检索结果-内蒙古大学图书馆

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Yuvaneswaren, R.S. Prakash, S Tarun Sudha, K. Computer Science and Engineering St.Joseph's College of Engineering Chennai India

ISBN: (纸本)9798350372120

Corrosion, the ongoing degradation of materials caused by chemical reactions with their surroundings, poses a continuous and expensive obstacle across various industrial domains. From bridges and pipelines to machinery and storage tanks, corrosion poses a substantial threat to infrastructure integrity, safety, and longevity. timely detection and precise localization of corrosion areas are vital for proactive maintenance, reducing downtime, and ensuring the longevity of critical assets. Traditionally, corrosion inspection has relied heavily on manual, time-intensive methods, which are often limited in accuracy and efficiency. However, the advent of deep learning, a subfield of artificial intelligence, has revolutionized the domain of image analysis, offering unparalleled potential for automated and precise corrosion *** project undertakes a transformative journey in leveraging the capabilities of deep learning, particularly focusing on computer vision, to achieve precise and efficient corrosion segmentation in industrial imagery. The primary objective is to employ cutting-edge deep learning models, with a specific emphasis on the YOLOv8 architecture, to create a robust solution capable of accurately identifying and outlining corrosion regions within intricate industrial scenes. Furthermore, the project explores the potential of utilizing cloud-based virtual machines, specifically the WandB Cloud offering, as a cost-effective alternative to conventional solutions such as Azure for model deployment and monitoring. Noteworthy attributes of YOLOv8 include its distinctive single-pass detection methodology, where the entire video frame undergoes processing in a single forward pass through the neural network, eliminating the need for intricate post-processing and enhancing detection speed. © 2024 IEEE.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Speech Enhancement Using Optimal Transport and Speech Presence Probability

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE processing 2024年 32卷 4445-4455页

作者： Jiang, Wenbin Yu, Kai Wen, Fei Hangzhou Dianzi Univ Sch Commun Engn Hangzhou 310018 Peoples R China Shanghai Jiao Tong Univ Dept Comp Sci & Engn X LANCE Lab Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Dept Elect Engn Shanghai 200240 Peoples R China

Speech enhancement models based on deep learning are typically trained in a supervised manner, requiring a substantial amount of paired noisy-to-clean speech data for training. However, synthetically generated training data can only capture a limited range of realistic environments, and it is often challenging or even impractical to gather real-world pairs of noisy and ground-truth clean speech. To overcome this limitation, we propose an unsupervised learning approach for speech enhancement that eliminates the need for paired noisy-to-clean training data. Specifically, our method utilizes the optimal transport criterion to train the speech enhancement model in an unsupervised manner. It employs a fidelity loss based on noisy speech and a distribution divergence loss to minimize the difference between the distribution of the model's output and that of unpaired clean speech. Further, we use the speech presence probability as an additional optimization objective and incorporate the short-time Fourier transform (STFT) domain loss as an extra term for the unsupervised learning loss. We also apply the multi-resolution STFT loss as the validation loss to enhance the stability of the training process and improve the algorithm's performance. Experimental results on the VCTK + DEMAND benchmark demonstrate that the proposed method achieves competitive performance compared to the supervised methods. Furthermore, the speech recognition results on the CHiME4 benchmark show the superiority of the proposed method over its supervised counterpart.

关键词： Speech enhancement unsupervised learning optimal transport generative adversarial networks speech presence probability unsupervised learning optimal transport generative adversarial networks speech presence probability

来源：评论

学校读者我要写书评

暂无评论

deep learning-Based real-time Face Mask Detection for Human Using Novel YOLOv2 with Higher Accuracy 5th

Deep Learning-Based Real-Time Face Mask Detection for Human ...

引用

5th International Conference on Computer and Communication Technologies, IC3T 2023

作者： Tun, Nay Kyi Myat, Aye Min Oo, Htet Ne Thu, Amar Myo Win, Kyaw Thu Faculty of Computer System and Technology Myanmar Information Institute of Technology Mandalay Myanmar Pyin Oo Lwin Myanmar Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Electronic Department Defence Services Academy Pyin Oo Lwin Myanmar

ISBN: (纸本)9789819997060

A novel deep learning-based face mask detection system is designed to enhance public safety in various environments. With the ongoing global health concerns, the need for efficient and accurate methods to identify individuals wearing or not wearing face masks has become crucial. By utilizing convolutional neural networks (CNNs) and transfer learning techniques, proposed model achieves impressive accuracy while maintaining high-speed processing capabilities. This paper outlines the architecture, training process, and performance evaluation of the proposed deep learning-based face mask detection system, highlighting its promising role in contributing to a safer and healthier society. The development of a vision-based safety system, the transfer of a small YOLO object detection model, and the creation of a CNN-based classification model are the key objectives of this study. According to experimental findings, proposed system is capable of real-time face mask detection and classification with an accuracy of over 98%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

deep TEMPORAL GRAPH CLUSTERING 12

DEEP TEMPORAL GRAPH CLUSTERING

引用

12th International Conference on learning Representations, ICLR 2024

作者： Liu, Meng Liu, Yue Liang, Ke Tu, Wenxuan Wang, Siwei Zhou, Sihang Liu, Xinwang National University of Defense Technology Changsha China Intelligent Game and Decision Lab Beijing China

deep graph clustering has recently received significant attention due to its ability to enhance the representation learning capabilities of models in unsupervised scenarios. Nevertheless, deep clustering for temporal graphs, which could capture crucial dynamic interaction information, has not been fully explored. It means that in many clustering-oriented real-world scenarios, temporal graphs can only be processed as static graphs. This not only causes the loss of dynamic information but also triggers huge computational consumption. To solve the problem, we propose a general framework for deep Temporal Graph Clustering called TGC, which introduces deep clustering techniques to suit the interaction sequence-based batch-processing pattern of temporal graphs. In addition, we discuss differences between temporal graph clustering and static graph clustering from several levels. To verify the superiority of the proposed framework TGC, we conduct extensive experiments. The experimental results show that temporal graph clustering enables more flexibility in finding a balance between time and space requirements, and our framework can effectively improve the performance of existing temporal graph learning methods. The code is released: https://***/MGitHubL/deep-Temporal-Graph-Clustering. © 2024 12th International Conference on learning Representations, ICLR 2024. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Multi-label dental disorder diagnosis based on MobileNetV2 and swin transformer using bagging ensemble classifier

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-23页

作者： Alsakar, Yasmin M. Elazab, Naira Nader, Nermeen Mohamed, Waleed Ezzat, Mohamed Elmogy, Mohammed Mansoura Univ Fac Comp & Informat Informat Technol Dept Mansoura 35516 Dakahlia Egypt Mansoura Univ Fac Comp & Informat Comp Sci Dept Mansoura 35516 Dakahlia Egypt Minist Hlth & Populat Directorate Hlth Dakahilia Cairo Egypt

Dental disorders are common worldwide, causing pain or infections and limiting mouth opening, so dental conditions impact productivity, work capability, and quality of life. Manual detection and classification of oral diseases is time-consuming and requires dentists' evaluation and examination. The dental disease detection and classification system based on machine learning and deep learning will aid in early dental disease diagnosis. Hence, this paper proposes a new diagnosis system for dental diseases using X-ray imaging. The framework includes a robust pre-processing phase that uses image normalization and adaptive histogram equalization to improve image quality and reduce variation. A dual-stream approach is used for feature extraction, utilizing the advantages of Swin Transformer for capturing long-range dependencies and global context and MobileNetV2 for effective local feature extraction. A thorough representation of dental anomalies is produced by fusing the extracted features. To obtain reliable and broadly applicable classification results, a bagging ensemble classifier is utilized in the end. We evaluate our model on a benchmark dental radiography dataset. The experimental results and comparisons show the superiority of the proposed system with 95.7% for precision, 95.4% for sensitivity, 95.7% for specificity, 95.5% for Dice similarity coefficient, and 95.6% for accuracy. The results demonstrate the effectiveness of our hybrid model integrating MoileNetv2 and Swin Transformer architectures, outperforming state-of-the-art techniques in classifying dental diseases using dental panoramic X-ray imaging. This framework presents a promising method for robustly and accurately diagnosing dental diseases automatically, which may help dentists plan treatments and identify dental diseases early on.

关键词： Dentistry MobileNetV2 Swin transformer Annotation deep learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Automated Face Mask Detection Using Ensemble learning Approach 5

An Automated Face Mask Detection Using Ensemble Learning App...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Kumar, B. Kiran Mounika, Guggilam Harish, R.V.S. Nagarjuna, Valeti St. Ann's College of Engineering & Technology Embedded Systems Andhra Pradesh Chirala523187 India St. Ann's College of Engineering & Technology Andhra Pradesh Chirala523187 India Kallam Haranadhareddy Institute of Technology Dept of Cse NH-16 Andhra Pradesh Chowdavaram India

ISBN: (纸本)9798350379945

The COVID-19 pandemic and other infectious diseases are spreading quickly, which has brought attention to how essential face masks are in stopping the spread of respiratory disorders. To ensure compliance with mask-wearing rules, automatic face mask detection devices are becoming increasingly important. The application of Automated Convolutional Neural Networks (ACNN) in conjunction with Internet of Things (IoT) devices for an Automated Face Mask Detection is the main emphasis of this research. The suggested method correctly detects people wearing or not wearing face masks in real-time video and picture data by leveraging ACNN, a deep-learning architecture created for image segmentation. A wide range of labeled photos of people wearing and not wearing masks are used to train the FCNN. The model is ideal for real-world applications in public areas, healthcare facilities, and educational institutions due to its high accuracy and efficiency. real-time monitoring and notifications are made possible by the integration of IoT devices, which improves the operation of the system. In order to collect images and videos data, IoT sensors and cameras are positioned strategically in specific regions. A central processing unit (CPU) that executes the trained FCNN model is connected to these devices. Using email, SMS, or a mobile app, the system instantly notifies the appropriate authorities or persons when it finds someone not donning a face mask. © 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 Progressive Subnetwork Searching Framework for Dynamic Inference

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2024年第3期35卷 3809-3820页

作者： Yang, Li He, Zhezhi Cao, Yu Fan, Deliang Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85287 USA Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China

deep neural network (DNN) model compression is a popular and important optimization method for efficient and fast hardware acceleration. However, the compressed model is usually fixed, without the capability to tune the computing complexity (i.e., latency in hardware) on-the-fly, depending on dynamic latency requirements, workloads, and computing hardware resource allocation. To address this challenge, dynamic DNN with run-time adaption of computing structures has been constructed through training with a cross-entropy objective function consisting of multiple subnets sampled from the supernet. Our investigations in this work show that the performance of dynamic inference highly relies on the quality of subnet sampling. To construct a dynamic DNN with multiple high-quality subnets, we propose a progressive subnetwork searching framework, which is embedded with several proposed new techniques, including trainable noise ranking, channel-group sampling, selective fine-tuning, and subnet filtering. Our proposed framework empowers the target dynamic DNN with higher accuracy for all the subnets compared with prior works on both the Canadian Institute for Advanced Research dataset with 10 classes (CIFAR-10) and imageNet datasets. Specifically, compared with United States-Neural Network (US-NN), our method achieves 0.9% average accuracy gain for Alexnet, 2.5% for ResNet18, 1.1% for Visual Geometry Group (VGG)11, and 0.58% for MobileNetv1, on the imageNet dataset, respectively. Moreover, to demonstrate run-time tuning of computing latency of dynamic DNN in real computing system, we have deployed our constructed dynamic networks into Nvidia Titan graphics processing unit (GPU) and Intel Xeon central processing unit (CPU), showing great improvement over prior works. The code is available at https://***/ASU-ESIC-FAN-Lab/Dynamic-inference.

关键词： Computational modeling Dynamic scheduling Neural networks Hardware Graphics processing units Switches Costs deep neural network (DNN) dynamic inference dynamic network subnet searching

来源：评论

学校读者我要写书评

暂无评论

A data-driven dynamic method of downhole rock characterisation for the vibro-impact drilling system

引用

MECHANICAL SYSTEMS AND SIGNAL processing 2025年 223卷

作者： Afebu, Kenneth Omokhagbo Liu, Yang Papatheou, Evangelos Univ Exeter Engn Dept Exeter Small Scale Robot Lab Exeter EX4 4QF England

For the real-time characterisation of an inhomogeneous impact inhibiting constraint such as downhole rock layers, an unconventional method using machine learning (ML) and drill-bit vibrations is investigated. An impact oscillator with one-sided elastic constraint is employed in modelling the bit-rock impact actions. Measurable drill-bit dynamics, such as acceleration, were acquired and processed into features and 2D-images that were later used in developing ML models capable of predicting the stiffness of impacted rock constraint. Explored ML networks include Multilayer Perceptron (MLP), Convolutional Neural Network and Long Short-Term Memory Network. Both simulation and experimental studies have been presented to validate the proposed method while using coefficient of determination (R-2) and normalised mean absolute error (NMAE) as the performance metrics of the ML models. Results showed that the feature- based models had better performances for both simulation and experiment compared to the raw signal and 2D-image based models. Aside being simple and computationally less expensive, the feature-based MLP models outperformed other models having R-2 values > 0.7 and NMAE values < 0.2 for both simulation and experiment, thus presenting them as the preferred ML model for dynamic downhole rock characterisation. In general, this study presents a new modality to achieving logging-while-drilling during deep-hole drilling operations such as carried out in hydrocarbon, mineral and geothermal exploration.

关键词： Rotary-percussive drilling Rock characterisation Impact oscillator Signal processing Impact durations Artificial networks

来源：评论

学校读者我要写书评

暂无评论

A Multi-Element Identification System Based on deep learning for the Visual Field of Percutaneous Endoscopic Spine Surgery

引用

INDIAN JOURNAL OF ORTHOPAEDICS 2024年第5期58卷 587-597页

作者： Bu, Jinhui Lei, Yan Wang, Yari Zhao, Jiaqi Huang, Sen Liang, Jun Wang, Zhenfei Xu, Long He, Bo Dong, Minghui Liu, Guangpu Niu, Ru Ma, Chao Liu, Guangwang Xuzhou Med Univ Affiliated Xuzhou Clin Coll Xuzhou 221009 Peoples R China China Univ Min & Technol Sch Comp Sci Xuzhou 221116 Peoples R China Southeast Univ Nanjing Med Univ Nanjing Univ Chinese Med Xuzhou Cent HospMed SchXuzhou Sch Clin MedDept Xuzhou 221009 Peoples R China Bengbu Med Coll Bengbu 233000 Peoples R China

BackgroundLumbar disc herniation is a common degenerative lumbar disease with an increasing incidence. Percutaneous endoscopic lumbar discectomy can treat lumbar disc herniation safely and effectively with a minimally invasive procedure. However, the learning curve of this technology is steep, which means that initial learners are often not sufficiently proficient in endoscopic operations, which can easily lead to iatrogenic damage. At present, the application of computer deep learning technology to clinical diagnosis, treatment, and surgical navigation has achieved satisfactory *** objective of our team is to develop a multi-element identification system for the visual field of endoscopic spine surgery using deep learning algorithms and to evaluate the feasibility of this *** established an image database by collecting surgical videos of 48 patients diagnosed with lumbar disc herniation, which was labeled by two spinal surgeons. We selected 6000 images of the visual field of percutaneous endoscopic spine surgery (including various tissue structures and surgical instruments), divided into the training data, validation data, and test data according to 2:1:2. We developed convolutional neural network models based on instance segmentation-Solov2, CondInst, Mask R-CNN and Yolact, and set the four network model backbone as ResNet101 and ResNet50 respectively. Mean average precision (mAP) and frames per second (FPS) were used to measure the performance of each model for classification, localization and recognition in real time, and AP (average) is used to evaluate how easily an element is detected by neural networks based on computer deep *** comparing mAP and FSP of each model for bounding box test and segmentation task for the test set of images, we found that Solov2 (ResNet101) (mAP = 73.5%, FPS = 28.9), Mask R-CNN (ResNet101) (mAP = 72.8%, FPS = 28.5) models are the most stable, with higher precision and faster ima

关键词： Spinal endoscopy Artificial intelligence Lumbar disc herniation deep learning PELD

来源：评论

学校读者我要写书评

暂无评论

Neural Architecture Search Based on a Multi-Objective Evolutionary Algorithm With Probability Stack

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2023年第4期27卷 778-786页

作者： Xue, Yu Chen, Chen Slowik, Adam Nanjing Univ Informat Sci & Technol Sch Software Nanjing 210044 Peoples R China Koszalin Univ Technol Dept Elect & Comp Sci Koszalin PL-75453 Poland

With the emergence of deep neural networks, many research fields, such as image classification, object detection, speech recognition, natural language processing, machine translation, and automatic driving, have made major breakthroughs in technology and the research achievements have been successfully applied in many real-life applications. Combining evolutionary computation and neural architecture search (NAS) is an important approach to improve the performance of deep neural networks. Usually, the related researchers only focus on precision. Thus, the searched neural architectures always perform poorly in the other indexes such as time cost. In this article, a multi-objective evolutionary algorithm with a probability stack (MOEA-PS) is proposed for NAS, which considers the two objects of precision and time consumption. MOEA-PS uses an adjacency list to represent the internal structure of deep neural networks. Besides, a unique mechanism is introduced into the multi-objective genetic algorithm to guide the process of crossover and mutation when generating offspring. Furthermore, the structure blocks are stacked using a proxy model to generate deep neural networks. The results of the experiments on Cifar-10 and Cifar-100 demonstrate that the proposed algorithm has a similar error rate compared with the most advanced NAS algorithms, but the time cost is lower. Finally, the network structure searched on Cifar-10 is transferred directly to the imageNet dataset, which can achieve 73.6% classification accuracy.

关键词： deep learning evolutionary computation multiobjective optimization neural architecture search (NAS)

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：