IEEE Open Journal of the Computer Society最新文献

{"title":"Enhanced Lithographic Hotspot Detection via Multi-Task Deep Learning With Synthetic Pattern Generation","authors":"Xinguang Zhang;Shiyang Chen;Zhouhang Shao;Yongjie Niu;Li Fan","doi":"10.1109/OJCS.2024.3510555","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3510555","url":null,"abstract":"Lithographic hotspot detection is crucial for ensuring manufacturability and yield in advanced integrated circuit (IC) designs. While machine learning approaches have shown promise, they often struggle with detecting truly-never-seen-before (TNSB) hotspots and reducing false alarms on hard-to-classify (HTC) patterns. This article presents a novel multi-task deep learning framework for lithographic hotspot detection that addresses these challenges. Our key contributions include: (1) A synthetic pattern generation method based on early design space exploration (EDSE) to augment training data and improve TNSB hotspot detection; (2) A multi-task convolutional neural network architecture that jointly performs hotspot classification and localization; and (3) An adaptive loss function that balances hotspot detection accuracy and false alarm reduction. Experimental results on the ICCAD-2019 benchmark dataset demonstrate that our approach achieves 98.5% accuracy in hotspot detection with only 1.2% false alarm rate, significantly outperforming state-of-the-art methods. Furthermore, we show a 22% improvement in TNSB hotspot detection and a 5X reduction in false alarms on HTC patterns compared to previous techniques. The proposed framework provides a robust solution for lithographic hotspot detection in early stages of IC design, enabling more efficient design-for-manufacturability optimization.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"140-151"},"PeriodicalIF":0.0,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10772617","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938081","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}

{"title":"CD-LLMCARS: Cross Domain Fine-Tuned Large Language Model for Context-Aware Recommender Systems","authors":"Adeel Ashraf Cheema;Muhammad Shahzad Sarfraz;Usman Habib;Qamar Uz Zaman;Ekkarat Boonchieng","doi":"10.1109/OJCS.2024.3509221","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3509221","url":null,"abstract":"Recommender systems are essential for providing personalized content across various platforms. However, traditional systems often struggle with limited information, known as the cold start problem, and with accurately interpreting a user's comprehensive preferences, referred to as context. The proposed study, CD-LLMCARS (Cross-Domain fine-tuned Large Language Model for Context-Aware Recommender Systems), presents a novel approach to addressing these issues. CD-LLMCARS leverages the substantial capabilities of the Large Language Model (LLM) Llama 2. Fine-tuning Llama 2 with information from multiple domains can enhance the generation of contextually relevant recommendations that align with a user's preferences in areas such as movies, music, books, and CDs. Techniques such as Low-Rank Adaptation (LoRA) and Half Precision Training (FP16) are both effective and resource-efficient, allowing CD-LLMCARS to perform optimally in cold start scenarios. Extensive testing of CD-LLMCARS indicates outstanding accuracy, particularly in challenging scenarios characterized by limited user history data relevant to the cold start problem. CD-LLMCARS offers precise and pertinent recommendations to users, effectively mitigating the limitations of traditional recommender systems.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"49-59"},"PeriodicalIF":0.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10771726","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938076","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}

{"title":"ECMO: An Efficient and Confidential Outsourcing Protocol for Medical Data","authors":"Xiangyi Meng;Yuefeng Du;Cong Wang","doi":"10.1109/OJCS.2024.3506114","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3506114","url":null,"abstract":"Cloud computing has significantly advanced medical data storage capabilities, enabling healthcare institutions to outsource data management. However, this shift introduces critical security and privacy risks, as sensitive patient information is stored on untrusted third-party servers. Existing cryptographic solutions, such as searchable encryption, offer some security guarantees but struggle with challenges like leakage-based attacks, high computational overhead, and limited scalability. To address these limitations in medical data outsourcing, we present ECMO, a novel protocol that combines an ordered additive secret sharing algorithm with a unique index permutation method. This approach efficiently outsources medical data while safeguarding both the data itself and access patterns from potential leakage. Our experimental results demonstrate ECMO's efficiency and scalability, with a single store operation containing 500 keywords taking only \u0000<inline-formula><tex-math>$42.5 ;mu s$</tex-math></inline-formula>\u0000 on average.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"37-48"},"PeriodicalIF":0.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10767272","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938074","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}

{"title":"Boosting Depth Estimation for Self-Driving in a Self-Supervised Framework via Improved Pose Network","authors":"Yazan Dayoub;Andrey V. Savchenko;Ilya Makarov","doi":"10.1109/OJCS.2024.3505876","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3505876","url":null,"abstract":"Depth estimation is a critical component of self-driving vehicles, enabling accurate scene understanding, obstacle detection, and precise localization. Improving the performance of depth estimation networks without increasing computational cost is highly advantageous for autonomous driving systems. In this article, we propose to enhance depth estimation by improving the pose network in a self-supervised framework. Unlike conventional pose networks, our approach preserves more detailed spatial information by integrating multi-scale features and normalized coordinates. This improved spatial awareness allows for more accurate depth predictions. Comprehensive evaluations on the KITTI and Make3D datasets show that our method yields a 2-7% improvement in the absolute relative error (abs_rel) metric. Furthermore, on the KITTI odometry dataset, our approach demonstrates competitive performance, with relative translational error (\u0000<inline-formula><tex-math>$t_{rel}$</tex-math></inline-formula>\u0000) of \u0000<inline-formula><tex-math>$6.11$</tex-math></inline-formula>\u0000 and \u0000<inline-formula><tex-math>$7.21$</tex-math></inline-formula>\u0000, and relative rotational error (\u0000<inline-formula><tex-math>$r_{rel}$</tex-math></inline-formula>\u0000) of \u0000<inline-formula><tex-math>$1.12$</tex-math></inline-formula>\u0000 and \u0000<inline-formula><tex-math>$2.05$</tex-math></inline-formula>\u0000 for sequences 9 and 10, respectively.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"109-118"},"PeriodicalIF":0.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10767273","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938079","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}

{"title":"IGFU: A Hybrid Underwater Image Enhancement Approach Combining Adaptive GWA, FFA-Net With USM","authors":"Xin Yuan;Chenhui Wang;Xiaohong Chen;Mingxuan Wang;Ning Li;Changli Yu","doi":"10.1109/OJCS.2024.3492698","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3492698","url":null,"abstract":"To address the issue of color distortion and blurriness in underwater imageries, a hybrid Underwater Image Enhancement (UIE) method combining Adaptive Gray World Algorithm (GWA), Feature Fusion Attention Network (FFA-Net) and Unsharp Masking (USM) is proposed in this research. This method begins with color correction by applying different stretching processes to the RGB components based on the image's color information, and iteratively corrects the colors. Next, the corrected image undergoes dehazing via FFA-Net to eliminate underwater haze and improve clarity. Ultimately, USM is applied to amplify high-frequency components, thus enhancing edge details. Qualitative and quantitative comparisons demonstrate that the proposed Improved GWA FFA-Net USM (IGFU) method outperforms existing techniques in underwater image quality.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"294-306"},"PeriodicalIF":0.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10767312","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403969","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}

{"title":"DiReDi: Distillation and Reverse Distillation for AIoT Applications","authors":"Chen Sun;Qiang Tong;Wenshuang Yang;Wenqi Zhang","doi":"10.1109/OJCS.2024.3505195","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3505195","url":null,"abstract":"Artificial Intelligence & Internet of Things (AIoT) have been widely utilized in various application scenarios. Significant efficiency can typically be achieved by deploying different edge-AI models in various real-world scenarios while a few large models manage those edge-AI models remotely from cloud servers. However, customizing edge-AI models for each user's specific application or extending current models to new application scenarios remains a challenge. Inappropriate local training or fine-tuning of edge-AI models by users can lead to model malfunction, potentially resulting in legal issues for the manufacturer. To address the aforementioned issues, this article proposes an innovative framework called “DiReDi”, which involves knowledge \u0000<bold>Di</b>\u0000stillation & \u0000<bold>Re</b>\u0000verse \u0000<bold>Di</b>\u0000stillation. In the initial step, an edge-AI model is trained with presumed data and a knowledge distillation (KD) process using the cloud AI model in the upper management cloud server. This edge-AI model is then dispatched to edge-AI devices solely for inference in the user's application scenario. When the user needs to update the edge-AI model to better fit the actual scenario, two reverse distillation (RD) processes are employed to extract the knowledge – the difference between user preferences and the manufacturer's presumptions from the edge-AI model using the user's exclusive data. Only the extracted knowledge is reported back to the upper management cloud server to update the cloud AI model, thus protecting user privacy by not using any exclusive data. The updated cloud AI can then update the edge-AI model with the extended knowledge. Simulation results demonstrate that the proposed DiReDi framework allows the manufacturer to update the user model by learning new knowledge from the user's actual scenario with private data. The initial redundant knowledge is reduced since the retraining emphasizes user private data. Furthermore, this model update approach via cloud allows manufacture to check model updates ensuring that all models are managed safely and effectively.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"748-760"},"PeriodicalIF":0.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10766444","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798053","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}

{"title":"Emerging Technologies Driving Zero Trust Maturity Across Industries","authors":"Hrishikesh Joshi","doi":"10.1109/OJCS.2024.3505056","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3505056","url":null,"abstract":"This study explores the profound impact of emerging technologies on the Zero Trust paradigm and the challenges they present in the evolving cybersecurity landscape. As organizations grapple with increasingly complex threats, the integration of innovative technologies with Zero Trust principles offers both promising solutions and new challenges. The research investigates how artificial intelligence, machine learning, blockchain, quantum computing, and cloud/edge technologies are reshaping the implementation and efficacy of Zero Trust architectures. These technologies enable more sophisticated trust evaluation algorithms, enhanced threat intelligence, and dynamic access control mechanisms, thereby extending the boundaries of traditional Zero Trust models. The rapid pace of innovation introduces complexities in maintaining continuous verification and least-privilege access across hybrid and multi-cloud environments. Furthermore, the integration of AI and machine learning in Zero Trust frameworks raises questions about data privacy, algorithmic bias, and the need for explainable security decisions. The article proposes a methodology for addressing these challenges, emphasizing the need for adaptive Zero Trust strategies that can evolve alongside technological advancements. Through examination of real-world case studies and empirical research, this study provides insights into the practical implications of emerging technologies on Zero Trust implementation. It offers guidance for enterprises on harnessing these technologies to create more resilient, responsive, and effective cybersecurity measures. This research aims to equip organizations with the knowledge and strategies necessary to embrace emerging technologies within a Zero Trust framework, enabling them to navigate the complex interplay between innovation and security in the digital age.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"25-36"},"PeriodicalIF":0.0,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10764723","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940869","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}

{"title":"Time Series Classification of Raw Voice Waveforms for Parkinson's Disease Detection Using Generative Adversarial Network-Driven Data Augmentation","authors":"Marta Rey-Paredes;Carlos J. Pérez;Alfonso Mateos-Caballero","doi":"10.1109/OJCS.2024.3504864","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3504864","url":null,"abstract":"Parkinson's disease (PD) is a neurodegenerative disorder that affects more than 10 million people worldwide. Despite its prevalence, the detection of PD remains a complicated task, as no gold standard test has yet been developed to provide an accurate diagnosis. In this context, many recent studies have focused on the automatic detection and progression tracking of PD from voice-related characteristics, being feature engineering the most common approach. This work intends to address an existing research gap by introducing a novel strategy that analyzes raw voice waveforms. Despite recent advancements, one of the significant hurdles is still the lack of extensive and diverse datasets. This article also implements a data augmentation solution. Big Vocoder Slicing Adversarial Network (BigVSAN) is used to generate synthetic voice data that mimics the characteristics of real patients and healthy subjects. For the PD detection task, deep learning models such as ResNet, LSTM-FCN, InceptionTime, and CDIL-CNN are used. The experiments were performed using the speech task of sustained vowel /a/ in the PC-GITA database, which contains the recordings of healthy and PD subjects. CDIL-CNN achieves the best results, improving the accuracy by 15.87% (8.96%) compared to the model that does not use augmented data (from the best method found in the literature that uses voice waveforms). The results of this study indicate that models trained with raw waveforms showcase modest but promising performance, underlying the potential of audio analysis to improve the early detection of PD, providing a non-invasive and potentially remotely applicable method.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"72-84"},"PeriodicalIF":0.0,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10764737","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938077","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}

{"title":"Multimodal EEG-fNIRS Seizure Pattern Decoding Using Vision Transformer","authors":"Rafat Damseh;Abdelhadi Hireche;Parikshat Sirpal;Abdelkader Nasreddine Belkacem","doi":"10.1109/OJCS.2024.3500032","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3500032","url":null,"abstract":"Epilepsy has been analyzed through uni-modality non-invasive brain measurements such as electroencephalogram (EEG) signal, but identifying seizure patterns is more challenging due to the non-stationary nature of the brain activity and various non-brain artifacts. In this article, we leverage a vision transformer model (ViT) to classify three types of seizure patterns based on multimodal EEG and functional near-infrared spectroscopy (fNIRS) recordings. We used spectral encoding techniques to capture temporal and spatial relationships for brain signals as feature map inputs to the transformer architecture. We evaluated model performance using the receiver operating characteristic (ROC) curves and the area under the curve (AUC), demonstrating that multimodal EEG-fNIRS signals improved the classification accuracy of seizure patterns. Our work showed that power spectral density (PSD) features often led to better results than features derived from dynamic mode decomposition (DMD), particularly for seizures with high-frequency oscillations (HFO) and generalized spike-and-wave discharge (GSWD) patterns, with an accuracy of 93.14% and 91.69%, respectively. Low-voltage fast activity (LVFA) seizures achieved consistently high performance in EEG, fNIRS, and multimodal EEG-fNIRS setups. Overall, our findings suggest the effectiveness of using the ViT architecture with multimodal brain data accompanied by appropriate spectral features to classify the neural activity of epileptic seizure patterns.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"724-735"},"PeriodicalIF":0.0,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10755173","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713874","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}

{"title":"GHOSTForge: A Scalable Consensus Mechanism for DAG-Based Blockchains","authors":"Misbah Khan;Shabnam Kasra Kermanshahi;Jiankun Hu","doi":"10.1109/OJCS.2024.3497892","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3497892","url":null,"abstract":"Blockchain scalability has long been a critical issue, and Directed Acyclic Graphs (DAGs) offer a promising solution by enabling higher throughput. However, despite their scalability, achieving global convergence or consensus in heterogeneous DAG networks remains a significant challenge. This work, introduces GHOSTForge, building on the Greedy Heaviest-Observed Sub-tree (GHOST) protocol to address these challenges. GHOSTForge incorporates unique coloring and scoring mechanisms alongside stability thresholds and order-locking processes. This protocol addresses the inefficiencies found in existing systems, such as PHANTOM, by offering a more proficient two-level coloring and scoring method that eliminates circular dependencies and enhances scalability. The use of stability thresholds enables the early locking of block orders, reducing computational overhead while maintaining robust security. GHOSTForge's design adapts dynamically to varying network conditions, ensuring quick block order convergence and strong resistance to attacks, such as double-spending. Our experimental results demonstrate that GHOSTForge excels in achieving both computational efficiency and rapid consensus, positioning it as a powerful and scalable solution for decentralized, heterogeneous DAG networks.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"736-747"},"PeriodicalIF":0.0,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10753055","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142736362","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}