检索结果-内蒙古大学图书馆

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Warda A. A. Altawati Lubna A. B. Mohammed Mohamed A. E. Abdalla Dept. of Computer Science Faculty of Information Technology University of Benghazi Benghazi Libya Dept. of Artificial Intelligence and Computer Systems Faculty of Information Technology University of Benghazi Benghazi Libya

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Liver diseases are known as one of the deadly diseases around the world. The diagnosis is crucial due to the fact of that the high incidence and death rates. Although, there are commonly used methods for diagnosing liver disorders, they are too expensive. People who are at risk of liver health issues would benefit from the early and low-cost diagnosis for effective treatment. Recently, machine learning plays obvious roles on healthcare to help medical experts to detect illnesses at early onset of the disease. The diagnosis of the liver diseases has been considered in several studies. This paper develops the accuracy rate of the diagnosis of liver diseases with less size of features. Decreasing the size of feature vectors minimizes the time cost of the machine learning model. The paper puts into practice feature selection techniques: Relief, PCA, PSO, and OS to gain its aim. The proposed method of this paper of the diagnosis is applied on two different datasets: ILPD and BUPA. Four different experiments have been carried out for acquiring high level of outcomes. Despite the promised results obtained from all feature selection techniques considered in this study, the selected features using Relief with the random forest classifier (RF) has yielded the best accuracy rates of 91.3% and 98.55% from ILPD and BUPA respectively.

关键词： Accuracy Liver diseases Mortality Feature extraction Vectors Particle swarm optimization Random forests Principal component analysis Diseases Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

POCS-based Image Compression: An Empirical Examination 7

POCS-based Image Compression: An Empirical Examination

引用

7th International Conference on Green technology and Sustainable Development, GTSD 2024

作者： Do, Truong-Dong Tran, Le-Anh Nguyen, Thanh-Dat Truong, Nghe-Nhan Park, Dong-Chul Le, My-Ha Sejong University Dept. of Aerospace Systems Engineering Seoul Korea Republic of Myongji University Dept. of Electronics Engineering Yongin Korea Republic of Dept. of Research and Development Ocst Co. Ltd. Seoul Korea Republic of Sejong University Dept. of Computer Science & Engineering Seoul Korea Republic of Hcmc University of Technology & Education Dept. of Electrical & Electronics Engineering Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350386073

This paper investigates the applicability of the Pro-jection onto Convex Set (POCS)-based clustering algorithm to image compression tasks. The POCS-based clustering approach treats all data points in a given dataset as non-intersecting convex sets and performs POCS-based parallel projections from each cluster prototype onto corresponding member data points to minimize an objective function and update cluster prototypes. The POCS-based clustering algorithm has been proven to be able to yield promising results against other prevailing clustering approaches in terms of convergence time and clustering error on general clustering tasks. In this study, a comparison of various clustering schemes for image compression applications has been conducted. The evaluations and analyses on various standard test images verify that the POCS-based clustering algorithm can perform competitively against other conventional clustering methods in image compression problems. © 2024 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards responsible AI in education: Challenges and implications for research and practice

引用

computers and Education: Artificial Intelligence 2024年

作者： Pargman, Teresa Cerratto McGrath, Cormac Milrad, Marcelo Stockholm University Dept. of Computer & Systems Sciences 16425 Sweden Stockholm University Dept. of Education Stockholm10691 Sweden Linnaeus University Dept. of Computer Science & Media Technology Växjö35195 Sweden

来源：评论

学校读者我要写书评

暂无评论

Efficient Blind Channel Estimation for IRS-Assisted Joint Communication and Sensing in 6G Networks

Efficient Blind Channel Estimation for IRS-Assisted Joint Co...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Siddig, Ali A. Al-Dweik, Arafat Iraqi, Youssef Pandey, Anshul Giacalone, Jean-Pierre Hamila, Ridha Al-Rimawi, Ashraf Khalifa University of Science and Technology Dept. of Computer and Information Eng. PO Box 127788 Abu Dhabi United Arab Emirates Mohammed VI Polytechnic College of Computing Benguerir Morocco Secure Systems Research Center Abu Dhabi United Arab Emirates Qatar University Dept. of Electrical Eng. Doha Qatar Birzeit University Dept. of Electrical and Computer Eng. Birzeit Palestine

ISBN: (纸本)9798350376715

To achieve the ultimate performance of intelligent reflecting surface (IRS), an accurate channel estimation is required, which in turns induces significant signaling overhead. This work presents a novel blind channel estimation scheme for IRS-assisted heterogeneous communications and sensing networks. The proposed scheme consists of two transmission stages, one for sensing and the other for communications. By noting that the sensing information have generally less stringent quality of service (QoS) requirements, the sensing stage is used for joint blind sensing data detection and blind channel estimation for the subsequent communications stage. Channel estimation is achieved using a specific frame structure where the modulated sensing symbols cooperate to estimate the channel coefficients for all IRS reflecting elements blindly and jointly. The simulation results obtained show that the proposed blind channel estimation accuracy is comparable to pilot-based schemes. © 2024 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

RadioModRec-l: A Large Scale Radio Frequency Dataset for Automatic Modulation Recognition Research 4

RadioModRec-l: A Large Scale Radio Frequency Dataset for Aut...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Adetiba, Emmanuel Olasina, Jamiu R. Obiyemi, Obiseye Covenant University Covenant Applied Informatics and Communication Africa Center of Excellence Dept. of Electrical and Information Engineering Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban4001 South Africa Federal Polytechnic Ilaro Dept. of Computer Engineering Ilaro Nigeria Durban University of Technology Space Science Centre Dept. of Electrical Power Engineering Durban South Africa

ISBN: (纸本)9798350353266

Access to well-curated large datasets remains a significant bottleneck in AI-based research within wireless communication. Rapid advancements in neighbouring fields, such as computer vision and natural language processing, are largely due to the availability of extensive open-access datasets. However, similar progress has not been observed in wireless communication. To address this gap, we curated a comprehensive dataset for fifteen digital modulation schemes, including 4QAM, 16QAM, 64QAM, 256QAM, 8PSK, 16PSK, 32PSK, 64PSK, 128PSK, 256PSK, CPFSK, DBPSK, DQPSK, GFSK, and GMSK. Our dataset considers Rayleigh and Rician channel models under Additive White Gaussian Noise (A WGN) with SNRs ranging from -20dB to + 20dB in 5dB increments. The data samples were converted to constellation signal images and carefully pre-processed. Named RadioModRec, this dataset provides a valuable resource for researchers to train and evaluate AI models. It is freely accessible on Kaggle, promoting further innovation in the wireless communication domain. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Controlled Dropout for Uncertainty Estimation

Controlled Dropout for Uncertainty Estimation

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Hasan, Mehedi Hossain, Ibrahim Rahman, Ashikur Nahavandi, Saeid Institute for Intelligent Systems Research and Innovation Deakin University GeelongVIC3220 Australia Bangladesh University of Engineering and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350337020

Uncertainty quantification in a neural network is one of the most discussed topics for safety-critical applications. Though Neural Networks (NNs) have achieved state-of-the-art performance for many applications, they still provide unreliable point predictions, which lack information about uncertainty estimates. Among various methods to enable neural networks to estimate uncertainty, Monte Carlo (MC) dropout has gained much popularity in a short period due to its simplicity. In this study, we present a new version of the traditional dropout layer where we are able to fix the number of dropout configurations. As such, each layer can take and apply the new dropout layer in the MC method to quantify the uncertainty associated with NN predictions. We conduct experiments on both toy and realistic datasets and compare the results with the MC method using the traditional dropout layer. Performance analysis utilizing uncertainty evaluation metrics corroborates that our dropout layer offers better performance in most cases. © 2023 IEEE.

关键词： dropout Monte Carlo dropout neural network Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Smart Greenhouse Control System using Multi-Objective Adaptive Policy Gradient and Neural Meta Controller 4

Smart Greenhouse Control System using Multi-Objective Adapti...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information systems, ICUIS 2024

作者： Himabindu, C.H. Sreeramu, M. Chaganti, Koushik Reddy Gutta, Pruthvi Krishna Nagesh, C. Ruksana, S. Vignan Institute of Technology and Science Dept of Mba Hyderabad India University of the Cumberlands Dept. of Computer and Information Systems KY United States Tesla Dept of It AustinTX United States Srinivasa Ramanujan Institute of Technology Department of Cse Anantapur India Gates Institute of Technology and Science Department of Cse Anantapur India

ISBN: (纸本)9798331529635

This confluence of escalating energy costs and upsurges in the demand for high-quality crop yields under uncertain environmental conditions makes a strong case for the urgent optimization of greenhouse operations. The most currently used control systems for smart greenhouses are founded upon static or even narrowly focused optimization approaches, which severely limit their adaptability and efficiency in dynamic settings. These methodologies fail to address the challenge of multiple objectives, such as the consumption of energy and crop yield, with unpreparedness for disturbances caused by external influences and computational bottlenecks. This paper brings about a collective framework for three of the most advanced RL methodologies: Multi-Objective Adaptive Policy Gradient with Environmental Feedback, Hierarchical Reinforcement Learning with Temporal Decision Decomposition, and Neural Meta-Controller with Self-Organizing Sub-Networks. MAPGEF utilizes real-time environmental feedback to dynamically adjust policy weights, thus achieving up to a 25% reduction in energy use and an 18% increase in crop yield through accurate environmental tuning. The HRL-TDD utilizes hierarchical RL combined with temporal decomposition in order to handle tough tasks of a greenhouse, thus improving a decision by up to 30%, with energy efficiency improved by 20% and crop yield stabilized with 15%. NMCSOS introduces a neural meta-controller coordinating self-organizing sub-networks, ensuring robust responses to external disturbances with 33% faster recovery, 22% better energy optimization, and 18% reduced yield variability levels. Together, these methodologies address the pressing need for adaptable, scalable, and energy-efficient greenhouse control systems. By integrating multi-objective learning, temporal decomposition, and self-organizing networks, this work significantly advances greenhouse management, promoting sustainable agriculture and resilience in the face of environmental uncert

关键词： Adaptive Policy Gradient Multi-Objective Reinforcement Learning Neural Meta-Controller Scenarios Smart Greenhouse Sustainable Agriculture

来源：评论

学校读者我要写书评

暂无评论

LightNN: An Optimized Deep Learning Framework for Enhanced Fruit Classification

LightNN: An Optimized Deep Learning Framework for Enhanced F...

引用

Computing, Applications and systems (COMPAS), IEEE International Conference on

作者： Maharin Afroj Israt Jahan Md Polash Islam Md. Saifur Rahman Dept. of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh Dept. of Computer and Systems Sciences Stockholm University Stockholm Sweden

ISBN: (数字)9798331529765

ISBN: (纸本)9798331529772

The crucial field of fruit classification in computer vision and deep learning brings about breakthroughs that have broad applications in the retail and agricultural industries. By automating the identification and sorting of various fruit types, these technologies enhance efficiency, accuracy, and scalability, benefiting processes from farm production to market distribution. The integration of sophisticated algorithms and neural networks not only improves the speed and reliability of fruit classification but also offers the potential for real-time quality control and inventory management, revolutionizing traditional methods and paving the way for more innovative, data-driven approaches in these sectors. This study introduces LightNN, a novel and effective paradigm with a lightweight architecture that tackles the complex problems related to computational efficiency. Combining a small classifier with a simplified feature extractor, LightNN achieves the ideal balance between simplicity and accuracy. The feature extractor is capable of extracting hierarchical features from RGB images by using convolutional layers with ReLU activations and max-pooling procedures. The flattened output is then processed by the classifier, which consists of fully connected layers with ReLU activations and dropout regularisation. Remarkably, LightNN, with just 298,835 parameters, manages to get a respectable 96.37% test accuracy in fruit categorization tasks. The results highlight LightNN’s promise as an effective and efficient fruit classifying method, particularly in situations with constrained computational resources.

关键词： Deep learning Training Visualization Accuracy Computational modeling Scalability computer architecture Feature extraction Computational efficiency Sorting

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Based Prediction for Lateral Acceleration of Vehicles 2

Neural Network-Based Prediction for Lateral Acceleration of ...

引用

2nd IEEE Conference on Information technology and Data Science, CITDS 2022

作者： Kontos, Janos Kranicz, Balazs Vathy-Fogarassy, Agnes University of Pannonia Continental Automotive Hungary Ltd. Dept. of Computer Science and Systems Technology Veszprém Hungary Continental Automotive Hungary Ltd. Veszprém Hungary University of Pannonia Dept. of Computer Science and Systems Technology Veszprém Hungary

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

Lateral acceleration is a key element of vehicle dynamics. It is consumed by several control, stability and comfort functions of the vehicle. In this paper a neural network-based prediction method is demonstrated for predicting the value of lateral acceleration. The inputs of the method are the most accessible signals in any modern vehicle: wheel speed information, longitudinal acceleration and steering wheel angle. For training, validating and testing the neural network, experimental data was used. The hyperparameters of the neural network were tuned by a hybrid approach. The accuracy of the approach was evaluated by comparing the actual measured values to those predicted by the neural network. Evaluation results convincingly demonstrate the usefulness and reliability of the developed model. © 2022 IEEE.

关键词： Neural networks

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：