检索结果-内蒙古大学图书馆

International Conference on ICT For Smart Society (ICISS)

作者： Wikan Danar Sunindyo Alfrojems Knowledge and Software Engineering Research Group School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Indonesia Business Coalition for Women Empowerment South Jakarta Indonesia

Accelerating regional economic growth is needed to be able to catch up with a region, especially if the region has economic potential, especially in terms of natural capital, such as a beautiful environment. However, in practice, a development process will experience obstacles as an inseparable part. This condition certainly requires appropriate treatment efforts based on empirical evidence data. This also happened to West Lombok. Where in fact the regions that get the opportunity to become Smart City pilots certainly have a positive impact, but the challenges that must be carried out also go hand in hand with the process of implementing these efforts. Referring to this background, the purpose of this research is to be able to explore and analyze the challenges experienced by West Lombok in implementing the Smart City program in its region. The method used is qualitative with data collection techniques in the form of documentation studies, observations, interviews, and focus group discussions. This study involved 50 informants with various backgrounds but still in accordance with the characteristics of the informants determined by the researcher through the use of purposive sampling technique. The results of this study are that there are four challenges that need to get more attention from the local government of West Lombok and its stakeholders as an effort to realize West Lombok as a smart city. The four challenges include policy, infrastructure, human capital, and environment. The need for strategic efforts carried out by West Lombok to be able to encourage the achievement of the target of becoming a smart city in Indonesia, especially in West Nusa Tenggara Province.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using analytic hierarchy process to evaluate deep learning for infrared target recognition

引用

Multimedia Tools and Applications 2024年第38期83卷 86229-86245页

作者： Xu, Laixiang Cao, Bingxu Wei, Xinhong Li, Bei Su, Jingfeng Ning, Shiyuan Zhao, Junmin School of Computer and Data Science Henan University of Urban Construction Pingdingshan467036 China School of Information Engineering Luohe Vocational Technology College Henan University of Technology Luohe Institute of Technology Luohe462000 China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Pingdingshan467036 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan467036 China Department of Software Information China Electronics Technology Group Corporation 36-th Research Institute Jiaxing314033 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan467036 China

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

ONNXPruner: ONNX-Based General Model Pruning Adapter

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第07期PP卷 PP页

作者： Ren, Dongdong Li, Wenbin Ding, Tianyu Wang, Lei Fan, Qi Huo, Jing Pan, Hongbing Gao, Yang Nanjing University School of Electronic Science and Engineering China Nanjing University State Key Laboratory for Novel Software Technology School of Intelligence Science and Technology China Microsoft Corporation Applied Sciences Group RedmondWA98052 United States University of Wollongong School of Computing and Information Technology NSW2522 Australia

Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically adapt to various model architectures. These trees clarify the structural relationships between nodes, guiding the pruning process, particularly highlighting the impact on interconnected nodes. Furthermore, we introduce a tree-level evaluation method. By leveraging node association trees, this method allows for a comprehensive analysis beyond traditional single-node evaluations, enhancing pruning performance without the need for extra operations. Experiments across multiple models and datasets confirm ONNXPruner's strong adaptability and increased efficacy. Our work aims to advance the practical application of model pruning. © 1979-2012 IEEE.

关键词： deep neural network General model pruning ONNX tree-level evaluation

来源：评论

学校读者我要写书评

暂无评论

Assessing the Security of GitHub Copilot's Generated Code - A Targeted Replication Study

Assessing the Security of GitHub Copilot's Generated Code - ...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Vahid Majdinasab Michael Joshua Bishop Shawn Rasheed Arghavan Moradidakhel Amjed Tahir Foutse Khomh Department of Computer and Software Engineering Polytechnique Montreal Canada School of Mathematical and Computational Sciences Massey University New Zealand Information & Communication Technology Group UCOL - Te Pukenga New Zealand

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

AI-powered code generation models have been developing rapidly, allowing developers to expedite code generation and thus improve their productivity. These models are trained on large corpora of code (primarily sourced from public repositories), which may contain bugs and vulnerabilities. Several concerns have been raised about the security of the code generated by these models. Recent studies have investigated security issues in AI-powered code generation tools such as GitHub Copilot and Amazon Code Whisperer, revealing several security weaknesses in the code generated by these tools. As these tools evolve, it is expected that they will improve their security protocols to prevent the suggestion of insecure code to developers. This paper replicates the study of Pearce et al., which investigated security weaknesses in Copilot and uncovered several weaknesses in the code suggested by Copilot across diverse scenarios and languages (Python, C, and Verilog). Our replication examines Copilot's security weaknesses using newer versions of Copilot and CodeQL (the security analysis framework). The replication focused on the presence of security vulnerabilities in Python code. Our results indicate that, with the improvements in newer versions of Copilot, the percentage of vulnerable code suggestions has reduced from 36.54% to 27.25%. Nonetheless, it remains evident that the model still suggests insecure code.

关键词： Productivity Codes Protocols Reviews Filtering software Security

来源：评论

学校读者我要写书评

暂无评论

Human Resource Application Development using Person-Job Matching for Placement of Prospective Employees

Human Resource Application Development using Person-Job Matc...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Alifiah Putri Sinung Suakanto Joko Siswanto Farah Fitriavida Arifin Irfan Darmawan Dina Angela Department of Information System Faculty of Software Engineering Telkom University Bandung Indonesia Industrial Engineering Research Group Bandung of Institute Technology Bandung Indonesia Information Techology Research Group Faculty of Industrial Engineering Institut Teknologi Harapan Bangsa Bandung Indonesia

The recruitment process presents a significant challenge for Human Resource (HR) staff, particularly in their ability to objectively assess candidate competencies and align them with job requirements. While qualitative comparisons between resumes and position requirements may yield candidates who appear suitable, this approach proves ineffective in terms of time and cost. Furthermore, many recruiters lack sufficient knowledge of the positions they are hiring for, making it difficult to justify their selection decisions. This research aims to address this challenge by developing an HR person-job matching application for the recruitment of prospective employees. The study focuses on analyzing and designing applications that can quantitatively measure the competencies of candidates and compare them with job requirements using a person-job matching method. The effectiveness of this approach was evaluated by testing it on a sample of employees from small and medium-sized enterprises (SMEs). The study found that out of the 16 employees across three job positions, the person-job matching application achieved an accuracy rate of 75%. This accuracy percentage was determined by comparing the fit value results with the actual conditions of the employees in their respective workplaces. The findings highlight the potential of the HR person-job matching application to enhance the efficiency and effectiveness of recruitment efforts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tiled Phased Array Antennas by 3D Hybrid Integration technology

Tiled Phased Array Antennas by 3D Hybrid Integration Technol...

引用

International Conference on Systems and Informatics (ICSAI)

作者： Wei Hao Han Wei Zhang Naibo The 54th Research institute of China Electronics Technology Group Corporation (CETC-54) Shijiazhuang China National Engineering Research Center of Communication Software and ASIC Design Shijiazhuang China

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

In order to decrease the weight and size of phased array antennas (PAA) with the performance of high reliability, the novel tiled PAA by three-dimensional (3D) hybrid integration technology was designed. The proposed PAA include 36-element antenna units in package (AiP) based on high temperature co-fired ceramic (HTCC) substrate, 36-channel ratio frequency (RF) transmit/receive (T/R) module, a beam-form networks using hybrid power dividers, a beam-form control circuit and other devices. The tiled integration of the PAA use the ceramic interposer with multilayer circuits, fuzz buttons and balls grid array(BGA), whose size and weight are less than $\mathbf{60}\mathbf{mm}\times \mathbf{60}\mathbf{mm}\times \mathbf{18}\mathbf{mm}$ and 134g, respectively. To improve the circular polarization of the AiP, a unit cell of every 4-element is designed by sequentially clockwise by 90 degree. Measured results demonstrate that, from 21GHz to 21.5GHz, the PAA's normal EIRP and G/T are better than 49dBm and -10dB/K, respectively. The scan angle of the beam form is more than $\pm \mathbf{45}^{\circ}$ . The measured results achieve a good agreement with the simulated results.

关键词： Phased arrays Antenna measurements Wiring Three-dimensional displays Transmitting antennas Seals Nonhomogeneous media Ceramics Temperature control Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

Pixel memory sharing based multi-scale features perception method for remote sensing images

Pixel memory sharing based multi-scale features perception m...

引用

2024 International Conference on Remote Sensing and Digital Earth, RSDE 2024

作者： Li, Ziyan Wang, Biao Yang, Hui Wu, Yongchuang Ye, Zhiyuan Wu, Yanlan School of Artificial Intelligence Anhui University Anhui Hefei230601 China School of Resource and Environmental Engineering Anhui University Anhui Hefei230601 China Institutes of Physical Science and Information Technology Anhui University Anhui Hefei230601 China State Grid Information & Telecommunication Group Co. Ltd Anhui Jiyuan Software Co.Ltd Anhui Hefei230088 China

ISBN: (数字)9781510688223

ISBN: (纸本)9781510688216

Semantic segmentation of high-resolution remote sensing images is vital for various applications, including environmental monitoring, urban planning, and land resource management. Nonetheless, these images frequently pose challenges owing to substantial intra-class similarity and considerable inter-class variation, which often result in the misclassification of small target objects. To address these issues, we introduce an innovative deep learning network model that employs pixel memory sharing to improve feature representation and enhance segmentation accuracy. Our model employs the Swin Transformer as the backbone, which effectively reduces the computational burden associated with high-resolution feature extraction while maintaining rich contextual information. Despite these advancements, semantic information loss during the encoder phase poses a significant question, potentially compromising the overall segmentation accuracy. To address this question, we introduce the Pixel Memory Feature Fusion Module (PMFFM), which retains original pixel features and mitigates detailed information loss during feature propagation through effective memory sharing and fusion. PMFFM assigns different weights to each pixel to represent memory and guide multi-level feature fusion. During the decoder, the integration of feature memory sharing with PMFFM ensures the completeness of features at each layer, allowing each multi-scale feature layer to be representative and distinctive. Extensive experiments conducted on the ISPRS Vaihingen dataset demonstrate that our proposed method substantially enhances segmentation performance, leading to significant improvements across key evaluation metrics. © 2025 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

MKGL: mastery of a three-word language 24

MKGL: mastery of a three-word language

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Lingbing Guo Zhongpu Bo Zhuo Chen Yichi Zhang Jiaoyan Chen Yarong Lan Mengshu Sun Zhiqiang Zhang Yangyifei Luo Qian Li Qiang Zhang Wen Zhang Huajun Chen College of Computer Science and Technology Zhejiang University and ZJU-Ant Group Joint Lab of Knowledge Graph Ant Group Department of Computer Science The University of Manchester School of Computer Science and Engineering Beihang University School of Computer Science Beijing University of Posts and Telecommunications School of Software Technology Zhejiang University and ZJU-Ant Group Joint Lab of Knowledge Graph

ISBN: (纸本)9798331314385

Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal hallucinations, remains an underexplored frontier. In this paper, we investigate the integration of LLMs with KGs by introducing a specialized KG Language (KGL), where a sentence precisely consists of an entity noun, a relation verb, and ends with another entity noun. Despite KGL's unfamiliar vocabulary to the LLM, we facilitate its learning through a tailored dictionary and illustrative sentences, and enhance context understanding via real-time KG context retrieval and KGL token embedding augmentation. Our results reveal that LLMs can achieve fluency in KGL, drastically reducing errors compared to conventional KG embedding methods on KG completion. Furthermore, our enhanced LLM shows exceptional competence in generating accurate three-word sentences from an initial entity and interpreting new unseen terms out of KGs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prune and Merge: Efficient Token Compression for Vision Transformer with Spatial Information Preserved

引用

IEEE Transactions on Multimedia 2025年

作者： Mao, Junzhu Shen, Yang Guo, Jinyang Yao, Yazhou Hua, Xiansheng Shen, Hengtao Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Beihang University State Key Laboratory of Software Development Environment Institute of Artificial Intelligence Beijing100191 China Terminus Group Beijing100027 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token compression method called Prune and Merge. Our approach integrates token pruning and merging operations within transformer models to achieve layer-wise token compression. By introducing trainable merge and reconstruct matrices and utilizing shortcut connections, we efficiently merge tokens while preserving important information and enabling the restoration of pruned tokens. Additionally, we introduce a novel gradient-weighted attention scoring mechanism that computes token importance scores during the training phase, eliminating the need for separate computations during inference and enhancing compression efficiency. We also leverage gradient information to capture the global impact of tokens and automatically identify optimal compression structures. Extensive experiments on the ImageNet-1k and ADE20K datasets validate the effectiveness of our approach, achieving significant speed-ups with minimal accuracy degradation compared to state-of-the-art methods. For instance, on DeiT-Small, we achieve a 1.64× speed-up with only a 0.2% drop in accuracy on ImageNet-1k. Moreover, by compressing segmenter models and comparing with existing methods, we demonstrate the superior performance of our approach in terms of efficiency and effectiveness. Code and models have been made available at https://***/NUST-Machine-Intelligence-Laboratory/prune_and_merge. © 1999-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

MODELLING THE THREE-POINT BENDING OF NOVEL BIOINSPIRED DENTAL CROWN COMPOSITES 23

MODELLING THE THREE-POINT BENDING OF NOVEL BIOINSPIRED DENTA...

引用

23rd International Conference on Composite Materials, ICCM 2023

作者： Jargalsaikhan, U. Wan, H. Leung, N. Su, B. Song, X. Hu, J. Sui, T. Bioinspired Materials Group Department of Mechanical Engineering Sciences University of Surrey Guildford Surrey United Kingdom Bristol Dental School University of Bristol Bristol United Kingdom Department of Mechanical and Automation Engineering Chinese University of Hong Kong Shatin Hong Kong Sente Software Ltd. Surrey Technology Centre 40 Occam Road Guildford Surrey United Kingdom

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：