2021 7th International Conference on Computing and Artificial Intelligence最新文献_第5页

An IoT Based Intruder and Smoke Monitoring System 基于物联网的入侵者和烟雾监测系统

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467778

Vipa Thananant, Chumpol Mokarat

{"title":"An IoT Based Intruder and Smoke Monitoring System","authors":"Vipa Thananant, Chumpol Mokarat","doi":"10.1145/3467707.3467778","DOIUrl":"https://doi.org/10.1145/3467707.3467778","url":null,"abstract":"Burglar and fire are the two dangerous life events. An IoT based intruder and smoke monitoring system is proposed to protect us from these events. The proposed system is a low cost and energy efficient alternative to the existing systems. It is an integrated system that can detect and monitor theft and fire. The system consists of hardware and software parts. The hardware parts have two separated subsystems, smoke and intruder subsystem. The smoke subsystem uses an ESP8266 Arduino board with a smoke sensor (MQ2) and a buzzer. The intruder subsystem uses an ESPIno32CAM board with an ultrasonic sensor (HC-SR04). The software parts consist of three applications that are web, android, and LINE application. Both subsystems share the same web, android, and LINE application. When a smoke is detected by the sensor, the alarm sounds. The smoke subsystem sends a notification to the web and LINE application and the gas concentration level is sent to MySQL database. When an intruder is detected by the sensor, the intruder subsystem captures his photo and sends it to the LINE application for notification. The system also has the ability to recognize faces so that when a homeowner is detected by the sensor, no notifications are displayed in LINE and web application. Web application shows an alert message when there is an intruder and a smoke. It also shows a graph of gas level values. Android application can turn on and off the device in the system.","PeriodicalId":145582,"journal":{"name":"2021 7th International Conference on Computing and Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133762232","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 Metaheuristic Approach for Hub Location Problem with Multiple Functions 多函数枢纽定位问题的元启发式方法

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467761

B. Du, Xia Chen, Shengnan Wu, Yu Wang, Jianwei Lin, Liang Yan

引用次数: 0

Design of ROS Automatic Search Robot based on Voice Interaction and Object Recognition 基于语音交互和目标识别的ROS自动搜索机器人设计

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467731

Yanni Zhao, Huaizhong Zhu, Yan He

引用次数: 0

Research on Apple Variety Classification Based on the Combination of Hyperspectral and Deep Learning 基于高光谱与深度学习相结合的苹果品种分类研究

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467716

Lei Geng, Yalong Huang, Wen Wang, Ye Song, Nu-lee Song, Heng Zhao, Quan Guo

{"title":"Research on Apple Variety Classification Based on the Combination of Hyperspectral and Deep Learning","authors":"Lei Geng, Yalong Huang, Wen Wang, Ye Song, Nu-lee Song, Heng Zhao, Quan Guo","doi":"10.1145/3467707.3467716","DOIUrl":"https://doi.org/10.1145/3467707.3467716","url":null,"abstract":"At present, the classification of apple varieties is mainly manual sorting. Due to the small differences between some apple types, manual discrimination has the problems of strong subjectivity, low efficiency and high cost. Therefore, in order to realize the real-time detection of apple varieties sold by merchants, the spectral data of different apple varieties were collected by the hyperspectral image acquisition system, and an automatic apple recognition model based on double-branch structure was proposed. One of the branches is the basic TCN network to extract the morphological information of the signal. The other branch is an enhancement module composed of two long and short-term memory networks (LSTM) to capture the timing characteristics of the signal. Then, the apple spectrum data under the feature band is input into the two branches at the same time, and the features from the two branches are merged using vector splicing, and finally the soft-max classifier is applied to output the network classification results. The experimental results show that the overall classification accuracy of seven kinds of apples reached 99.74%.","PeriodicalId":145582,"journal":{"name":"2021 7th International Conference on Computing and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134287894","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: 1

Adaptive Temporal High-pass Infrared Non-uniformity Correction Algorithm Based on Guided Filter 基于制导滤波的自适应时域高通红外非均匀性校正算法

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467776

Y. I. Zhang, Xuwen Li, Xin Zheng, Qiang Wu

{"title":"Adaptive Temporal High-pass Infrared Non-uniformity Correction Algorithm Based on Guided Filter","authors":"Y. I. Zhang, Xuwen Li, Xin Zheng, Qiang Wu","doi":"10.1145/3467707.3467776","DOIUrl":"https://doi.org/10.1145/3467707.3467776","url":null,"abstract":"In the scene-based infrared focal plane non-uniformity correction algorithm, the temporal high-pass filter non-uniformity correction algorithm is widely cited in various system platforms due to its low hardware platform requirements, but this algorithm is prone to \"ghosting\" problems and the corrected image still contains certain non-uniformity problems. To solve these problems, this paper proposes an adaptive temporal high-pass filter algorithm based on guided filter. The algorithm uses guided filter to accurately separate high-frequency components containing a large amount of fixed noise and image details, and performs image motion through adjacent frame residual images detection to determine whether to use high-frequency components for iterative operations in the temporal high-pass algorithm, and use the current image detail information to adaptively update the correction parameters of the temporal high-pass filter to avoid the accumulation of image detail information to complete the entire infrared non-uniformity correction . The algorithm in this paper uses actual infrared scene images to compare with the traditional temporal high-pass filter algorithm and bilateral filtering temporal high-pass algorithm. The results show that the algorithm proposed in this paper not only has a good correction effect, but also effectively suppresses the \"ghosting\" problem.","PeriodicalId":145582,"journal":{"name":"2021 7th International Conference on Computing and Artificial Intelligence","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130914841","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: 1

Attribute Reduction Method Using Adaptive Genetic Algorithm and Particle Swarm Optimization 基于自适应遗传算法和粒子群优化的属性约简方法

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467749

Shangzhi Wu, Fan Zhang, Xuwen Wang, Ning Xia

引用次数: 1

Real Time Controllable Multi Channel HD Digital Video Processing System Based on FPGA and MicroBlaze 基于FPGA和MicroBlaze的实时可控多通道高清数字视频处理系统

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467734

Lei Sun, Enchang Sun, Yaping Yu

{"title":"Real Time Controllable Multi Channel HD Digital Video Processing System Based on FPGA and MicroBlaze","authors":"Lei Sun, Enchang Sun, Yaping Yu","doi":"10.1145/3467707.3467734","DOIUrl":"https://doi.org/10.1145/3467707.3467734","url":null,"abstract":"In order to realize the real-time processing and display control of multi-channel high-definition digital video, this paper proposes an embedded solution for real-time processing of multi-channel high-definition digital video based on FPGA (Field Programmable Gate Array). The overall system design includes three parts: hardware platform design with MicroBlaze as the core controller, software application design and OSD (On Screen Display) display control design. The system proposed in this paper implements the encoding, decoding, scaling and overlay of multiple high-definition video streams in a single FPGA embedded with MicroBlaze, which improves the system integration. Through the design of the OSD control layered architecture, the information interaction between the keystrokes and the OSD image interface is realized, and four video display parameters can be configured on the screen. Experiments show that the system proposed in this paper can process and display four high-definition video streams in real time, with an output frame rate of 60 frames/s. Compared with the current mainstream video fusion system solutions, the system integration level has been improved.","PeriodicalId":145582,"journal":{"name":"2021 7th International Conference on Computing and Artificial Intelligence","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129910398","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: 1

SE-MIDNet Based on Deep Learning for Diabetic Retinopathy Classification 基于SE-MIDNet深度学习的糖尿病视网膜病变分类

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467720

Zhi-Bo Xiao, Yaxin Zhang, Jun Wu, Xinxin Zhang

{"title":"SE-MIDNet Based on Deep Learning for Diabetic Retinopathy Classification","authors":"Zhi-Bo Xiao, Yaxin Zhang, Jun Wu, Xinxin Zhang","doi":"10.1145/3467707.3467720","DOIUrl":"https://doi.org/10.1145/3467707.3467720","url":null,"abstract":"Diabetic Retinopathy (DR) is one of the most serious complications of diabetes. At present, DR detection mainly relies on detailed analysis by ophthalmologists. However, manual diagnosis is time-consuming and low efficiency. Aiming at the task of DR automatic classification, this paper proposes a classification method of DR based on deep learning. In view of the different sizes of the lesion area, firstly, an improved Inception module is proposed, which enables the network to efficiently extract multi-scale features of DR images. Then, the dense connection method is used to splice the output feature maps of the improved Inception module and send them to the subsequent layers to realize the multi-scale feature reuse of DR images and enhance the feature representation of small targets. Finally, the Squeeze-and-Excitation (SE) module is used to obtain the global information of the feature map on each channel, and the dynamic nonlinear modeling of each channel is carried out to improve the generalization ability of the network. The experimental results show that the network structure designed in this paper has good generalization ability, and the accuracy of DR automatic classification reaches 88.24%, the sensitivity reaches 99.43%, and the specificity reaches 97.6%, which can meet the needs of hospitals for DR classification.","PeriodicalId":145582,"journal":{"name":"2021 7th International Conference on Computing and Artificial Intelligence","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121854362","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: 3

Prediction Model of Blood Pressure during Hemodialysis Base on Deep Learning 基于深度学习的血液透析血压预测模型

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467772

Guanjun Wang, Haojie Fan

{"title":"Prediction Model of Blood Pressure during Hemodialysis Base on Deep Learning","authors":"Guanjun Wang, Haojie Fan","doi":"10.1145/3467707.3467772","DOIUrl":"https://doi.org/10.1145/3467707.3467772","url":null,"abstract":"Hemodialysis is the main treatment for patients with renal failure. Significant complications associated with treatment include hypotension, cramps, insufficient blood flow, and arrhythmia. Most complications are related to unstable blood pressure during hemodialysis. Although the science and technology and computer industry have made great progress in recent years, the problem of blood pressure prediction during hemodialysis is still a big challenge. Aiming at the problem that the shallow model used in the current research does not consider the high-dimensional nonlinear combination characteristics of hemodialysis data, this paper proposes a blood pressure prediction model during hemodialysis based on deep belief network (DBN) and support vector regression (SVR). In this model, DBN extracts the non-linear combination features of hemodialysis data layer by layer, and then transfers the extracted high-dimensional features to the top-level SVR for regression prediction. The experimental results show that the mean absolute error (MAE) of the model is 3.79, the root mean square error (RMSE) is 9.01, and is 0.88. Compared with the shallow model used in the current research, the prediction effect has been significantly improved.","PeriodicalId":145582,"journal":{"name":"2021 7th International Conference on Computing and Artificial Intelligence","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123066803","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

Intelligent Measurement of Object Volume Based on Image 基于图像的物体体积智能测量

2021 7th International Conference on Computing and Artificial Intelligence Pub Date : 2021-04-23 DOI: 10.1145/3467707.3467728

Caixia Zhang, L. Han

引用次数: 1