電腦學刊 Pub Date : 2023-06-01 DOI: 10.53106/199115992023063403027

Dian Zhang Dian Zhang, Yi-Qun Wang Dian Zhang, Wen-bai Chen Yi-Qun Wang

{"title":"Prediction and Early Warning Methods for Agricultural Commodity Price Based on SSA-LSTM","authors":"Dian Zhang Dian Zhang, Yi-Qun Wang Dian Zhang, Wen-bai Chen Yi-Qun Wang","doi":"10.53106/199115992023063403027","DOIUrl":"https://doi.org/10.53106/199115992023063403027","url":null,"abstract":"\u0000 China is a large agricultural country. Fluctuations in the prices of agricultural products can have a significant impact on the income of farmers. It is also a barometer of the agricultural market. Accurate and effective price forecasting of agricultural products plays an important role in strengthening agricultural informatization. Therefore, it is important to explore the characteristics and laws of agricultural price fluctuations to stabilize agricultural market prices and protect farmers’ incomes. This paper takes the price of pork among agricultural products as an example. This paper summarises several key factors that influence pork price fluctuations. Ultimately, this paper uses three pig prices, namely Outer Ternary, Inner Ter-nary and Black pig, and two feed ingredient prices, namely soybean meal, and maize, for a total of five indicators to forecast pork prices. This study uses the Sparrow Search Algorithm (SSA) to optimize the Long Short-Term Memory (LSTM) hyperparameters to enhance the forecasting capability of the LSTM. An early warning mechanism for pork prices was established to warn of pork price fluctuations. The experimental results verified the prediction accuracy of the proposed model and the effectiveness of the early warning mechanism. \u0000","PeriodicalId":345067,"journal":{"name":"電腦學刊","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114631024","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

EEG Emotion Recognition Method Based on 3D Feature Map and Improved DenseNet 基于三维特征图和改进DenseNet的脑电情绪识别方法

電腦學刊 Pub Date : 2023-06-01 DOI: 10.53106/199115992023063403008

Jing-Ran Su Jing-Ran Su, Qiu-Sheng Li Jing-Ran Su, Qian-Li Zhang Qiu-Sheng Li, Jun-Yong Hu Qian-Li Zhang

{"title":"EEG Emotion Recognition Method Based on 3D Feature Map and Improved DenseNet","authors":"Jing-Ran Su Jing-Ran Su, Qiu-Sheng Li Jing-Ran Su, Qian-Li Zhang Qiu-Sheng Li, Jun-Yong Hu Qian-Li Zhang","doi":"10.53106/199115992023063403008","DOIUrl":"https://doi.org/10.53106/199115992023063403008","url":null,"abstract":"\u0000 Emotion, as a high-level function of the human brain, has a great impact on people’s mental health. To fully con-sider EEG signals’ spatial information and time-frequency information, and realize human-computer interaction better. This paper proposes an improved DenseNet emotion recognition model based on 3D feature map. By extracting the differential entropy features of the θ, α, β and γ frequency bands of the EEG signals, and combining the position mapping relationship of the EEG channel electrodes, a three-dimensional feature map is constructed, and then the improved densely connected convolutional network (DenseNet) is used for secondary feature extraction and classification. To verify the effectiveness of this method, a classification experiment including positive, neutral and negative emotions is carried out on the SEED data set. The classification accuracy rates obtained in the single-subject experiment and the all-subject experiment are 98.51% and 98.68%, respectively. The experimental results show that the method of 3D feature map combined with feature reuse can get high-precision classification results, which provides a new direction for emotion recognition.\u0000 \u0000","PeriodicalId":345067,"journal":{"name":"電腦學刊","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130577085","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

Computer Vision Recognition Method for Surface Defects of Casting Workpieces 铸造工件表面缺陷的计算机视觉识别方法

電腦學刊 Pub Date : 2023-06-01 DOI: 10.53106/199115992023063403022

Xiaoning Bo Xiaoning Bo, Jin Wang Xiaoning Bo, Qingfang Liu Jin Wang, Peng Yang Qingfang Liu, Honglan Li Peng Yang

引用次数: 0

Artificial Intelligence Assisted Intelligent Adjustment Method for Urban Rail Transit Train Operation 人工智能辅助的城市轨道交通列车运行智能调节方法

電腦學刊 Pub Date : 2023-06-01 DOI: 10.53106/199115992023063403020

Fei An Fei An, Xiu-Juan Chang Fei An, Ya-Ping Liu Xiu-Juan Chang, Bin He Ya-Ping Liu, Dong-Mei Guo Bin He, Yan-Xiang Yao Dong-Mei Guo, Ze Chang Yan-Xiang Yao

引用次数: 0

An Efficient and Reliable Blockchain-based Trust Management Model for Electricity Trading Terminal 基于区块链的高效可靠电力交易终端信任管理模型

電腦學刊 Pub Date : 2023-06-01 DOI: 10.53106/199115992023063403018

Zhenzhen Liu Zhenzhen Liu, Rui Zhou Zhenzhen Liu, Kangqian Huang Rui Zhou, Xin Hu Kangqian Huang, Kaiyang Deng Xin Hu, Binsi Cai Kaiyang Deng, Kaiguo Yuan Binsi Cai

{"title":"An Efficient and Reliable Blockchain-based Trust Management Model for Electricity Trading Terminal","authors":"Zhenzhen Liu Zhenzhen Liu, Rui Zhou Zhenzhen Liu, Kangqian Huang Rui Zhou, Xin Hu Kangqian Huang, Kaiyang Deng Xin Hu, Binsi Cai Kaiyang Deng, Kaiguo Yuan Binsi Cai","doi":"10.53106/199115992023063403018","DOIUrl":"https://doi.org/10.53106/199115992023063403018","url":null,"abstract":"\u0000 A safe and reliable terminal environment is crucial to ensure the security of the electricity trading system. The existing terminal security system based on identity authentication and access control has internal threats that are difficult to solve. For example, multiple internal malicious nodes cause broadcast message tampering attacks and malicious packet loss, resulting in message dissemination failure. Existing blockchain-based trust management systems are good for addressing insider threats, but suffer from low efficiency. In order to solve the internal threat problem of the electric electricity trading system, from the perspective of trust evaluation and trust management of the terminal environment, an efficient and reliable blockchain-based electric trading terminal (ERBTM) trust management model is proposed. First of all, we collect a variety of trust factors to evaluate the credibility of the terminal, which solves the problem of accuracy in the process of trust assessment; secondly, we improve the speed of storing trust values on the chain and ensure the robustness of the system by improving the consensus algorithm; Finally, we designed the structure of the block that stores the trust value to ensure that the trust value is not tampered with. The experimental results show that, compared with similar methods, the ERBTM model can effectively deal with the endogenous security threats of terminals in the electricity trading environment, and has significant advantages in terms of efficiency and reliability. \u0000 \u0000","PeriodicalId":345067,"journal":{"name":"電腦學刊","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128387980","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

The Prediction of Apple Pests Based on CEEMD-GWO-GRU 基于CEEMD-GWO-GRU的苹果害虫预测

電腦學刊 Pub Date : 2023-06-01 DOI: 10.53106/199115992023063403028

Bo-Wen Lv Bo-Wen Lv, Wen-Bai Chen Bo-Wen Lv, Yi-Qun Wang Wen-Bai Chen

引用次数: 0

Research on Intelligent Assembly Strategy and Workpiece Grasping Method for Industrial Robots Based on Deep Learning 基于深度学习的工业机器人智能装配策略及工件抓取方法研究

電腦學刊 Pub Date : 2023-06-01 DOI: 10.53106/199115992023063403023

Jie Yu Jie Yu, Xi-Lin Li Jie Yu, Cai-Wen Niu Xi-Lin Li, Yu-Xin Zhang Cai-Wen Niu, Shu-Hui Xu Yu-Xin Zhang

引用次数: 0

Surface Defect Recognition of Wind Turbine Blades Based on Improved YOLOX-X Model 基于改进YOLOX-X模型的风电叶片表面缺陷识别

電腦學刊 Pub Date : 2023-04-01 DOI: 10.53106/199115992023043402002

Changhao Dong Changhao Dong, Chao Zhang Changhao Dong, Jianjun Li Chao Zhang, Jiaxue Liu Jianjun Li

引用次数: 0

A Real-Time Monitoring and Diagnosis Method of Production Line Conveyor Chain for Digital Twin 数字孪生生产线输送链实时监测与诊断方法

電腦學刊 Pub Date : 2023-04-01 DOI: 10.53106/199115992023043402014

Bo Liu Bo Liu, Ying-Ming Shi Bo Liu

引用次数: 0

Research on Rip Currents Detection Method Based on Improved YOLOv5s 基于改进YOLOv5s的离岸流检测方法研究

電腦學刊 Pub Date : 2023-04-01 DOI: 10.53106/199115992023043402009

Rui Qi Rui Qi, Dao-Heng Zhu Rui Qi, Xue Qin Dao-Heng Zhu

{"title":"Research on Rip Currents Detection Method Based on Improved YOLOv5s","authors":"Rui Qi Rui Qi, Dao-Heng Zhu Rui Qi, Xue Qin Dao-Heng Zhu","doi":"10.53106/199115992023043402009","DOIUrl":"https://doi.org/10.53106/199115992023043402009","url":null,"abstract":"\u0000 Rip currents are common natural disaster and widely distributed on beaches around the world, which can quickly bring swimmers into deep water and cause safety accidents. Rip currents are generally sudden and insidious, making it difficult for inexperienced beach managers and tourists to identify them, and presenting a high risk to swimmers. Deep learning is a popular technology in the field of computer vision, but its applications in rip currents recognition are rare, and it is difficult to realize real-time detection of rip currents. In response to the above problems, we propose an improved YOLOv5s rip currents identification method. Firstly, a joint dilated convolution module is designed to expand the receptive field, which not only improves the utilization of feature information, but also effectively reduces the amount of parameters. Then, a parameter-free attention mechanism module is added, which does not increase the complexity of the model and can improve the detection accuracy at the same time. Finally, the Neck area of the original YOLOv5s model is simplified, the 80x80 feature map branch suitable for detecting small targets is deleted, and the overall complexity of the model is reduced by reducing the amount of parameters to improve the real-time detection. We have conducted multiple sets of experiments on public data set. The results show that compared with the original YOLOv5s model, the mAP of the improved model for identifying rip currents on the same data sets has increased by 4%, reaching 92.15%, and the frame rate has increased 2.18 frames per second, and the model size is only increased by 0.45 MB. Compared with several mainstream models, the improved model not only has a simplified structure but also significantly improves the detection accuracy, indicating that our model has the accuracy and efficiency in detecting rip currents, and can provide an effective way for embedded devices to perform accurate target detection.\u0000 \u0000","PeriodicalId":345067,"journal":{"name":"電腦學刊","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122436142","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

電腦學刊最新文献