检索结果-内蒙古大学图书馆

ACS/IEEE International conference on Computer Systems and Applications

作者： Ahmed Alhamadah Muntasir Mamun Henry Harms Mathew Redondo Yu-Zheng Lin Jesus Pacheco Soheil Salehi Pratik Satam Department of Systems and Industrial Engineering University of Arizona Department of Electrical and Computer Engineering University of Arizona School of Industrial Engineering University of Sonora Mexico

ISBN: (数字)9798331518240

ISBN: (纸本)9798331518257

The onset of Industry 4.0 is rapidly transforming the manufacturing world through the integration of cloud computing, machine learning (ML), artificial intelligence (AI), and universal network connectivity, resulting in performance optimization and increased productivity. Digital Twins (DT) are one such transformational technology that leverages software systems to replicate physical process behavior, and representing it in a digital environment. This paper aims to explore the use of photogrammetry (which is the process of reconstructing physical objects into virtual 3D models using photographs) and 3D Scanning techniques to create accurate visual representation of the ‘Physical Process', to interact with the ML/AI based behavior models. To achieve this, we have used a readily available consumer device, the iPhone 15 Pro, which features stereo vision capabilities, to capture the depth of an Industry 4.0 system. By processing these images using 3D scanning tools, we created a raw 3D model for 3D modeling and rendering software for the creation of a DT model. The paper highlights the reliability of this method by measuring the error rate in between the ground truth (measurements done manually using a tape measure) and the final 3D model created using this method. The overall mean error is 4.97 % and the overall standard deviation error is 5.54% between the ground truth measurements and their photogrammetry counterparts. The results from this work indicate that photogrammetry using consumer-grade devices can be an efficient and cost-efficient approach to creating DTs for smart manufacturing, while the approaches flexibility allows for iterative improvements of the models over time.

关键词： Solid modeling visualization Three-dimensional displays Accuracy Measurement uncertainty Fourth Industrial Revolution Digital twins Photogrammetry Standards Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Balancing Energy Consumption and Latency in Vehicle Edge Computing for 6G Networks

Balancing Energy Consumption and Latency in Vehicle Edge Com...

引用

International Wireless Communications and Mobile Computing conference, IWCMC

作者： Bingxin Wang Dan Tu Jie Wang Beijing Research Institute China Beijing China Telecom Corporation Limited China Beijing China

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The rapid evolution of wireless communication technologies has led to the emergence of 6G networks, promising unprecedented connectivity and data processing capabilities. Within the 6G landscape, vehicle edge computing has gained increasing importance due to its potential to enhance real-time applications and services for connected and autonomous vehicles. However, the seamless integration of vehicles into edge computing environments presents a significant challenge—balancing the trade-off between energy consumption and latency. This research paper explores the critical problem of achieving an equilibrium between energy efficiency and low-latency communication in vehicle edge computing within the context of 6G networks. We propose a novel approach that integrates energy-aware computing strategies and latency optimization techniques to strike the optimal balance between these two conflicting objectives. In the methodology section, we provide a comprehensive overview of our proposed approach, detailing how it measures and evaluates both energy consumption and latency in the context of vehicle-edge interactions. We leverage advanced algorithms and models to efficiently allocate computing resources, optimize task scheduling, and minimize data transmission delays, all while considering the energy constraints of the vehicular devices. To validate the effectiveness of our approach, extensive experiments were conducted in a simulated vehicular edge computing environment. The experimental results demonstrate a substantial reduction in energy consumption while maintaining low-latency communication, outperforming existing methods. We present these results in graphical form, offering clear visual evidence of the improvements achieved.

关键词： 6G mobile communication Wireless communication Energy consumption visualization Connected vehicles Energy efficiency Low latency communication

来源：评论

学校读者我要写书评

暂无评论

Maize Seed Quality detection using ResNet V2 Deep Learning Technique

Maize Seed Quality detection using ResNet V2 Deep Learning T...

引用

Intelligent Technologies (ACOIT), Asian conference on

作者： R. Kavitha V. Murugananthan M. Kavitha R. Srinivasan K. Rajathi Department of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai India School of Computing Asia Pacific University of Technology & Innovation (APU) Technology Park Malaysia Kuala Lumpur Malaysia

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

Recent advancements in agricultural technology have seen the application of computational methods for seed quality detection. A range of studies have explored the use of deep learning in seed quality detection in agriculture. For the agricultural sector to achieve maximum crop yields and food security, the quality of the maize seeds must be guaranteed. The conventional techniques for evaluating the quality of seeds, which depend on visual inspection and biochemical analyses, are labor-intensive, time-consuming, and frequently prone to human error. We suggest using the ResNet $\mathbf{v} 2$ deep learning architecture in an automated maize seed quality detection system to overcome these issues. In the proposed work, we assembled an extensive dataset of photos of maize seeds. To assess the performance of the model, the dataset was divided into subsets for training, validation, and testing. To improve the model’s capacity for generalization, data augmentation methods including rotation, zooming, and flipping were used during training. Starting with pre-trained weights on ImageNet, the ResNet v2 model was refined via transfer learning. Stochastic gradient descent with a learning rate scheduler was then used to further optimize the model. This research employs images of maize seeds for the purpose of classification. The process of classification is facilitated through the utilization of a Convolutional Neural Network (CNN) that operates on the ResNet152 v2 architecture. The chosen hyperparameters include a learning rate set at 0.001, a batch size of 512, and an epoch of 150. The optimization technique employed is Adaptive Moment Estimation (Adam). The distribution between training and validation data is maintained at a ratio of $80: 20$. Analysis of the validation outcomes reveals an accuracy rate of $\mathbf{9 6 \%}$ compared to other traditional models.

关键词： Deep learning Training visualization Accuracy Transfer learning Stochastic processes Seeds (agriculture) Convolutional neural networks Time factors Testing

来源：评论

学校读者我要写书评

暂无评论

Visual-LIDAR SLAM Based on Supervised Hierarchical Deep Neural Networks

Visual-LIDAR SLAM Based on Supervised Hierarchical Deep Neur...

引用

Youth Academic Annual conference of Chinese Association of Automation (YAC)

作者： Yi An Zhuo Sun Chao Zhang Haifeng Yue Yan Zhi Hongliang Xu School of Control Science and Engineering Dalian University of Technology Dalian China School of Electrical Engineering Xinjiang University Urumqi China Ministry of Water Resources Information Center Beijing China State Key Laboratory of Intelligent Mining Equipment Technology Taiyuan China Shanxi TZCO Intelligent Mining Equipment Technology Co. Ltd Taiyuan China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

Deep learning has become increasingly crucial in simultaneous localization and mapping (SLAM). Supervised deep learning SLAM methods need ground truth data for training but achieve highly accurate predictions. Such training techniques are used by some visual or LiDAR SLAM methods. However, these methods mostly rely on single-sensor data, missing the combined advantages of LiDAR and visual information. Multisensor fusion SLAM merges diverse data types, enriching features and boosting performance. This paper presents a new deep visual-LiDAR SLAM method that integrates both visual and LiDAR data. The SLAM system includes a deep visual-LiDAR odometry module, a deep learning-based loop closure detection module, and a 3D mapping module. The deep visual-LiDAR odometry module uses a hierarchical feature encoding module to capture features from two frames of color point clouds at various levels. An attention feature decoding module employs an attention mechanism to merge these features, determining their relative pose. The iterative pose optimization module continuously refines the pose accuracy, improving robustness to outliers. The loop closure detection module uses a deep learning-based global descriptor for precise positional matching. The 3D mapping module constructs the environmental map. Experimental results on the KITTI odometry dataset show that our method outperforms other supervised and traditional geometric methods, with lower rotation and translation errors. By integrating visual and LiDAR data, our SLAM system achieves higher accuracy and robustness in pose estimation compared to single-modal SLAM systems.

关键词： Point cloud compression Training visualization Simultaneous localization and mapping Three-dimensional displays Laser radar Accuracy

来源：评论

学校读者我要写书评

暂无评论

Optimizing Food Image Classification Using Black Widow Algorithm and Deep Learning techniques

Optimizing Food Image Classification Using Black Widow Algor...

引用

International conference on Advances in Information Technology (ICAIT)

作者： Bhavana Jamalpur Sakthi Priya G S. Venkat Aarthi R S. Kavitha G. Charles Babu Department of Computer Science and Artificial Intelligence S R University Hanamkonda Telangana Computer science and engineering Ramco Institute of Technology Rajapalayam Department of ECE S.A. Engineering College Chennai Department of ECE R.M.D Engineering College Department of CSE Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of CSE Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Hyderabad Telangana

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

Food image classification is a key application of computer vision and Machine Learning (ML) devoted to mechanically classifying and labelling different food items depending on visual content seized in images. Using sophisticated Convolutional Neural Networks (CNNs) and deep learning (DL) models, this skill permits detection of different dishes, culinary creations, ingredients and raises many practical uses. From supporting nutritional choices and recipe recommendations to menu analysis and food quality control, food image detection updates procedures of food identification, providing valuable insights for users, food experts as well as food industry. Its high potential is to power detection and classification of food items provide benefits in upholding better eating habits, cooking improvement, and enhancing food creation and management procedures. This research proposed Food Image Classification Using Black Widow Algorithm and Deep Learning (FIC-BWODL) model. The developed FIC-BWODL method combines a multifaceted model starting with Contrast Limited Adaptive Histogram Equalization (CLAHE) for image preprocessing, certifying improved image quality and optimum feature extraction. Extraction of features executed by utilizing Capsule Networks (CapsNet) which is famous for their capability to capture difficult classified image patterns. Classification performed via Convolutional Autoencoders (CAE), exactly classifying food images. Moreover, model controls Black Widow optimization Algorithm (BWO) for hyperparameter tuning that enhances the act and supports it with exclusive features of a dataset. FIC-BWODL methodology provides an important leap in food image detection that provides a strong and exact solution for automated food detection.

关键词： Deep learning Image quality Adaptation models visualization Quality control Feature extraction Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Audio-Visual Speech Enhancement via Attention-based Sparse Graph Convolutional Neural Networks with Fire Hawk optimization

Enhanced Audio-Visual Speech Enhancement via Attention-based...

引用

Automation, Computing and Renewable Systems (ICACRS), International conference on

作者： Dheeraj Hebri Rakesh Kumar Joon Mohan M P S Ramapraba Venkata Satish Dhulipudi Jonnadula Narasimharao Department of Master of Computer Applications Srinivas Institute of Technology Mangalore Karnataka India Department of Electronics and Communication Engineering Ganga Institute of Technology and Management Haryana India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Panimalar Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering BVC Institute of Technology and Science Andhra Pradesh India Department of Computer Science and Engineering CMR Technical Campus Hyderabad Telangana India

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

Audio-Visual Speech Enhancement (AVSE) has the vision to enhance speech quality and requite intelligibility by using both audio and video inputs, which is quite useful in noisy conditions. This approach acknowledges the fact that modalities such as lip movement may be equally informative of the auditory signals as the actual sound in cases where audio signals are distorted. In this research, an innovation approach to the AVSE is presented, which involves several state-of-the-art techniques. The data preprocessing step uses Z-score Min-Max Normalization to normalize the input data to help enhance the feature extraction process. Differentiable adaptive short-time Fourier transform (DA-STFT) is employed as the method of audio feature extraction that provides key temporal information. In the feature extraction process, a local directional structural pattern (LDSP) is utilized for the extraction of visual features since it examines the moving patterns on the face effectively. The fusion of data is done using a quadruplet depth-wise separable fusion convolutional neural network (QDSFCNN), which enhances the amalgamation of the audio and visual cues. Classification is done using an attention-based sparse graph convolutional neural network, known as ASGCNN, since the focus is on the relevant stipulations. Finally, to achieve the highest performance level, the fire hawk optimizer (FHO) is used for tuning parameters in the presented model. This combined approach presents advanced developments in AVSE, which provide improved speech quality in difficult conditions.

关键词： visualization Technological innovation Lips Speech enhancement Feature extraction Convolutional neural networks Noise measurement Synchronization Tuning Streams

来源：评论

学校读者我要写书评

暂无评论

Sports Event Detection Using a 3D Convolutional Neural Network with Equiangular Basis Vector in Video Processing

Sports Event Detection Using a 3D Convolutional Neural Netwo...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International conference on

作者： M. Ashok Kumar Laith H. Jasim Sudhakar K R. Archana Reddy N. Naga Saranya Department of Computer Science Software Engineering and Cyber Security Skyline University Nigeria Kano State Nigeria Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Dept. of AI & DS Nitte Meenakshi Institute of Technology Bengaluru India School of Computer Science and Engineering SR University Warangal India Department of Computer Applications Saveetha College of Liberal Arts & Science SIMATS Chennai India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

As sports video collections continue to expand at a rapid pace, there is a need for advanced classification methods that can accurately and efficiently categorize and manage the massive amount of content available. These methods must be able to dynamically adapt to changes in the collection, ensuring that the videos are properly organized and easily searchable for users. Traditional classification methods are not able to keep up with the rapid growth and complexity of sports video collections, leading to incomplete classification and impacting search and retrieval processes. This paper addresses this challenge using the UCF sports dataset and proposes a Visual Geometry Group-19 (VGG-19) based CNN classifier and Equiangular Basis Vector (EBV) representation introduced for efficient classification and category representation. Furthermore, a 3D Convolutional Neural Network (3D-CNN) architecture extracts both spatial and temporal features from videos for accurate action classification. The Adam optimizer in the optimization algorithm is employed to optimize the learning process. This paper shows that the proposed 3D-CNN model outperforms existing methods a Hybrid Convolutional Neural Network with a Bidirectional Recurrent Neural Network (HCNN-BiRNN) model, Deformable Convolution Networks (DCN), 2D-Convolutional Neural Network (2D-CNN), Convolutional Neural Network - Long Short-Term Frequency (CNN-LSTM) in terms of accuracy (99.45%), precision (98.00%), sensitivity (96.98%), and F1-score (97.05%).

关键词： Geometry Deformable models visualization Three-dimensional displays Sensitivity Event detection Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Comparison of handwriting curve reconstruction using whale optimization algorithm and least square approximation

引用

AIP conference Proceedings 2019年第1期2184卷

作者： Nur Awanis Helmee Zainor Ridzuan Yahya Institute of Engineering Mathematics Universiti Malaysia Perlis Kampus Pauh Putra 02600 Arau Perlis Malaysia

Curve representation is widely used in reverse engineering to reconstruct the curves. This paper discusses the comparison on using two different approaches of curve fitting, namely Whale optimization Algorithm (WOA) and Least Square Approximation for curve reconstruction. The WOA is a novel nature-inspired meta-heuristic algorithm in solving optimization problem. Both techniques are used in the curve fitting process to find the optimal value for the control points of the cubic Bézier curve. Sum Square Error (SSE) is used to determine the difference in distance of the original curve with the reconstructed curve. Then, SSE of the two techniques is compared. visualization and numerical comparison are then obtained.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Virtual visualization Technology of Flight Simulation

引用

IOP conference Series: Materials Science and Engineering 2018年第4期452卷

作者： Peigang Jiao Lei Wang Office of Academic Research Shandong Jiaotong University Jinan Shandong Province 250357 China School of Mechanical Engineering Shandong Jiaotong University Jinan Shandong Province 250357 China

This paper describes various common modeling techniques and optimization methods in visual flight simulation. A large area of terrain, airplane and instrument are modeled visually using modeling tools Creator. The models are optimized using the LOD (Levels of Detail), DOF (Degree of Freedom), Fst and bounding volume techniques. In the design of the visual virtual environment, the environmental sounds are joined in order to enhance the realism of virtual environment. Through visual programming LynX and code writing, the real-time dynamic interactive driving of the instrument in the cockpit has been realized, and the prototype of the flight simulation visualization system has been realized.

关键词：

来源：评论

学校读者我要写书评

暂无评论

optimization techniques for business intelligence reports

引用

AIP conference Proceedings 2021年第1期2333卷 070010页

作者： V. Naneva K. Stefanova Faculty of Mathematics and Informatics Plovdiv University “Paisii Hilendarski” 236 Bulgaria Blvd. 4027 Plovdiv Bulgaria

Data analysis, processing and visualization determine the main features of Business Intelligence (BI). BI technologies track and present a large amount of structured and unstructured information in relational tables. They create complex visual reports using customized tools and calculations. The end user of the visual pays attention not only to the included slicers, charts and tables in the dashboard, but also to the speed of the query by which the current dataset is processed. The last factor is crucial to the performance of such interactive data visualizations. In this paper we will consider different techniques for optimization of data reports which can derive to fast and meaningful representation of data. Also, some useful practices will be suggested which cover important aspects such as model structuring, relationship management and syntax complexity.

关键词：

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：