检索结果-内蒙古大学图书馆

International eConference on computer and Knowledge engineering (ICCKE)

作者： Reza Shami Tanha Mohsen Hooshmand Mohsen Afsharchi Dept. Computer Science and IT Institute for Advanced Studies in Basic Sciences (IASBS) Zanjan Iran Dept. Electrical and Computer Engineering University of Zanjan Zanjan Iran

Wildfire in the forest leads to a huge amount of financial and human losses. That is it causes damage to the forest and the life of firefighters. To reduce the amount of such damage, unmanned aerial vehicles are among the best options to do the job of firefighting. Their orchestration of effective fire extinguishing is a must and essential. This work proposes a multi-agent reinforcement learning method using an actor-critic structure to extinguish the fire. While the learning is centralized, their execution is decentralized. Moreover, we define two models of fire spreading based on the discrete-time Markov process. The results show that the proposed method outperforms the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Indian Food Segmentation and Calorie Estimation Using CatBoost and Masked Convolutional Neural Networks

Indian Food Segmentation and Calorie Estimation Using CatBoo...

引用

Network, Multimedia and Information technology (NMITCON) International Conference on

作者： Nabin Acharya Ayush Kumar Singh Anshuman Kumar Dwivedi Jayanthi M. G Prashant Kannadaguli Dept. of Information Science and Engineering Cambridge Institute of Technology Bengaluru India Dept. of Artificial Intelligence and Machine Learning Cambridge Institute of Technology Bengaluru India Dept. of Computer Science and Engineering Cambridge Institute of Technology Bengaluru India Dhaarini Academy of Technical Education Bengaluru India

Accurate food segmentation and calorie estimation play a pivotal role in effective dietary monitoring and health management. In this paper, after extensive experimentation on a diverse Indian food dataset of 20 classes collected by us, we present two separate innovative models designed to address these tasks with exceptional precision. The first model employs a machine learning approach by incorporating the CatBoost algorithm, while the second model leverages a deep learning technique utilizing the U-Net architecture for high-quality image segmentation. Additionally, we merge the U-Net outcomes with a convolutional neural network (CNN) to enhance the deep learning-based classification. Our models effectively handle categorical features and address imbalanced data, resulting in significantly improved accuracy in food item delineation within images. This advancement enables a more reliable and comprehensive analysis of dietary patterns. We demonstrate the effectiveness and robustness of our proposed models. Comparative evaluations against state-of-the-art methods verify exceptional performance in terms of segmentation accuracy, precision in food classification, and estimation of calorie intake. Notably, our models are specifically tailored for food images and do not take ingredients or any other information into consideration. In comparison CNN model is performs better than CatBoost, achieving an accuracy of 78%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition using ShuffleNetV2 Model

Human Activity Recognition using ShuffleNetV2 Model

引用

Intelligent Computing and Control for engineering and Business Systems (ICCEBS)

作者： Shanufa Nazrin P S J.V. Bibal Benifa Anu K. P Aiswarya Vijayakumar dept. of Computer Science St.Joseph's college (university of calicut) Thrissur Kerala dept.of Computer Science and Engineering Indian Institute of Information Technology kottayam Kerala India

HAR is specified as the crucial task within the field of computer vision and artificial intelligence. Main aim of HAR is to observing and labelling different human activity images of distinct data sources by machines such as computer. HAR has applications in various fields. CNN model is an appropriate model for HAR task, due to their ability to automaticaly acquire relevant spatial features, capture hierarchical representations, and handle input of various sizes and types. So it is utilized for developing HAR model. This model can detect objects and also can classify images. The model contains wide ranging catogories. ShuffleNetV2 is a particular architecture within it, mainly for efficient and lightweight deep learning task. This paper develops an intelligent HAR using ShuffleNetV2 model which acquired an accuracy about 69.52 percentage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Word Prediction Model Using LSTM Neural Network with Optimization Strategies

Implementation of a Word Prediction Model Using LSTM Neural ...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： Jagadevi P Yeresime Suresh Dept. of Computer Science & Engg. Ballari Institute of Technology and Management Ballari Visvesvaraya Technological University Belagavi Karnataka India Dept. of CSE - Artificial Intelligence Ballari Institute of Technology and Management Ballari

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

The development of word predictive models has significantly advanced with the integration of deep learning techniques, particularly in the domain of natural language processing (NLP). Early models like n-grams and basic Recurrent Neural Networks (RNNs), laid the foundation for sequence based text generation by predicting the next word based on a fixed number of preceding words. However such approaches frequently struggled with capturing long range dependencies due to their limited context window and inability to maintain memory over extended sequences. This paper presents the implementation of word prediction model using Long Short-Term Memory (LSTM) neural networks that predicts the next word in a given sequence. The proposed model is trained on a diverse dataset and evaluating performance through several test cases. The model incorporates several optimization strategies to enhance its performance regarding scalability, fault tolerance, and resource allocation. Experimental results demonstrate the effectiveness of these optimizations in improving prediction accuracy and computational efficiency.

关键词： Fault tolerance Accuracy Computational modeling Scalability Fault tolerant systems Predictive models Transformers Natural language processing Optimization Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A Way of Safe Wireless Networks using IμUWB/Vision through Sensor Networks 4

A Way of Safe Wireless Networks using IμUWB/Vision through ...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Sharmila, P. Maheswaran, M. Mohanraj, T. Verma, Rajan Malviya, Bhupendra Subbarao, S.P.V. Prince Shri Venkateshwara Padmavathy Engineering College S & H Dept TN India Nehru Institute of Engineering and Technology Department of Mechatronics Engineering Tamil Nadu T.M.Palayam India Karpagam Academy of Higher Education Department of Computer Science and Engineering TN India Chitkara University Chitkara Center for Research and Development Himachal Pradesh India M.P Bhopal India Sreenidhi Institute of Science and Technology Electronics and Communication Engineering Department Hyderabad India

ISBN: (纸本)9798350360165

In current military and private spheres, the demand for exact localization within the home of mobile agents, especially small unmanned aircraft (UAVs), has attracted significant attention. This paper shows a new method to indoor UAV localization using Ultra-WideBand technology, combined with a cost-effective Motion Measurement Unit (IMU) while vision-based devices. A vital improvement to the positioning process is brought through the inclusion of an additional Kalman filter (EKF). The utilization of an inexpensive and low-cost IMU with the modeling phase, paired with the inclusion of vision odometer measurements for identifying marks in the closeness of the landing area, forms a key aspect of this method. The addition of range data plays a key role in reducing mistakes affiliated with the limited capabilities of gyroscopes and accelerometers, which are inherent in inertial devices. By deploying these multi-modal technologies that the suggested approach achieves a surprising level of precision, with data showing an amazing precision equal to 10 centimeters. This development holds potential for improving the operating effectiveness of small UAVs in indoor settings, offering a robust solution that joins Ultra-WideBand technology, IMU, while vision-based sensors throughout the framework of an Extension Kalman Filter. © 2024 IEEE.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

EFFECTIVE NOISE-AWARE DATA SIMULATION FOR DOMAIN-ADAPTIVE SPEECH ENHANCEMENT LEVERAGING DYNAMIC STOCHASTIC PERTURBATION

arXiv

引用

arXiv 2024年

作者： Wang, Chien-Chun Chen, Li-Wei Lee, Hung-Shin Chen, Berlin Wang, Hsin-Min Dept. Computer Science and Information Engineering National Taiwan Normal University Taiwan Institute of Computer Science Academia Sinica Taiwan United-Link Co. Ltd. Taiwan

Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch between training and test conditions. This study puts forward a novel data simulation method to address this issue, leveraging noise-extractive techniques and generative adversarial networks (GANs) with only limited target noisy speech data. Notably, our method employs a noise encoder to extract noise embeddings from target-domain data. These embeddings aptly guide the generator to synthesize utterances acoustically fitted to the target domain while authentically preserving the phonetic content of the input clean speech. Furthermore, we introduce the notion of dynamic stochastic perturbation, which can inject controlled perturbations into the noise embeddings during inference, thereby enabling the model to generalize well to unseen noise conditions. Experiments on the VoiceBank-DEMAND benchmark dataset demonstrate that our domain-adaptive SE method outperforms an existing strong baseline based on data simulation. © 2024, CC BY.

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

An Effective Framework for Detecting Epileptic Seizures using CNN and Encrypted EEG Signals

An Effective Framework for Detecting Epileptic Seizures usin...

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Pradeep, G. Bala, Saroj Satheesh, N.P. Mahalakshmi, M. Balasamy, K. Suganyadevi, S. Sri Krishna College of Engineering and Technology Department of M.Tech. Computer Science and Engineering Coimbatore India Ajay Kumar Garg Engineering College Department of Mca Ghaziabad India Bannari Amman Institute of Technology Department of Ai & Ds Sathyamangalam India Saveetha Engineering College Dept of Artificial Intelligence & Data Science Chennai India Kpr Institute of Engineering and Technology Department of Ece Coimbatore India

ISBN: (纸本)9798350333602

Electroencephalogram (EEG) signals may be used to autonomously diagnose epilepsy, eliminating the requirement for a medical professional's involvement in the process. A good classification performance is really necessary if you do not want to pass up any possible discoveries. In this piece of research, the authors offer a technique for the automated identification of epilepsy using EEG waves. In order to extract features, the raw EEG signals were first put through a discrete Fourier transform, also known as a DFT, as well as a discrete wavelet transform (DWT). Therefore, researchers have been exploring different methods to improve the accuracy of EEG signal analysis. One such method proposed in this study is the Wavelet Transform based Fourier-Bessel series expansion (WT - FBSE) method. This method utilizes the WT - FBSE spectrum to segment multiple frame-size time-segmented EEG signals using the scale-space boundary detection method. The WT - FBSE technique decomposes the EEG signals into narrow sub-band signals, which are then used to extract various features such as log-energy-entropy (LEnt), line-length (LL), and norm-entropy (NEnt) from different frequency ranges. In order to choose the features that are most important, the relief-F feature ranking approach is applied. This helps to limit the amount of computing work that is required by the models. The study evaluates two time-segmentation approaches and four different frame sizes to analyse the EEG signals and achieves better performance when compared to the existing systems. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

I-Card: A Generative AI-Supported Intelligent Design Method Card Deck 25

I-Card: A Generative AI-Supported Intelligent Design Method ...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Chen, Liuqing Cheang, Wengteng Jiang, Zhaojun Xu, Yuan Cai, Zebin Sun, Lingyun Childs, Peter Han, Ji Hansen, Preben Zuo, Haoyu College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou China School of Computer Science and Engineering Central South University Hunan Changsha China International Design Institute Zhejiang University Zhejiang Hangzhou China Dyson School of Design Engineering Imperial College London London United Kingdom Department of Innovation Technology and Entrepreneurship University of Exeter Exeter United Kingdom Dept of Computer and Systems Sciences Stockholm University Kista Sweden

ISBN: (纸本)9798400713941

A design method card deck helps designers understand and provoke thinking by presenting each method in a simple format and allow designers to switch between methods seamlessly by maintaining the same simple format across the deck. However, recent observations have shown designers hesitate to use a card deck due to the lack of support, while other tools have provided identified support with generative AI. Through a formative study, we identified the specific support designers need when applying the design method cards and intentions in integrating generative AI. Accordingly, we developed the intelligent design method card deck, I-Card, which integrates generative AI to provide applicable design methods, design knowledge and data support, and interactive and dynamic support. A user study demonstrates that I-Card improved the design efficiency and applicability by offering personalized guidance, enhanced decision-making with comprehensive data generation and provided more design inspiration via interactive support. © 2025 Copyright held by the owner/author(s).

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Investigating the Impact of Heuristic Algorithms on Cyberthreat Detection

Investigating the Impact of Heuristic Algorithms on Cyberthr...

引用

Advances in Computation, Communication and Information technology (ICAICCIT), International Conference on

作者： Dinesh Kalla Abdul Sajid Mohammed Venkata Nagesh Boddapati Nasmin Jiwani T. Kiruthiga Dept. of Computer Science Colorado Technical University Charlotte NC USA Dept of School of Computer and Information Sciences University of the Cumberlands Kentucky USA Dept. of Computer Science Microsoft Charlotte NC USA Dept. of Information Technology University of The Cumberlands Williamsburg KY USA Department of ECE Vetri Vinayaha College of Engineering and Technology Trichy Tamil Nadu India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

This paper investigates the effect of heuristic algorithms on cybersecurity hazard detection and mitigation. To be able to do so, the authors analyze the performance of two heuristics-based algorithms—the simple Heuristic set of rules (SHA) and greedy Heuristic set of rules (GHA)—on 4 distinct datasets. The datasets contain malicious and non-malicious packets. Effects of the experiments show that each algorithms exhibit extraordinarily correct predictions of malicious packets while as compared to the floor-reality labels, and showcase an excessive level of detection accuracy in detecting threats. The SHA set of rules tested the strongest performance, achieving an accuracy of as much as 95 and ninety-seven percentage on datasets. The authors further take a look at that once both algorithms are utilized in aggregate, the overall performance progressed. The research findings may be generalized in further contexts and assist the notion that heuristics algorithms may be effective in threat detection and mitigation.

关键词： Handwriting recognition Ethics Accuracy Heuristic algorithms Prevention and mitigation Prediction algorithms Threat assessment Hazards Information and communication technology computer security

来源：评论

学校读者我要写书评

暂无评论

Cyber Security Threats Detection Analysis and Remediation 1

Cyber Security Threats Detection Analysis and Remediation

引用

1st IEEE Mysore Sub Section International Conference, MysuruCon 2021

作者： Darshini, P. Mohana Kumar, S. Raghavendra, C.G. Krishna Prasad, S.J. Kavitha, H. Divakara, S.S. Ramaiah Institute of Technology Dept. of Computer Science Bangalore India Ramaiah Institute of Technology Bangalore Dept. of Computer Science Bangalore India Ramaiah Institute of Technology Dept. of Electronics and Communication Bangalore India Ramaiah Institute of Technology Dept. of Electronics and Telecommunication Bangalore India Siddaganga Institute of Technology Dept. Infomation and Science Tumkur India Coorg Institute of Technology Dept. of Electronics and Communication Ponnampet India

ISBN: (纸本)9780738146621

The devices of the organization such as laptops, desktops and mobiles are connected to the internet are vulnerable to cyber attacks, attacking on these components may lead to security breach, credential theft, malware implantation, DDoS attack, man in middle attacks, ransomware attacks and many more. Therefore, to defend against these attacks there requires proper security controls in place to detect the threats in the business environment. Security Threats generally propagates through various SQL Injection, Cross Site Scripting or unauthorized excessive login into any servers. These could lead company to huge loss of information and revenue. Suspicious emails are the most dangerous way to attack on any organization by employing techniques such as phishing, fraud, Spam and spoofing the email headers. These emails are sent through outside company environment. It poses extensive threats and it can be a major setback. This work explores confident ways to automate the process of cyber security threat and change in a rules-set. With the help of proposed cyber tool to remediate false positives response time against every attack, these helps the organizations to minimize the suspicious attack. © 2021 IEEE.

关键词： Malware

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：