Crowdsourcing delivers responses that are asynchronous and incomplete, making offline aggregators that assume complete response sets impractical. Prior online methods often either require per-step completeness or repeatedly reload historical responses, which is storage- and privacy-unfriendly and susceptible to forgetting. We present OLA-Incomplete, an online label-aggregation framework designed for incomplete response streams. It integrates a variational-inference aggregator with a generative replay module that preserves historical information without reloading prior responses and explicitly models unknown worker reliability. At each update step, the generator replays cumulative responses and side information for previously observed instances to mitigate catastrophic forgetting, while the aggregator infers current truths by maximizing the evidence lower bound over a mixture of replayed and newly received labels. Across three public datasets-Duck, RTE, and PostSent-OLA-Incomplete attains final accuracies of 90.74%, 92.50%, and 95.99%, respectively, delivering at least 7.79% relative improvement over the strongest baseline. The approach further exhibits strong instantaneous online accuracy and robustness across response-chunk sizes and arrival orders, underscoring its practical utility for real-world crowdsourcing workflows.
{"title":"Online label aggregation with incomplete crowd responses.","authors":"Yuyang Liu, Haoyu Liu, Runze Wu, Chengliang Chai, Minmin Lin, Renyu Zhu, Hui Liu, Tangjie Lv, Changjie Fan","doi":"10.1007/s44443-025-00381-z","DOIUrl":"https://doi.org/10.1007/s44443-025-00381-z","url":null,"abstract":"<p><p>Crowdsourcing delivers responses that are asynchronous and incomplete, making offline aggregators that assume complete response sets impractical. Prior online methods often either require per-step completeness or repeatedly reload historical responses, which is storage- and privacy-unfriendly and susceptible to forgetting. We present OLA-Incomplete, an online label-aggregation framework designed for incomplete response streams. It integrates a variational-inference aggregator with a generative replay module that preserves historical information without reloading prior responses and explicitly models unknown worker reliability. At each update step, the generator replays cumulative responses and side information for previously observed instances to mitigate catastrophic forgetting, while the aggregator infers current truths by maximizing the evidence lower bound over a mixture of replayed and newly received labels. Across three public datasets-Duck, RTE, and PostSent-OLA-Incomplete attains final accuracies of 90.74%, 92.50%, and 95.99%, respectively, delivering at least 7.79% relative improvement over the strongest baseline. The approach further exhibits strong instantaneous online accuracy and robustness across response-chunk sizes and arrival orders, underscoring its practical utility for real-world crowdsourcing workflows.</p>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"38 2","pages":"76"},"PeriodicalIF":6.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12948928/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147327830","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}
Pub Date : 2024-12-01Epub Date: 2024-11-05DOI: 10.1016/j.jksuci.2024.102234
Zhan Jingchun , Goh Eg Su , Mohd Shahrizal Sunar
Enhancing low-light images in computer vision is a significant challenge that requires innovative methods to improve its robustness. Low-light image enhancement (LLIE) enhances the quality of images affected by poor lighting conditions by implementing various loss functions such as reconstruction, perceptual, smoothness, adversarial, and exposure. This review analyses and compares different methods, ranging from traditional to cutting-edge deep learning methods, showcasing the significant advancements in the field. Although similar reviews have been studied on LLIE, this paper not only updates the knowledge but also focuses on recent deep learning methods from various perspectives or interpretations. The methodology used in this paper compares different methods from the literature and identifies the potential research gaps. This paper highlights the recent advancements in the field by classifying them into three classes, demonstrated by the continuous enhancements in LLIE methods. These improved methods use different loss functions showing higher efficacy through metrics such as Peak Signal-to-Noise Ratio, Structural Similarity Index Measure, and Naturalness Image Quality Evaluator. The research emphasizes the significance of advanced deep learning techniques and comprehensively compares different LLIE methods on various benchmark image datasets. This research is a foundation for scientists to illustrate potential future research directions.
{"title":"Low-light image enhancement: A comprehensive review on methods, datasets and evaluation metrics","authors":"Zhan Jingchun , Goh Eg Su , Mohd Shahrizal Sunar","doi":"10.1016/j.jksuci.2024.102234","DOIUrl":"10.1016/j.jksuci.2024.102234","url":null,"abstract":"<div><div>Enhancing low-light images in computer vision is a significant challenge that requires innovative methods to improve its robustness. Low-light image enhancement (LLIE) enhances the quality of images affected by poor lighting conditions by implementing various loss functions such as reconstruction, perceptual, smoothness, adversarial, and exposure. This review analyses and compares different methods, ranging from traditional to cutting-edge deep learning methods, showcasing the significant advancements in the field. Although similar reviews have been studied on LLIE, this paper not only updates the knowledge but also focuses on recent deep learning methods from various perspectives or interpretations. The methodology used in this paper compares different methods from the literature and identifies the potential research gaps. This paper highlights the recent advancements in the field by classifying them into three classes, demonstrated by the continuous enhancements in LLIE methods. These improved methods use different loss functions showing higher efficacy through metrics such as Peak Signal-to-Noise Ratio, Structural Similarity Index Measure, and Naturalness Image Quality Evaluator. The research emphasizes the significance of advanced deep learning techniques and comprehensively compares different LLIE methods on various benchmark image datasets. This research is a foundation for scientists to illustrate potential future research directions.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102234"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657773","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}
Pub Date : 2024-12-01Epub Date: 2024-11-20DOI: 10.1016/j.jksuci.2024.102251
Khandakar Md Shafin , Saha Reno
In order to maintain the value of the national currency and control foreign debt, central banks are vital to the management of a nation’s foreign exchange reserves. These reserves, however, are vulnerable to a variety of hazards, including as money laundering, fraud, theft, and cyberattacks. These are issues that traditional financial systems frequently face because of their vulnerabilities and inefficiency. Using modern innovations in a blockchain-based solution can help tackle these serious issues. To protect data privacy, the Microsoft SEAL library is utilized for homomorphic encryption (FHE). For the development of smart contracts, Solidity is employed within the Ethereum blockchain ecosystem. Additionally, Amazon Web Services (AWS) is leveraged to provide a scalable and powerful infrastructure to support our solution. To guarantee safe and effective transaction validation, our method incorporates a hybrid consensus process that combines Proof of Authority (PoA) with Byzantine Fault Tolerance (BFT). The administration of foreign exchange reserves by central banks is made more secure, transparent, and operationally efficient by this all-inclusive approach.
为了保持本国货币的价值和控制外债，中央银行对国家外汇储备的管理至关重要。然而，这些储备容易受到各种危害的影响，包括洗钱、欺诈、盗窃和网络攻击。这些都是传统金融系统因其脆弱性和低效率而经常面临的问题。在基于区块链的解决方案中使用现代创新技术有助于解决这些严重问题。为了保护数据隐私，微软 SEAL 库被用于同态加密（FHE）。为了开发智能合约，在以太坊区块链生态系统中使用了 Solidity。此外，亚马逊网络服务（AWS）为支持我们的解决方案提供了可扩展的强大基础设施。为了保证安全有效的交易验证，我们的方法采用了混合共识流程，将权威证明（PoA）与拜占庭容错（BFT）相结合。通过这种包罗万象的方法，中央银行对外汇储备的管理变得更加安全、透明和高效。
{"title":"Enhancing foreign exchange reserve security for central banks using Blockchain, FHE, and AWS","authors":"Khandakar Md Shafin , Saha Reno","doi":"10.1016/j.jksuci.2024.102251","DOIUrl":"10.1016/j.jksuci.2024.102251","url":null,"abstract":"<div><div>In order to maintain the value of the national currency and control foreign debt, central banks are vital to the management of a nation’s foreign exchange reserves. These reserves, however, are vulnerable to a variety of hazards, including as money laundering, fraud, theft, and cyberattacks. These are issues that traditional financial systems frequently face because of their vulnerabilities and inefficiency. Using modern innovations in a blockchain-based solution can help tackle these serious issues. To protect data privacy, the Microsoft SEAL library is utilized for homomorphic encryption (FHE). For the development of smart contracts, Solidity is employed within the Ethereum blockchain ecosystem. Additionally, Amazon Web Services (AWS) is leveraged to provide a scalable and powerful infrastructure to support our solution. To guarantee safe and effective transaction validation, our method incorporates a hybrid consensus process that combines Proof of Authority (PoA) with Byzantine Fault Tolerance (BFT). The administration of foreign exchange reserves by central banks is made more secure, transparent, and operationally efficient by this all-inclusive approach.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102251"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705879","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}
Pub Date : 2024-12-01Epub Date: 2024-11-23DOI: 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.
{"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}
Pub Date : 2024-12-01Epub Date: 2024-12-11DOI: 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}
Pub Date : 2024-12-01Epub Date: 2024-12-11DOI: 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.
{"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}
Pub Date : 2024-12-01Epub Date: 2024-11-19DOI: 10.1016/j.jksuci.2024.102249
Muhammad Sheraz , Teong Chee Chuah , Kashif Sultan , Manzoor Ahmed , It Ee Lee , Saw Chin Tan
Cache-enabled Device-to-Device (D2D) communications is an effective way to improve data sharing. User Equipment (UE)-level caching holds the potential to reduce the data traffic burden on the core network. Licensed spectrum is utilized for D2D communications, but due to spectrum scarcity, exploring unlicensed spectrum is essential to enhance network capacity. In this paper, we propose caching at the UE-level and exploit both licensed and unlicensed spectrum for optimizing throughput. First, we propose a reinforcement learning-based data caching scheme leveraging an actor–critic network to improve cache-enabled D2D communications. Besides, licensed and unlicensed spectrum are devised for D2D communications considering interference from existing cellular and Wi-Fi users. A duty cycle-based unlicensed spectrum access algorithm is employed, guaranteeing the Signal-to-Interference and Noise Ratio (SINR) required by the users. The unlicensed spectrum is prone to data packets collisions. Therefore, Request-to-Send/Clear-to-Send (RTS/CTS) mechanism is utilized in conjunction with Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) to alleviate both the interference and packets collision problems of the unlicensed spectrum. Extensive simulations are performed to analyze the performance gain of our proposed scheme compared to the benchmarks under different network scenarios. The obtained results demonstrate that our proposed scheme possesses the potential to optimize network performance.
{"title":"Improving cache-enabled D2D communications using actor–critic networks over licensed and unlicensed spectrum","authors":"Muhammad Sheraz , Teong Chee Chuah , Kashif Sultan , Manzoor Ahmed , It Ee Lee , Saw Chin Tan","doi":"10.1016/j.jksuci.2024.102249","DOIUrl":"10.1016/j.jksuci.2024.102249","url":null,"abstract":"<div><div>Cache-enabled Device-to-Device (D2D) communications is an effective way to improve data sharing. User Equipment (UE)-level caching holds the potential to reduce the data traffic burden on the core network. Licensed spectrum is utilized for D2D communications, but due to spectrum scarcity, exploring unlicensed spectrum is essential to enhance network capacity. In this paper, we propose caching at the UE-level and exploit both licensed and unlicensed spectrum for optimizing throughput. First, we propose a reinforcement learning-based data caching scheme leveraging an actor–critic network to improve cache-enabled D2D communications. Besides, licensed and unlicensed spectrum are devised for D2D communications considering interference from existing cellular and Wi-Fi users. A duty cycle-based unlicensed spectrum access algorithm is employed, guaranteeing the Signal-to-Interference and Noise Ratio (SINR) required by the users. The unlicensed spectrum is prone to data packets collisions. Therefore, Request-to-Send/Clear-to-Send (RTS/CTS) mechanism is utilized in conjunction with Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) to alleviate both the interference and packets collision problems of the unlicensed spectrum. Extensive simulations are performed to analyze the performance gain of our proposed scheme compared to the benchmarks under different network scenarios. The obtained results demonstrate that our proposed scheme possesses the potential to optimize network performance.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102249"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705873","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}
Pub Date : 2024-12-01Epub Date: 2024-11-15DOI: 10.1016/j.jksuci.2024.102238
Abdulbasit A. Darem , Tareq M. Alkhaldi , Asma A. Alhashmi , Wahida Mansouri , Abed Saif Ahmed Alghawli , Tawfik Al-Hadhrami
Sixth-generation (6G) communication advancements target massive connectivity, ultra-reliable low-latency communication (URLLC), and high data rates, essential for IoT applications. Yet, in natural disasters, particularly in dense urban areas, 6G quality of service (QoS) can falter when terrestrial networks—such as base stations—become unavailable, unstable, or strained by high user density and dynamic environments. Additionally, high-rise buildings in smart cities contribute to signal blockages. To ensure reliable, high-quality connectivity, integrating low-Earth Orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and reconfigurable intelligent surfaces (RIS) into a multilayer (ML) network offers a solution: LEO satellites provide broad coverage, UAVs reduce congestion with flexible positioning, and RIS enhances signal quality. Despite these benefits, this integration brings challenges in resource allocation, requiring path loss models that account for both line-of-sight (LOS) and non-line-of-sight (NLOS) links. To address these, a joint optimization problem is formulated focusing on resource distribution fairness. Given its complexity, a framework is proposed to decouple the problem into subproblems using the block coordinate descent (BCD) method. These subproblems include UAV placement optimization, user association, subcarrier allocation via orthogonal frequency division multiple access (OFDMA), power allocation, and RIS phase shift control. OFDMA efficiently manages shared resources and mitigates interference. This iterative approach optimizes each subproblem, ensuring convergence to a locally optimal solution. Additionally, we propose a low-complexity solution for RIS phase shift control, proving its feasibility and efficiency mathematically. The numerical results demonstrate that the proposed scheme achieves up to 43.5% higher sum rates and 80% lower outage probabilities compared to the schemes without RIS. The low complexity solution for RIS optimization achieves performance within 1.8% of the SDP approach in terms of the sum rate. This model significantly improves network performance and reliability, achieving a 16.3% higher sum rate and a 44.4% reduction in outage probability compared to joint optimization of SAT-UAV resources. These findings highlight the robustness and efficiency of the ML network model, making it ideal for next-generation communication systems in high-density urban environments.
{"title":"Optimizing resource allocation for enhanced urban connectivity in LEO-UAV-RIS networks","authors":"Abdulbasit A. Darem , Tareq M. Alkhaldi , Asma A. Alhashmi , Wahida Mansouri , Abed Saif Ahmed Alghawli , Tawfik Al-Hadhrami","doi":"10.1016/j.jksuci.2024.102238","DOIUrl":"10.1016/j.jksuci.2024.102238","url":null,"abstract":"<div><div>Sixth-generation (6G) communication advancements target massive connectivity, ultra-reliable low-latency communication (URLLC), and high data rates, essential for IoT applications. Yet, in natural disasters, particularly in dense urban areas, 6G quality of service (QoS) can falter when terrestrial networks—such as base stations—become unavailable, unstable, or strained by high user density and dynamic environments. Additionally, high-rise buildings in smart cities contribute to signal blockages. To ensure reliable, high-quality connectivity, integrating low-Earth Orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and reconfigurable intelligent surfaces (RIS) into a multilayer (ML) network offers a solution: LEO satellites provide broad coverage, UAVs reduce congestion with flexible positioning, and RIS enhances signal quality. Despite these benefits, this integration brings challenges in resource allocation, requiring path loss models that account for both line-of-sight (LOS) and non-line-of-sight (NLOS) links. To address these, a joint optimization problem is formulated focusing on resource distribution fairness. Given its complexity, a framework is proposed to decouple the problem into subproblems using the block coordinate descent (BCD) method. These subproblems include UAV placement optimization, user association, subcarrier allocation via orthogonal frequency division multiple access (OFDMA), power allocation, and RIS phase shift control. OFDMA efficiently manages shared resources and mitigates interference. This iterative approach optimizes each subproblem, ensuring convergence to a locally optimal solution. Additionally, we propose a low-complexity solution for RIS phase shift control, proving its feasibility and efficiency mathematically. The numerical results demonstrate that the proposed scheme achieves up to 43.5% higher sum rates and 80% lower outage probabilities compared to the schemes without RIS. The low complexity solution for RIS optimization achieves performance within 1.8% of the SDP approach in terms of the sum rate. This model significantly improves network performance and reliability, achieving a 16.3% higher sum rate and a 44.4% reduction in outage probability compared to joint optimization of SAT-UAV resources. These findings highlight the robustness and efficiency of the ML network model, making it ideal for next-generation communication systems in high-density urban environments.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102238"},"PeriodicalIF":5.2,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705878","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}
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.
{"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}
Pub Date : 2024-12-01Epub Date: 2024-12-07DOI: 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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号