices improve machine maintenance, supply chain management and inventory management. Healthcare uses IoT for drug tracking and patient tracking. Transportation can benefit from improved visibility and streamlining of operations. In the energy sector, IoT optimizes use and reduces waste. New IoT applications can be used in a variety of industries to increase productivity, efficiency and effectiveness.","PeriodicalId":516643,"journal":{"name":"International Journal of Networks and Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140512062","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 : 2024-01-08DOI: 10.30534/ijns/2024/011312024
This review paper delves into the pivotal realm of animal classification using images obtained through diverse techniques in forest environments. A robust framework is introduced, employing Transfer Learning (TL) within a Convolutional Neural Network (CNN) and leveraging the power of the Region-based Convolutional Neural Network (R-CNN) model for the construction of an automated animal identification system. This innovative framework is adeptly applied to analyze and identify focal species within captured images, contributing to the advancement of wildlife monitoring technologies. The dataset under scrutiny comprises 6,203 camera trap images featuring 11 distinct species, including Wild pig, Barking deer, Chital, Elephant, Gaur, Hare, Jackal, Junglecat, Porcupine, Sambhar, and Sloth bear. The inclusion of this diverse set of species ensures the robustness and applicability of the proposed methodology across a broad spectrum of wildlife scenarios. The integration of Transfer Learning withinthe Region-based Convolutional Neural Network (R-CNN) emerges as a crucial element, showcasing outstanding performance in species classification.Notably, the proposed model achieves a remarkable accuracy rate of 96% on the test dataset after a mere 18 epochs, employing a batch size of 32. This breakthrough holds the potential to expedite research outcomes, foster the evolution of more efficient and dependable animal monitoring systems, and consequently, alleviate the time and effort invested by researchers.In line with ethical considerations, the authors maintain anonymity in theircontribution, focusing on the significant strides made in the classification andanalysis of camera trap images within the observed site. This paper positions itself as a noteworthy and impactful contribution to the broader field of wildlife research and technology
{"title":"R-CNN Based Deep Learning Approach for Counting Animals in the Forest: A Survey","authors":"","doi":"10.30534/ijns/2024/011312024","DOIUrl":"https://doi.org/10.30534/ijns/2024/011312024","url":null,"abstract":"This review paper delves into the pivotal realm of animal classification using images obtained through diverse techniques in forest environments. A robust framework is introduced, employing Transfer Learning (TL) within a Convolutional Neural Network (CNN) and leveraging the power of the Region-based Convolutional Neural Network (R-CNN) model for the construction of an automated animal identification system. This innovative framework is adeptly applied to analyze and identify focal species within captured images, contributing to the advancement of wildlife monitoring technologies. The dataset under scrutiny comprises 6,203 camera trap images featuring 11 distinct species, including Wild pig, Barking deer, Chital, Elephant, Gaur, Hare, Jackal, Junglecat, Porcupine, Sambhar, and Sloth bear. The inclusion of this diverse set of species ensures the robustness and applicability of the proposed methodology across a broad spectrum of wildlife scenarios. The integration of Transfer Learning withinthe Region-based Convolutional Neural Network (R-CNN) emerges as a crucial element, showcasing outstanding performance in species classification.Notably, the proposed model achieves a remarkable accuracy rate of 96% on the test dataset after a mere 18 epochs, employing a batch size of 32. This breakthrough holds the potential to expedite research outcomes, foster the evolution of more efficient and dependable animal monitoring systems, and consequently, alleviate the time and effort invested by researchers.In line with ethical considerations, the authors maintain anonymity in theircontribution, focusing on the significant strides made in the classification andanalysis of camera trap images within the observed site. This paper positions itself as a noteworthy and impactful contribution to the broader field of wildlife research and technology","PeriodicalId":516643,"journal":{"name":"International Journal of Networks and Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139640630","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 : 2024-01-08DOI: 10.30534/ijns/2024/031312024
Smart card technology has emerged as a powerful tool in the field of secure identification, authentication, and transaction processing. This abstract provides a comprehensive overview of smart card technology, highlighting its key features, applications, and benefits. Smart cards, also known as integrated circuit cards, are portable devices that incorporate a microprocessor and memory to securely store and process information. These cards have revolutionized various industries by enabling secure access control, secure payment transactions, and secure storage of sensitive data. The abstract begins by exploring the fundamental components and architecture of smart cards. It delves into the different types of smart cards, such as contact-based and contactless cards, and explains the communication protocols employed in their operation. Furthermore, the abstract discusses the extensive range of applications where smart cards have found widespread adoption. These applications include identification cards, payment cards, healthcare cards, transportation cards, and more. The abstract highlights the advantages of using smart cards in each of these domains, such as enhanced security, convenience, and interoperability.
{"title":"Secure Transactions in a Chip: A Contemporary Review of Smart Card Innovations","authors":"","doi":"10.30534/ijns/2024/031312024","DOIUrl":"https://doi.org/10.30534/ijns/2024/031312024","url":null,"abstract":"Smart card technology has emerged as a powerful tool in the field of secure identification, authentication, and transaction processing. This abstract provides a comprehensive overview of smart card technology, highlighting its key features, applications, and benefits. Smart cards, also known as integrated circuit cards, are portable devices that incorporate a microprocessor and memory to securely store and process information. These cards have revolutionized various industries by enabling secure access control, secure payment transactions, and secure storage of sensitive data. The abstract begins by exploring the fundamental components and architecture of smart cards. It delves into the different types of smart cards, such as contact-based and contactless cards, and explains the communication protocols employed in their operation. Furthermore, the abstract discusses the extensive range of applications where smart cards have found widespread adoption. These applications include identification cards, payment cards, healthcare cards, transportation cards, and more. The abstract highlights the advantages of using smart cards in each of these domains, such as enhanced security, convenience, and interoperability.","PeriodicalId":516643,"journal":{"name":"International Journal of Networks and Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140512700","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 : 2024-01-08DOI: 10.30534/ijns/2024/021312024
This study addresses the transformative integration of 5G networks with Edge Computing and Mobile Edge Computing (MEC) and explores the collaborative standards established by industry associations such as ETSI and 3GPP. The article explores the multiple possibilities of this integration, encompassing consumer and operator services, and meeting the demands of new technologies such as augmented reality, virtual reality and the Internet of Things. The strategic coexistence of distributed MEC is explored, while the security and privacy challenges of MEC are explored, emphasizing layered security and blockchain technologies. The study highlights the role of 5G and MEC in reshaping the communications landscape, providing affordable and efficient computing at the network edge, and improving network performance and quality of experience (QoE). As the 5G and MEC ecosystem evolves, the paper predicts a transformative impact on connectivity, speed, reliability and responsiveness across industries, and emphasizes the continued importance of research and development in shaping the future of communications and computing.
{"title":"5G's Integration with Edge Computing","authors":"","doi":"10.30534/ijns/2024/021312024","DOIUrl":"https://doi.org/10.30534/ijns/2024/021312024","url":null,"abstract":"This study addresses the transformative integration of 5G networks with Edge Computing and Mobile Edge Computing (MEC) and explores the collaborative standards established by industry associations such as ETSI and 3GPP. The article explores the multiple possibilities of this integration, encompassing consumer and operator services, and meeting the demands of new technologies such as augmented reality, virtual reality and the Internet of Things. The strategic coexistence of distributed MEC is explored, while the security and privacy challenges of MEC are explored, emphasizing layered security and blockchain technologies. The study highlights the role of 5G and MEC in reshaping the communications landscape, providing affordable and efficient computing at the network edge, and improving network performance and quality of experience (QoE). As the 5G and MEC ecosystem evolves, the paper predicts a transformative impact on connectivity, speed, reliability and responsiveness across industries, and emphasizes the continued importance of research and development in shaping the future of communications and computing.","PeriodicalId":516643,"journal":{"name":"International Journal of Networks and Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140512200","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}