检索结果-内蒙古大学图书馆

Hierarchical Partitioning-Based Inter-Chip Redistribution Layer Routing for Fan-Out Wafer-Level Packaging

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Xu, Haoyang Huang, Xing Zhuang, Zhen Yu, Zhiwen Guo, Bin Chao, Kai-Yuan Yu, Bei Ho, Tsung-Yi Wong, Martin D. F. Northwestern Polytechnical University School of Computer Science Xi’an China Harbin Engineering University College of Computer Science and Technology Harbin China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong Siemens Digital Industries Software WilsonvilleOR United States Hong Kong Baptist University Hong Kong

In modern advanced fan-out wafer-level packaging (FOWLP), redistribution layers (RDLs) are used to implement efficient interconnections among chips, where both flexible vias and irregular pad structures can be deployed to realize highly integrated heterogeneous systems. With the sharp increase in chip densities, however, it becomes challenging to fully utilize the routing resources in RDLs. The routing graph without optimized resource planning can lead to significant deterioration in the solution quality of RDL design. Furthermore, prior work determines via locations in the RDLs before identifying wire routes, thus offsetting the advantages of flexible vias and irregular pads. To systematically solve the RDL routing problem in FOWLP, in this paper, we propose a hierarchical partitioning-based inter-chip routing method considering both flexible vias and irregular pads, so that optimized RDL solutions can be generated automatically and efficiently. The proposed method includes the following key techniques: 1) a channel planning method for optimized routing region partition and a dynamic routing graph-based pathfinding method for efficient global routing, 2) a binarysearch-based hierarchical tile segmentation method for conflict removal and wirelength reduction, 3) a novel monotonicityanalysis-based access point optimization method and a staggered via planning strategy for both wirelength and detour reduction, and 4) a geometry-based detailed routing algorithm for innertile wire routing. The experimental results demonstrate that the proposed algorithm leads to 100% routablility and 4.8% wirelength reduction on average compared to the state-of-the-art work, with a maximum reduction rate of 10.3% across all the benchmarks. © 1982-2012 IEEE.

关键词： Chip scale packages

来源：评论

学校读者我要写书评

暂无评论

CAPAST: Content Affinity Preserved Arbitrary Style Transfer

CAPAST: Content Affinity Preserved Arbitrary Style Transfer

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xinyuan Zheng Xiaojie Li Canghong Shi Jia He Zhan Ao Huang Xian Zhang Imran Mumtaz School of Computer Science Chengdu University of Information Technology China School of Computer and Software Engineering Xihua University China Faculty of Engineering and Mathematical Sciences The University of Western Australia Australia Department of Computer Science University of Agriculture Faisalabad Pakistan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Balancing the consistency of style and the integrity of content is the main challenge in arbitrary style transfer domain. Currently, local style details can be effectively captured by attention mechanism but easily produce distorted style patterns and inconsistent content structure. In this paper, we propose a Content Affinity Preserving Arbitrary Style Transfer (CAPAST) framework to ensure style features can be stably integrated into the content structure. Considering the local feature learning ability of CNN and the global feature representation advantage of transformer, a dual encoder is proposed to capture local and global features of images with the combination between transformer and CNN. In addition, a channel and spatially aligned attention (CSAA) is introduced to generate high-quality results by stably fusing style features and content features. In experiments, we demonstrated the superior performance of our method in preventing content structure distortion and maintaining consistency between style and content. Codes are available at https://***/miaopashi-zxy/CAPAST.

关键词： Representation learning Acoustic distortion Codes Attention mechanisms Fuses Transformers Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

An empirical study of exploring the predictors of university teachers’ job satisfaction in Bangladesh: A structural equation modeling approach

引用

Heliyon 2025年第2期11卷 e41740页

作者： Zebon, Md Abdul Hye Sattar, Abdus Ahamed, Md Sazzadur Department of Software Engineering Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh

This study aims to investigate the factors influencing job satisfaction among university teachers, considering various complex constructs such as salary and financial benefits, career growth and opportunities, relationships with colleagues, recognition, working environment, and leadership. Utilizing a quantitative cross-sectional research design, the present study was conducted in Bangladesh between August and December 2022. Encompassing 7 public universities and 12 private universities, the research purposively sampled 95 participants, adhering to a systematic and comprehensive approach to data collection. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The empirical findings of the study revealed that career growth and opportunities (β = 0.225, t = 2.023, p < 0.10), leadership (β = 0.262, t = 1.757, p < 0.10), and relationships with colleagues (β = 0.166, t = 1.519, p < 0.10) had a significant positive impact on university teachers' job satisfaction. On the other hand, salary and financial benefits (β = 0.082, t = 0.823, p > 0.10), recognition (β = 0.02, t = 0.208, p > 0.10), and working environment (β = 0.14, t = 1.057, p > 0.10) had a positive but less significant impact on job satisfaction among university teachers. The overall findings provide valuable insights that can assist policymakers and stakeholders in implementing synchronized strategies to enhance job satisfaction among university teachers, ultimately leading to improved university teachers’ job performance. © 2025 The Authors

关键词： Bangladesh Career growth and opportunity Job satisfaction Leadership PLS-SEM Recognition Relationship with colleagues Salary and financial benefits University teachers Working environment

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Tesseract and EasyOCR for Bangla Optical Character Recognition on the Novel Bangla CrossHair Dataset

Performance Analysis of Tesseract and EasyOCR for Bangla Opt...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Abdulla Nasir Chowdhury Aftar Ahmad Sami Shah Masud Parvej Mamun Shakib Absar Fuad Rahman Md. Saidur Rahman Kohinoor Department of Electrical and Electronic Engineering Leading University Sylhet Bangladesh Department of Computer Science and Engineering Leading University Sylhet Bangladesh Department of Software Engineering Taylor’s University Kualalampur Malaysia Department of Information and Computer Science King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

This paper presents a comparative study of key metrics for OCR engines in Bangla language processing. PyTesseract (a Python wrapper for Tesseract OCR) and EasyOCR were benchmarked on a novel dataset, "Bangla-CrossHair," created for testing OCR engines. This dataset combines samples from "Bangla Text Detection and Recognition," "Bangla Handwritten Characters," and "Bangla Handwritten Words" datasets and includes diverse image types, such as blurred, clear, torn, and tilted. Results show EasyOCR outperforms PyTesseract in several scenarios, while PyTesseract consistently demonstrated faster processing. Since many OCR engines provide pre-trained capabilities, traditional metrics like training and validation accuracy are challenging to measure for some models, including PyTesseract. Instead, Character Level Accuracy, Word Level Accuracy, Levenshtein Distance, Character Error Rate, Word Error Rate, Precision, Recall, F1-Score, and Inference time were measured for an unbiased evaluation.

关键词： Training Accuracy Error analysis Text recognition Optical character recognition Measurement uncertainty Text detection Time measurement Performance analysis Engines

来源：评论

学校读者我要写书评

暂无评论

MAP-SIM: A DNN-Specific Mapping Optimization Framework for Shared-Memory CPU-Systolic Array Architectures

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Li, Yuhang Wen, Mei Shen, Junzhong Chen, Zhaoyun Shi, Yang Wang, Tianyu Shao, Zili National University of Defense Technology College of Computer Science and Technology Hunan Changsha410073 China Shenzhen University College of Computer Science and Software Engineering Guangdong Shenzhen518052 China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong

As performance demands continue to rise, Shared-Memory Heterogeneous Systems (SMHSs) have been widely adopted for their ability to enable efficient communication and data sharing between different heterogeneous cores. However, existing SMHS face challenges in uneven workload distribution among heterogeneous cores and suboptimal mapping schemes, preventing them from fully leveraging their architectural advantages. To address these issues, this paper proposes a mapping-aware framework for modeling SMHSs called MAP-SIM. By performing performance modeling for CPUs and Systolic Arrays (SAs), and considering rational schemes for the partition and mapping of computational tasks, MAP-SIM aims to evaluate and optimize the computational performance of heterogeneous multicore architectures. The experimental results show that compared to previous work, MAP-SIM can increase simulation speed by 14 to 67 times and can also enhance the computational performance of SMHS by 1.4 to 4.4 times. © 1982-2012 IEEE.

关键词： Photomapping

来源：评论

学校读者我要写书评

暂无评论

AI Integration in the IT Professional Workplace: A Scoping Review and Interview Study with Implications for Education and Professional Competencies 2024

AI Integration in the IT Professional Workplace: A Scoping R...

引用

29th Working Group Reports on Innovation and Technology in computer science Education, ITiCSE WGR 2024

作者： Clear, Tony Cajander, Åsa Clear, Alison Mcdermott, Roger Daniels, Mats Divitini, Monica Forshaw, Matthew Humble, Niklas Kasinidou, Maria Kleanthous, Styliani Kultur, Can Parvini, Ghazaleh Polash, Mohammad Zhu, Tingting Department of Computer Science and Software Engineering Auckland University of Technology Auckland New Zealand Department of Information Technology Uppsala University Uppsala Sweden School of Business Eastern Institute of Technology Auckland New Zealand School of Computing Robert Gordon University Aberdeen United Kingdom Dpt. of Computer Science Norwegian University of Science and Technology Trondheim Norway The Alan Turing Institute Newcastle Upon Tyne United Kingdom Open University of Cyprus Nicosia Cyprus The Open University of Cyprus Nicosia Cyprus School of Computer Science Carnegie Mellon University PittsburghPA United States Manning College of Information and Computer Sciences University of Massachusetts Amherst Amherst United States School of Computer Science University of Sydney Sydney Australia Department of Geography Geomatics and Environment University of Toronto Mississauga Toronto Canada School of Computer Science Newcastle University Newcastle upon Tyne United Kingdom

ISBN: (纸本)9798400712081

As Artificial Intelligence (AI) continues transforming workplaces globally, particularly within the Information Technology (IT) industry, understanding its impact on IT professionals and computing curricula is crucial. This research builds on joint work from two countries, addressing concerns about AI's increasing influence in IT sector workplaces and its implications for tertiary education. The study focuses on AI technologies such as generative AI (GenAI) and large language models (LLMs). It examines how they are perceived and adopted and their effects on workplace dynamics, task allocation, and human-system interaction. IT professionals, noted as early adopters of AI, offer valuable insights into the interplay between AI and work engagement, highlighting the significant competencies required for digital workplaces. This study employs a dual-method approach, combining a systematic and multi-vocal literature review and qualitative research methods. These included a thematic analysis of a set of 47 interviews conducted between March and May of 2024 with IT professionals in two countries (New Zealand and Sweden). The research aimed to understand the implications for computing students, education curricula, and the assessment of emerging professional competencies. The literature review found insufficient evidence addressing comprehensive AI practice methodologies, highlighting the need to both develop and regulate professional competencies for effective AI integration. Key interview findings revealed diverse levels of GenAI adoption, ranging from individual experimentation to institutional integration. Participants generally expressed positive attitudes toward the technology and were actively pursuing self-learning despite some concerns. The themes emerging from the interviews included AI's role in augmenting human tasks, privacy and security concerns, productivity enhancements, legal and ethical challenges, and the evolving need for new competencies in the workplace.

关键词： artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

AI-powered Career Guidance System

AI-powered Career Guidance System

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Nuha El-Khalili Kinda Suliman Dardese Nagham Thamer Alotaibi Yara Mubaydeen Iman Tahboub Software Engineering Department University of Petra Amman Jordan Data Science and Artificial Intelligence University of Petra Amman Jordan Computer Science Department University of Petra Amman Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Choosing the right major at an early age can be overwhelming. In addition, career advising is limited in many schools. Studies show that among the factors that affects career selection are personal attributes, passion, and career exploration activities. In this study, we present an AI powered application utilizing Flutter and Virtual Reality (VR) technology to assist high school and university students in making informed career choices. The application provides personalized career recommendations based on personality tests. The study analyzed a publicly available dataset combining the results of Big Five personality test with personal information including the study majors. Synthetic Minority Oversampling Technique (SMOTE) was employed to handle class imbalance. Multiple classification models (Random Forest, Gradient Boosting, Decision Tree, Naive Bayes, and KNN) were tested. Our findings demonstrate that the Random Forest classifier, achieved better performance with an accuracy of 87.3% and an AUC-ROC of 0.99.

关键词： Solid modeling Accuracy Machine learning algorithms engineering profession Virtual reality Nearest neighbor methods Prediction algorithms User experience Random forests Tuning

来源：评论

学校读者我要写书评

暂无评论

A Transfer Learning-based Framework for Enhanced Classification of Perceived Mental Stress using EEG Spectrograms

引用

IEEE Access 2025年 13卷 89266-89286页

作者： Khan, Sheharyar Noorani, Sadam Hussain Frnda, Jaroslav Rauf, Usman Arsalan, Aamir Saeed, Sanay Muhammad Umar University of Engineering and Technology Department of Computer Engineering Taxila47050 Pakistan HITEC University Department of Computer Science Taxila47050 Pakistan University of Žilina Faculty of Operation and Economics of Transport and Communications Department of Quantitative Methods and Economic Informatics Žilina01026 Slovakia Fatima Jinnah Women University Department of Software Engineering Rawalpindi46000 Pakistan

Stress is a significant health concern, impacting both physical and mental well-being. Prolonged exposure to stress can lead to numerous physical health issues, including cardiovascular diseases, and a weakened immune system. This study presents a novel methodology for classifying perceived mental stress using electroencephalography (EEG) signals. By utilizing the publicly available Leipzig Study for Mind-Body-Emotion Interactions dataset, we analyze EEG data collected from 53 participants over a 7-minute resting-state duration. Our approach involves transforming EEG signals into spectrograms using the Short-Time Fourier Transform (STFT), resulting in a time-frequency representation of the input *** employ transfer learning to fine-tune three pre-trained deep neural networks i.e., ResNet50, EfficientNetB0, and DenseNet121 for classifying stress into two and three levels. Our findings demonstrate that the ResNet50 model achieves superior classification accuracies of 95.80% and 86.02% for two and three-level stress classification, respectively, outperforming existing state-of-the-art methods. This study is the first to utilize STFT-generated spectrograms and transfer learning for perceived stress classification, highlighting the efficacy of deep learning techniques in quantifying perceived mental stress through non-invasive EEG recordings. Our results indicate that the proposed method can significantly enhance the accuracy of stress classification frameworks, offering potential improvements in mental health assessment and intervention strategies. © 2013 IEEE.

关键词： Noninvasive medical procedures

来源：评论

学校读者我要写书评

暂无评论

Privacy-Enhancing Paradigms within Federated Multi-Agent Systems

arXiv

引用

arXiv 2025年

作者： Shi, Zitong Wan, Guancheng Huang, Wenke Zhang, Guibin Shao, Jiawei Ye, Mang Yang, Carl National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China National University of Singapore Singapore China Department of Computer Science Emory University United States

LLM-based Multi-Agent Systems (MAS) have proven highly effective in solving complex problems by integrating multiple agents, each performing different roles. However, in sensitive domains, they face emerging privacy protection challenges. In this paper, we introduce the concept of Federated MAS, highlighting the fundamental differences between Federated MAS and traditional FL. We then identify key challenges in developing Federated MAS, including: 1) heterogeneous privacy protocols among agents, 2) structural differences in multi-party conversations, and 3) dynamic conversational network structures. To address these challenges, we propose Embedded Privacy-Enhancing Agents (EPEAgents), an innovative solution that integrates seamlessly into the Retrieval-Augmented Generation (RAG) phase and the context retrieval stage. This solution minimizes data flows, ensuring that only task-relevant, agent-specific information is shared. Additionally, we design and generate a comprehensive dataset to evaluate the proposed paradigm. Extensive experiments demonstrate that EPEAgents effectively enhances privacy protection while maintaining strong system performance. The code will be availiable at https://***/ZitongShi/EPEAgent Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation with Auxiliary Points Prediction of Lesion Location and Boundary

Medical Image Segmentation with Auxiliary Points Prediction ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yu Fan Zhihui Lai Heng Kong Tianying Feng College of Computer Science and Software Engineering Shenzhen University China Department of Thyroid and Breast Surgery BaoAn Central Hospital of Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In order to obtain good medical image segmentation results, existing studies usually extract multi-scale features or design special attention to obtain global and local information of images. However, the above methods are very cumbersome or have a high computational burden. Theoretically, global and local contexts are used to locate objects and refine their contours respectively. Therefore, from a novel points prediction perspective, this work adopts a convolutional model and employs the deep supervision method to assist segmentation by predicting points of the lesion location and boundary. Specifically, we use two points prediction branches to generate location and boundary heatmaps, which implicitly locate lesions and refine contours. Furthermore, in order to train the multi-task model effectively, this work proposes a simple supervision signals design principle to guide deep supervision, so that the training of the auxiliary branch does not conflict with the main task branch. It is worth noting that our simple and end-to-end approach achieves the state-of-the-art results without the need for post-processing. Extensive experiments on three challenging medical image segmentation benchmarks demonstrate the superior performance.

关键词： Training Image segmentation Ultrasonic imaging Convolution Predictive models Breast Feature extraction Lesions Signal design Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：