检索结果-内蒙古大学图书馆

Rule-based Explaining Module: Enhancing the Interpretability of Recurrent Relational Network in Sudoku Solving

Machine Graphics and Vision 2023年第3-4期32卷 125-145页

作者： Cheewaprakobkit, Pimpa Shih, Timothy K. Lau, Timothy Lin, Yu-Cheng Lin, Chih-Yang Department of Information Technology Asia-Pacific International University Saraburi Thailand Department of Computer Science and Information Engineering National Central University Taoyuan Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan Department of Mechanical Engineering National Central University Taoyuan Taiwan

computer vision has gained significant attention in the field of information technology due to its widespread application that addresses real-world challenges, surpassing human intelligence in tasks such as image recognition, classification, natural language processing, and even game playing. Sudoku, a challenging puzzle that has captivated many people, exhibits a complexity that has attracted researchers to leverage deep learning techniques for its solution. However, the reliance on black-box neural networks has raised concerns about transparency and explainability. In response to this challenge, we present the Rule-based Explaining Module (REM), which is designed to provide explanations of the decision-making processes using Recurrent Relational Networks (RRN). Our proposed methodology is to bridge the gap between complex RRN models and human understanding by unveiling the specific rules applied by the model at each stage of the Sudoku puzzle solving process. Evaluating REM on the Minimum Sudoku dataset, we achieved an accuracy of over 98.00%. © 2023 Institute of information technology, Warsaw University of Life Sciences - SGGW. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Image Fuzzy Enhancement Based on Membrane Computing Particle Swarm Optimization Algorithm

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第2期9卷 658-672页

作者： Hou, Xiao-Mao Cai, Liu-Ping Wang, Yan-Hui Automation and Information Engineering College Hunan Chernical Vocational Technology College Zhuzhou412000 China Graduate School Department Saint Paul University Tuguegarao3500 Philippines School of Computer Science and Engineering Hunan University of Information Technology Changsha410151 China

Image fuzzy enhancement is a research hotspot in the field of image processing, which aims to recover enhanced beginning clear images from degraded images. Based on the research of traditional particle swarm optimization algorithm and fuzzy enhancement algorithm, an image fuzzy enhancement method based on membrane computing particle swarm algorithm is proposed. Firstly, in order to make full use of the sparse characteristics of the clear image, the coefficient decomposition under wavelet domain and tightly supported wavelet domain is performed on the image respectively. Then, a joint optimisation model is constructed using L1 parametric constraints to achieve pretzel noise cancellation. Next, the MMH-PSO algorithm is designed by improving the particle swarm algorithm using membrane computing and Metropolis-Hastings sampling. Based on the simulated annealing algorithm temperature drop process, Metropolis-Hastings sampling is used to add randomness to the particle swarm algorithm so that it has the ability to jump out of the local optimum. The use of membrane computing enhances the parallelism of the particle swarm algorithm and can reduce the time complexity in solving complex problems. Finally, MMH-PSO is used to simultaneously search out the magnitude of the two fuzzy parameters in the traditional fuzzy enhancement algorithm in order to improve the accuracy of the algorithm. The experimental results show that the proposed algorithm has better SSIM values than the traditional fuzzy enhancement algorithm, which effectively improves the image quality and makes the image edge information more abundant. © 2024, J. Network Intell. All rights reserved.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

YOLOv8 Based Detection of Fall Armyworm in Field Crops 5

YOLOv8 Based Detection of Fall Armyworm in Field Crops

引用

5th IEEE India Council International Subsections Conference, INDISCON 2024

作者： Mhala, Prit Gupta, Amogh Sharma, Sanjeev Indian Institute of Information Technology Pune Department of Computer Science and Engineering Pune India

ISBN: (纸本)9798350376753

In India, the role of agriculture is pivotal contributing to the growth of the Indian economy and employment. It is essential to focus on the security of food which ensures individuals' health. Pest plays a major role in damaging and harming crop growth leading to effective control measures for pests. One such pest, Spodoptera frugiperda(Fall armyworm), poses significant damage to various crops. Deep Learning provides promising solutions by using Object detection techniques to detect the fall armyworm pest at early stages to avoid damage. This work intends to use YOLO as an object detection method. This paper achieved remarkable results using the YOLOv8 models. A mean average precision (mAP50) value of 78.60%, 80.67%, and 89.50% was achieved using YOLOv81, YOLOv8m, and YOLOv8n, respectively. The best results were achieved by YOLOv8n giving 89.50% mean average precision. This work, thus aims for precise detection of fall armyworms to enhance crop safety. © 2024 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Optimizing IoT Workloads for Minimal Time and Energy with UAV Networks Using Deep Q Network 18

Optimizing IoT Workloads for Minimal Time and Energy with UA...

引用

18th IEEE International Conference on Vehicular Electronics and Safety, ICVES 2024

作者： Singhal, Priyansh Chauhan, Harshit Hazra, Abhishek Joshi, Piyush Indian Institute of Information Technology Sri City Department of Computer Science and Engineering India

ISBN: (纸本)9798350387278

The rapid growth in the use of IoT devices has highlighted significant challenges due to their limited computational power and battery life, often resulting in long task execution times and potential battery depletion. The problem we address is the inefficiency in task completion and high battery usage in IoT devices. Our key objective is to minimize time delays and energy consumption in IoT workloads. To solve this problem, we propose a partial offloading algorithm for IoT devices, utilizing Unmanned Aerial Vehicles (UAVs) due to their larger battery capacity and greater computational power. UAVs provide flexibility in task management by moving to high-demand areas. Given the battery constraints of UAVs, a network of UAVs is used to share tasks among neighboring UAVs, balancing the load. Additionally, tasks can be offloaded to a ground-based cloud server to prevent overloading the UAV network. Our main contribution is the implementation of a Deep Q Network (DQN) reinforcement learning approach to manage the dynamic nature of task distribution. We achieved a significant reduction in both time delays and energy consumption. Our results displayed approximately a 15-fold reduction in total delay and a 6-fold reduction in total energy consumption, demonstrating the effectiveness of DQNs in this task offloading scenario. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

AI-Infused Strategies for Mitigating Uncertainty in Continental-Scale Surface Mass Change Analysis Through GPS and GRACE-FO

引用

Remote Sensing in Earth Systems Sciences 2024年第2期7卷 80-89页

作者： Kadrolli, Vijayalaxmi Kalnoor, Gauri Department of Information Technology Terna Engineering College Nerul Navi Mumbai India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru MAHE Manipal India

Understanding mass movements at spatial scales below 300 km requires screening and analysing GPS data in combination with GRACE-FO gravity products, which is summed up in this abstract. Based on prior research recommendations, this study establishes a thorough procedure for GPS VLD estimations, with an emphasis on corrections for surface mass separation. It also sets processing standards and uncertainty quantification approaches. In order to fix mistakes that might cause different responses from different observation platforms, it stresses the need of better background modelling. Locating troublesome locations and outlining required repairs, such as fixing missing antenna offsets, is made possible by screening metrics. When considering hydrological signals, several uncertainty quantification approaches (e.g. root mean square (RMSE), random walk, white noise, flicker noise, and noise) provide insight into noise levels and spectrum distributions. Improving our understanding of surface mass fluctuations across North America and related uncertainties, this suggested approach sets the basis for formal data combining of GPS-GRACE-FO and provides a framework for future research to refine GPS station errors internationally. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： GPS GRACE-FO Surface mass change Uncertainty identification

来源：评论

学校读者我要写书评

暂无评论

Text Summary Generation based on Data Augmentation and Contrastive Learning

Text Summary Generation based on Data Augmentation and Contr...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Wang, Jenq-Haur Zhuang, Jie-An National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350362480

In recent years, there has been a rapid growth in the volume of textual data generated from various sources, including industries, news media, and social media, across various fields worldwide. It contains valuable information and knowledge, but its sheer volume requires effective summarization techniques to make it useful. Text summarization has thus become an important technology for distilling large amounts of information and capturing key insights. With advancements in large language models (LLMs), most existing abstractive summarization models leverage pretrained models such as BART. These models are based on Transformer architectures and undergo unsupervised pretraining, followed by fine-tuning on specific datasets for downstream tasks, particularly text summarization. These models have demonstrated superiority in this field. Real-world data often contains noise, and most pretrained language models suffer from exposure bias and a discrepancy between their training objectives and real evaluation metrics. In this paper, we introduce sentence-level data augmentation to simulate real-world text variations and enhance the model's denoising capability. Furthermore, contrastive learning is employed to learn to distinguish the differences between the original article with candidate summaries and among candidate summaries themselves. Finally, the highest-scoring article is output as the resulting summary. The experimental results on the CNN/DailyMail and XSum datasets indicate that this model shows improvement in generating text summaries compared to pretrained models and existing methods with contrastive learning. When comparing to the multitask learning framework BRIO variant with contrastive loss, our proposed method achieves a better ROUGE-1 of 48.52 and comparable ROUGE-2/L of 24.84 and 39.78. This shows the potential of our proposed method. Further investigation is needed to verify the performance in real-world texts in various domains. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Optimizing Multi-hop Distributed Collaborative Task Offloading in R2X

引用

IEEE Transactions on Vehicular technology 2025年第6期74卷 9533-9548页

作者： Zhao, Wei Weng, Tangjie Cheng, Yu Liu, Zhi Kato, Nei Anhui University of Technology School of Computer Science and Technology Anhui Ma'anshan243032 China University of Electro-Communications Department of Computer and Network Engineering Tokyo Japan Tohoku University Graduate School of Information Sciences Sendai Japan

Roadside units (RSUs) with strong sensing abilities enhance the viability of the RSU-to-Everything (R2X) paradigm, offering crucial infrastructure support for Mobile Edge Computing (MEC) that enables real-time data processing and reduced delay. Since RSUs collect a large volume of data but have limited computing capability, data analysis tasks are usually offloaded to other network nodes, such as the cloud, other RSUs, or even vehicles. The multi-hop distributed collaborative task offloading scheme is expected to achieve high resource utilization efficiency and low task delay in this scenario, despite increasing energy consumption in data transmission. However, the highly dynamic nature of the R2X network topology makes it challenging for a node to independently select the next hop and collaboratively allocate tasks to neighbors in a multi-hop transmission path. Specifically, offloading decisions made by an individual node are influenced not only by its immediate neighbors but also by other nodes along the multi-hop path, referred to in this paper as the effect value. Additionally, the heterogeneity in computing resources and link delays among network nodes further increases the difficulty. To address these challenges, we first apply a Long Short-Term Memory (LSTM) model to predict and update the neighbors for each node while considering effect values, allowing them to independently adapt to environmental changes. Then, we design a two-layer Deep Reinforcement Learning (DRL) algorithm for network nodes to make decisions. The first-layer DRL algorithm is implemented by RSUs to determine task offloading modes. When an RSU decides to offload tasks to multiple vehicles for collaborative computing, the second-layer DRL algorithm is used by a vehicle to select its next hop vehicle and allocate tasks. Simulation results show that our proposed approach effectively adapts to topology changes in complex and highly dynamic network environments. Compared with existing methods,

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Frequency disentangled residual network

引用

Multimedia Systems 2024年第1期30卷 1-13页

作者： Singh, Satya Rajendra Yedla, Roshan Reddy Dubey, Shiv Ram Sanodiya, Rakesh Kumar Chu, Wei-Ta Computer Science and Engineering Group Indian Institute of Information Technology Andhra Pradesh Sri India Stony Brook University Stony BrookNY United States Computer Vision and Biometrics Lab Indian Institute of Information Technology Uttar Pradesh Allahabad India Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan

Residual networks (ResNets) have been utilized for various computer vision and image processing applications. The residual connection improves the training of the network with better gradient flow. A residual block consists of a few convolutional layers having trainable parameters, which leads to overfitting. Moreover, the present residual networks are not able to utilize the high- and low-frequency information suitably, which also challenges the generalization capability of the network. In this paper, a frequency-disentangled residual network (FDResNet) is proposed to tackle these issues. Specifically, FDResNet includes separate connections in the residual block for low- and high-frequency components, respectively. Basically, the proposed model disentangles the low- and high-frequency components to increase the generalization ability. Moreover, the computation of low- and high-frequency components using fixed filters further avoids the overfitting. The proposed model is tested on benchmark CIFAR-10/100, Caltech, and TinyImageNet datasets for image classification. The performance of the proposed model is also tested in the image retrieval framework. It is noticed that the proposed model outperforms its counterpart residual model. The effect of kernel size and standard deviation is also evaluated. The impact of the frequency disentangling is also analyzed using a saliency map. © 2024, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

ENHANCING HEALTH CARE THROUGH REMOTE SERVICES AND INTERACTIVE TECHNOLOGIES 9

ENHANCING HEALTH CARE THROUGH REMOTE SERVICES AND INTERACTIV...

引用

9th International Conference on Big Data Analytics, Data Mining and Computational Intelligence, BigDaCI 2024, the 10th International Conference on Connected Smart Cities, CSC 2024 and the 16th International Conference on e-Health, EH 2024, Part of the 18th Multi Conference on computer Science and information Systems 2024, MCCSIS 2024

作者： Lu, Ssu-Hsuan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan Taiwan

ISBN: (纸本)9789898704597

With the aging population, health issues have become a significant challenge for society. The increasing demand for remote medical services stems from changing interests in reducing healthcare costs and the sudden outbreak of COVID-19 globally. As the Internet of Things (IoT) and cloud technology advance rapidly worldwide, this trend has driven the digital transformation of biotechnology and pharmaceutical-related industries. Health care is shifting from a focus on medical institutions to a decentralized approach, emphasizing care facilities and home-based services. However, remote medical care brings about certain challenges, such as limited appointment availability due to network constraints, concerns about internet security, data encryption, privacy issues, and lack of awareness among people in remote areas. With the continuous development and widespread adoption of technology, smart home systems have become an integral part of modern life. In this project, the system emphasizes interaction with the elderly and utilizes the multifunctionality of touch screens. It provides various features through a simple and user-friendly interface, including health monitoring, outpatient services, life assistance, and social interaction functions. In the future, the system can incorporate more interactive features for the elderly, such as mini-games to enhance cognitive abilities, hand-eye coordination, or rehabilitation training. © 2024 Big Data Analytics, Data Mining and Computational Intelligence. All Rights Reserved.

关键词： Touch screens

来源：评论

学校读者我要写书评

暂无评论

Detecting ugly and derogatory words in Serbian language using a web browser extension 32

Detecting ugly and derogatory words in Serbian language usin...

引用

32nd Telecommunications Forum, TELFOR 2024

作者： Milakovic, Adrian Jocovic, Vladimir Cincovic, Jelica Micovic, Marko Radenkovic, Uros Draskovic, Drazen University of Belgrade School of Electrical Engineering Department of Computer Science and Information Technology Serbia

ISBN: (纸本)9798350391053

In natural language processing, data acquisition and preprocessing techniques are significant for experiments involving training models on cleaned data. This paper describes the formation of a dataset of ugly and derogatory words in the Serbian language and the development of a web extension to analyze texts in which such words appear and then their censoring. Developing such an add-on is essential in creating a safer and healthier digital environment for young users who are just developing their Internet habits and adults who want to avoid unwanted content. It is crucial to point out that there are few software tools for natural languages with limited resources, such as the Serbian language. This software could analyze the frequency of certain foul words on different sites, which would contribute to a better understanding of the impact of such language on users. © 2024 IEEE.

关键词： Web browsers

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：