检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2024

作者： Guo, Pengyu Yang, Haoyi Qiao, Jiarui Xia, Fanya Zhou, Yuxiao Lin, Jiayi Harbin Institute of Technology School of Software Harbin China Guangdong Technion-Israel Institute of Technology Mathematics with Computer Science Shantou China Harbin Institute of Technology School of Marine Science and Technology Harbin China Harbin Institute of Technology School of Science Harbin China Harbin Institute of Technology Faculty of Computing Harbin China

ISBN: (纸本)9798350366174

With the advancement of science and technology and the popularization of the concept of environmental protection, the increase in the number of electric vehicles is becoming a new trend in social development. However, related safety issues have also emerged with the increase in the number of electric vehicles, especially the fire phenomenon. In view of the limitations of traditional manual supervision in dealing with intrusion detection and alarm with low efficiency and frequent false alarms, this paper proposes a method based on the YOLOv8 algorithm for electric battery entry detection, and adds an attention mechanism to obtain better picture features. In this paper, the effectiveness of the improvement is verified experimentally for the YOLO model before and after the improvement. © 2024 IEEE.

关键词： Attention mechanism Battery Testing Target detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Building a Stronger Case: Combining Evidence and Law in Scenario-Based Bayesian Networks 3

Building a Stronger Case: Combining Evidence and Law in Scen...

引用

3rd International Conference on Hybrid Human-Artificial Intelligence, HHAI 2024

作者： Van Leeuwen, Ludi Verbrugge, Rineke Verheij, Bart Renooij, Silja Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Netherlands Department of Information and Computing Sciences Utrecht University Netherlands

ISBN: (纸本)9781643685229

Existing approaches to modelling legal cases in Bayesian networks focus either on correctly representing an empirical probabilistic model of evidence traces, or on modeling alternative scenarios that can explain what happened in a case. However, neither approach legally interprets, or qualifies, aspects of a scenario as a normative legal fact. Hence, the fact that a Bayesian network representing a scenario assigns a high posterior probability to a certain victim having been killed by a certain suspect, does not imply that that suspect is guilty of murder in the legal sense, because the events in the scenario cannot be qualified as legal facts. This paper proposes an architecture for concrete legal fact idioms that qualify events in a narrative Bayesian network. This bridges the gap between the real world and the normative legal world through so-called counts-as rules. By modeling the legal facts explicitly in the Bayesian network, we can show whether a narrative completes one or more legal fact idioms. This is demonstrated using a case study. The proposed architecture may help judges and lawyers decide on which narratives they should investigate further and which narratives are stronger than others with regard to both the evidence and the legal facts. © 2024 The Authors.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Advancing Color Perception: An IoT-driven Pedagogical System for Visually Impaired Children 1

Advancing Color Perception: An IoT-driven Pedagogical System...

引用

1st IEEE International Conference on Advances in Signal Processing, Power, Communication, and computing, ASPCC 2024

作者： Balage, Prasandika Jayawardene, Nuwan University of Westminster School of Computer Science and Engineering London United Kingdom Informatics Institute of Technology Department of Computing Colombo Sri Lanka

ISBN: (纸本)9798350355093

Visual impairment is characterized by the loss of vision, encompassing both complete blindness and partial vision loss. Studies reveal a notable prevalence of visual impairment among school-aged children. The significance of colors in acquiring and discerning visual information is crucial, aiding children in effectively perceiving and comprehending their surroundings. This study presents an Internet of Things (IoT) system designed for teaching colors to visually impaired children. The system achieved an accuracy rate surpassing 77.8%, and it is operated effectively regardless of surrounding lighting conditions. Given that the target users of the system are visually impaired children, this research was conducted in close alignment with Human-computer Interaction (HCI) principles. © 2024 IEEE.

关键词： Color vision

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of XAI-based Approaches on Brain Disease Detection using Brain MRI Images 4

A Systematic Literature Review of XAI-based Approaches on Br...

引用

4th International Conference on Advanced Research in computing, ICARC 2024

作者： Madapatha, Savin Fernando, Pumudu University of Westminster Department of Computer Science and Engineering London United Kingdom School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (纸本)9798350384864

Brain Magnetic Resonance Imaging (MRI) analysis is a widely used medical procedure for the early diagnosis of various brain diseases. Accurate pathology identification during the brain MRI analysis procedure is crucial as misdiagnoses or missed findings can greatly affect a patient's treatment and long-term prediction. With the recent advancement of Artificial Intelligence (AI) in the medical field, researchers have approached various techniques to detect brain diseases using AI. Although AI models exhibit high accuracy, they suffer from a lack of transparency and interpretability, paving the way for the development of eXplainable Artificial Intelligence (XAI) methods in brain disease diagnosis. Image segmentation, machine learning, deep learning and XAI are important for assisting the diagnostic procedure. In this paper, a comprehensive overview of various existing techniques in brain disease detection using MRI is presented, starting with image segmentation techniques, followed by classification techniques, and finally, XAI techniques. In conclusion, the paper identifies a critical need for further research on XAI integration to advance brain disease detection. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Expand VSR Benchmark for VLLM to Expertize in Spatial Rules 39

Expand VSR Benchmark for VLLM to Expertize in Spatial Rules

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xie, Peijin Sun, Lin Liu, Bingquan Wang, Dexin Zhang, Xiangzheng Sun, Chengjie Zhang, Jiajia Faculty of Computing Harbin Institute of Technology Harbin150001 China 360 Search Department Beijing100020 China School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China

ISBN: (纸本)157735897X

Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED comprehensively have evaluated various capabilities which already include visual spatial reasoning(VSR). There is still a lack of sufficient quantity and quality evaluation and optimization datasets for Vision Large Language Models(VLLMs) specifically targeting visual positional reasoning. To handle this, we first diagnosed current VLLMs with the VSR dataset and proposed a unified test set. We found current VLLMs to exhibit a contradiction of over-sensitivity to language instructions and under-sensitivity to visual positional information. By expanding the original benchmark from two aspects of tunning data and model structure, we mitigated this phenomenon. To our knowledge, we expanded spatially positioned image data controllably using diffusion models for the first time and integrated original visual encoding(CLIP) with other 3 powerful visual encoders(SigLIP, SAM and DINO). After conducting combination experiments on scaling data and models, we obtained a VLLM VSR Expert(VSRE) that not only generalizes better to different instructions but also accurately distinguishes differences in visual positional information. VSRE achieved over a 27% increase in accuracy on the VSR test set. It becomes a per-formant VLLM on the position reasoning of both the VSR dataset and relevant subsets of other evaluation benchmarks. We hope it will accelerate advancements in VLLM on VSR learning. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OGGPS: An Automatic Intelligence Driven Approach for Ontology Generation on Gandhian Philosophy and Peace Studies 23th

OGGPS: An Automatic Intelligence Driven Approach for Ontolog...

引用

23rd International Conference on Intelligent Systems Design and Applications, ISDA 2023

作者： Sharma, Ojasvi Sawarn, Shivam Deepak, Gerard School of Computing DIT University Dehradun India Department of Computer Science and Engineering BMS Institute of Technology and Management Yelahanka Bangalore India

ISBN: (纸本)9783031647789

This research aims to exploit the integration and competition of Generative Reciprocal Networks (GANs). An Algorithm to Facilitate Automatic Ontology Generation and Knowledge Graph (KG) Synthesis of Gandhi and Peace Studies. Combining the power of GANs to generate synthetic data and a competitive analysis algorithm and ordering concepts, comprehensive ontology and data graph can be created. This approach allows Systematic organization and presentation of concepts and relationships central to Gandhi's philosophy and peace studies. The iterative process allows for refinement and improvement, ensuring the accuracy of the ontology and KG to capture the complexity of the domain. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Algorithmic Trading Based on News and Events Strategies 7th

Deep Learning-Based Algorithmic Trading Based on News and Ev...

引用

7th International Conference on Soft computing: Theories and Applications, SoCTA 2023

作者： Kayathri, V. Prabakaran, P. Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai600 117 India

ISBN: (纸本)9789819720309

Successful stock market investors should consider these trends. This article defines price effect, optimal execution, and placement through the lens of algorithmic trading and strategies based on news and events. By using feedbacks controlled to include consideration of a stop-loss order, algorithmic trading allows traders and investors at large to liquidate or construct big securities positions in a fully automated manner, thus generalising the existing stock trading results. Trading decisions made by the AI agent could affect the asset price. We see this as a marketplace where people are bartering and swapping goods. Creating a new market is the driving force behind our research into generative models. This news sentiment does a good job of describing stocks, and AI systems that read the news and quantify them react to factors that affect prices far more quickly than humans do. All three of the stock market's underpinnings—price, volume, and volatility—respond strongly to news events. Sentiment analysis is a method for gauging the overall tone of a news piece and classifying it as optimistic, pessimistic, or neutral. The simulation is conducted in python to test the effectiveness of the model in trading in an automated manner for stocks. The results show that the proposed sentimental analysis for stock trading achieves higher rate of accuracy and precision than the other methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning

引用

ACM Transactions on Graphics 2023年第5期42卷 1-16页

作者： Zhang, Yuxin Tang, Fan Dong, Weiming Huang, Haibin Ma, Chongyang Lee, Tong-Yee Xu, Changsheng MAIS Institute of Automation China and School of Artificial Intelligence CAS UCAS China Institute Of Computing Technology CAS China Kuaishou Technology China Department of Computer Science and Information Engineering National Cheng-Kung University Taiwan

This work presents Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, that can fit in most existing arbitrary image style transfer models, such as CNN-based, ViT-based, and flow-based methods. As the key component in image style transfer tasks, a suitable style representation is essential to achieve satisfactory results. Existing approaches based on deep neural networks typically use second-order statistics to generate the output. However, these hand-crafted features computed from a single image cannot leverage style information sufficiently, which leads to artifacts such as local distortions and style inconsistency. To address these issues, we learn style representation directly from a large number of images based on contrastive learning by considering the relationships between specific styles and the holistic style distribution. Specifically, we present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components: a parallel contrastive learning scheme for style representation and transfer, a domain enhancement (DE) module for effective learning of style distribution, and a generative network for style transfer. Qualitative and quantitative evaluations show the results of our approach are superior to those obtained via state-of-the-art methods. The code is available at https://***/zyxElsa/CAST_pytorch. © 2023 Copyright held by the owner/author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing TCP Congestion Control: A Comparative Analysis, and Algorithmic Modifications using NS2

Enhancing TCP Congestion Control: A Comparative Analysis, an...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Thangam, S. Trisha, K. Hima Sree, N. Reddy P, Srinithya Balakrishnan, Sivaneasan Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India Singapore Institute of Technology Singapore

ISBN: (纸本)9798350309140

The transmission control protocol is essentially a computer network protocol and ensures the reliability of the transmitted data. TCP's congestion control algorithms support network performance and stability. Network congestion has become a major issue in network analysis. TCP (Transmission Control Protocol) Congestion control algorithms ensure smooth transmission of data across networks. This work examines TCP congestion algorithms. The main objective is to increase its efficiency and modify the algorithm. A detailed performance analysis of the enhanced TCP congestion control algorithms namely Tahoe, New Reno, and Vegas is performed and simulations are used to evaluate its performance under different network conditions such as high latency, constant bit rate (CBR) bandwidth load, and varying traffic loads. Metrics such as latency, throughput, and round-trip time are analyzed under the scenarios using ns-2 simulator. © 2024 IEEE.

关键词： Transmission control protocol

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Enabled Photonic Assisted Adaptive Multipath Self-Interference Cancellation: A Novel Approach 15

Deep Reinforcement Learning-Enabled Photonic Assisted Adapti...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Singh, Nongmeikapam Thoiba Dutta, Neha Dutt, Krishan Rani, Jyoti Kumar, Munish Nailwal, Sagar Bindra, Kunal Chandigarh University Department of Computer Science And Engineering Punjab India Lovely Professional University Department of Computer Science And Engineering Punjab India University Institute of Computing Chandigarh University Punjab India

ISBN: (纸本)9798350370249

Multipath self-interference is an inherent problem in wireless communication systems that reduces spectral efficiency and performance. In response, this work presents a novel method that combines Deep Reinforcement Learning (DRL) with Photonic-Assisted Adaptive Multipath Self-Interference Cancellation (PAM-SIC). Because traditional cancellation methods are rigid and have little flexibility, they frequently perform poorly in dynamic contexts. Our solution effectively combats multipath interference by utilizing the synergies between photonic-assisted approaches and DRL algorithms to provide autonomous and adaptive cancellation capabilities. We start by summarizing the basic problems that multipath interference in wireless communications poses and highlighting the need for creative fixes. An effective means of reducing interference and maximizing signal integrity and spectrum efficiency is the use of photonic-assisted adaptive cancellation. Meanwhile, DRL presents itself as a potent paradigm that effortlessly conforms to the needs of adaptive interference cancellation, enhancing decision-making in dynamic contexts. We exhibit the robustness and effectiveness of the proposed PAM-SIC with DRL through extensive simulations and performance assessments. Results show that, as compared to traditional methods, there are notable gains in spectral efficiency, interference cancellation, and system dependability. Given its adaptive character, the suggested framework ensures optimal performance in a variety of operating scenarios by allowing real-time response to changing channel conditions and system parameters. © 2024 IEEE.

关键词： deep reinforcement learning interference photonics signal spectral efficiency wireless communication

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：