Journal of King Saud University-Computer and Information Sciences最新文献

Unmanned combat aerial vehicle path planning in complex environment using multi-strategy sparrow search algorithm with double-layer coding 基于双层编码的多策略麻雀搜索算法的复杂环境下无人机路径规划

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102255

Liangdong Qu , Jingkun Fan

Unmanned combat aerial vehicles (UCAV) path planning in complex environments demands a substantial number of path points to determine feasible paths. Establishing an effective flight path for UCAVs requires numerous path points to account for fuel constraints, artillery threats, and radar avoidance. This increase in path points raises the dimensionality of the problem, which in turn degrades algorithm performance. To mitigate this issue, a double-layer coding (DLC) model is utilized to remove redundant path points, consequently lowering computational complexity and operational difficulties. Meanwhile, this paper introduces a novel enhanced sparrow search algorithm (MESSA) based on multi-strategy for UCAV path planning. The MESSA incorporates a novel dynamic fitness regulation learning strategy (DFRL), a random differential learning strategy (RDL), an elite example equilibrium learning strategy (EEEL), a dynamic elimination and regeneration strategy based on the elite example (DERE), and quadratic interpolation (QI). Furthermore, MESSA is compared against 11 state-of-the-art algorithms, demonstrating exceptional optimization performance and robustness. Additionally, the combination of MESSA with the DLC model (DLC-MESSA) is applied to solve the UCAV path planning problem. The experimental results from five complex environments indicate that DLC-MESSA outperforms other algorithms in 80% of the cases by achieving the lowest average cost, thereby demonstrating its superior robustness and computational efficiency.

复杂环境下的无人机路径规划需要大量路径点来确定可行路径。为无人驾驶飞机建立有效的飞行路径需要许多路径点来考虑燃料限制、火炮威胁和雷达规避。路径点的增加提高了问题的维度，这反过来又降低了算法的性能。为了解决这一问题，采用双层编码（DLC）模型去除冗余路径点，从而降低了计算复杂度和操作难度。同时，提出了一种新的基于多策略的增强型麻雀搜索算法（MESSA）用于无人机路径规划。MESSA包含了一种新的动态适应度调节学习策略（DFRL）、随机差分学习策略（RDL）、精英样本均衡学习策略（EEEL）、基于精英样本的动态消除和再生策略（DERE）和二次插值（QI）。此外，将MESSA与11种最先进的算法进行了比较，证明了卓越的优化性能和鲁棒性。此外，将MESSA与DLC模型相结合（DLC-MESSA）用于解决无人机的路径规划问题。五个复杂环境的实验结果表明，在80%的情况下，DLC-MESSA算法的平均成本最低，优于其他算法，从而证明了其优越的鲁棒性和计算效率。

{"title":"Unmanned combat aerial vehicle path planning in complex environment using multi-strategy sparrow search algorithm with double-layer coding","authors":"Liangdong Qu , Jingkun Fan","doi":"10.1016/j.jksuci.2024.102255","DOIUrl":"10.1016/j.jksuci.2024.102255","url":null,"abstract":"<div><div>Unmanned combat aerial vehicles (UCAV) path planning in complex environments demands a substantial number of path points to determine feasible paths. Establishing an effective flight path for UCAVs requires numerous path points to account for fuel constraints, artillery threats, and radar avoidance. This increase in path points raises the dimensionality of the problem, which in turn degrades algorithm performance. To mitigate this issue, a double-layer coding (DLC) model is utilized to remove redundant path points, consequently lowering computational complexity and operational difficulties. Meanwhile, this paper introduces a novel enhanced sparrow search algorithm (MESSA) based on multi-strategy for UCAV path planning. The MESSA incorporates a novel dynamic fitness regulation learning strategy (DFRL), a random differential learning strategy (RDL), an elite example equilibrium learning strategy (EEEL), a dynamic elimination and regeneration strategy based on the elite example (DERE), and quadratic interpolation (QI). Furthermore, MESSA is compared against 11 state-of-the-art algorithms, demonstrating exceptional optimization performance and robustness. Additionally, the combination of MESSA with the DLC model (DLC-MESSA) is applied to solve the UCAV path planning problem. The experimental results from five complex environments indicate that DLC-MESSA outperforms other algorithms in 80% of the cases by achieving the lowest average cost, thereby demonstrating its superior robustness and computational efficiency.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102255"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving clustering-based and adaptive position-aware interpolation oversampling for imbalanced data classification 改进基于聚类和自适应位置感知的插值超采样，实现不平衡数据分类

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102253

Yujiang Wang , Marshima Mohd Rosli , Norzilah Musa , Lei Wang

Class imbalance is one of the most significant difficulties in modern machine learning. This is because of the inherent bias of standard classifiers toward favoring majority instances while often ignoring minority instances. Interpolation-based oversampling techniques are among the most popular solutions for generating synthetic minority samples to correct imbalanced class distributions. However, synthetic minority samples have a risk of overlapping with the majority-class samples. Inappropriate interpolation of minority samples during oversampling can also result in over generalization. To overcome these drawbacks, we propose a Clustering-based and Adaptive Position-aware Interpolation Oversampling algorithm (CAPAIO) for imbalanced binary dataset classification. CAPAIO initially employs an improved density-based clustering algorithm to group minority instances into inland, borderline, and trapped samples. It then adaptively determines the size of each subcluster and allocates weights to minority samples, guiding the synthesis of minority samples based on these weights. Finally, distinct interpolation oversampling algorithms are individually performed on these three categories of minority samples. The experimental results demonstrate the effectiveness of the proposed CAPAIO in most datasets compared with eleven other oversampling algorithms.

{"title":"Improving clustering-based and adaptive position-aware interpolation oversampling for imbalanced data classification","authors":"Yujiang Wang , Marshima Mohd Rosli , Norzilah Musa , Lei Wang","doi":"10.1016/j.jksuci.2024.102253","DOIUrl":"10.1016/j.jksuci.2024.102253","url":null,"abstract":"<div><div>Class imbalance is one of the most significant difficulties in modern machine learning. This is because of the inherent bias of standard classifiers toward favoring majority instances while often ignoring minority instances. Interpolation-based oversampling techniques are among the most popular solutions for generating synthetic minority samples to correct imbalanced class distributions. However, synthetic minority samples have a risk of overlapping with the majority-class samples. Inappropriate interpolation of minority samples during oversampling can also result in over generalization. To overcome these drawbacks, we propose a Clustering-based and Adaptive Position-aware Interpolation Oversampling algorithm (CAPAIO) for imbalanced binary dataset classification. CAPAIO initially employs an improved density-based clustering algorithm to group minority instances into inland, borderline, and trapped samples. It then adaptively determines the size of each subcluster and allocates weights to minority samples, guiding the synthesis of minority samples based on these weights. Finally, distinct interpolation oversampling algorithms are individually performed on these three categories of minority samples. The experimental results demonstrate the effectiveness of the proposed CAPAIO in most datasets compared with eleven other oversampling algorithms.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102253"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On the robustness of arabic aspect-based sentiment analysis: A comprehensive exploration of transformer-based models 基于阿拉伯语方面的情感分析的稳健性：基于转换器模型的全面探索

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102264

Alanod AlMasaud, Heyam H. Al-Baity

In the era of rapid technological advancement, users generate an overwhelming volume of data on social media networks and e-commerce platforms daily. This data, rich in opinions, sentiments, values, and habits, holds immense value for both consumers and businesses. Leveraging this unstructured data manually is error-prone and time-consuming. The field of Sentiment Analysis automates the process of analyzing human opinions from this data. Sentiment Analysis classifies text into positive, negative, or neutral sentiments. However, it confines text classification to a single sentiment polarity, providing a broad overview without accounting for specific aspects. With the growing demand for data analysis, this standard sentiment polarity classification is no longer sufficient. Aspect-Based Sentiment Analysis has emerged to dig deeper into the text, uncovering perspectives and points of view. It can identify multiple aspects in text with corresponding sentiment polarity. Therefore, interest in this field has increased and many research efforts have been devoted recently to tackle this problem for the English language. Unfortunately, there is a scarcity of Arabic research in this field. This study will address the aforementioned deficiency by investigating the potential of four transformer models namely, AraBERT v2.0, ArBERT, MARBERT, and Multilingual BERT in enhancing the accuracy of Aspect-Based Sentiment Analysis for Arabic texts using two dedicated corpora (AraMA and AraMAMS). The extensive experiments revealed that the proposed approach achieved its expected effect surpassing the results of previous studies in the field. The best results of Aspect Category Detection and Aspect Sentiment Classification tasks in AraMA corpus were obtained by using AraBERT v2.0 with F1-Measure result equals to 95.75% and 92.83% respectively. In addition, the best result of Aspect Category Detection and Aspect Sentiment Classification tasks in AraMAMS corpus were achieved by using AraBERT v2.0 with F1-Measure result equals to 95.54% and 89.52% respectively.

在技术飞速发展的时代，用户每天都会在社交媒体网络和电子商务平台上产生大量数据。这些数据蕴含着丰富的观点、情感、价值观和习惯，对消费者和企业都具有巨大的价值。手动利用这些非结构化数据既容易出错，又耗费时间。情感分析领域可自动分析这些数据中的人类观点。情感分析将文本分为正面、负面或中性情感。然而，它将文本分类局限于单一的情感极性，只提供了一个广泛的概述，而没有考虑到具体的方面。随着数据分析需求的不断增长，这种标准的情感极性分类已不再足够。基于方面的情感分析法应运而生，它能深入挖掘文本，揭示观点和视角。它可以识别文本中具有相应情感极性的多个方面。因此，人们对这一领域的兴趣与日俱增，近来许多研究人员都致力于解决英语语言中的这一问题。遗憾的是，阿拉伯语在这一领域的研究却很少。本研究将针对上述不足，使用两个专用语料库（AraMA 和 AraMAMS）研究四种转换器模型（即 AraBERT v2.0、ArBERT、MARBERT 和多语言 BERT）在提高阿拉伯语文本基于方面的情感分析准确性方面的潜力。大量实验表明，所提出的方法达到了预期效果，超过了该领域以往的研究结果。通过使用 AraBERT v2.0，AraMA 语料库中的方面类别检测和方面情感分类任务获得了最佳结果，F1-Measure 结果分别为 95.75% 和 92.83%。此外，在 AraMAMS 语料库中，使用 AraBERT v2.0 进行的方面类别检测和方面情感分类任务取得了最佳结果，F1-Measure 结果分别为 95.54% 和 89.52%。

{"title":"On the robustness of arabic aspect-based sentiment analysis: A comprehensive exploration of transformer-based models","authors":"Alanod AlMasaud, Heyam H. Al-Baity","doi":"10.1016/j.jksuci.2024.102264","DOIUrl":"10.1016/j.jksuci.2024.102264","url":null,"abstract":"<div><div>In the era of rapid technological advancement, users generate an overwhelming volume of data on social media networks and e-commerce platforms daily. This data, rich in opinions, sentiments, values, and habits, holds immense value for both consumers and businesses. Leveraging this unstructured data manually is error-prone and time-consuming. The field of Sentiment Analysis automates the process of analyzing human opinions from this data. Sentiment Analysis classifies text into positive, negative, or neutral sentiments. However, it confines text classification to a single sentiment polarity, providing a broad overview without accounting for specific aspects. With the growing demand for data analysis, this standard sentiment polarity classification is no longer sufficient. Aspect-Based Sentiment Analysis has emerged to dig deeper into the text, uncovering perspectives and points of view. It can identify multiple aspects in text with corresponding sentiment polarity. Therefore, interest in this field has increased and many research efforts have been devoted recently to tackle this problem for the English language. Unfortunately, there is a scarcity of Arabic research in this field. This study will address the aforementioned deficiency by investigating the potential of four transformer models namely, AraBERT v2.0, ArBERT, MARBERT, and Multilingual BERT in enhancing the accuracy of Aspect-Based Sentiment Analysis for Arabic texts using two dedicated corpora (AraMA and AraMAMS). The extensive experiments revealed that the proposed approach achieved its expected effect surpassing the results of previous studies in the field. The best results of Aspect Category Detection and Aspect Sentiment Classification tasks in AraMA corpus were obtained by using AraBERT v2.0 with F1-Measure result equals to 95.75% and 92.83% respectively. In addition, the best result of Aspect Category Detection and Aspect Sentiment Classification tasks in AraMAMS corpus were achieved by using AraBERT v2.0 with F1-Measure result equals to 95.54% and 89.52% respectively.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102264"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Picking point identification and localization method based on swin-transformer for high-quality tea

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102262

Zhiyao Pan, Jinan Gu, Wenbo Wang, Xinling Fang, Zilin Xia, Qihang Wang, Mengni Wang

In the nature scene, because of the high degree of similarity between the background and the tea buds, as well as the different growth postures of the tea buds, finding and precisely identifying the picking point is challenging. To solve these issues, this paper proposes a precise way to find the best picking point for tea buds by combining traditional algorithms with Swin-Transformer-based target detection and semantic segmentation algorithms, namely SORC-SFT. Firstly, an improved target detection algorithm, Swin-Oriented R-CNN (SORC), is used to realize the recognition of four types of high-quality tea. The mean Average Precision (mAP) of the four categories was 82.3% after replacing the feature fusion network FPN with PAFPN and adding the Coordinate Attention (CA) mechanism. Secondly, the corresponding segmentation mask of the four recognized categories is obtained by adding Semask, Feature Alignment Module (FAM), and Feature Selection Module (FSM) to the improved semantic segmentation algorithm Semask-Fa-Transformer (SFT). The mean Intersection over Union (mIoU) of the semantic segmentation algorithm for each category is 89.83%, 91.97%, 88.85%, and 89.68%, respectively. Finally, the morphology of different categories of tea buds is analyzed, and the traditional algorithm is used to realize the accurate localization of the identified tea buds. For the four tested categories, the proportion of correct samples in locating picking points is 96.18%, 91.28%, 93.85%, and 90.58%, respectively. The experimental results show that, out of all the algorithms, the proposed picking point identification and localization approach has the best performance and will make a strong contribution to the accurate identification of tea leaves during the intelligent picking process.

在自然场景中，由于背景与茶芽的相似度较高，且茶芽的生长姿态各不相同，因此寻找并精确识别采摘点具有一定的挑战性。为了解决这些问题，本文通过将传统算法与基于斯文变换器的目标检测和语义分割算法（即 SORC-SFT）相结合，提出了一种精确寻找茶芽最佳采摘点的方法。首先，使用改进的目标检测算法 Swin-Oriented R-CNN (SORC) 实现对四种优质茶叶的识别。将特征融合网络 FPN 替换为 PAFPN 并加入坐标注意（CA）机制后，四类茶叶的平均精度（mAP）为 82.3%。其次，在改进的语义分割算法 Semask-Fa-Transformer（SFT）中加入 Semask、特征对齐模块（FAM）和特征选择模块（FSM），得到四个识别类别的相应分割掩码。每个类别的语义分割算法的平均交集大于联合率（mIoU）分别为 89.83%、91.97%、88.85% 和 89.68%。最后，对不同类别的茶芽进行形态分析，并利用传统算法实现对识别出的茶芽的精确定位。对于四个测试类别，采摘点定位的正确样本比例分别为 96.18%、91.28%、93.85% 和 90.58%。实验结果表明，在所有算法中，所提出的采摘点识别和定位方法性能最佳，将为智能采摘过程中茶叶的准确识别做出有力贡献。

{"title":"Picking point identification and localization method based on swin-transformer for high-quality tea","authors":"Zhiyao Pan, Jinan Gu, Wenbo Wang, Xinling Fang, Zilin Xia, Qihang Wang, Mengni Wang","doi":"10.1016/j.jksuci.2024.102262","DOIUrl":"10.1016/j.jksuci.2024.102262","url":null,"abstract":"<div><div>In the nature scene, because of the high degree of similarity between the background and the tea buds, as well as the different growth postures of the tea buds, finding and precisely identifying the picking point is challenging. To solve these issues, this paper proposes a precise way to find the best picking point for tea buds by combining traditional algorithms with Swin-Transformer-based target detection and semantic segmentation algorithms, namely SORC-SFT. Firstly, an improved target detection algorithm, Swin-Oriented R-CNN (SORC), is used to realize the recognition of four types of high-quality tea. The mean Average Precision (mAP) of the four categories was 82.3% after replacing the feature fusion network FPN with PAFPN and adding the Coordinate Attention (CA) mechanism. Secondly, the corresponding segmentation mask of the four recognized categories is obtained by adding Semask, Feature Alignment Module (FAM), and Feature Selection Module (FSM) to the improved semantic segmentation algorithm Semask-Fa-Transformer (SFT). The mean Intersection over Union (mIoU) of the semantic segmentation algorithm for each category is 89.83%, 91.97%, 88.85%, and 89.68%, respectively. Finally, the morphology of different categories of tea buds is analyzed, and the traditional algorithm is used to realize the accurate localization of the identified tea buds. For the four tested categories, the proportion of correct samples in locating picking points is 96.18%, 91.28%, 93.85%, and 90.58%, respectively. The experimental results show that, out of all the algorithms, the proposed picking point identification and localization approach has the best performance and will make a strong contribution to the accurate identification of tea leaves during the intelligent picking process.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102262"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semi-supervised learning for skeleton behavior recognition: A multi-dimensional graph comparison approach

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102266

Qiang Zhao , Moyan Zhang , Hongjuan Li , Baozhen Song , Yujun Li

Skeleton-based action recognition, as a crucial research direction in computer vision, confronts numerous issues and challenges. Most existing research methods rely heavily on extensive labeled data for training, which significantly constraints their training effectiveness and generalization capability when labeled data is scarce. Consequently, how to integrate labeled and unlabeled data to overcome the limitations imposed by label scarcity has emerged as a pivotal research focus in skeleton-based action recognition. Targeting this label scarcity problem, this paper introduces a semi-supervised skeleton-based action recognition approach leveraging multi-dimensional feature-based graph contrastive learning. Firstly, three feature extractors are devised to extract and exploit the available informative cues from limited data thoroughly. The holistic feature extractor comprises five spatio-temporal graph convolutional blocks and a global average pooling layer. The detailed feature extractor is constructed by stacking the same spatio-temporal graph convolutional blocks, while the relational feature extractor primarily integrates stacked attention graph convolutional blocks and a global average pooling layer. Secondly, the sample relationship construction mechanism in graph contrastive learning is enhanced. A clustering process is employed to formulate soft positive/negative sample pairs based on sample similarity, and a sample connectivity matrix further weights the distances between these pairs, thereby enhancing classification accuracy. Furthermore, a novel loss function grounded in the information bottleneck theory is formulated to guide the model towards learning more robust and efficient skeleton action representations. Experimental evaluations demonstrate the superiority of our proposed method (MDKS) on two datasets, NTU60 and NW-UCLA. Specifically, on the NTU60 dataset, MDKS achieves classification accuracy improvements of 4.7% and 1.9% under the X-sub and X-view evaluation protocols, respectively, compared to the benchmark MAC-Learning method. On the NW-UCLA dataset, MDKS outperforms MAC-Learning by 1.4%, 1.2%, 1.9%, and 1.4% in classification accuracy under different labeled data ratios ranging from 5% to 40%. This work offers novel insights and methodologies for advancing skeleton-based action recognition. Future research will delve into label imbalance, label noise, multi-modal information fusion, and cross-scene generalization capabilities.

{"title":"Semi-supervised learning for skeleton behavior recognition: A multi-dimensional graph comparison approach","authors":"Qiang Zhao , Moyan Zhang , Hongjuan Li , Baozhen Song , Yujun Li","doi":"10.1016/j.jksuci.2024.102266","DOIUrl":"10.1016/j.jksuci.2024.102266","url":null,"abstract":"<div><div>Skeleton-based action recognition, as a crucial research direction in computer vision, confronts numerous issues and challenges. Most existing research methods rely heavily on extensive labeled data for training, which significantly constraints their training effectiveness and generalization capability when labeled data is scarce. Consequently, how to integrate labeled and unlabeled data to overcome the limitations imposed by label scarcity has emerged as a pivotal research focus in skeleton-based action recognition. Targeting this label scarcity problem, this paper introduces a semi-supervised skeleton-based action recognition approach leveraging multi-dimensional feature-based graph contrastive learning. Firstly, three feature extractors are devised to extract and exploit the available informative cues from limited data thoroughly. The holistic feature extractor comprises five spatio-temporal graph convolutional blocks and a global average pooling layer. The detailed feature extractor is constructed by stacking the same spatio-temporal graph convolutional blocks, while the relational feature extractor primarily integrates stacked attention graph convolutional blocks and a global average pooling layer. Secondly, the sample relationship construction mechanism in graph contrastive learning is enhanced. A clustering process is employed to formulate soft positive/negative sample pairs based on sample similarity, and a sample connectivity matrix further weights the distances between these pairs, thereby enhancing classification accuracy. Furthermore, a novel loss function grounded in the information bottleneck theory is formulated to guide the model towards learning more robust and efficient skeleton action representations. Experimental evaluations demonstrate the superiority of our proposed method (MDKS) on two datasets, NTU60 and NW-UCLA. Specifically, on the NTU60 dataset, MDKS achieves classification accuracy improvements of 4.7% and 1.9% under the X-sub and X-view evaluation protocols, respectively, compared to the benchmark MAC-Learning method. On the NW-UCLA dataset, MDKS outperforms MAC-Learning by 1.4%, 1.2%, 1.9%, and 1.4% in classification accuracy under different labeled data ratios ranging from 5% to 40%. This work offers novel insights and methodologies for advancing skeleton-based action recognition. Future research will delve into label imbalance, label noise, multi-modal information fusion, and cross-scene generalization capabilities.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102266"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A secure, privacy-preserving, and cost-efficient decentralized cloud storage framework using blockchain

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102260

Swatisipra Das , Minati Mishra , Rojalina Priyadarshini , Rabindra Kumar Barik , Manob Jyoti Saikia

Cloud services benefit countless users worldwide due to notable features, such as on-demand self-service, scalability, easy maintenance, etc. Secure storage and access to data in the cloud is critical. Cloud Identity and Access Management (IAM) service, which acts in a centralized way to provide access requests to the authenticated users. Controlled access sometimes fails to preserve the privacy of the sensitive information stored in the cloud due to several reasons, such as insider attacks, breaches of data security, or any other types of unauthorized access. This paper suggests a blockchain-assisted secure storage and access mechanism to secure sensitive data. Here blockchain is used as a trust management entity that verifies the identity of the user. Along with this it issues the Access Control Lists (ACLs) and identity token, and at the same time, it records all the interactions between the users and service providers. Data transmission is transparent since transactions are recorded. Importance is given to user privacy and decryption keys security. Linear(t,n) secret sharing scheme is used for key share generation and distribution. For experimentation, in MetaMask cryptocurrency wallet Goerli test network is used. Results reveal that our model consumes less cost to execute than other existing works. The total execution cost to upload and download a data file is 0.00281392 and 0.02455307 GoerliETH. Where the all verification operations such as identity token, ACL, access_log, and data integrity are executed in Zero gas value. The proposed model maintains a constant gas cost regardless of transaction volume, with costs of 33.04 ETH and 32.24 ETH for data upload and download. Moreover, we present a comparison of execution time performance in three different system configurations.

云服务具有按需自助服务、可扩展性、易于维护等显著特点，使全球无数用户受益。在云中安全存储和访问数据至关重要。云身份和访问管理（IAM）服务以集中方式向经过验证的用户提供访问请求。受控访问有时无法保护存储在云中的敏感信息的隐私，原因有多种，如内部攻击、数据安全漏洞或任何其他类型的未经授权的访问。本文提出了一种区块链辅助安全存储和访问机制，以确保敏感数据的安全。在这里，区块链被用作验证用户身份的信任管理实体。与此同时，它还会发布访问控制列表（ACL）和身份令牌，并记录用户与服务提供商之间的所有互动。由于交易被记录在案，因此数据传输是透明的。用户隐私和解密密钥安全受到重视。线性（t,n）秘密共享方案用于密钥共享的生成和分配。在实验中，MetaMask 加密货币钱包使用了 Goerli 测试网络。结果表明，与其他现有作品相比，我们的模型执行成本更低。上传和下载数据文件的总执行成本分别为 0.00281392 GoerliETH 和 0.02455307 GoerliETH。所有验证操作，如身份令牌、ACL、access_log 和数据完整性，都在零气体值中执行。无论交易量大小，拟议模型都能保持恒定的气体成本，数据上传和下载的成本分别为 33.04 ETH 和 32.24 ETH。此外，我们还比较了三种不同系统配置下的执行时间性能。

{"title":"A secure, privacy-preserving, and cost-efficient decentralized cloud storage framework using blockchain","authors":"Swatisipra Das , Minati Mishra , Rojalina Priyadarshini , Rabindra Kumar Barik , Manob Jyoti Saikia","doi":"10.1016/j.jksuci.2024.102260","DOIUrl":"10.1016/j.jksuci.2024.102260","url":null,"abstract":"<div><div>Cloud services benefit countless users worldwide due to notable features, such as on-demand self-service, scalability, easy maintenance, etc. Secure storage and access to data in the cloud is critical. Cloud Identity and Access Management (IAM) service, which acts in a centralized way to provide access requests to the authenticated users. Controlled access sometimes fails to preserve the privacy of the sensitive information stored in the cloud due to several reasons, such as insider attacks, breaches of data security, or any other types of unauthorized access. This paper suggests a blockchain-assisted secure storage and access mechanism to secure sensitive data. Here blockchain is used as a trust management entity that verifies the identity of the user. Along with this it issues the Access Control Lists (ACLs) and identity token, and at the same time, it records all the interactions between the users and service providers. Data transmission is transparent since transactions are recorded. Importance is given to user privacy and decryption keys security. Linear(t,n) secret sharing scheme is used for key share generation and distribution. For experimentation, in MetaMask cryptocurrency wallet Goerli test network is used. Results reveal that our model consumes less cost to execute than other existing works. The total execution cost to upload and download a data file is 0.00281392 and 0.02455307 GoerliETH. Where the all verification operations such as identity token, ACL, access_log, and data integrity are executed in Zero gas value. The proposed model maintains a constant gas cost regardless of transaction volume, with costs of 33.04 ETH and 32.24 ETH for data upload and download. Moreover, we present a comparison of execution time performance in three different system configurations.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102260"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing stock market predictions via hybrid external trend and internal components analysis and long short term memory model

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102252

Fatene Dioubi , Negalign Wake Hundera , Huiying Xu , Xinzhong Zhu

When it comes to financial decision-making, stock market predictability is extremely important since it offers valuable information that may guide investment strategies, risk management, and portfolio allocation overall. Traditional methods often fail to accurately predict stock prices due to their complexity and inability to handle non-linear and non-stationary patterns in market data. To address these issues, this study introduces an innovative model that combines the External Trend and Internal Components Analysis decomposition method (ETICA) with the Long Short-Term Memory (LSTM) model, aiming to enhance stock market predictions for S&P 500, NASDAQ, Dow Jones, SSE and SZSE indices. Through rigorous testing across various training data proportions and epoch settings, our findings reveal that the proposed hybrid model outperforms the single LSTM model, delivering significantly lower Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) values. This enhanced precision reduces prediction errors, underscoring the model’s robustness and reliability. The superior performance of the ETICA-LSTM model highlights its potential as a powerful financial forecasting tool, promising to transform investment strategies, optimize risk management, and enhance portfolio performance.

在金融决策方面，股票市场的可预测性极为重要，因为它提供了宝贵的信息，可以指导投资策略、风险管理和投资组合的整体配置。传统方法由于其复杂性以及无法处理市场数据中的非线性和非平稳模式，往往无法准确预测股票价格。为了解决这些问题，本研究引入了一个创新模型，将外部趋势和内部成分分析分解法（ETICA）与长短期记忆（LSTM）模型相结合，旨在提高对 S&P 500、纳斯达克、道琼斯、上证和深证指数的股市预测能力。通过对各种训练数据比例和历时设置进行严格测试，我们的研究结果表明，所提出的混合模型优于单一的 LSTM 模型，其均方根误差（RMSE）和平均绝对误差（MAE）值明显降低。精度的提高减少了预测误差，凸显了模型的鲁棒性和可靠性。ETICA-LSTM 模型的卓越性能彰显了其作为强大的金融预测工具的潜力，有望改变投资策略、优化风险管理并提高投资组合绩效。

{"title":"Enhancing stock market predictions via hybrid external trend and internal components analysis and long short term memory model","authors":"Fatene Dioubi , Negalign Wake Hundera , Huiying Xu , Xinzhong Zhu","doi":"10.1016/j.jksuci.2024.102252","DOIUrl":"10.1016/j.jksuci.2024.102252","url":null,"abstract":"<div><div>When it comes to financial decision-making, stock market predictability is extremely important since it offers valuable information that may guide investment strategies, risk management, and portfolio allocation overall. Traditional methods often fail to accurately predict stock prices due to their complexity and inability to handle non-linear and non-stationary patterns in market data. To address these issues, this study introduces an innovative model that combines the External Trend and Internal Components Analysis decomposition method (ETICA) with the Long Short-Term Memory (LSTM) model, aiming to enhance stock market predictions for S&P 500, NASDAQ, Dow Jones, SSE and SZSE indices. Through rigorous testing across various training data proportions and epoch settings, our findings reveal that the proposed hybrid model outperforms the single LSTM model, delivering significantly lower Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) values. This enhanced precision reduces prediction errors, underscoring the model’s robustness and reliability. The superior performance of the ETICA-LSTM model highlights its potential as a powerful financial forecasting tool, promising to transform investment strategies, optimize risk management, and enhance portfolio performance.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102252"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A hierarchical and secure approach for automotive firmware upgrades

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102258

Feng Luo , Zhihao Li , Jiajia Wang , Cheng Luo , Hongqian Liu , Dengcheng Liu

With the development of intelligent and connected vehicles, the expansion of software necessitates an increased significance and frequency of automotive firmware upgrades. The abundance of potential attack vectors and valuable data renders these upgrades enticing targets for attackers. However, the prevailing security services used for automotive firmware upgrades are no longer sufficient to meet security requirements. Hence, this paper proposes a Secure Automotive Firmware Upgrade Approach (SAFUA), aimed at enhancing authentication and communication security during automotive firmware upgrades. To address the heterogeneous performance of in-vehicle nodes and diverse application contexts, this approach introduces multiple authentication modes tailored to various upgrade scenarios. Moreover, hierarchical authentication and secure communication strategies are designed to achieve a balance between security and efficiency requirements. Consolidating these methodologies, a standardized automotive firmware upgrade process is delineated. Formal and informal verification of the proposed approach is conducted to attest its security efficacy. Furthermore, a simulated vehicular environment is constructed to evaluate the temporal and spatial efficiency of the approach across diverse bus and device configurations. The results confirm the adaptability of the secure upgrade approach outlined herein to the automotive firmware upgrade landscape, offering robust security alongside enhanced upgrade efficiency.

{"title":"A hierarchical and secure approach for automotive firmware upgrades","authors":"Feng Luo , Zhihao Li , Jiajia Wang , Cheng Luo , Hongqian Liu , Dengcheng Liu","doi":"10.1016/j.jksuci.2024.102258","DOIUrl":"10.1016/j.jksuci.2024.102258","url":null,"abstract":"<div><div>With the development of intelligent and connected vehicles, the expansion of software necessitates an increased significance and frequency of automotive firmware upgrades. The abundance of potential attack vectors and valuable data renders these upgrades enticing targets for attackers. However, the prevailing security services used for automotive firmware upgrades are no longer sufficient to meet security requirements. Hence, this paper proposes a Secure Automotive Firmware Upgrade Approach (SAFUA), aimed at enhancing authentication and communication security during automotive firmware upgrades. To address the heterogeneous performance of in-vehicle nodes and diverse application contexts, this approach introduces multiple authentication modes tailored to various upgrade scenarios. Moreover, hierarchical authentication and secure communication strategies are designed to achieve a balance between security and efficiency requirements. Consolidating these methodologies, a standardized automotive firmware upgrade process is delineated. Formal and informal verification of the proposed approach is conducted to attest its security efficacy. Furthermore, a simulated vehicular environment is constructed to evaluate the temporal and spatial efficiency of the approach across diverse bus and device configurations. The results confirm the adaptability of the secure upgrade approach outlined herein to the automotive firmware upgrade landscape, offering robust security alongside enhanced upgrade efficiency.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102258"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143179572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

T-SRE: Transformer-based semantic Relation extraction for contextual paraphrased plagiarism detection T-SRE：基于转换的语义关系提取，用于上下文释义抄袭检测

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102257

Pon Abisheka , C. Deisy , P. Sharmila

Plagiarism has become a pervasive issue in academics and professionals to safeguard academic integrity and intellectual property rights. The escalating sophistication of plagiarized content through semantic manipulation and structural reorganization poses significant challenges to existing detection systems that rely primarily on lexical similarity measures. The proposed T-SRE (Transformer-based Semantic Relation Extraction), a novel framework addresses the limitations of traditional n-gram and string-matching approaches by leveraging deep semantic analysis. The proposed framework combines Dependency Parsing (DP) for syntactic relationship mapping and Named Entity Recognition (NER) for contextual entity identification, augmented by a transformer-based neural network that captures long-range contextual dependencies. This learning methodology incorporates three key components: a position-aware word reordering algorithm, Levenshtein distance metric for structural similarity, and contextual word embeddings for semantic preservation detection. The proposed T-SRE enhances text structure recognition by combining position-aware reordering with semantic preservation through ensemble learning. The system implements a hierarchical classification scheme that quantifies plagiarism severity through a four-tier taxonomy: heavy, low, non-plagiarized and verbatim copy. The Udacity benchmark dataset showcases the model’s superior detection capabilities, achieving 92% precision, 89% recall, and an F1-score of 90.5%, particularly in lightweight textual modifications.The framework achieves a granularity score of 1.28, outperforming existing approaches.

为了维护学术诚信和知识产权，剽窃已成为学术界和专业人士普遍存在的问题。通过语义操纵和结构重组不断升级的剽窃内容复杂性对主要依赖词汇相似性度量的现有检测系统提出了重大挑战。本文提出的基于变换的语义关系提取（T-SRE）框架利用深度语义分析解决了传统n图和字符串匹配方法的局限性。该框架结合了用于句法关系映射的依赖解析（DP）和用于上下文实体识别的命名实体识别（NER），并通过基于转换器的神经网络进行增强，以捕获远程上下文依赖关系。该学习方法包含三个关键组件：位置感知词重排算法，用于结构相似性的Levenshtein距离度量，以及用于语义保存检测的上下文词嵌入。本文提出的T-SRE通过集成学习将位置感知重排序和语义保存相结合来增强文本结构识别。该系统实现了一种分层分类方案，通过四层分类来量化抄袭的严重程度：重抄袭、低抄袭、非抄袭和逐字抄袭。Udacity基准数据集展示了该模型卓越的检测能力，达到了92%的准确率、89%的召回率和90.5%的f1分数，特别是在轻量级文本修改方面。该框架的粒度得分为1.28，优于现有的方法。

{"title":"T-SRE: Transformer-based semantic Relation extraction for contextual paraphrased plagiarism detection","authors":"Pon Abisheka , C. Deisy , P. Sharmila","doi":"10.1016/j.jksuci.2024.102257","DOIUrl":"10.1016/j.jksuci.2024.102257","url":null,"abstract":"<div><div>Plagiarism has become a pervasive issue in academics and professionals to safeguard academic integrity and intellectual property rights. The escalating sophistication of plagiarized content through semantic manipulation and structural reorganization poses significant challenges to existing detection systems that rely primarily on lexical similarity measures. The proposed T-SRE (Transformer-based Semantic Relation Extraction), a novel framework addresses the limitations of traditional n-gram and string-matching approaches by leveraging deep semantic analysis. The proposed framework combines Dependency Parsing (DP) for syntactic relationship mapping and Named Entity Recognition (NER) for contextual entity identification, augmented by a transformer-based neural network that captures long-range contextual dependencies. This learning methodology incorporates three key components: a position-aware word reordering algorithm, Levenshtein distance metric for structural similarity, and contextual word embeddings for semantic preservation detection. The proposed T-SRE enhances text structure recognition by combining position-aware reordering with semantic preservation through ensemble learning. The system implements a hierarchical classification scheme that quantifies plagiarism severity through a four-tier taxonomy: heavy, low, non-plagiarized and verbatim copy. The Udacity benchmark dataset showcases the model’s superior detection capabilities, achieving 92% precision, 89% recall, and an F1-score of 90.5%, particularly in lightweight textual modifications.The framework achieves a granularity score of 1.28, outperforming existing approaches.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102257"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Audio analysis with convolutional neural networks and boosting algorithms tuned by metaheuristics for respiratory condition classification

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-12-01 DOI: 10.1016/j.jksuci.2024.102261

Safet Purkovic , Luka Jovanovic , Miodrag Zivkovic , Milos Antonijevic , Edin Dolicanin , Eva Tuba , Milan Tuba , Nebojsa Bacanin , Petar Spalevic

In contemporary medical research, respiratory disorders have become a primary focus. Improving patient outcomes for any medical condition largely depends on early identification and prompt treatment. Traditionally, medical professionals diagnose respiratory diseases by auscultating a patient’s breathing. However, this method has inherent limitations, as it may not enable physicians to accurately identify every respiratory condition. This study explores the potential of using convolutional neural networks (CNNs) in conjunction with audio analysis for the identification of respiratory problems. This work proses a novel two-tier framework that integrates CNNs with extreme gradient boosting (XGBoost) and adaptive boosting (AdaBoost) models to classify respiratory conditions. Additionally, modern optimization techniques are employed to enhance classification efficiency, recognizing the significant impact that appropriate hyperparameter tuning has on machine learning (ML) and deep learning (DL) performance. This research introduces a modified version of particle swarm optimization (PSO) tailored to meet the specific needs of ML and DL tuning. The proposed approach is validated using a real-world clinical dataset. Two studies, both based on mel spectrograms of patient breathing patterns, were conducted: the first aimed at determining whether patients have respiratory conditions (binary classification), while the second employed the same data structure for multi-class classification. In both scenarios, advanced optimizers were utilized to optimize model architecture and training settings. Under identical testing conditions, the proposed PSO metaheuristic achieved an accuracy of 98.14

%

for respiratory condition detection in binary classification and a slightly lower accuracy of 81.25

%

for specific condition identification in multi-class classification.

{"title":"Audio analysis with convolutional neural networks and boosting algorithms tuned by metaheuristics for respiratory condition classification","authors":"Safet Purkovic , Luka Jovanovic , Miodrag Zivkovic , Milos Antonijevic , Edin Dolicanin , Eva Tuba , Milan Tuba , Nebojsa Bacanin , Petar Spalevic","doi":"10.1016/j.jksuci.2024.102261","DOIUrl":"10.1016/j.jksuci.2024.102261","url":null,"abstract":"<div><div>In contemporary medical research, respiratory disorders have become a primary focus. Improving patient outcomes for any medical condition largely depends on early identification and prompt treatment. Traditionally, medical professionals diagnose respiratory diseases by auscultating a patient’s breathing. However, this method has inherent limitations, as it may not enable physicians to accurately identify every respiratory condition. This study explores the potential of using convolutional neural networks (CNNs) in conjunction with audio analysis for the identification of respiratory problems. This work proses a novel two-tier framework that integrates CNNs with extreme gradient boosting (XGBoost) and adaptive boosting (AdaBoost) models to classify respiratory conditions. Additionally, modern optimization techniques are employed to enhance classification efficiency, recognizing the significant impact that appropriate hyperparameter tuning has on machine learning (ML) and deep learning (DL) performance. This research introduces a modified version of particle swarm optimization (PSO) tailored to meet the specific needs of ML and DL tuning. The proposed approach is validated using a real-world clinical dataset. Two studies, both based on mel spectrograms of patient breathing patterns, were conducted: the first aimed at determining whether patients have respiratory conditions (binary classification), while the second employed the same data structure for multi-class classification. In both scenarios, advanced optimizers were utilized to optimize model architecture and training settings. Under identical testing conditions, the proposed PSO metaheuristic achieved an accuracy of 98.14<span><math><mtext>%</mtext></math></span> for respiratory condition detection in binary classification and a slightly lower accuracy of 81.25<span><math><mtext>%</mtext></math></span> for specific condition identification in multi-class classification.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102261"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0