检索结果-内蒙古大学图书馆

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Lee, Pei-Jun Yu, Chun-Hsien Shiu, Shiuan-Hal Weng, Chi Wei Huang, Shu-Chun Xu, Guo-Cheng Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan Research and Development Department Liscotech System Co.Ltd Taipei Taiwan

ISBN: (纸本)9781665492324

In this paper, we designed and implemented an FPGA-based image system for satellite applications. The FPGA utilizes LVDS receivers to capture data up to eight 180MHz channels. The captured image data will be adjusted by the ADC offset compensator immediately, and after this adjustment, the histogram of each color channel will be booked. The summation of all pixels and the summation of pixels of four-color channels are calculated separately. Then, the control system decides whether the calculation of de-bayer, histogram equalization, and automatic white balance is needed. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

On Pipelined GCN with Communication-Efficient Sampling and Inclusion-Aware Caching

On Pipelined GCN with Communication-Efficient Sampling and I...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Shulin Wang Qiang Yu Xiong Wang Yuqing Li Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Graph convolutional network (GCN) has achieved enormous success in learning structural information from unstructured data. As graphs become increasingly large, distributed training for GCNs is severely prolonged by frequent cross-worker communications. Existing efforts to improve the training efficiency often come at the expense of GCN performance, while the communication overhead persists. In this paper, we propose PSC-GCN, a holistic pipelined framework for distributed GCN training with communication-efficient sampling and inclusion-aware caching, to address the communication bottleneck while ensuring satisfactory model performance. Specifically, we devise an asynchronous pre-fetching scheme to retrieve stale statistics (features, embedding, gradient) of boundary nodes in advance, such that the embedding aggregation and model update are pipelined with statistics transmission. To alleviate communication volume and staleness effect, we introduce a variance-reduction based sampling policy, which prioritizes inner nodes over boundary ones for reducing the access frequency to remote neighbors, thus mitigating cross-worker statistics exchange. Complementing graph sampling, a feature caching module is co-designed to buffer hot nodes with high inclusion probability, ensuring that frequently sampled nodes will be available in local memory. Extensive evaluations on real-world datasets show the superiority of PSC-GCN over state-of-the-art methods, where we can reduce training time by 72%-80% without sacrificing model accuracy.

关键词： Training Estimation error Accuracy Graph convolutional networks Computational modeling Probability Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Proposed National Artificial Intelligence Strategy

Proposed National Artificial Intelligence Strategy

引用

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

作者： Bilal Zahran Belal Ayyoub Department of computer science University of Petra Jordan Department of computer information system Al-Balqa Applied University Jordan Department of Electrical Engineering Al-Balqa Applied University Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

The rapid pace of development in Artificial Intelligence (AI) necessitates formulating effective national strategies for its maximization and minimizing its accompanying repercussions. In this article, a proposed National Artificial Intelligence Strategy for Jordan is formulated, with an orientation towards a systemic and organized national structure relevant to Jordan's socio-economic environment. What is new in this proposed National AI Strategy is its localized orientation, blending AI-facilitated economic development, governance, and ethics relevant to Jordan. It also formulates a governance model, with coordination between principal entities such as government, academia, and private sectors, for effective implementation. The proposed strategy sets specific digital transformation targets, in consonance with Jordan's Vision 2030 and National Strategy for Digital Transformation (2021–2025). AI use in critical sectors such as national security, energy, healthcare, and education takes a top position, with a view towards adhering to regulations, utilizing AI in an ethical manner, and developing technology in a sustainable manner. Outcomes include enhancing AI literacy, diversifying economies, enhancing employment in AI-related industries, and national competitiveness at a global level. This work forms part of an emerging portfolio of studies in national AI strategies and sets a country-specific model in consonance with Jordan's specific development aims, offering a model for AI strategy development in emerging economies.

关键词： Ethics Digital transformation Medical services Regulation Proposals Artificial intelligence Socioeconomics National security Portfolios Videos

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Feature Extraction with Supervised Contrastive Learning for Vulnerability Detection 36

Multi-Scale Feature Extraction with Supervised Contrastive L...

引用

36th International Conference on Software engineering and Knowledge engineering, SEKE 2024

作者： Zhao, Yahui Lu, Lu Liang, Zhihong Suo, Siliang School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China Pengcheng Laboratory Shenzhen China Electric Power Research Institute CSG Guangzhou China Guangdong Provincial Key Laboratory of Power System Network Security Guangzhou China

ISBN: (纸本)1891706594

The capacity of Deep Learning to automatically learn features from source code has facilitated its extensive utilization in detecting software vulnerabilities. However, existing pre-trained models regard code snippets as token sequences, neglecting the inherent structure of the code. The utilization of graph-based code representations is constrained by the limitations of Graph Neural Networks, particularly the difficulty in capturing long-range dependencies, which renders it challenging to learn grammatical and semantic information from complex code graph representations. This paper proposes a novel multi-scale software vulnerability detection method based on supervised contrastive learning. The method integrates local features obtained from code paths with structural features extracted from the Code Property Graph by GraphTrans, thereby achieving a multi-scale feature representation of the source code. Additionally, a supervised contrastive loss function is employed during training in order to fully utilize label information and address the class imbalance problem. The experimental results demonstrate that the proposed method outperforms existing state-of-the-art methods, achieving the highest accuracy, precision, and F1 on the real-world benchmark dataset CodeXGLUE for software vulnerability detection. © 2024 Knowledge systems Institute Graduate School. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Spatial Data Pipeline for Streaming Smart City Data

A Spatial Data Pipeline for Streaming Smart City Data

引用

International Conference on Software engineering Research, Management and Applications (SERA)

作者： Chase Carthen Araam Zaremehrjardi Vinh Le Carlos Cardillo Scotty Strachan Alireza Tavakkoli Sergiu M. Dascalu Frederick C. Harris Computer Science and Engineering University of Nevada Reno Nevada Center for Applied Research University of Nevada Reno System Computing Services Nevada System of Higher Education Reno Reno Nevada

ISBN: (数字)9798350391343

ISBN: (纸本)9798350391350

Point cloud data in the form of LiDAR is often utilized for its spatial qualities, especially in smart city projects for tasks involving vehicles and pedestrians. However, the process in which LiDAR data is acquired can be cumbersome to setup and automate. In this paper, we introduce a streaming and an on-demand pipeline for capturing LiDAR data from Velodyne Ultra Pucks placed along northern Nevada intersections known as the Living Lab as part of a smart city project for the city of Reno. The data coming from these intersections consist of the following formats: ROS 2 bag file, PCD, LAZ, Google Draco, and PCAP. A streaming point cloud service with PCD, LAZ, and Draco was implemented to stream any of these formats, as well as to allow the user to capture the current monitored point cloud. Additionally, two on-demand web services were implemented for both the PCAP and ROS 2 bag file to enable a user to start and stop the acquisition of LiDAR data in these formats. Through our analysis, it was discovered that Draco provided the best processing time and had a wider range of options that affected the quality of the point cloud. To evaluate this pipeline, the features of existing software were compared and a discussion was provided with an analysis of the point cloud formats.

关键词： Point cloud compression Laser radar Pedestrians Smart cities Web services Pipelines Spatial databases

来源：评论

学校读者我要写书评

暂无评论

Recommending Public Transit Route: Ant-Colony Optimization or Dijkstra?

Recommending Public Transit Route: Ant-Colony Optimization o...

引用

Modeling & E-Information Research, Artificial Learning and Digital Applications (ICMERALDA), International Conference on

作者： Abdul Jabbar Aryo Pinandito Informatics Engineering Department Faculty of Computer Science Universitas Brawijaya Malang Indonesia Information System Department Faculty of Computer Science Universitas Brawijaya Malang Indonesia

Advances in algorithmic studies have been made recently, especially in the area of finding the shortest path. Despite taking a greedy approach, the Dijkstra algorithm is well recognized for its efficacy and has established itself as the industry standard for identifying the shortest path in a graph. Conversely, scientists have embraced the Ant-Colony Optimization (ACO) approach, which draws inspiration from the behavior of ants. This study examines the two methods and determines if, given equivalent resources, ACO can generate Dijkstra-like recommendations. Research data is subjected to both algorithms, and the outcomes are presented visually. In data measurement, Dijkstra is processed first to determine the best path, and then the ACO method is applied to produce findings that are similar to Dijkstra. In data measurement, Dijkstra is processed first to determine the best path, and then the ACO method is applied to produce findings that are similar to Dijkstra. Memory consumption, computation time, initial memory allocation, and final memory allocation are evaluation parameters. ACO is more efficient than Dijkstra in terms of execution time and number of pathways traversed, according to the study's repeated evaluation methodology. This iterative assessment procedure is carried out to address the possibility of single measurements resulting from the JavaScript Garbage Collector. The study's findings imply that a larger memory may be necessary for ACO to deliver the desired outcomes. These results could also be impacted by each algorithm's distinct qualities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal planning of a green hydrogen fueling station

Optimal planning of a green hydrogen fueling station

引用

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： António Coelho Filipe Soares José Iria Center for Power and Energy System INESC TEC Porto Portugal College of Engineering and Computer Science Australian National University Canberra Australia

ISBN: (数字)9798350390421

ISBN: (纸本)9798350390438

As the global community transitions towards decarbonization and sustainable energy, green hydrogen is emerging as a key clean energy carrier. This paper addresses the role of hydrogen in transportation, emphasizing the European Union's additionality principle for renewable energy sources in green hydrogen production. It introduces a model for optimally designing hydrogen fueling stations, considering electrolyzers, hydrogen storage, fuel cells, PV systems, and batteries. This model also considers the participation in electricity (energy and secondary reserve), hydrogen, and oxygen markets, and it is evaluated under different additionality policy scenarios. Results indicate that stricter additionality policies reduce the internal rate of return. However, participation in secondary reserve markets significantly boosts operational revenues and compensates for higher investment costs.

关键词： Green energy Electricity Europe Transportation Production Green hydrogen Low carbon economy Planning Smart grids Investment

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection Based on Pre-trained Code Language Model and Convolutional Neural Network 36

Vulnerability Detection Based on Pre-trained Code Language M...

引用

36th International Conference on Software engineering and Knowledge engineering, SEKE 2024

作者： Liao, Tingfeng Lu, Lu Liang, Zhihong Suo, Siliang School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China Pengcheng Laboratory Shenzhen China Electric Power Research Institute CSG Guangzhou China Guangdong Provincial Key Laboratory of Power System Network Security Guangzhou China

ISBN: (纸本)1891706594

Software vulnerabilities damage the reliability of software systems. Recently, many methods based on deep learning have been proposed for vulnerability detection by learning features from code sequences or various property graphs. However, sequence-based methods frequently fail to consider the structural information of the code, whereas graph-based methods often encounter difficulties in capturing long-distance contextual semantic information. To overcome these limitations, we propose PTCN, a novel vulnerability detection method that integrates Pre-Trained code language model and Convolutional Neural Network (CNN). First, the code tokens sequence and the propagation chains are constructed from the source code in preparation for the subsequent feature extraction. Next, GraphCodeBERT, a graph-based pre-trained code language model, is introduced as a means of learning both the semantic and structural information contained in the code tokens sequence and the propagation chains. Then, a CNN architecture is designed to effectively extract the crucial vulnerability features from the hidden states of the last Transformer layer of GraphCodeBERT for vulnerability detection. The experiments on the public benchmark dataset REVEAL indicate that PTCN outperforms the state-of-the-art methods with respect to the Accuracy and F1-score metrics by 3.41%-15.80% and 22.68%-104.27%, respectively. © 2024 Knowledge systems Institute Graduate School. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Novel orange-red glaze based on in-doped CaFe2O4 red chromophore: Synthesis, properties and characterizations

引用

Ceramics International 2025年

作者： Qi, Menghang Tian, Liangsheng Wang, Qiuying Xiao, Ruoxiu Hu, Nan Shi, Lin Siritanon, Theeranun Jiang, Peng Department of Inorganic Nonmetallic Materials School of Materials Science and Engineering University of Science and Technology Beijing Beijing100083 China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China Institute of Surface-Earth System Science School of Earth System Science Tianjin University Tianjin300072 China School of Chemistry Institute of Science Suranaree University of Technology 111 University Avenue Muang Nakhon Ratchasima30000 Thailand

The CaFe2-xInxO4 (0 ≤ x ≤ 1) pigment with red shade was successfully synthesized through solid state reactions. The crystal structure, color development mechanism, morphology and its application in the glaze were studied. XPS analysis confirmed Fe resides in +3 oxidation state. Combined with UV–Vis–NIR analysis, it is determined that the formation of red shade of the pigment is due to the 6A1(S) → 4T2(D), 6A1(S) → 4A1, 4E(G) and 6A1(S) → 4T2(G) transitions of Fe3+ in the visible light region. The pigment was applied to the lead-free low temperature glaze to evaluate its potential in preparing new glaze color. The as-synthesized glaze showed orange-red shade. With increased In3+ doping concentration, the glaze demonstrates a stronger red tone. The glaze also shows high NIR solar reflectance. Inferred from SEM-EDS, the pigment particles are evenly scattered in the glaze. Therefore, CaFe2-xInxO4 (0 ≤ x ≤ 1) red pigment is a qualified candidate for red shade glaze preparation. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Crystal structure

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：