Pub Date : 2024-06-10DOI: 10.2174/0126662558279046240126051302
Satendra Kumar, Raj Kumar, A. Saini
One of the challenging problems facing the modern Internet is spam, which can annoy individual customers and wreak financial havoc on businesses. Spam communications target customers without their permission and clog their mailboxes. They consume more time and organizational resources when checking for and deleting spam. Even though most web users openly dislike spam, enough are willing to accept lucrative deals that spam remains a real problem. While most web users are well aware of their hatred of spam, the fact that enough of them still click on commercial offers means spammers can still make money from them. While most customers know what to do, they need clear instructions on avoiding and deleting spam. No matter what you do to eliminate spam, you won't succeed. Filtering is the most straightforward and practical technique in spam-blocking strategies. We present procedures for identifying emails as spam or ham based on text classification. Different methods of e-mail organization preprocessing are interrelated, for example, applying stop word exclusion, stemming, including reduction and highlight selection strategies to extract buzzwords from each quality, and finally, using unique classifiers to Quarantine messages as spam or ham. The Nave Bayes classifier is a good choice. Some classifiers, such as Simple Logistic and Adaboost, perform well. However, the Support Vector Machine Classifier (SVC) outperforms it. Therefore, the SVC makes decisions based on each case's comparisons and perspectives. Many spam separation studies have focused on recent classifier-related challenges. Machine Learning (ML) for spam detection is an important area of modern research. Today, spam detection using ML is an important area of research. Examine the adequacy of the proposed work and recognize the application of multiple learning estimates to extract spam from emails. Similarly, estimates have also been scrutinized.
垃圾邮件是现代互联网面临的挑战性问题之一，它不仅会惹恼个人客户，还会给企业造成经济损失。垃圾邮件在未经客户许可的情况下以客户为目标，堵塞了他们的邮箱。在检查和删除垃圾邮件时，它们会消耗更多的时间和组织资源。尽管大多数网络用户公开表示不喜欢垃圾邮件，但他们愿意接受有利可图的交易，因此垃圾邮件仍然是一个现实问题。虽然大多数网络用户都很清楚自己憎恨垃圾邮件，但他们中仍有足够多的人点击商业广告，这意味着垃圾邮件发送者仍能从中牟利。虽然大多数客户知道该怎么做，但他们需要明确的说明来避免和删除垃圾邮件。无论你用什么方法来消除垃圾邮件，都不会成功。在垃圾邮件拦截策略中，过滤是最直接、最实用的技术。我们介绍了基于文本分类识别垃圾邮件或火腿肠邮件的程序。不同的电子邮件组织预处理方法是相互关联的，例如，应用停止词排除、词干处理、包括缩减和高亮选择策略，从每个质量中提取流行词，最后，使用独特的分类器将邮件隔离为垃圾邮件或火腿肠。一些分类器，如 Simple Logistic 和 Adaboost，表现也不错。不过，支持向量机分类器（SVC）的表现要优于它。因此，支持向量机分类器根据每个案例的比较和视角做出决策。用于垃圾邮件检测的机器学习（ML）是现代研究的一个重要领域。如今，使用 ML 进行垃圾邮件检测是一个重要的研究领域。检查提议的工作是否充分，并认识到应用多种学习估计值从邮件中提取垃圾信息的重要性。同样，也对估计值进行了仔细研究。
{"title":"Supervised Learning based E-mail/ SMS Spam Classifier","authors":"Satendra Kumar, Raj Kumar, A. Saini","doi":"10.2174/0126662558279046240126051302","DOIUrl":"https://doi.org/10.2174/0126662558279046240126051302","url":null,"abstract":"\u0000\u0000One of the challenging problems facing the modern Internet is spam,\u0000which can annoy individual customers and wreak financial havoc on businesses. Spam communications target customers without their permission and clog their mailboxes. They consume\u0000more time and organizational resources when checking for and deleting spam. Even though\u0000most web users openly dislike spam, enough are willing to accept lucrative deals that spam remains a real problem. While most web users are well aware of their hatred of spam, the fact\u0000that enough of them still click on commercial offers means spammers can still make money\u0000from them. While most customers know what to do, they need clear instructions on avoiding\u0000and deleting spam. No matter what you do to eliminate spam, you won't succeed. Filtering is\u0000the most straightforward and practical technique in spam-blocking strategies.\u0000\u0000\u0000\u0000We present procedures for identifying emails as spam or ham based on text classification. Different methods of e-mail organization preprocessing are interrelated, for example, applying stop word exclusion, stemming, including reduction and highlight selection strategies to\u0000extract buzzwords from each quality, and finally, using unique classifiers to Quarantine messages as spam or ham.\u0000\u0000\u0000\u0000The Nave Bayes classifier is a good choice. Some classifiers, such as Simple Logistic\u0000and Adaboost, perform well. However, the Support Vector Machine Classifier (SVC) outperforms it. Therefore, the SVC makes decisions based on each case's comparisons and perspectives.\u0000\u0000\u0000\u0000Many spam separation studies have focused on recent classifier-related challenges. Machine Learning (ML) for spam detection is an important area of modern research. Today,\u0000spam detection using ML is an important area of research. Examine the adequacy of the proposed work and recognize the application of multiple learning estimates to extract spam from\u0000emails. Similarly, estimates have also been scrutinized.\u0000","PeriodicalId":506582,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":" 57","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141366173","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 : 2024-06-06DOI: 10.2174/0126662558304595240528111535
Sandeep Kumar, Arun Solanki, NZ Jhanjhi
Prior research on abstractive text summarization has predominantly relied on the ROUGE evaluation metric, which, while effective, has limitations in capturing semantic meaning due to its focus on exact word or phrase matching. This deficiency is particularly pronounced in abstractive summarization approaches, where the goal is to generate novel summaries by rephrasing and paraphrasing the source text, highlighting the need for a more nuanced evaluation metric capable of capturing semantic similarity. In this study, the limitations of existing ROUGE metrics are addressed by proposing a novel variant called ROUGE-SS. Unlike traditional ROUGE metrics, ROUGE-SS extends beyond exact word matching to consider synonyms and semantic similarity. Leveraging resources such as the WordNet online dictionary, ROUGE-SS identifies matches between source text and summaries based on both exact word overlaps and semantic context. Experiments are conducted to evaluate the performance of ROUGE-SS compared to other ROUGE variants, particularly in assessing abstractive summarization models. The algorithm for the synonym features (ROUGE-SS) is also proposed. The experiments demonstrate the superior performance of ROUGE-SS in evaluating abstractive text summarization models compared to existing ROUGE variants. ROUGE-SS yields higher F1 scores and better overall performance, achieving a significant reduction in training loss and impressive accuracy. The proposed ROUGE-SS evaluation technique is evaluated in different datasets like CNN/Daily Mail, DUC-2004, Gigawords, and Inshorts News datasets. ROUGE-SS gives better results than other ROUGE variant metrics. The F1-score of the proposed ROUGE-SS metric is improved by an average of 8.8%. These findings underscore the effectiveness of ROUGE-SS in capturing semantic similarity and providing a more comprehensive evaluation metric for abstractive summarization. In conclusion, the introduction of ROUGE-SS represents a significant advancement in the field of abstractive text summarization evaluation. By extending beyond exact word matching to incorporate synonyms and semantic context, ROUGE-SS offers researchers a more effective tool for assessing summarization quality. This study highlights the importance of considering semantic meaning in evaluation metrics and provides a promising direction for future research on abstractive text summarization.
{"title":"ROUGE-SS: A New ROUGE Variant for the Evaluation of Text\u0000Summarization","authors":"Sandeep Kumar, Arun Solanki, NZ Jhanjhi","doi":"10.2174/0126662558304595240528111535","DOIUrl":"https://doi.org/10.2174/0126662558304595240528111535","url":null,"abstract":"\u0000\u0000Prior research on abstractive text summarization has predominantly\u0000relied on the ROUGE evaluation metric, which, while effective, has limitations in capturing\u0000semantic meaning due to its focus on exact word or phrase matching. This deficiency is particularly pronounced in abstractive summarization approaches, where the goal is to generate novel summaries by rephrasing and paraphrasing the source text, highlighting the need for a more\u0000nuanced evaluation metric capable of capturing semantic similarity.\u0000\u0000\u0000\u0000In this study, the limitations of existing ROUGE metrics are addressed by proposing\u0000a novel variant called ROUGE-SS. Unlike traditional ROUGE metrics, ROUGE-SS extends\u0000beyond exact word matching to consider synonyms and semantic similarity. Leveraging resources such as the WordNet online dictionary, ROUGE-SS identifies matches between source\u0000text and summaries based on both exact word overlaps and semantic context. Experiments are\u0000conducted to evaluate the performance of ROUGE-SS compared to other ROUGE variants,\u0000particularly in assessing abstractive summarization models. The algorithm for the synonym\u0000features (ROUGE-SS) is also proposed.\u0000\u0000\u0000\u0000The experiments demonstrate the superior performance of ROUGE-SS in evaluating\u0000abstractive text summarization models compared to existing ROUGE variants. ROUGE-SS\u0000yields higher F1 scores and better overall performance, achieving a significant reduction in\u0000training loss and impressive accuracy. The proposed ROUGE-SS evaluation technique is evaluated in different datasets like CNN/Daily Mail, DUC-2004, Gigawords, and Inshorts News\u0000datasets. ROUGE-SS gives better results than other ROUGE variant metrics. The F1-score of\u0000the proposed ROUGE-SS metric is improved by an average of 8.8%. These findings underscore the effectiveness of ROUGE-SS in capturing semantic similarity and providing a more\u0000comprehensive evaluation metric for abstractive summarization.\u0000\u0000\u0000\u0000In conclusion, the introduction of ROUGE-SS represents a significant advancement in the field of abstractive text summarization evaluation. By extending beyond exact\u0000word matching to incorporate synonyms and semantic context, ROUGE-SS offers researchers\u0000a more effective tool for assessing summarization quality. This study highlights the importance\u0000of considering semantic meaning in evaluation metrics and provides a promising direction for\u0000future research on abstractive text summarization.\u0000","PeriodicalId":506582,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"207 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141375871","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 : 2024-06-03DOI: 10.2174/0126662558297036240527120451
K. Shastry
The increasing availability of digital healthcare data has opened up fresh prospects for improving healthcare through data analysis. Machine learning (ML) procedures exhibit great promise in analyzing large volumes of healthcare data to extract insights that could be utilized to improve patient outcomes and healthcare delivery. In this work, we suggest an integrated framework for digital healthcare data analysis by integrating unsupervised learning techniques and natural language processing (NLP) techniques into the analysis pipeline. The module on unsupervised learning will involve techniques, such as clustering and anomaly detection. By clustering similar patients together based on their medical history and other relevant factors, healthcare providers can identify subgroups of patients who may require different treatment approaches. Anomaly detection can also help to detect patients who stray from the norm, which could be indicative of underlying health issues or other issues that need additional investigation. The second module on NLP will enable healthcare providers to analyze unstructured text data such as clinical notes, patient surveys, and social media posts. NLP techniques can help to identify key themes and patterns in these datasets, requiring awareness that could not be readily apparent through other means. Overall, incorporating unsupervised learning techniques and NLP into the analysis pipeline for digital healthcare data possesses the promise to enhance patient results and lead to more personalized treatments, and represents a potential domain for upcoming research in this field. In this research, we also review the current state of research in digital healthcare information examination with ML, including applications like forecasting clinic readmissions, finding cancerous tumors, and developing personalized drug dosing recommendations. We also examine the potential benefits and challenges of utilizing ML in healthcare data analysis, including issues related to data quality, privacy, and interpretability. Lastly, we discuss the forthcoming research paths, involving the necessity for enhanced methods for incorporating information from several resources, developing more interpretable ML patterns, and addressing ethical and regulatory challenges. The usage of ML in digital healthcare data analysis promises to transform healthcare by empowering more precise diagnoses, personalized treatments, and improved health outcomes, and this work offers a complete overview of the current trends.
越来越多的数字医疗数据为通过数据分析改善医疗服务开辟了新的前景。机器学习（ML）程序在分析大量医疗保健数据以提取可用于改善患者治疗效果和医疗保健服务的洞察力方面大有可为。在这项工作中，我们通过将无监督学习技术和自然语言处理（NLP）技术整合到分析管道中，为数字医疗保健数据分析提出了一个集成框架。无监督学习模块将涉及聚类和异常检测等技术。通过根据病史和其他相关因素对相似患者进行聚类，医疗服务提供者可以识别出可能需要不同治疗方法的患者亚群。异常检测还有助于发现偏离常规的病人，这可能表明潜在的健康问题或其他需要进一步调查的问题。关于 NLP 的第二个模块将使医疗服务提供者能够分析临床笔记、患者调查和社交媒体帖子等非结构化文本数据。NLP 技术可以帮助识别这些数据集中的关键主题和模式，这就需要认识到通过其他方法无法轻易发现的问题。总之，将无监督学习技术和 NLP 纳入数字医疗数据的分析管道有望提高患者的治疗效果，并带来更加个性化的治疗方法，这也是该领域即将开展的研究的一个潜在领域。在这项研究中，我们还回顾了利用 ML 进行数字医疗信息检查的研究现状，包括预测门诊再入院率、发现癌症肿瘤和开发个性化用药建议等应用。最后，我们还讨论了未来的研究方向，其中包括必须改进方法以整合来自多个资源的信息、开发更多可解释的 ML 模式以及应对伦理和监管方面的挑战。在数字医疗数据分析中使用 ML 有望通过提供更精确的诊断、个性化的治疗和更好的医疗效果来改变医疗行业。
{"title":"A Generic Integrated Framework of Unsupervised Learning and Natural\u0000Language Processing Techniques for Digital Healthcare: A Comprehensive\u0000Review and Future Research Directions","authors":"K. Shastry","doi":"10.2174/0126662558297036240527120451","DOIUrl":"https://doi.org/10.2174/0126662558297036240527120451","url":null,"abstract":"\u0000\u0000The increasing availability of digital healthcare data has opened up fresh prospects\u0000for improving healthcare through data analysis. Machine learning (ML) procedures exhibit\u0000great promise in analyzing large volumes of healthcare data to extract insights that could be\u0000utilized to improve patient outcomes and healthcare delivery. In this work, we suggest an integrated\u0000framework for digital healthcare data analysis by integrating unsupervised learning\u0000techniques and natural language processing (NLP) techniques into the analysis pipeline. The\u0000module on unsupervised learning will involve techniques, such as clustering and anomaly detection.\u0000By clustering similar patients together based on their medical history and other relevant\u0000factors, healthcare providers can identify subgroups of patients who may require different\u0000treatment approaches. Anomaly detection can also help to detect patients who stray from the\u0000norm, which could be indicative of underlying health issues or other issues that need additional\u0000investigation. The second module on NLP will enable healthcare providers to analyze unstructured\u0000text data such as clinical notes, patient surveys, and social media posts. NLP techniques\u0000can help to identify key themes and patterns in these datasets, requiring awareness that could\u0000not be readily apparent through other means. Overall, incorporating unsupervised learning\u0000techniques and NLP into the analysis pipeline for digital healthcare data possesses the promise\u0000to enhance patient results and lead to more personalized treatments, and represents a potential\u0000domain for upcoming research in this field. In this research, we also review the current state of\u0000research in digital healthcare information examination with ML, including applications like\u0000forecasting clinic readmissions, finding cancerous tumors, and developing personalized drug\u0000dosing recommendations. We also examine the potential benefits and challenges of utilizing\u0000ML in healthcare data analysis, including issues related to data quality, privacy, and interpretability.\u0000Lastly, we discuss the forthcoming research paths, involving the necessity for enhanced\u0000methods for incorporating information from several resources, developing more interpretable\u0000ML patterns, and addressing ethical and regulatory challenges. The usage of ML in digital\u0000healthcare data analysis promises to transform healthcare by empowering more precise diagnoses,\u0000personalized treatments, and improved health outcomes, and this work offers a complete\u0000overview of the current trends.\u0000","PeriodicalId":506582,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141388369","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 : 2024-04-15DOI: 10.2174/0126662558292891240409050246
Binghua Xu, Yan Jin, Lei Yu
Cloud computing is usually introduced to execute computing intensive tasks for data processing and data mining. As a supplement to cloud computing, edge computing is provided as a new paradigm to effectively reduce processing latency, energy consumption cost and bandwidth consumption for time-sensitive tasks or resource-sensitive tasks. To better meet such requirements during task assignment in edge computing systems, an intelligent task migration assignment mechanism based on blockchain is proposed, which jointly considers the factors of resource allocation, resource control and credit degree. Cloud computing are usually introduced to execute computing intensive tasks for data processing and data mining. However, this paradigm may not be effective to execute latency sensitive or dynamic interactive tasks. As a supplement to the cloud computing, edge computing has attracted much attention because it can effectively reduce task processing latency, energy consumption cost and bandwidth consumption. In this paper, an optimization problem is firstly constructed to minimize the total cost of completing all tasks under constraints of delay, energy consumption, communication, and credit degree. Here, the terminal node mines computing resources from edge nodes to complete task migration. An incentive method based on blockchain is provided to mobilize the activity of terminal nodes and edge nodes, and to ensure the security of the transaction during migration. The designed allocation rules ensure the fairness of rewards for successfully mining resource. To solve the optimization problem, an intelligent migration algorithm that utilizes a dual “actor-reviewer” neural network on inverse gradient update is proposed which makes the training process more stable and easier to converge. To better meet requirements of the latency, energy consumption and security for computing intensive tasks, an intelligent computing migration mechanism based on blockchain applications is proposed, which considers the factors of resource allocation, resource control and credit degree. Compared to the existing two benchmark mechanisms, the extensive simulation results indicate that the proposed mechanism based on neural network can converge at a faster speed and achieve the minimal total cost. To satisfy the requirements of delay and energy consumption for computing intensive tasks in edge computing scenarios, an intelligent, blockchain based task migration assignment mechanism with joint resource allocation and control is proposed. To realize this mechanism effectively, a dual “actor-reviewer” neural network algorithm is designed and executed.
{"title":"A Cost-Minimized Task Migration Assignment Mechanism in Blockchain Based Edge Computing System","authors":"Binghua Xu, Yan Jin, Lei Yu","doi":"10.2174/0126662558292891240409050246","DOIUrl":"https://doi.org/10.2174/0126662558292891240409050246","url":null,"abstract":"\u0000\u0000Cloud computing is usually introduced to execute computing intensive\u0000tasks for data processing and data mining. As a supplement to cloud computing, edge\u0000computing is provided as a new paradigm to effectively reduce processing latency, energy consumption\u0000cost and bandwidth consumption for time-sensitive tasks or resource-sensitive tasks.\u0000To better meet such requirements during task assignment in edge computing systems, an intelligent\u0000task migration assignment mechanism based on blockchain is proposed, which jointly\u0000considers the factors of resource allocation, resource control and credit degree.\u0000\u0000\u0000\u0000Cloud computing are usually introduced to execute computing intensive tasks for data processing and data mining. However, this paradigm may not be effective to execute latency sensitive or dynamic interactive tasks. As a supplement to the cloud computing, edge computing has attracted much attention because it can effectively reduce task processing latency, energy consumption cost and bandwidth consumption.\u0000\u0000\u0000\u0000In this paper, an optimization problem is firstly constructed to minimize the total\u0000cost of completing all tasks under constraints of delay, energy consumption, communication,\u0000and credit degree. Here, the terminal node mines computing resources from edge nodes to\u0000complete task migration. An incentive method based on blockchain is provided to mobilize the\u0000activity of terminal nodes and edge nodes, and to ensure the security of the transaction during\u0000migration. The designed allocation rules ensure the fairness of rewards for successfully mining\u0000resource. To solve the optimization problem, an intelligent migration algorithm that utilizes a\u0000dual “actor-reviewer” neural network on inverse gradient update is proposed which makes the\u0000training process more stable and easier to converge.\u0000\u0000\u0000\u0000To better meet requirements of the latency, energy consumption and security for computing intensive tasks, an intelligent computing migration mechanism based on blockchain applications is proposed, which considers the factors of resource allocation, resource control and credit degree.\u0000\u0000\u0000\u0000Compared to the existing two benchmark mechanisms, the extensive simulation results\u0000indicate that the proposed mechanism based on neural network can converge at a faster\u0000speed and achieve the minimal total cost.\u0000\u0000\u0000\u0000To satisfy the requirements of delay and energy consumption for computing intensive\u0000tasks in edge computing scenarios, an intelligent, blockchain based task migration assignment\u0000mechanism with joint resource allocation and control is proposed. To realize this\u0000mechanism effectively, a dual “actor-reviewer” neural network algorithm is designed and executed.\u0000","PeriodicalId":506582,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"298 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140703769","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 : 2024-03-20DOI: 10.2174/0126662558296699240314055348
Ramasamy Mariappan
Artificial Intelligence (AI) techniques are widely being used in the medical fields or various applications including diagnosis of diseases, prediction and classification of diseases, drug discovery, etc. However, these AI techniques are lacking in the transparency of the predictions or decisions made due to their black box-type operations. The explainable AI (XAI) addresses such issues faced by AI to make better interpretations or decisions by physicians. This article explores XAI techniques in the field of healthcare applications, including the Internet of Medical Things (IoMT). XAI aims to provide transparency, accountability, and traceability in AI-based systems in healthcare applications. It can help in interpreting the predictions or decisions made in medical diagnosis systems, medical decision support systems, smart wearable healthcare devices, etc. Nowadays, XAI methods have been utilized in numerous medical applications over the Internet of Things (IOT), such as medical diagnosis, prognosis, and explanations of the AI models, and hence, XAI in the context of IoMT and healthcare has the potential to enhance the reliability and trustworthiness of AI systems.
{"title":"Extensive Review of Literature on Explainable AI (XAI) in Healthcare\u0000Applications","authors":"Ramasamy Mariappan","doi":"10.2174/0126662558296699240314055348","DOIUrl":"https://doi.org/10.2174/0126662558296699240314055348","url":null,"abstract":"\u0000\u0000Artificial Intelligence (AI) techniques are widely being used in the medical fields or\u0000various applications including diagnosis of diseases, prediction and classification of diseases,\u0000drug discovery, etc. However, these AI techniques are lacking in the transparency of the predictions\u0000or decisions made due to their black box-type operations. The explainable AI (XAI)\u0000addresses such issues faced by AI to make better interpretations or decisions by physicians.\u0000This article explores XAI techniques in the field of healthcare applications, including the Internet\u0000of Medical Things (IoMT). XAI aims to provide transparency, accountability, and traceability\u0000in AI-based systems in healthcare applications. It can help in interpreting the predictions\u0000or decisions made in medical diagnosis systems, medical decision support systems, smart\u0000wearable healthcare devices, etc. Nowadays, XAI methods have been utilized in numerous\u0000medical applications over the Internet of Things (IOT), such as medical diagnosis, prognosis,\u0000and explanations of the AI models, and hence, XAI in the context of IoMT and healthcare has\u0000the potential to enhance the reliability and trustworthiness of AI systems.\u0000","PeriodicalId":506582,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"60 S278","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140224184","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 : 2024-03-15DOI: 10.2174/0126662558282684240213062932
R. Shukla, A. Tiwari, Ashish Ranjan Mishra
The purpose of this paper was to use Machine Learning (ML) techniques to extract facial features from images. Accurate face detection and recognition has long been a problem in computer vision. According to a recent study, Local Binary Pattern (LBP) is a superior facial descriptor for face recognition. A person's face may make their identity, feelings, and ideas more obvious. In the modern world, everyone wants to feel secure from unauthorized authentication. Face detection and recognition help increase security; however, the most difficult challenge is to accurately recognise faces without creating any false identities. The proposed method uses a Local Binary Pattern Histogram (LBPH) and Convolution Neural Network (CNN) to preprocess face images with equalized histograms. LBPH in the proposed technique is used to extract and join the histogram values into a single vector. The technique has been found to result in a reduction in training loss and an increase in validation accuracy of over 96.5%. Prior algorithms have been reported with lower accuracy when compared to LBPH using CNN. This study demonstrates how studying characteristics produces more precise results, as the number of epochs increases. By comparing facial similarities, the vector has generated the best result.
{"title":"Face Recognition Using LBPH and CNN","authors":"R. Shukla, A. Tiwari, Ashish Ranjan Mishra","doi":"10.2174/0126662558282684240213062932","DOIUrl":"https://doi.org/10.2174/0126662558282684240213062932","url":null,"abstract":"\u0000\u0000The purpose of this paper was to use Machine Learning (ML) techniques\u0000to extract facial features from images. Accurate face detection and recognition has long been a\u0000problem in computer vision. According to a recent study, Local Binary Pattern (LBP) is a superior\u0000facial descriptor for face recognition. A person's face may make their identity, feelings,\u0000and ideas more obvious. In the modern world, everyone wants to feel secure from unauthorized\u0000authentication. Face detection and recognition help increase security; however, the most difficult\u0000challenge is to accurately recognise faces without creating any false identities.\u0000\u0000\u0000\u0000The proposed method uses a Local Binary Pattern Histogram (LBPH) and Convolution\u0000Neural Network (CNN) to preprocess face images with equalized histograms.\u0000\u0000\u0000\u0000LBPH in the proposed technique is used to extract and join the histogram values into a\u0000single vector. The technique has been found to result in a reduction in training loss and an increase\u0000in validation accuracy of over 96.5%. Prior algorithms have been reported with lower\u0000accuracy when compared to LBPH using CNN.\u0000\u0000\u0000\u0000This study demonstrates how studying characteristics produces more precise results,\u0000as the number of epochs increases. By comparing facial similarities, the vector has generated\u0000the best result.\u0000","PeriodicalId":506582,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"21 52","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240419","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 : 2024-03-08DOI: 10.2174/0126662558294125240307094426
Abolfazl Zare, Aliakbar Jalali
After decades of introducing the concept of virtual reality, the expansion, and significant advances of technologies and innovations, such as 6g, edge computing, the internet of things, robotics, artificial intelligence, blockchain, quantum computing, and digital twins, the world is on the cusp of a new revolution. By moving through the three stages of the digital twin, digital native, and finally surrealist, the metaverse has created a new vision of the future of human and societal life so that we are likely to face the next generation of societies (perhaps society 6) in the not too distant future. However, until then, the reality has been that the metaverse is still in its infancy, perhaps where the internet was in 1990. There is still no single definition, few studies have been conducted, there is no comprehensive and complete paradigm or clear framework, and due to the high financial volume of technology giants, most of these studies have focused on profitable areas such as gaming and entertainment. The motivation and purpose of this article are to introduce a prospective metaverse paradigm based on the revised reality-virtuality continuum and provide a new supporting taxonomy with the three dimensions of interaction, immersion, and extent of world knowledge to develop and strengthen the theoretical foundations of the metaverse and help researchers. Furthermore, there is still no comprehensive and agreed-upon conceptual framework for the metaverse. To this end, by reviewing the research literature, discovering the important components of technological building blocks, especially digital twins, and presenting a new concept called meta-twins, a prospective conceptual framework based on the revised reality-virtuality continuum with a new supporting taxonomy was presented.
{"title":"A Prospective Metaverse Paradigm Based on the Reality-Virtuality Continuum and Digital Twins","authors":"Abolfazl Zare, Aliakbar Jalali","doi":"10.2174/0126662558294125240307094426","DOIUrl":"https://doi.org/10.2174/0126662558294125240307094426","url":null,"abstract":"\u0000\u0000After decades of introducing the concept of virtual reality, the expansion, and significant\u0000advances of technologies and innovations, such as 6g, edge computing, the internet of\u0000things, robotics, artificial intelligence, blockchain, quantum computing, and digital twins, the\u0000world is on the cusp of a new revolution. By moving through the three stages of the digital\u0000twin, digital native, and finally surrealist, the metaverse has created a new vision of the future\u0000of human and societal life so that we are likely to face the next generation of societies (perhaps\u0000society 6) in the not too distant future. However, until then, the reality has been that the\u0000metaverse is still in its infancy, perhaps where the internet was in 1990. There is still no single\u0000definition, few studies have been conducted, there is no comprehensive and complete paradigm\u0000or clear framework, and due to the high financial volume of technology giants, most of these\u0000studies have focused on profitable areas such as gaming and entertainment. The motivation and\u0000purpose of this article are to introduce a prospective metaverse paradigm based on the revised\u0000reality-virtuality continuum and provide a new supporting taxonomy with the three dimensions\u0000of interaction, immersion, and extent of world knowledge to develop and strengthen the theoretical\u0000foundations of the metaverse and help researchers. Furthermore, there is still no comprehensive\u0000and agreed-upon conceptual framework for the metaverse. To this end, by reviewing\u0000the research literature, discovering the important components of technological building\u0000blocks, especially digital twins, and presenting a new concept called meta-twins, a prospective\u0000conceptual framework based on the revised reality-virtuality continuum with a new supporting\u0000taxonomy was presented.\u0000","PeriodicalId":506582,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140257298","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 : 2024-03-01DOI: 10.2174/0126662558286885240223093414
Pradeep Kumar N.S, M. P. Kantipudi, Praveen N, Suresh S, Dr Rajanikanth Aluvalu, Jayant Jagtap
The attacks on IoT systems are increasing as the devices and communication networks are progressively integrated. If no attacks are found in IoT for a long time, it will affect the availability of services that can result in data leaks and can create a significant impact on the associated costs and quality of services. Therefore, the attacks and security vulnerability in the IoT ecosystem must be detected to provide robust security and defensive mechanisms for real-time applications. This paper proposes an analytical design of an intelligent attack detection framework using multiple machine learning techniques to provide cost-effective and efficient security analysis services in the IoT ecosystem. The performance validation of the proposed framework is carried out by multiple performance indicators. The simulation outcome exhibits the effectiveness of the proposed system in terms of accuracy and F1-score for the detection of various types of attacking scenarios.
{"title":"A Security Analysis Model for IoT-ecosystem Using Machine Learning-\u0000(ML) Approach","authors":"Pradeep Kumar N.S, M. P. Kantipudi, Praveen N, Suresh S, Dr Rajanikanth Aluvalu, Jayant Jagtap","doi":"10.2174/0126662558286885240223093414","DOIUrl":"https://doi.org/10.2174/0126662558286885240223093414","url":null,"abstract":"\u0000\u0000The attacks on IoT systems are increasing as the devices and communication\u0000networks are progressively integrated. If no attacks are found in IoT for a long time, it\u0000will affect the availability of services that can result in data leaks and can create a significant\u0000impact on the associated costs and quality of services. Therefore, the attacks and security vulnerability\u0000in the IoT ecosystem must be detected to provide robust security and defensive\u0000mechanisms for real-time applications.\u0000\u0000\u0000\u0000This paper proposes an analytical design of an intelligent attack detection framework\u0000using multiple machine learning techniques to provide cost-effective and efficient security\u0000analysis services in the IoT ecosystem.\u0000\u0000\u0000\u0000The performance validation of the proposed framework is carried out by multiple performance\u0000indicators.\u0000\u0000\u0000\u0000The simulation outcome exhibits the effectiveness of the proposed system in\u0000terms of accuracy and F1-score for the detection of various types of attacking scenarios.\u0000","PeriodicalId":506582,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":" 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140091041","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：