2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )最新文献

{"title":"Research on Bridge Crack Recognition Algorithm Based on Image Processing","authors":"Xiaoyan Yang","doi":"10.1109/ICKII55100.2022.9983578","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983578","url":null,"abstract":"Concrete is a common material of bridges. Due to durability, high pressure, and other reasons, it is easy to cause cracks on the surface of bridges, which affects the appearance and causes structural safety problems. The traditional manual testing of bridge crack is time-consuming and laborious. Therefore, we propose an algorithm for concrete crack recognition based on image processing. Images for the crack area are taken by using high-definition cameras. The collected image is pretreated for graying, denoising, and filtering with the treatment of dummy pixel and fracture problems. The improved multistage filtering algorithm was used to extract the complete crack, and the width and length of the crack were calculated. Experimental results show that the proposed algorithm effectively detects concrete surface cracks with high accuracy.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129830422","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}

{"title":"Improvement of Dye-sensitized Solar Cells by Using Compact and Pressed Layer of TiO2","authors":"Wei-Ming Huang, J. Tsai, T. Wu, T. Meen","doi":"10.1109/ICKII55100.2022.9983594","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983594","url":null,"abstract":"Introducing a TiO<inf>2</inf> compact layer and a pressed TiO<inf>2</inf> layer into DSSC devices improves the power conversion efficiency of the dye-sensitized solar cell (DSSC). In this study, spin coating is used to deposit the TiO<inf>2</inf> compact layer on fluorine-doped tin oxide (FTO) glass, while screen printing is used to deposit the mesoporous TiO<inf>2</inf> layer. The mesoporous TiO<inf>2</inf> layer is pressurized by a hydraulic press to form a pressed TiO<inf>2</inf> layer. The DSSC photoanode structure is composed of a mesoporous TiO<inf>2</inf> layer and a pressed TiO<inf>2</inf> layer on a TiO<inf>2</inf> compact layer. The lifetime of electrons for DSSC with a pressed TiO<inf>2</inf> layer and mesoporous-TiO<inf>2</inf> layer are 8.217 and 6.287 ms. The current density-voltage characteristics indicate that the efficiency of the power conversion of the DSSC device with the pressed TiO<inf>2</inf> layer and the TiO<inf>2</inf> compact layer increases by 4.09 to 5.00%, compared with the mesoporous-TiO<inf>2</inf> layer.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130765637","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}

{"title":"Extendable B-tree on Multi-channel Nonvolatile Memory Devices","authors":"Pin-Tzu Huang, Ting-Syuan Lin, Po-Chun Huang","doi":"10.1109/ICKII55100.2022.9983552","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983552","url":null,"abstract":"B-tree is used to be a popular index structure in a variety of application scenarios such as file systems and databases. In a B-tree, each node is allocated to a fixed number of sectors of storage space, and once a node exhausts its allocated space, it overflows and has to be split. When this happens, the data items in the overflown node have to be migrated to the newly split node, which might incur severe performance overheads. The nodes of the B-tree are limited by the capacity upper bound to guarantee the worst-case time to search for a key in the node. However, nonvolatile memories (NVMs) are relatively slower on write operations, which makes the unsorted B-tree a preferred choice over the default B-tree. Observing the different performances and searching a key in a sorted node and unsorted node, we present how to adaptively extend the leaf nodes according to the key distributions to optimize the holistic latency to search a key in a B-tree. The main objective is to maximally postpone the timing of node overflows and improve the overall performance of the B-tree. The proposal in this study is verified through analytical and experimental studies, as the results are promising.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129207206","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}

{"title":"A CNN Approach To Predicting Non-Invasive Blood Pressure of Surgical Patients","authors":"Pin-You Ko, Lien-Fu Lai, T. Ku, Yue-Der Lin","doi":"10.1109/ICKII55100.2022.9983601","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983601","url":null,"abstract":"The occurrence of intraoperative hypertension/ hypotension may cause danger to a patient. Therefore, the monitoring of blood pressure change during surgical operation is momentous for anesthetized patient undergoing surgical procedures. The invasive method of measuring arterial blood pressure (ABP) provides accurate and much information, but it requires evaluation by an anesthesiologist and with its long-term use, it also brings a higher risk of infection, and even some patients have pain and discomfort at the catheter placement site after surgery, so it is not suitable for all types of patients. On the other hand, non-invasive method of measuring cuff blood pressure provides little information because of non-continuous measurement. With the emerging of deep learning, there has been more and more discussion on whether non-invasive Photoplethysmography (PPG) can replace invasive ABP as an alternative to continuous BP measurement and even BP prediction. This paper aims to implement a deep learning model to predict SBP/DBP signal by PPG, PPG extended data and Electrocardiography (ECG) data. We trained the CNN-based architecture on preprocessed data including ECG, PPG, 1st and 2nd derivative PPG signal extracted from MIMIC-III(Medical Information Mart for Intensive Care III) waveform database matched subset to predict continuous ABP signals using real world data. The value of SBP and DBP are directly predicted to effectively estimate the accuracy of the predictions. The prediction results fulfill the grade A in British Hypertension Society (BHS) standard and most part of Association for the Advancement of Medical Instrumentation (AAMI)’s standard. The proposed model has been applied for CHANGHUA CHRISTIAN HOSPITAL’s IRB NO:191240. The results depict that our proposed model could effectively predict SBP/DBP signal and be deployed to the operating room realistically.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123284645","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}

{"title":"Review of PV Array Reconfiguration to Maximize Power Generation","authors":"Yuan-Kang Wu, Ba Long-Dong, Manh-Hai Pham, Cheng-Liang Huang","doi":"10.1109/ICKII55100.2022.9983600","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983600","url":null,"abstract":"Solar arrays are inevitably plagued by shadow challenges, leading to a reduction in power production. The effect of partial shading can be effectively reduced by rearranging the connection among photovoltaic (PV) arrays. Thus, it is required to apply appropriate algorithms for PV-array reconfiguration to increase the power output. Various methods are introduced for PV array reconfiguration to decrease energy losses and increase the efficiency of grid-connected solar systems under partial shading conditions. The main concept for PV-array reconfiguration is to swap the PV-module connection from one row to another row to minimize the difference between the total irradiance at each row, which helps optimize the power outputs of a PV system. In this study, a simulation platform is established with PV arrays, a converter with maximum power point tracking (MPPT) function, and a controller for switching the connection topology. In addition, a case study by considering partial shading on PV panels is carried out through the established simulation platform. The results demonstrate that the developed system that combines module-connection switching with MPPT achieves the maximum power output from the PV system.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132710359","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}

{"title":"Fake Beef Detection with Machine Learning Technique","authors":"Pimrawee Chanasupaprakit, Nawaree Khusita, Chalothon Chootong, Jirawan Charoensuk, W. Gunarathne, S. Ruengittinun","doi":"10.1109/ICKII55100.2022.9983559","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983559","url":null,"abstract":"Increased demand for meat causes diverse concerns, including misuse of sales by offering fake meats. Hence, consumers must be shielded from these cheated sellers. Yet, distinguishing faked meat and quality meat is not easy for regular consumers as, at present, meat identification is done manually using visual identification of human vision. Therefore, in this study, we proposed a concept to minimize the above issue by developing a virtual expert to assist in meat inspection. After extracting and pre-processing the relevant images, the model training was accomplished with the SVM, and CNN approaches. The determination of subjection of this classification process is evaluated using F1-Score and precision. Our model evaluation for pork and beef classification utilizing 20% test data against the five classification models showed that the VGG16 produced the highest accuracy rate of 95.20% with 1200 images. Besides, the best accuracy result demonstrated as (Class, F1-Score, Precision) of (Pork, 98.00%, 98.00%) and (Beef, 98.00%, 98.00%).","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133545539","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}

{"title":"Research on Intuitive Gesture Recognition Control and Navigation System of UAV","authors":"Yu-Peng Yeh, Shu-Jung Cheng, Chih-Hsiung Shen","doi":"10.1109/ICKII55100.2022.9983607","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983607","url":null,"abstract":"UAVs (unmanned aerial vehicles) are mostly equipped with GPS and additional sensors. However, the control of the UAV still depends on the skill of the operator. Inexperienced control often leads to accidents that damage the UAV and harm the environment, pedestrians, and buildings. In this research, we propose a superior control of the UAV through intuitive gestures based on deep learning of gesture recognition, which reduces the difficulty of UAV control. To improve the flight control technology of the UAV and reduce accidents caused by improper UAV control, an intuitive gesture recognition control system is constructed. The gesture recognition control is operated by a series of gesture recognition and LSTM (Long Short-Term Memory) neural networks which output the label as the control commands of the UAV. Eight different control commands are defined and generated for the control. After identifying the pickup gesture, the coordinates of the index finger are projected to the UAV's screen, and the target can be easily positioned to identify objects. The system is expected to be used for subsequent automatic flight navigation. The gesture recognition system achieves 99.54% accuracy in the training set and 99.17% accuracy in the testing set. The method to realize the control of the UAV is to send a control command back to the UAV after the computer recognizes a frame of the input hand image. The original output screen of gesture recognition has only 10‒12 FPS, and the control of the drone has a latency of about 83.33‒100 ms. After using multi-threaded processing, the FPS is increased to 15‒16, which reduces the delay, so that the latency is only about 62.5‒66.67 ms. Through a high-accuracy and low-latency intuitive gesture recognition control system, we have enough confidence to replace the method of controlling UAVs with remote control for easy control.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115289105","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}

{"title":"Research on Deep Learning with Gesture Recognition and LSTM in Sign Language","authors":"Yi-Jiuan Chung, Chih-Hsiung Shen","doi":"10.1109/ICKII55100.2022.9983520","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983520","url":null,"abstract":"Sign language is a tool for the hearing impaired to communicate with each other. It is a channel for expressing thoughts and emotions, and also one of the ways they communicate with ordinary people. However, not everyone can read sign language. For those who do not understand sign language, it is difficult to receive its meaning quickly. At the same time, it also causes inconvenience for the hearing impaired. Thus, gesture recognition combined with deep learning techniques of Long Short-Term Memory (LSTM) is used to translate sign language into sentences with the correct meaning in this study. Then, the convenience of communication between hearing-impaired and ordinary people can be enhanced. People can more easily understand the sign language expressions of hearing-impaired and improve their willingness to communicate and interact. The study of Sign Language Recognition (SLR) is to translate the gesture and continuity of the sign language for expressing the semantics, which provides a convenient tool for communication. In this study, we constructed a complete recognition model by combining a Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) neural network to complete continuous recognition work. An ordered image sequence is extracted from the video and converted into a vector through the image database for training and learning sign language using the powerful image recognition capabilities of CNN. Next, the LSTM model is used to connect with the fully connected layer of CNN to complete the accomplished semantic recognition. In particular, the concept of Recurrent Neural Network (RNN) is suitable for time series data processing and the construction of sequence data learning. After making modifications to the traditional RNN architecture, the LSTM performs better in terms of memory and appropriate data length. We built gesture and sign language datasets and adopted the CNN-LSTM recognition method. As a result, a higher recognition rate was achieved with a smaller training set, which meets the needs of real-time SLR systems.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126372874","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}

{"title":"Research on Autonomous Mobile Intelligent IoT Platform in Mushroom Cultivation","authors":"R. Jou, Wu-Jeng Li, H. Shih, Hong-Cheng Chiu","doi":"10.1109/ICKII55100.2022.9983567","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983567","url":null,"abstract":"We design an autonomous mobile platform with self-navigation, obstacle avoidance, multi-point cruise, quantity calculation of king oyster mushrooms, and environmental data collection. It can be used for patrol inspection of mushroom cultivation farms, replacing manual patrol inspection to overcome the problem of labor shortage. The autonomous mobile platform is based on the ROS (Robot Operating System) architecture with many nodes (programs). The platform integrates a mobile chassis drive node, field mapping node, navigation node, robotic arm control node, and camera node. There is also a smart IoT sensor module on the mobile platform to collect environmental data such as temperature, humidity, and carbon dioxide concentration in real-time and store the data in the network database. Environmental information is sent to managers by LINE notify through IFTTT. The environmental data is shown in graphs by using the visualization software (Grafana). In addition, a thermal imaging sensor records and stores the thermal distribution image. The images are identified by the self-trained YOLO V4 neural network model to predict the production quantity of king oyster mushrooms.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114320878","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}

{"title":"CMOS Charge Pump with Ultra-Low Current Mismatch","authors":"Chun-Chieh Chen, Nan-Ku Lu","doi":"10.1109/ICKII55100.2022.9983569","DOIUrl":"https://doi.org/10.1109/ICKII55100.2022.9983569","url":null,"abstract":"We propose an ultra-low current mismatch CMOS charge pump. With a cascode gain-boosting technique, the proposed charge pump obtains an ultra-high equivalent output resistance over a wide output-voltage range. A current mismatch between the discharging and charging current of less than 0.015 % has been simulated by using a 0.18-μm mixedsignal 1P6M 1.8-V CMOS process. The output current and the output voltage ranges of the proposed charge pump are 600 μA and 0.38−1.41 V, respectively.","PeriodicalId":352222,"journal":{"name":"2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII )","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125726329","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}