Pub Date : 2025-05-01DOI: 10.1016/j.jiixd.2025.02.001
Mingyang Liu , Zhengguang Tang , Hailong You , Cong Li , Guangxin Guo , Zeyuan Wang , Linying Zhang , Xingming Liu , Yu Wang , Yong Dai , Geng Bai , Xiaoling Lin
The standard design technology co-optimization (DTCO) involves frequent interactions between circuit design and process manufacturing, which requires several months. To assist designers in establishing a bridge between device parameters and circuit metrics efficiently, and provide guidance for parameter optimization in the early stages of circuit design. In this paper, we propose an efficient machine learning (ML)-enhanced DTCO framework. This framework achieves the co-optimization of device parameters and circuit metrics. We select the gate metal work function (WF) as the parameter to validate the effectiveness of our framework. And the ridge regression approach is used to bypass TCAD simulation, compact model extraction and cell library characterization. We reduces time consumption by at least 92% compared to traditional DTCO framework, while ensuring that errors of delay, internal power consumption and leakage power below 4 ps, 0.035 mJ, and 0.4 μW, respectively. By adjusting the WF, we achieved a better balance between circuit delay and power consumption. This work contributes to designers exploring a broader design space and achieving a efficient DTCO flow.
{"title":"An efficient machine learning-enhanced DTCO framework for low-power and high-performance circuit design","authors":"Mingyang Liu , Zhengguang Tang , Hailong You , Cong Li , Guangxin Guo , Zeyuan Wang , Linying Zhang , Xingming Liu , Yu Wang , Yong Dai , Geng Bai , Xiaoling Lin","doi":"10.1016/j.jiixd.2025.02.001","DOIUrl":"10.1016/j.jiixd.2025.02.001","url":null,"abstract":"<div><div>The standard design technology co-optimization (DTCO) involves frequent interactions between circuit design and process manufacturing, which requires several months. To assist designers in establishing a bridge between device parameters and circuit metrics efficiently, and provide guidance for parameter optimization in the early stages of circuit design. In this paper, we propose an efficient machine learning (ML)-enhanced DTCO framework. This framework achieves the co-optimization of device parameters and circuit metrics. We select the gate metal work function (WF) as the parameter to validate the effectiveness of our framework. And the ridge regression approach is used to bypass TCAD simulation, compact model extraction and cell library characterization. We reduces time consumption by at least 92% compared to traditional DTCO framework, while ensuring that errors of delay, internal power consumption and leakage power below 4 ps, 0.035 mJ, and 0.4 μW, respectively. By adjusting the WF, we achieved a better balance between circuit delay and power consumption. This work contributes to designers exploring a broader design space and achieving a efficient DTCO flow.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 3","pages":"Pages 194-209"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144490375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-05-01DOI: 10.1016/j.jiixd.2025.03.003
Wei Guo , Kai Liang , Yuewen Song , Xiaoli Chu , Gan Zheng , Kai-Kit Wong
Enhanced mobile broadband (eMBB) and ultra-reliable low-latency communication (URLLC) are two critical services in 5G mobile networks. While there has been extensive research on their coexistence, few studies have considered the impact of bursty URLLC on their coexistence performance. In this paper, we propose a method to allocate computing and radio resources for coexisting eMBB and bursty URLLC services by preempting both computing queues in the base station (BS) and time-frequency resources at the air interface. Specifically, we first divide the computing resources at the BS into a shared part for both URLLC and eMBB users and an exclusive part only for eMBB users, and propose a queuing mechanism with preemptive-resume priority for accessing the shared computing resources. Furthermore, we propose a preemptive puncturing method and a threshold-based queuing mechanism in the air interface to enable the multiplexing of eMBB and URLLC on shared time-frequency resources. We analytically derive the average queuing delay, average computation delay, and average transmission delay of eMBB and URLLC packets. Based on this analysis, we formulate a mixed-integer nonlinear programming problem to minimize the average delay of URLLC packets while satisfying the average delay and throughput requirements of eMBB by jointly optimizing the eMBB subcarrier allocation, the URLLC subcarrier scheduling and the computing resource allocation. We decompose this problem into three sub-problems and solve them alternately using a block coordinate descent algorithm. Numerical results show that our proposed method reduces the outage probability and average delay of URLLC compared to the existing works.
{"title":"Resource allocation for coexistence of eMBB and bursty URLLC based on queueing with preemption","authors":"Wei Guo , Kai Liang , Yuewen Song , Xiaoli Chu , Gan Zheng , Kai-Kit Wong","doi":"10.1016/j.jiixd.2025.03.003","DOIUrl":"10.1016/j.jiixd.2025.03.003","url":null,"abstract":"<div><div>Enhanced mobile broadband (eMBB) and ultra-reliable low-latency communication (URLLC) are two critical services in 5G mobile networks. While there has been extensive research on their coexistence, few studies have considered the impact of bursty URLLC on their coexistence performance. In this paper, we propose a method to allocate computing and radio resources for coexisting eMBB and bursty URLLC services by preempting both computing queues in the base station (BS) and time-frequency resources at the air interface. Specifically, we first divide the computing resources at the BS into a shared part for both URLLC and eMBB users and an exclusive part only for eMBB users, and propose a queuing mechanism with preemptive-resume priority for accessing the shared computing resources. Furthermore, we propose a preemptive puncturing method and a threshold-based queuing mechanism in the air interface to enable the multiplexing of eMBB and URLLC on shared time-frequency resources. We analytically derive the average queuing delay, average computation delay, and average transmission delay of eMBB and URLLC packets. Based on this analysis, we formulate a mixed-integer nonlinear programming problem to minimize the average delay of URLLC packets while satisfying the average delay and throughput requirements of eMBB by jointly optimizing the eMBB subcarrier allocation, the URLLC subcarrier scheduling and the computing resource allocation. We decompose this problem into three sub-problems and solve them alternately using a block coordinate descent algorithm. Numerical results show that our proposed method reduces the outage probability and average delay of URLLC compared to the existing works.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 3","pages":"Pages 223-241"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144490377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-05-01DOI: 10.1016/j.jiixd.2025.02.004
Long Liu , Qingquan Luo , Wenbo Zhang , Mengxuan Zhang , Bowen Zhai
Multimodal emotion recognition technology leverages the power of deep learning to address advanced visual and emotional tasks. While generic deep networks can handle simple emotion recognition tasks, their generalization capability in complex and noisy environments, such as multi-scene outdoor settings, remains limited. To overcome these challenges, this paper proposes a novel multimodal emotion recognition framework. First, we develop a robust network architecture based on the T5-small model, designed for dynamic-static fusion in complex scenarios, effectively mitigating the impact of noise. Second, we introduce a dynamic-static cross fusion network (D-SCFN) to enhance the integration and extraction of dynamic and static information, embedding it seamlessly within the T5 framework. Finally, we design and evaluate three distinct multi-task analysis frameworks to explore dependencies among tasks. The experimental results demonstrate that our model significantly outperforms other existing models, showcasing exceptional stability and remarkable adaptability to complex and dynamic scenarios.
{"title":"Multimodal emotion recognition method in complex dynamic scenes","authors":"Long Liu , Qingquan Luo , Wenbo Zhang , Mengxuan Zhang , Bowen Zhai","doi":"10.1016/j.jiixd.2025.02.004","DOIUrl":"10.1016/j.jiixd.2025.02.004","url":null,"abstract":"<div><div>Multimodal emotion recognition technology leverages the power of deep learning to address advanced visual and emotional tasks. While generic deep networks can handle simple emotion recognition tasks, their generalization capability in complex and noisy environments, such as multi-scene outdoor settings, remains limited. To overcome these challenges, this paper proposes a novel multimodal emotion recognition framework. First, we develop a robust network architecture based on the T5-small model, designed for dynamic-static fusion in complex scenarios, effectively mitigating the impact of noise. Second, we introduce a dynamic-static cross fusion network (D-SCFN) to enhance the integration and extraction of dynamic and static information, embedding it seamlessly within the T5 framework. Finally, we design and evaluate three distinct multi-task analysis frameworks to explore dependencies among tasks. The experimental results demonstrate that our model significantly outperforms other existing models, showcasing exceptional stability and remarkable adaptability to complex and dynamic scenarios.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 3","pages":"Pages 257-274"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144490379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.jiixd.2024.06.002
Jun Niu , Peng Liu , Chunhui Huang , Yangming Zhang , Moxuan Zeng , Kuo Shen , Yangzhong Wang , Suyu An , Yulong Shen , Xiaohong Jiang , Jianfeng Ma , He Wang , Gaofei Wu , Anmin Fu , Chunjie Cao , Xiaoyan Zhu , Yuqing Zhang
Membership inference (MI) attacks threaten user privacy through determining if a given data example has been used to train a target model. Existing MI defenses protect the membership privacy through preemptive exclusion of members techniques and knowledge distillation. Unfortunately, using either of these two defenses alone, the defense effect can still offers an unsatisfactory trade-off between membership privacy and utility.
Given that the defense method that directly combines these two defenses is still very limited (e.g., the test accuracy of the target model is decreased by about 40% (in our experiments)), in this work, we propose a dual defense (DD) method that includes the preemptive exclusion of high-risk member samples module and the knowledge distillation module, which thwarts the access of the resulting models to the private training data twice to mitigate MI attacks. Our defense method can be divided into two steps: the preemptive exclusion of high-risk member samples (Step 1) and the knowledge distillation to obtain the protected student model (Step 2). We propose three types of exclusions: existing MI attacks-based exclusions, sample distances of members and nonmembers-based exclusions, and mutual information value-based exclusions, to preemptively exclude the high-risk member samples. During the knowledge distillation phase, we add ground-truth labeled data to the reference dataset to decrease the protected student model's dependency on soft labels, aiming to maintain or improve its test accuracy. Extensive evaluation shows that DD significantly outperforms state-of-the-art defenses and offers a better privacy-utility trade-off. For example, DD achieves ∼100% test accuracy improvement over the distillation for membership privacy (DMP) defense for ResNet50 trained on CIFAR100. DD simultaneously achieves the reductions in the attack effectiveness (e.g., the [email protected]%FPR of enhanced MI attacks decreased by 2.10% on the ImageNet dataset, the membership advantage (MA) of risk score-based attacks decreased by 56.30%) and improvements of the target models' test accuracies (e.g., by 42.80% on CIFAR100).
{"title":"Dual defense: Combining preemptive exclusion of members and knowledge distillation to mitigate membership inference attacks","authors":"Jun Niu , Peng Liu , Chunhui Huang , Yangming Zhang , Moxuan Zeng , Kuo Shen , Yangzhong Wang , Suyu An , Yulong Shen , Xiaohong Jiang , Jianfeng Ma , He Wang , Gaofei Wu , Anmin Fu , Chunjie Cao , Xiaoyan Zhu , Yuqing Zhang","doi":"10.1016/j.jiixd.2024.06.002","DOIUrl":"10.1016/j.jiixd.2024.06.002","url":null,"abstract":"<div><div>Membership inference (MI) attacks threaten user privacy through determining if a given data example has been used to train a target model. Existing MI defenses protect the membership privacy through preemptive exclusion of members techniques and knowledge distillation. Unfortunately, using either of these two defenses alone, the defense effect can still offers an unsatisfactory trade-off between membership privacy and utility.</div><div>Given that the defense method that directly combines these two defenses is still very limited (e.g., the test accuracy of the target model is decreased by about 40% (in our experiments)), in this work, we propose a dual defense (DD) method that includes the preemptive exclusion of high-risk member samples module and the knowledge distillation module, which thwarts the access of the resulting models to the private training data twice to mitigate MI attacks. Our defense method can be divided into two steps: the preemptive exclusion of high-risk member samples (Step 1) and the knowledge distillation to obtain the protected student model (Step 2). We propose three types of exclusions: existing MI attacks-based exclusions, sample distances of members and nonmembers-based exclusions, and mutual information value-based exclusions, to preemptively exclude the high-risk member samples. During the knowledge distillation phase, we add ground-truth labeled data to the reference dataset to decrease the protected student model's dependency on soft labels, aiming to maintain or improve its test accuracy. Extensive evaluation shows that DD significantly outperforms state-of-the-art defenses and offers a better privacy-utility trade-off. For example, DD achieves ∼100% test accuracy improvement over the distillation for membership privacy (DMP) defense for ResNet50 trained on CIFAR100. DD simultaneously achieves the reductions in the attack effectiveness (e.g., the [email protected]%FPR of enhanced MI attacks decreased by 2.10% on the ImageNet dataset, the membership advantage (MA) of risk score-based attacks decreased by 56.30%) and improvements of the target models' test accuracies (e.g., by 42.80% on CIFAR100).</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 1","pages":"Pages 68-92"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143148335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.jiixd.2024.06.003
Ziyuan Zhang , Ziyu Wang , Kaitai Guo , Yang Zheng , Minghao Dong , Jimin Liang
Previous efforts to boost the performance of brain-computer interfaces (BCIs) have predominantly focused on optimizing algorithms for decoding brain signals. However, the untapped potential of leveraging brain plasticity for optimization remains underexplored. In this study, we enhanced the temporal resolution of the human brain in discriminating visual stimuli by eliminating the attentional blink (AB) through color-salient cognitive training, and we confirmed that the mechanism was an attention-based improvement. Using the rapid serial visual presentation (RSVP)-based BCI, we evaluated the behavioral and electroencephalogram (EEG) decoding performance of subjects before and after cognitive training in high target percentage (with AB) and low target percentage (without AB) surveillance tasks, respectively. The results consistently demonstrated significant improvements in the trained subjects. Further analysis indicated that this improvement was attributed to the cognitively trained brain producing more discriminative EEG. Our work highlights the feasibility of cognitive training as a means of brain enhancement to boost BCI performance.
{"title":"Boosting brain-computer interface performance through cognitive training: A brain-centric approach","authors":"Ziyuan Zhang , Ziyu Wang , Kaitai Guo , Yang Zheng , Minghao Dong , Jimin Liang","doi":"10.1016/j.jiixd.2024.06.003","DOIUrl":"10.1016/j.jiixd.2024.06.003","url":null,"abstract":"<div><div>Previous efforts to boost the performance of brain-computer interfaces (BCIs) have predominantly focused on optimizing algorithms for decoding brain signals. However, the untapped potential of leveraging brain plasticity for optimization remains underexplored. In this study, we enhanced the temporal resolution of the human brain in discriminating visual stimuli by eliminating the attentional blink (AB) through color-salient cognitive training, and we confirmed that the mechanism was an attention-based improvement. Using the rapid serial visual presentation (RSVP)-based BCI, we evaluated the behavioral and electroencephalogram (EEG) decoding performance of subjects before and after cognitive training in high target percentage (with AB) and low target percentage (without AB) surveillance tasks, respectively. The results consistently demonstrated significant improvements in the trained subjects. Further analysis indicated that this improvement was attributed to the cognitively trained brain producing more discriminative EEG. Our work highlights the feasibility of cognitive training as a means of brain enhancement to boost BCI performance.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 1","pages":"Pages 19-35"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141690095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.jiixd.2024.08.001
Juan Song , Huixuechun Wang , Jianan Li , Jian Zheng , Zhifu Zhao , Qingshan Li
Skeleton-based sign language recognition (SLR) is a challenging research area mainly due to the fast and complex hand movement. Currently, graph convolution networks (GCNs) have been employed in skeleton-based SLR and achieved remarkable performance. However, existing GCN-based SLR methods suffer from a lack of explicit attention to hand topology which plays an important role in the sign language representation. To address this issue, we propose a novel hand-aware graph convolution network (HA-GCN) to focus on hand topological relationships of skeleton graph. Specifically, a hand-aware graph convolution layer is designed to capture both global body and local hand information, in which two sub-graphs are defined and incorporated to represent hand topology information. In addition, in order to eliminate the over-fitting problem, an adaptive DropGraph is designed in construction of hand-aware graph convolution block to remove the spatial and temporal redundancy in the sign language representation. With the aim to further improve the performance, the joints information, bones, together with their motion information are simultaneously modeled in a multi-stream framework. Extensive experiments on the two open-source datasets, AUTSL and INCLUDE, demonstrate that our proposed algorithm outperforms the state-of-the-art with a significant margin. Our code is available at https://github.com/snorlaxse/HA-SLR-GCN.
{"title":"Hand-aware graph convolution network for skeleton-based sign language recognition","authors":"Juan Song , Huixuechun Wang , Jianan Li , Jian Zheng , Zhifu Zhao , Qingshan Li","doi":"10.1016/j.jiixd.2024.08.001","DOIUrl":"10.1016/j.jiixd.2024.08.001","url":null,"abstract":"<div><div>Skeleton-based sign language recognition (SLR) is a challenging research area mainly due to the fast and complex hand movement. Currently, graph convolution networks (GCNs) have been employed in skeleton-based SLR and achieved remarkable performance. However, existing GCN-based SLR methods suffer from a lack of explicit attention to hand topology which plays an important role in the sign language representation. To address this issue, we propose a novel hand-aware graph convolution network (HA-GCN) to focus on hand topological relationships of skeleton graph. Specifically, a hand-aware graph convolution layer is designed to capture both global body and local hand information, in which two sub-graphs are defined and incorporated to represent hand topology information. In addition, in order to eliminate the over-fitting problem, an adaptive DropGraph is designed in construction of hand-aware graph convolution block to remove the spatial and temporal redundancy in the sign language representation. With the aim to further improve the performance, the joints information, bones, together with their motion information are simultaneously modeled in a multi-stream framework. Extensive experiments on the two open-source datasets, AUTSL and INCLUDE, demonstrate that our proposed algorithm outperforms the state-of-the-art with a significant margin. Our code is available at <span><span>https://github.com/snorlaxse/HA-SLR-GCN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 1","pages":"Pages 36-50"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143148333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.jiixd.2024.07.003
Wei Liu , Meng Niu , Yunghsiang S. Han
RSS fingerprint based indoor localization consists of two phases: offline phase and online phase. A RSS fingerprint database constructed at the offline phase may be outdated for online phase, which may significantly degrade the localization performance. Furthermore, maintaining an RSS fingerprint database is a labor intensive and time-consuming task. In this paper, we proposes a robust and iterative indoor localization algorithm based on Wi-Fi RSS fingerprints, referred to as RIFi, which does not need to update the RSS fingerprint database and perform well even if the RSS fingerprint database is outdated. Specifically, we demonstrate that smaller localization area can provides better performance for outdated fingerprint database. Furthermore, we propose an iterative algorithm to determine the smaller localization area. Finally, the K-nearest neighbors (KNN) algorithm is invoked for the determined smaller localization area. Simulation results show that the proposed RIFi algorithm can significantly outperforms the traditional KNN algorithm for outdated RSS fingerprint database, and is more robust.
{"title":"RIFi: Robust and iterative indoor localization based on Wi-Fi RSS fingerprints","authors":"Wei Liu , Meng Niu , Yunghsiang S. Han","doi":"10.1016/j.jiixd.2024.07.003","DOIUrl":"10.1016/j.jiixd.2024.07.003","url":null,"abstract":"<div><div>RSS fingerprint based indoor localization consists of two phases: offline phase and online phase. A RSS fingerprint database constructed at the offline phase may be outdated for online phase, which may significantly degrade the localization performance. Furthermore, maintaining an RSS fingerprint database is a labor intensive and time-consuming task. In this paper, we proposes a robust and iterative indoor localization algorithm based on Wi-Fi RSS fingerprints, referred to as RIFi, which does not need to update the RSS fingerprint database and perform well even if the RSS fingerprint database is outdated. Specifically, we demonstrate that smaller localization area can provides better performance for outdated fingerprint database. Furthermore, we propose an iterative algorithm to determine the smaller localization area. Finally, the K-nearest neighbors (KNN) algorithm is invoked for the determined smaller localization area. Simulation results show that the proposed RIFi algorithm can significantly outperforms the traditional KNN algorithm for outdated RSS fingerprint database, and is more robust.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 1","pages":"Pages 1-18"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143149201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.jiixd.2024.09.002
Zhicheng Cao , Weiqiang Zhao , Heng Zhao, Liaojun Pang
Palmprint recognition has attracted considerable attention due to its advantages over other biometric modalities such as fingerprints, in that it is larger in area, richer in information and able to work at a distance. However, the issue of palmprint privacy and security (especially palmprint template protection) remains under-studied. Among the very few research works, most of them only use orientational features of the palmprint with transformation processing, yielding unsatisfactory recognition and protection performance. Thus, this research work proposes a palmprint feature extraction method for palmprint template protection that is fixed-length and ordered in nature, by fusing point features and orientational features. Firstly, dual orientations are extracted and encoded with more accuracy based on the modified finite Radon transform (MFRAT). Then, SURF feature points are extracted and converted to be fixed-length and ordered features. Finally, composite fixed-length ordered features that fuse up the dual orientations and SURF points are transformed using the irreversible transformation of index-of-max (IoM) to generate the revocable palmprint templates. Experiments show that the matching accuracy of the proposed method of fixed-length and ordered point features are superior to all other feature extraction methods on the PolyU and CASIA datasets. It is also demonstrated that the EERs before and after IoM transformation are better than all other representative template protection methods. A thorough security and privacy analysis including brute-force attack, false accept attack, birthday attack, attack via record multiplicity, irreversibility, unlinkability and revocability is also given, which proves that our proposed method has both high performance and security.
{"title":"Composite fixed-length ordered features with index-of-max transformation for high-performing and secure palmprint template protection","authors":"Zhicheng Cao , Weiqiang Zhao , Heng Zhao, Liaojun Pang","doi":"10.1016/j.jiixd.2024.09.002","DOIUrl":"10.1016/j.jiixd.2024.09.002","url":null,"abstract":"<div><div>Palmprint recognition has attracted considerable attention due to its advantages over other biometric modalities such as fingerprints, in that it is larger in area, richer in information and able to work at a distance. However, the issue of palmprint privacy and security (especially palmprint template protection) remains under-studied. Among the very few research works, most of them only use orientational features of the palmprint with transformation processing, yielding unsatisfactory recognition and protection performance. Thus, this research work proposes a palmprint feature extraction method for palmprint template protection that is fixed-length and ordered in nature, by fusing point features and orientational features. Firstly, dual orientations are extracted and encoded with more accuracy based on the modified finite Radon transform (MFRAT). Then, SURF feature points are extracted and converted to be fixed-length and ordered features. Finally, composite fixed-length ordered features that fuse up the dual orientations and SURF points are transformed using the irreversible transformation of index-of-max (IoM) to generate the revocable palmprint templates. Experiments show that the matching accuracy of the proposed method of fixed-length and ordered point features are superior to all other feature extraction methods on the PolyU and CASIA datasets. It is also demonstrated that the EERs before and after IoM transformation are better than all other representative template protection methods. A thorough security and privacy analysis including brute-force attack, false accept attack, birthday attack, attack via record multiplicity, irreversibility, unlinkability and revocability is also given, which proves that our proposed method has both high performance and security.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 1","pages":"Pages 51-67"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143148334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-27DOI: 10.1016/j.jiixd.2024.08.002
Peitao Cheng , Xuanjiao Lei , Haoran Chen , Xiumei Wang
As a computer vision task, object detection algorithms can be applied to various real-world scenarios. However, efficient algorithms often come with a large number of parameters and high computational complexity. To meet the demand for high-performance object detection algorithms on mobile devices and embedded devices with limited computational resources, we propose a new lightweight object detection algorithm called DLE-YOLO. Firstly, we design a novel backbone called dual-branch lightweight excitation network (DLEN) for feature extraction, which is mainly constructed by dual-branch lightweight excitation units (DLEU). DLEU is stacked with different numbers of dual-branch lightweight excitation blocks (DLEB), which can extract comprehensive features and integrate information between different channels of features. Secondly, in order to enhance the network to capture key feature information in the regions of interest, the attention model HS-coordinate attention (HS-CA) is introduced into the network. Thirdly, the localization loss utilizes SIoU loss to further optimize the accuracy of the bounding box. Our method achieves a mAP value of 46.0% on the MS-COCO dataset, which is a 2% mAP improvement compared to the baseline YOLOv5-m, while bringing a 19.3% reduction in parameter count and a 12.9% decrease in GFLOPs. Furthermore, our method outperforms some advanced lightweight object detection algorithms, validating the effectiveness of our approach.
{"title":"DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network","authors":"Peitao Cheng , Xuanjiao Lei , Haoran Chen , Xiumei Wang","doi":"10.1016/j.jiixd.2024.08.002","DOIUrl":"10.1016/j.jiixd.2024.08.002","url":null,"abstract":"<div><div>As a computer vision task, object detection algorithms can be applied to various real-world scenarios. However, efficient algorithms often come with a large number of parameters and high computational complexity. To meet the demand for high-performance object detection algorithms on mobile devices and embedded devices with limited computational resources, we propose a new lightweight object detection algorithm called DLE-YOLO. Firstly, we design a novel backbone called dual-branch lightweight excitation network (DLEN) for feature extraction, which is mainly constructed by dual-branch lightweight excitation units (DLEU). DLEU is stacked with different numbers of dual-branch lightweight excitation blocks (DLEB), which can extract comprehensive features and integrate information between different channels of features. Secondly, in order to enhance the network to capture key feature information in the regions of interest, the attention model HS-coordinate attention (HS-CA) is introduced into the network. Thirdly, the localization loss utilizes SIoU loss to further optimize the accuracy of the bounding box. Our method achieves a mAP value of 46.0% on the MS-COCO dataset, which is a 2% mAP improvement compared to the baseline YOLOv5-m, while bringing a 19.3% reduction in parameter count and a 12.9% decrease in GFLOPs. Furthermore, our method outperforms some advanced lightweight object detection algorithms, validating the effectiveness of our approach.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"3 2","pages":"Pages 91-102"},"PeriodicalIF":0.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-18DOI: 10.1016/j.jiixd.2024.07.001
Chengjun Jiang , Chensi Zhang , Chongwen Huang , Jiaying He , Zhe Zhang , Jianhua Ge
The amplify-and-forward (AF) relay is widely employed owing to its simplicity, while reconfigurable intelligent surface (RIS) technology is envisioned as the next generation of relay technology due to its high energy efficiency. This paper compares these two technologies at the physical layer security (PLS) level for non-orthogonal multiple access (NOMA) with an internal near-end eavesdropper. Specifically, for a fair comparison, both the number of RIS elements and AF relay antennas are set to N, and similar secure transport strategies are utilized for both models to maximize the secrecy rate. Analytical results demonstrate that the PLS performance of RIS-assisted NOMA is better than that of AF relay-assisted NOMA if N reaches a certain threshold. Simulation results verify the correctness of the theoretical analysis.
放大-前向（AF）中继因其简单而被广泛采用，而可重构智能表面（RIS）技术因其高能效而被视为下一代中继技术。本文在物理层安全（PLS）层面对这两种技术进行了比较，它们适用于带有内部近端窃听器的非正交多址接入（NOMA）。具体来说，为了进行公平比较，RIS 元素和 AF 中继天线的数量都设为 N，并且两种模型都采用了类似的安全传输策略，以最大限度地提高保密率。分析结果表明，当 N 达到一定阈值时，RIS 辅助 NOMA 的 PLS 性能优于 AF 中继辅助 NOMA。仿真结果验证了理论分析的正确性。
{"title":"Secure performance comparison for NOMA: Reconfigurable intelligent surface or amplify-and-forward relay?","authors":"Chengjun Jiang , Chensi Zhang , Chongwen Huang , Jiaying He , Zhe Zhang , Jianhua Ge","doi":"10.1016/j.jiixd.2024.07.001","DOIUrl":"10.1016/j.jiixd.2024.07.001","url":null,"abstract":"<div><div>The amplify-and-forward (AF) relay is widely employed owing to its simplicity, while reconfigurable intelligent surface (RIS) technology is envisioned as the next generation of relay technology due to its high energy efficiency. This paper compares these two technologies at the physical layer security (PLS) level for non-orthogonal multiple access (NOMA) with an internal near-end eavesdropper. Specifically, for a fair comparison, both the number of RIS elements and AF relay antennas are set to <em>N</em>, and similar secure transport strategies are utilized for both models to maximize the secrecy rate. Analytical results demonstrate that the PLS performance of RIS-assisted NOMA is better than that of AF relay-assisted NOMA if <em>N</em> reaches a certain threshold. Simulation results verify the correctness of the theoretical analysis.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"2 6","pages":"Pages 514-524"},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141851257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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