检索结果-内蒙古大学图书馆

Recent Progress in Reinforcement Learning and Adaptive Dynamic Programming for Advanced Control Applications

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 18-36页

作者： Ding Wang Ning Gao Derong Liu Jinna Li Frank L.Lewis IEEE the Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent SystemBeijing Laboratory of Smart Environmental Protectionand Beijing Institute of Artificial IntelligenceBeijing University of TechnologyBeijing 100124China the School of System Design and Intelligent Manufacturing Southern University of Science and TechnologyShenzhen 518055China the Department of Electrical and Computer Engineering University of Illinois at ChicagoChicago IL 60607 USA the School of Information and Control Engineering Liaoning Petrochemical UniversityFushun 113001China the UTA Research Institute the University of Texas at ArlingtonArlington TX 76118 USA

Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, ***, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation ***, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.

关键词： Adaptive dynamic programming(ADP) advanced control complex environment data-driven control event-triggered design intelligent control neural networks nonlinear systems optimal control reinforcement learning(RL)

来源：评论

学校读者我要写书评

暂无评论

Identification of NPK Deficiency in Toor Dal Leaf Using CNN Technique

Identification of NPK Deficiency in Toor Dal Leaf Using CNN ...

引用

Integrated intelligence and Communication Systems (ICIICS), International Conference on

作者： Syeda Umme Hani Sujata V. Mallapur Artificial Intelligence & Data Science Faculty of Engineering & Technology Sharnbasva University Kalaburgi Karnataka India

The main economic contributor to India is agriculture. The Nitrogen (N), phosphorus (P), and potassium (K), are the crucial parts of nutrients in plant growth. NPK deficiency levels affect plant development and crop productivity. By analyzing the leaf properties, we hope to build a model for an artificial neural network (Convolutional Neural Network Technique) that will be able to identify and categorize nutrient deficiencies in toor dal leaf. The two main characteristics used to determine NPK deficiencies in plants are the color and shape of a leaf. The dynamic capture of toor dal leaves by scanning was employed in this work to investigate how the regulation of leaf attributes changed in response to nutritional stress. In this work, the impact of various activation functions on the artificial neural network is also investigated. The findings demonstrate that the suggested technique was highly accurate in classifying and identifying NPK deficiencies in toor dal leaf.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Childhood Malnutrition Using Survey data and Machine Learning Approaches 4

Early Detection of Childhood Malnutrition Using Survey Data ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Zumma, Thoufiq Rahaman, Anikur Islam Prova, Nuzhat Noor Haque, Tasriful Joy Bose, Julias Caeser Youki, Ravina Akter Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh Washington University Science and Technology Department of Computer Science New York United States Pace University Department of Seidenberg School of Csis New York United States Victorian Institute of Technology Master of Information Technology and Systems Australia University of Wollongong Faculty of Artificial Intelligence and Science Australia University of Technology Sydney Faculty of Engineering and It Australia

ISBN: (纸本)9798331523923

Children's physical, mental and emotional development depends heavily on sleep, with age-specific sleep needs fluctuating. Malnutrition may result from eating too little, absorbing nutrients poorly, being unwell, living in poverty or not knowing enough about nutrition. Food allergies and iron insufficiency are two examples of illnesses whose onsets might differ depending on environmental exposures and genetics. By providing proper diet, getting medical attention when necessary and encouraging healthy behaviors, parents play a crucial role in supporting their children's health. For children to grow and develop properly, they need meals high in fruits, vegetables, milk, protein, calcium, iron and fiber. Key advantages of a balanced diet include aiding bone formation, improving heart health and encouraging regular bowel motions and digestion. In general, children's general health and wellness depend on caregivers being aware of their dietary requirements and giving them the proper attention. The findings of the research imply that machine learning algorithms may be useful in understanding and predicting the prevalence of malnutrition in children. Furthermore, these algorithms could provide perceptive data that might help politicians create effective policies. In this research, we make use of five different machine learning algorithms. With a decision tree, the accuracy is 0.92%, followed by svm which provides 0.91%, KNN, which provides 0.84%, GBM classifier, which provides 0.79% and random forest, which provides 0.65%. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Computational Vision Techniques for Weed Detection in Crops

Leveraging Computational Vision Techniques for Weed Detectio...

引用

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Thendral, R. Ranjeeth, A. Ifet College of Engineering Department of Information Technology Gangarampalayam Tamil Nadu 605108 India Ifet College of Engineering Department of Artificial Intelligence and Data Science Gangarampalayam Tamil Nadu 605108 India

ISBN: (纸本)9798350315127

The precise utilization of herbicides can result in a significant decrease in their application levels within agricultural fields. The detection system plays a vital role in smart sprayers, enabling the identification of target weeds and facilitating informed spraying decisions. The development of near-ground image capture and processing techniques for weed detection in vegetable crops is the main topic of this research. The first step in the image processing involves detecting green plants, which helps to minimize irrelevant information and streamline the weed detection process. Subsequently, the study has emphasized vegetation segmentation through the application of morphological filtering and object labeling techniques, enabling weed detection based on a threshold derived from the area of detection. The proposed methods incorporate color and area analysis techniques, effectively distinguishing between crops, weeds, and soil. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Investigation on Nail Denting or Crumbling from Nail Psoriasis Patient Ailment data using the Machine Learning Algorithm and data Mining Techniques 8

Investigation on Nail Denting or Crumbling from Nail Psorias...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Janani, K. Santhoshkumar, S.P. Vikram, D. Priya, S. Vijayaraj, M. Priyanga, M. Manipal Institute of Technology Department of Data Science and Computer Applications Manipal India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Avadi Department of Computer Science and Engineering Chennai India Rathinam Technical Campus Department of Artificial Intelligence and Data Science Coimbatore India Rathinam Technical Campus Department of Information Technology Coimbatore India

ISBN: (纸本)9798350367904

Nail denting or crumbling may result from nail psoriasis. A nail condition known as psoriatic onychodystrophy or psoriatic nails. Psoriasis sufferers frequently experience it;reported occurrences range from 10% to 78%. Psoriatic nails are more common in the elderly and in people with psoriatic arthritis. By examining the nails on a human hand, numerous illnesses can be found early in the diagnosing process. The nail color of an individual can help in the diagnosis of specific medical disorders. In this case, the recommended method results in the decision-making process for sickness diagnosis. The system is fed by human nail art. The technique recognizes nail features unique to a given condition by analyzing images of nails. The suggested technique makes advantage of the various distinctive characteristics of human nails to detect illness by changing the colour of the nails. The first training set data, which is derived from an image of a patient's nails with a particular ailment, is handled by the Weka tool. To get the desired results, the feature discoveries of the picture are compared to the training dataset. The distortion of the nail unit is known as nail disease. Nail units have their own disease class due to their own indications, symptoms, causes, and consequences, which may or may not be related to other medical disorders. Nail problems are still difficult and ambiguous to identify. A novel machine learning method for recognising and classifying nail problems from photographs is presented in this study. This framework combines CNN models with data mining techniques to extract characteristics. This research was also contrasted with certain other province algorithms (Support vector, ANN, K - nearest neighbors, and RF) evaluated on datasets and showed positive results. The accuracy numbers show how well the model can distinguish nail conditions. This ground-breaking discovery lays the groundwork for precise diagnosis in dermatology, medical image processing, an

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Diabetic Foot Ulcer Detection with Deep Learning-Based Predictive Systems

Enhanced Diabetic Foot Ulcer Detection with Deep Learning-Ba...

引用

data science and Business Systems (ICDSBS), International Conference on

作者： A R Jariya Begum Poornima C Saranya S Akshaya Vardhini R Faculty of Artificial Intelligence and Data Science Meenakshi Sundararajan Engineering College Kodambakkam Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Meenakshi Sundararajan Engineering College Kodambakkam Chennai Tamil Nadu India

ISBN: (数字)9798331585600

ISBN: (纸本)9798331585617

Diabetes mellitus is a chronic metabolic disorder affecting millions of people globally, often leading to severe complications such as diabetic foot ulcers. DFUs can progress to infections, including cellulitis and gangrene, and may ultimately result in lower-limb amputations. Distal symmetric polyneuropathy (DSP) plays a key role in the development of these ulcers by impairing sensation and promoting unnoticed injuries. This paper presents a deep learning approach using convolutional neural networks to detect DFUs at an early stage through thermal imaging. The ResNet50, EfficientNetB0, MobileNet, and DenseNet121 models were trained to classify healthy and ulcerated foot images with high accuracy. Image preprocessing techniques, including edge detection and segmentation, were applied to improve feature extraction and enhance prediction performance. The results demonstrate that these models can effectively identify the early signs of DFUs, enabling timely medical intervention. This study highlights the potential of AIdriven diagnostic systems to reduce DFU-related complications and improve patient outcomes.

关键词： Deep learning Image segmentation Image edge detection data science Feature extraction Diabetes Convolutional neural networks Image preprocessing Medical diagnostic imaging Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Advanced Lung Cancer Diagnosis and Treatment with artificial intelligence: Applications, Methods, and Future Directions

Advanced Lung Cancer Diagnosis and Treatment with Artificial...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Pawan Dilip Chaudhari Amit Gudadhe Artificial Intelligence and Data Science Faculty of Engineering and Technology(DMIHER) Sawangi(M) Wardha Maharashtra India Computer Science and Design Faculty of Engineering and Technology(DMIHER)Sawangi(M) Wardha Maharashtra India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

AI technology revolutionizes the treatment of lung cancer and other related lung cancer diagnoses, hence becoming the game-changing technology in the diagnosis and treatment of this serious disease. As one of the most prevalent and deadliest cancers globally, early identification, precise diagnosis, and efficient planning for the treatment of lung cancer have always been difficult. The therapy using AI-based methods is introducing another novel way of addressing the problems concerning lung cancer via advanced imaging analysis, predictive modeling, and tailored plans of treatment, the most important among which is of course, imaging analysis. What is certainly most exciting among the applications of AI in lung cancer treatment is in the realm of imaging analysis. AI has been seen to be extremely clever in the interpretation of images rather than using machine learning or deep learning but has been much faster and more accurate than a human being while doing it. Besides, these systems also increase the general accurateness of diagnosis through a reduction of the error in diagnosis and consistent results. Alluring promises are made for AI soon for the treatment of lung cancer. In this paper, we discuss how AI has been transformed into imaging, diagnosis, and treatment planning and how this will improve patient outcomes and completely transform the way healthcare is delivered. We also consider barriers still to be cleared for realizing fully the potential benefits of AI. These include problems such as the quality of available data used in model interpretation and generalizability across different healthcare settings. Therefore, we end and suggest some future research on collaboration by emphasizing the safe, effective, and ethical entry of AI into normal clinical practice.

关键词： Analytical models Renewable energy sources Ethics Lung cancer Imaging Medical treatment Transforms Predictive models Planning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach and its Application in the Cybersecurity Domain

Deep Learning Approach and its Application in the Cybersecur...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Pawan Dilip Chaudhari Amit Gudadhe Faculty of Engineering and Technology(DMIHER) Artificial Intelligence and Data Science Sawangi(M) Wardha Maharashtra India Faculty of Engineering and Technology(DMIHER) Computer Science and Design Sawangi(M) Wardha Maharashtra India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Cyber Security has become especially prominent and critical for organizations all over the world because of the fast advancements in technology and the increasing sophistication of modern cyber threats. Most traditional methods related to cyber security are unable to match the scale and complexity of modern cyber-attacks. Deep learning has emerged in this context as a powerful tool for offering brand-new approaches and avenues toward threat detection, anomaly identification, and protection of data. In this paper, we investigate the basic principles of deep learning and its significant architectures Convolutional Neural Networks, Recurrent Neural Networks, and Generative Adversarial Networks which provide models for solving various issues in the field of cybersecurity. We describe the contribution of deep learning to intrusion detection systems, malware detection, phishing protection, DDoS attack mitigation, and fraud detection. Deep learning also presents some advantages in cybersecurity. In this paper, I reviewed the basic applications, challenges, and potential solutions for enhancing cybersecurity systems by techniques of deep learning. Every organization, right from financial institutes to the entire globe employing itself to reach a developmental stage, has been forced to consider the implications of cybersecurity threats carefully. Most traditional methods relevant to cybersecurity have been ineffective at combatting modern cyber-attacks' scale and complexity.

关键词： Deep learning Recurrent neural networks Prevention and mitigation Phishing Organizations Threat assessment Complexity theory Computer security Protection Cyberattack

来源：评论

学校读者我要写书评

暂无评论

Federated intelligence for Intelligent Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第5期9卷 1-5页

作者： Zhang, Weishan Zhang, Baoyu Jia, Xiaofeng Qi, Hongwei Qin, Rui Li, Juanjuan Tian, Yonglin Liang, Xiaolong Wang, Fei-Yue School of China University of Petroleum Qingdao China Department of Data Management Big Data Centre Beijing Beijing China Technology Company Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Innovation Engineering Macau University of Science and Technology Macao China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

This letter is a brief summary of a series of IEEE TIV's decentralized and hybrid workshops (DHWs) on Federated intelligence for Intelligent Vehicles. The discussed results are: 1) Different scales of large models (LMs) can be federated and deployed on IVs, and three types of federated collaboration between large and small models can be adopted for IVs. 2) Federated fine-tuning of LMs is beneficial for IVs data security. 3) The sustainability of IVs can be improved through optimizing existing models and continuous learning using federated intelligence. 4) LM-enhanced knowledge can make IVs smarter. IEEE

关键词： Intelligent vehicle highway systems

来源：评论

学校读者我要写书评

暂无评论

Autoencoder based Temporal Convolutional Network for Anomaly Detection in data Streams 1

Autoencoder based Temporal Convolutional Network for Anomaly...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Tamilselvan, K. Riadhwsein, Ramee Sundaram, S. Meenakshi Vigneshwaran, K.S. Abhinaya, S. Avs Engineering College Department of Information Technology Salem India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Data Science Bengaluru India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Computer Science and Engineering Mamallapuram India

ISBN: (纸本)9798331529246

Nowadays, the rapid growth of data stream from different sources has needed the development of effective Anomaly Detection (AD) methods. The existing unsupervised Deep Learning (DL) approaches learnt various patterns and relationships in data streams without labeled data. However, detecting anomalies in data streams led to significant challenges such as handling high-dimensional data and capturing temporal dependencies. Hence, this research proposes an Autoencoder based Temporal Convolutional Network (AE-TCN) for AD in data streams. Initially, the input data is collected from Numenta Anomaly Benchmark (NAB) repository and further preprocessed with Regression Imputation (RI) to handle missing values and logarithmic scaling to normalize the data respectively. After that, Robustly Optimized Bidirectional Encoder Representation from Transformer approach (RoBERTa) is employed to extract the semantic features. Finally, AE-TCN is introduced to identify the anomalies in data streams by extracting temporal features from reconstructed nominal patterns. From the results, the proposed AE-TCN established high results in terms of Accuracy (Acc), F1-score, and Area Under Curve (AUC) of 99.89%, 94.06%, and 99.85% respectively when compared with existing Deep Autoencoder Neural Network with Adamax Optimization (DANN-AO). © 2025 IEEE.

关键词： Spatio-temporal data

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：