2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)最新文献_第9页

TSM-MobileNetV3: A Novel Lightweight Network Model for Video Action Recognition tm - mobilenetv3:一种用于视频动作识别的新型轻量级网络模型

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212611

Shuang Zhang, Qing Tong, Zixiang Kong, Han Lin

{"title":"TSM-MobileNetV3: A Novel Lightweight Network Model for Video Action Recognition","authors":"Shuang Zhang, Qing Tong, Zixiang Kong, Han Lin","doi":"10.1109/AINIT59027.2023.10212611","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212611","url":null,"abstract":"The deployment of video action recognition models on mobile and embedded devices is challenging due to the limited computational resources and storage capacity. To address this issue, we propose a novel lightweight network architecture named TSM-MobileNetV3. Based on the Temporal Shift Module (TSM), we replace the backbone network with MobileNetV3, which is flexible and easy to implement. The proposed model is evaluated using the HMDB51 dataset, with detection accuracy, inference speed, and model size as the evaluation metrics. Experimental results demonstrate that TSM-MobileNetV3 achieves a detection accuracy of Top-1-0.70 and Top-5-0.89 with only a 0.02 decrease in accuracy, while achieving a 50.27% improvement in inference speed and a significant reduction in model size compared to other lightweight models. TSM-MobileNetV3 has been successfully deployed on NVIDIA-jetson devices, with reasonable agility and response speed. Our proposed model shows promising performance on mobile and embedded devices, with reduced training and deployment requirements, enabling deployment on edge devices. This study provides new insights and directions for designing and applying lightweight models. The proposed lightweight network model has broad prospects for application in various fields, such as smart homes, intelligent surveillance, and autonomous driving. Our team is currently investigating the deployment of this model on simulation platforms such as Unity for further testing.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122395935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Multi-Factor Subjective-Objective Fusion Weighting-Based Attraction Popularity Index Monitoring System 基于主客观融合权重的多因素景点人气指标监测系统

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212464

Rongli Li, Chong Feng, Li Wang

引用次数: 0

Transfer Learning in Grape Disease Leaf Detection Based on Convolutional Neural Network 基于卷积神经网络的葡萄病害叶片检测中的迁移学习

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212855

Yize Li, Zhe Liu, Yuxin Jiang, Teoh Teik Toe

{"title":"Transfer Learning in Grape Disease Leaf Detection Based on Convolutional Neural Network","authors":"Yize Li, Zhe Liu, Yuxin Jiang, Teoh Teik Toe","doi":"10.1109/AINIT59027.2023.10212855","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212855","url":null,"abstract":"In order to achieve rapid and accurate recognition of grape leaf disease images, this paper introduces a convolutional neural network model based on transfer learning for classifying diseased grape leaves. A new fully connected layer module was designed on the basis of the EfficientNetB0 model, and the convolutional layer of the EfficientNetB0 model, pre-trained on the ImageNet dataset, was transferred into this model. The training image data of thousands of images were obtained from Kaggle, including grape leaves with black rot disease, Esca disease virus, leaf blight disease, and healthy grape leaves. In order to expand the dataset and prevent overfitting, we carried out a series of preprocessing steps on the original dataset and divided the training and test sets in a 4:1 ratio. The test accuracy of our model reached 99.14% and the average F1-score reached 98.79%. This paper also compared the classification results of different model structures such as VGG-16 and RESNet50. Their test accuracy values are 96.29% and 97.06% respectively. To quantitatively evaluate the performance of the model, the accuracy, precision, recall and F1-socre of the model are calculated.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"388 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126740884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CATrack: Combining Convolutional and Attentional Methods for Visual Object Tracking CATrack:结合卷积和注意方法的视觉目标跟踪

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212501

Qingyang Lu, Hong Zhu, Guangling Yuan, Congli Li, Xiaoyan Qin

引用次数: 0

Change Point Detection Of Multi-functional Radar Work Mode Based On Window-sliding Algorithm 基于窗口滑动算法的多功能雷达工作模式变化点检测

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212583

Zhi Tang, Xueqiong Li, Xucan Chen

引用次数: 0

An Improved YOLOv7 Algorithm for Solder Defect Detection of Lithium Battery 锂电池焊料缺陷检测的改进YOLOv7算法

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212659

Yatao Yang, Junqing Li, Yunhao Zhou, Li Zhang

{"title":"An Improved YOLOv7 Algorithm for Solder Defect Detection of Lithium Battery","authors":"Yatao Yang, Junqing Li, Yunhao Zhou, Li Zhang","doi":"10.1109/AINIT59027.2023.10212659","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212659","url":null,"abstract":"The structural integrity of welded poles in power lithium batteries is closely related to the driving safety of the electric vehicles. Aiming at the problem of missed detection resulted from minor defects such as small coverage area and low pixel during the process of laser welding of traditional-pole for lithium battery, an improved YOLOv7 welding defect detection algorithm is proposed in this paper. First, an efficient channel attention mechanism C3SE module is introduced to improve the model's ability of extracting deep important features. Then, the improved BiFPN structure replaces PANet to improve the model's efficiency of feature utilization and the ability to express multi-scale targets. Finally, the MP structure uses the separate-merge operation and cascades the SE module in the subsequent convolutional layers to avoid losing the fine granularity of features. The experimental results show that the mAP of the improved algorithm for detecting defects reaches 96.4%, which is 1.2% higher than the original algorithm. Our work can provide important reference for similar tasks of welding defects detection using target detection scheme.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128251708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

YOLOv5s-Transformer: Improved YOLOv5 Network for Real-Time Detection of Cigarette Smoking Based on Image processing YOLOv5 - transformer:改进的基于图像处理的YOLOv5网络吸烟实时检测

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212761

Zhiyi Zhao, Yuxuan Zhao

引用次数: 0

Research on Knowledge Recommendation Technology Based on Domain Knowledge Graph: A Case Study in Aerospace Engine Domain 基于领域知识图的知识推荐技术研究——以航空发动机领域为例

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212707

Feifan Deng, Qingjie Hu, Bin Meng, Hong Zhang

引用次数: 0

Early Screening and Prediction of Alzheimer's Disease Based on Long-Term and Short-Term Memory Neural Networks 基于长期和短期记忆神经网络的阿尔茨海默病早期筛查和预测

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212782

Junhao Liang, Fengsen Dong, Hui Qi, Ying Chen, Guohua Qin, Weiwei Li

{"title":"Early Screening and Prediction of Alzheimer's Disease Based on Long-Term and Short-Term Memory Neural Networks","authors":"Junhao Liang, Fengsen Dong, Hui Qi, Ying Chen, Guohua Qin, Weiwei Li","doi":"10.1109/AINIT59027.2023.10212782","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212782","url":null,"abstract":"With the increase of the proportion of aging Chinese population, the incidence rate has increased in recent years. Because the disease has a latent onset, the course of the disease is slow and irreversible, and early screening and diagnosis of Alzheimer's disease is particularly important. With the development of computer computing power, the exploration of the field of deep learning has gradually unfolded. Because the long short-term memory neural network has a memory unit, it can capture the long-term dependence of time series data and record historical information, which has obvious advantages in disease prediction. LSTM neural networks have obvious advantages in memory, processing lagging data, preventing gradient disappearance, and learning ability, which makes them very suitable for predicting time series data and complex problems such as Alzheimer's disease. This can provide theoretical and technical support for related research, and help improve the accuracy and wide acceptance of predictions. In this paper, the NMR image information data is used to predict the population of patients without Alzheimer's disease (NC) or mild serious disorder (MCI) through the long-short-term memory neural network model, and the probability of disease in the next 3–5 years is obtained, which is also an effective attempt of long-short-term memory neural network in medical prediction.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133553636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on Human-computer Cooperation Accompanying Capability Based on Customer Service System 基于客户服务系统的人机协同陪伴能力研究

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212921

Hualin Huang, Shaojie Wang, Yong Wang, Xiang Yin, Shuang Li, Mengmeng Hu, Yingsheng Zhang, Shuqing Hu

{"title":"Research on Human-computer Cooperation Accompanying Capability Based on Customer Service System","authors":"Hualin Huang, Shaojie Wang, Yong Wang, Xiang Yin, Shuang Li, Mengmeng Hu, Yingsheng Zhang, Shuqing Hu","doi":"10.1109/AINIT59027.2023.10212921","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212921","url":null,"abstract":"In recent years, the demographic dividend has gradually disappeared and the growth rate of the customer service's business development has slowed down. Enterprise is more focused on the improvement of service quality. However, at present, there are some common problems in the service process of agents, such as lack of solving ability, inconvenient use of tools, lack of human-computer cooperation and so on. This paper further improves the man-machine cooperation accompanying ability of intelligent tools by studying the accompanying technology of tools and interactive question and answer technology. Based on the interactive contents such as agent operation, voice and IM, the assistant tools are displayed in real time to improve the service quality of agents. At the same time, We intensive study the language features, semantic recognition of agent natural language input, to achieve intelligent matching of agent questions and answers, and timely recommend relevant questions to agents to improve agent search efficiency and customer service satisfaction.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133372860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0