检索结果-内蒙古大学图书馆

An Efficient Multi-band Infrared Small Objects Detection Approach for Low-Altitude artificial intelligence of Thing

IEEE Internet of Things Journal 2025年第12期12卷 20757-20772页

作者： Peng, Yuhuai Wang, Jing Wang, Wenqian Liu, Lei Atiquzzaman, Mohammed Guizani, Mohsen Dustdar, Schahram Northeastern University School of Computer Science and Engineering Shenyang110819 China Zhiyuan Research Institute Hangzhou310024 China Northeastern University School of Computer Science and Engineering Shenyang110819 China Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China University of Oklahoma School of Computer Science NormanOK73019 United States Mohamed Bin Zayed University of Artificial Intelligence Department of Machine Learning Masdar United Arab Emirates Technische Universität Wien Distributed Systems Group Vienna1040 Austria

As a cutting-edge technology of low-altitude artificial intelligence of Thing (AIoT), UAV object detection significantly enhances the surveillance services capabilities of low-altitude AIoT. However, the difficulty of object detection is exacerbated by the high proportion of small and obscure objects in the captured images. To address the mentioned challenges, we present an efficient multi-band infrared small object detection approach for low-altitude intelligent surveillance services. Firstly, we propose the Multi-band infrared Image Fusion algorithm based on Cascade-GAN (MIF-CGAN), which produces fused images with high information entropy and high contrast. Then, the Transformer-based Multi-scale Dense Small Object Detection (MsDSOD) algorithm is proposed. The algorithm consists of the Global-Local Object Detection (G-LOD) network, the Object Dense Area Extraction (O-DAE) module, and the Weighted Boxes Fusion (WBF) module. It extracts small objects features at different scales from infrared images and fuses the global and local detection results to accurately identify small objects in dense scenes. Furthermore, compared to the traditional algorithms, the mean Average Precision (mAP) of MsDSOD is improved by 0.80% and the Average Precision in small object detection (APs) is improved by 0.72%. The proposed algorithm is optimally suited to deal with complex scenes with dense small objects and background occlusion. © 2014 IEEE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

ROBUST ADVERSARIAL REINFORCEMENT learning VIA BOUNDED RATIONALITY CURRICULA 12

ROBUST ADVERSARIAL REINFORCEMENT LEARNING VIA BOUNDED RATION...

引用

12th International Conference on learning Representations, ICLR 2024

作者： Reddi, Aryaman Tölle, Maximilian Peters, Jan Chalvatzaki, Georgia D'Eramo, Carlo Department of Computer Science TU Darmstadt Germany Germany Systems AI for Robot Learning Germany Center for Cognitive Science TU Darmstadt Germany Center for Artificial Intelligence and Data Science University of Würzburg Germany

Robustness against adversarial attacks and distribution shifts is a long-standing goal of Reinforcement learning (RL). To this end, Robust Adversarial Reinforcement learning (RARL) trains a protagonist against destabilizing forces exercised by an adversary in a competitive zero-sum Markov game, whose optimal solution, i.e., rational strategy, corresponds to a Nash equilibrium. However, finding Nash equilibria requires facing complex saddle point optimization problems, which can be prohibitive to solve, especially for high-dimensional control. In this paper, we propose a novel approach for adversarial RL based on entropy regularization to ease the complexity of the saddle point optimization problem. We show that the solution of this entropy-regularized problem corresponds to a Quantal Response Equilibrium (QRE), a generalization of Nash equilibria that accounts for bounded rationality, i.e., agents sometimes play random actions instead of optimal ones. Crucially, the connection between the entropy-regularized objective and QRE enables free modulation of the rationality of the agents by simply tuning the temperature coefficient. We leverage this insight to propose our novel algorithm, Quantal Adversarial RL (QARL), which gradually increases the rationality of the adversary in a curriculum fashion until it is fully rational, easing the complexity of the optimization problem while retaining robustness. We provide extensive evidence of QARL outperforming RARL and recent baselines across several MuJoCo locomotion and navigation problems in overall performance and robustness. © 2024 12th International Conference on learning Representations, ICLR 2024. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Meta Heuristic-Based Community Detection of Social Network Using Cuckoo with InfoMap Algorithm 1

引用

International Conference on Intelligent Manufacturing and Energy Sustainability, ICIMES 2022

作者： Devi, S. Rajalakshmi, M. Saranya, S. Shana, J. Department of Information Technology Coimbatore Institute of Technology Coimbatore India Department of Computer Science and Engineering Coimbatore Institute of Technology Coimbatore India Department of Artificial Intelligence and Machine Learning Coimbatore Institute of Technology Coimbatore India

ISBN: (数字)9789811984976

ISBN: (纸本)9789811984969

Facebook and Twitter are one of the social networks for communicating our thoughts, feelings, opinions of current scenarios. By using this communication platform rapidly, people can share information. In the analysis of the social network, identifying such communities and sharing information are a challenging task. These fast shares of information create scalability, inaccurate, genuine issues. Many existing techniques can be used for the community detection of the social network. However, these techniques are ineffective and high time-consuming for quick detection. This paper proposed a novel metaheuristic technique-based community detection of the social network by using the hybrid of cuckoo search with InfoMap algorithm (CIMA). In this proposed work, CIMA is used for community detection. This proposed work increases the intracommunity of the social network and improves its performance in an accurate way by detecting the community of the social network. The accuracy rate for AKSHO got 48%, ant lion got 52%, lion optimization got 66%, fish swarm optimization algorithm got 78%, and our proposed work CIMA got 94%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Sign Language Detection in Real-Time Applications

Sign Language Detection in Real-Time Applications

引用

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Milinda, Renata Rachael Sara Ramsiej, Barrister Yasmin, Reshma Ambeth Kumar, V.D. Sekar, K. Anna University India Dept. of Artificial Intelligence and Machine Learning Anna University India Dept. of Computer Engineering Mizoram University Aizawl India Department of AIML Rajalakshmi Engineering College Chennai India

ISBN: (纸本)9798331510299

Individuals with hearing and speech impairments often rely on gesture language for communication, but a lack of widespread understanding of this language among others creates significant barriers. A machine learning model that recognizes hand signals and converts them into English can help bridge this gap, facilitating communication between hearing and deaf individuals. Existing non-verbal communication identification systems, while leveraging computational learning and AI models for both single- and double-handed gestures, generally lack real-time capabilities. This research proposes a live symbolic language identification platform that uses a webcam to build a regional gesture communication dataset and TensorFlow for cross-domain learning. Despite a smaller dataset, the system targets high accuracy in recognition. Advanced technologies, including computer vision and deep learning, are applied to improve communication for deaf individuals by developing accessible technical applications and platforms. The proposed model, utilizing TensorFlow and OpenCV, aims to identify commonly used American Sign Language gestures in real time with accuracy and efficiency, including signs such as "hello, " "thanks, " "bye, " "yes, " "no, " "dad, " and "mom". © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

System for Detecting Intrusions using Raspberry PI

System for Detecting Intrusions using Raspberry PI

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

作者： Mathew, Dennise Kirubasri, G. Vijay, K. Eugene Berna, I. Sowmia, K.R. Baselios MathewsII College of Engineering Department of Computer Science and Engineering Kollam India Sona College of Technology Department of Computer Science and Engineering Salem India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798350348217

Home invasions and thefts have gotten far too frequent in recent years. However, it is uncommon for people to be familiar with different systems, such as intrusion detectors, surveillance systems, and so on. The average person finds it challenging to maintain his home secure as a result. CCTV cameras are expensive in surveillance since they employ computers. It sets aside an excessive amount of space for ongoing recording and needs personnel to find irregularities. Our goal is to develop a comprehensive home security system that will help homeowners protect their properties from such disasters. The Raspberry Pi4-based Home Security System project aims to let someone secure their home against burglary and theft in one go. However, the Raspberry Pi system is significantly less expensive, has greater resolution, and has capabilities that use less power than the current system. Here, infrared (IR) sensors are used as straightforward yet effective triggers for human presence. For tiny confidential data area surveillance, this solution is appropriate. i.e., a home office, a bank restroom, etc. The image is taken by the camera and momentarily saved in the Raspberry Pi module whenever motion is detected by the PIR sensor within the room. Applications built on the Internet of Things can be used remotely to monitor activities and receive alerts when motion is detected. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Improving the Quality of Diabetic Data with Large Language Model-driven Cleaning Techniques

Improving the Quality of Diabetic Data with Large Language M...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Biradar, Divya Dattangire, Rahul Vaidya, Ruchika Inti, NagaSuryaShivani University of Texas at Arlington Computer Science ArlingtonTX76013 United States Data Engineering HoustonTX77002 United States Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Maharashtra Wardha442001 India University of Texas at Arlington Computer and Information Science ArlingtonTX76013 United States

ISBN: (纸本)9798331539948

The data-cleaning approach applies the capabilities of large language models to reduce the noise in the extracted and received data from healthcare sources. The aim will be to clean the collected and extracted data by looking up and dealing with the inaccuracies encountered during the project like missing or duplicated records, outliers, and data that will not add any value to the project. The 'Diabetes' data set from Kaggle is divided into implementing the combined approach Data-cleaning process such as removing duplicate entries, and emptying fields by a Large Language Model, to improve the accuracy is assessed. Three components will increase the reliability of the collected data: 1. Gateway, 2. Storage 3. Cleaning. The outcomes demonstrated the LLMbased approach's effective impact in correcting and consistent data within the healthcare dataset. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Automatic Human Life Rescue Analysis Model with Incorporation of Deep learning Algorithm 5

Automatic Human Life Rescue Analysis Model with Incorporatio...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Kalaiselvi, V.K.G. Prithikhaa, S. Divya Darshini, J. Reddy, S Bharath Anandkumar, B. Hariharan, Shanmugasundaram Sri Sairam Engineering College Department of Information Technology Tamilnadu India KG Reddy College of Engineering and Technology Department of CSE Telangana India Vardhaman College of Engineering Department of Artificial Intelligence and Machine Learning India Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Hyderabad India

ISBN: (纸本)9798331530013

In today's fast-paced world, every passing moment can mean the difference between life and death. To address this critical issue, we have developed an innovative application designed to provide rapid emergency medical response. Ambulance services play a pivotal role in emergency healthcare by offering vital transportation and care. However, limited access to ambulance contact information often hampers patients' ability to secure timely assistance during emergencies. With the widespread adoption of smartphones and mobile applications, the proposed solution integrates React Native with a Convolutional Neural Network (CNN) to create an advanced mobile app for law enforcement, capable of real-time car accident detection. Utilizing datasets from Kaggle, images are resized to optimize CNN training. Through transfer learning, the CNN architecture effectively extracts spatial features, enabling accurate accident prediction, validated by robust evaluation metrics such as precision and recall. The React Native app facilitates swift notifications to law enforcement, utilizing cutting-edge deep learning technology to enhance road safety and improve emergency response efficiency. This project aims to streamline emergency services, minimizing response and transport times, thereby saving lives and fostering safer communities. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Neuro-Fuzzy Predictor Trained by an Elitism artificial Electric Field Algorithm for Estimation of Compressive Strength of Concrete Structures

Informatica (Slovenia)

引用

Informatica (Slovenia) 2023年第5期47卷 41-48页

作者： Kumar Dash, Ch Sanjeev Nayak, Sarat Chandra Behera, Ajit Kumar Dehuri, Satchidananda Department of Computer Science and Engineering Silicon Institute of Technology Silicon Hills Patia Bhubaneswar751024 India Department of Artificial Intelligence Engineering and Machine Learning CMR College of Engineering and Technology Hyderabad501401 India Department of Information and Communication Technology Fakir Mohan University Vyasa Vihar Odisha Balasore756019 India

Meta-heuristic learning-based forecasting is widely acceptable vis-à-vis manual and statistical methods in estimating the compressive strength of concrete structures. However, there is always a scope for exploring an effective, automated, and accurate predictor for this domain. This article proposes an elitism artificial electric field algorithm-based neuro-fuzzy network (eAEFA+NFN) for the prediction of compressive strength of concrete structures. The elitism method helps AEFA preserve the best individuals from iteration to iteration, by directly placing best fit particles into the population for the next generation and thus strengthening the optimization capacity of AEFA. A single hidden layer neural network (SHNN) is used as the base model and its inputs are fuzzified using the Gaussian triangular membership function with a degree of membership to different classes. The optimal number of input data, hidden neurons, bias, and weights for the hidden layer are decided by eAEFA. The model is evaluated on samples from a publicly available dataset with curing ages at 3, 7, 14, and 28 days. Considering four sample series, the eAEFA+NFN produced an average MAPE of 0.092073 and ARV of 0.139731 which are better compared to others. The experimental outcomes and analysis are in favor of the eAEFA+NFN-based forecasting. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Electric fields

来源：评论

学校读者我要写书评

暂无评论

MULTI-TASK REINFORCEMENT learning WITH MIXTURE OF ORTHOGONAL EXPERTS 12

MULTI-TASK REINFORCEMENT LEARNING WITH MIXTURE OF ORTHOGONAL...

引用

12th International Conference on learning Representations, ICLR 2024

作者： Hendawy, Ahmed Peters, Jan D'Eramo, Carlo Department of Computer Science TU Darmstadt Germany Germany Center for Cognitive Science TU Darmstadt Germany Systems AI for Robot Learning Germany Center for Artificial Intelligence and Data Science University of Würzburg Germany

Multi-Task Reinforcement learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems. To this end, sharing representations plays a fundamental role in capturing both unique and common characteristics of the tasks. Tasks may exhibit similarities in terms of skills, objects, or physical properties while leveraging their representations eases the achievement of a universal policy. Nevertheless, the pursuit of learning a shared set of diverse representations is still an open challenge. In this paper, we introduce a novel approach for representation learning in MTRL that encapsulates common structures among the tasks using orthogonal representations to promote diversity. Our method, named Mixture Of Orthogonal Experts (MOORE), leverages a Gram-Schmidt process to shape a shared subspace of representations generated by a mixture of experts. When task-specific information is provided, MOORE generates relevant representations from this shared subspace. We assess the effectiveness of our approach on two MTRL benchmarks, namely MiniGrid and MetaWorld, showing that MOORE surpasses related baselines and establishes a new state-of-the-art result on MetaWorld. © 2024 12th International Conference on learning Representations, ICLR 2024. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Doctor Assistance Tool: Personalized Healthcare Treatment Recommendations Journey from Deep Reinforcement learning to Generative AI

A Doctor Assistance Tool: Personalized Healthcare Treatment ...

引用

Delhi Section Conference (DELCON), IEEE

作者： Gautam Kumar Artificial Intelligence and Machine Learning Birla Institute of Technology and Science (BITS) Pilani India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

In personalized patient healthcare treatment recommendation, the goal is to recommend the most suitable course of treatment for an individual patient based on patient-specific data, including prior medical history, electronic health records (EHR), genetic information, lifestyle factors, and treatment outcomes. This study aims to extend the paradigm of personalized treatment recommendations from Deep Reinforcement learning (DRL) to Generative artificial intelligence (GenAI). A DRL algorithm is employed to derive the best policy for personalized treatment recommendations. At the same time, the Med-PaLM-2 large language model (LLM) is used to generate diagnosis reports tailored to the individual patient. I propose a Personalized Treatment Healthcare Recommendation System (PTHRS), using a fine-tuned Med-PaLM-2 model on the Intensive Care Unit (ICU) dataset and the Medical Information Mart for Intensive Care (MIMIC-III) dataset. The system is designed to formulate the best treatment policies and generate clinical documentation, including discharge summaries, progress notes, customer care notes, treatments, healthcare, medication, doctor consultations, nutrition, exercise, and medical reports. These documents capture essential information and generate personalized recommendations for diagnosis and treatment plans. Experimental results prove that the model achieves an accuracy of 66%, a BLEU score of 0.66, and a clinical validation success rate of 80%, outperforming baseline DRL techniques in generating the best policies for personalized treatment recommendations.

关键词： Accuracy Generative AI Large language models MIMICs Medical services Deep reinforcement learning Genetics History Medical diagnostic imaging Recommender systems

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：