{"title":"Binocular 3D Vision Fusion Measurement Technique","authors":"Chao-Kai Chang, Jih-Yi Liao, Der-Chin Chen, Feng-Ming Yeh, Shih-Tsung Chang, Cheng-Ko Hsu","doi":"10.1109/ISPACS51563.2021.9650981","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9650981","url":null,"abstract":"There are two major factors behind the visual discomfort for wearing glasses. One is the prism effect, in which the pupillary distance (PD) is out of the one between the optical center of the glasses. The other is the improper adjustment of the frame curvature, which causes distortion effects. These two factors may not be discovered due to the fast eye examination and the conscious perception of the inspected person’s old glasses of visual sight, which may cause visual discomfort after wearing the new glasses. Binocular 3D Vision Fusion Measurement B3D-VFM uses the subject’s visual choice with a double-slit plate inspection machine to measure the optic axis, combined with the curvature and curve rate of the frame, will effectively improve the visual fusion function. After being proved by Institutional Review Board (IRB), the Subjective fusion data of the 21 testees were measured 3 times compared with the Objective fusion, and it showed the data value was reduced by 83%. The new glasses technology ophthalmic dispensing technology developed in this experiment, for those who wear old glasses, have a difference in fusion. Then the comfort of the fusion rate reached to 91% of the technical experiment after effectively optimizing, and the effect of B3D-VFM is significant.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115280170","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":"FoD Enroll Image Quality Classification Method for Fingerprint Authentication System","authors":"Xiu-Zhi Chen, Jhe-Li Lin, Yen-Lin Chen","doi":"10.1109/ISPACS51563.2021.9651102","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651102","url":null,"abstract":"Typical fingerprint authentication system flow including preprocessing, feature extraction, and feature matching. To improve the user experience of it, more intelligent process for such system is needed. Fingerprint on display (FoD) is a popular kind of sensing technique in recent years, in this research, we proposed an enroll image quality classification method for the preprocessing step of the system, which is able to reject the invalid input, in order to shorten the response time, especially for FoD applications. We had evaluated our proposed method through a self-collected FoD sensing image dataset, including 50,130 fingerprint images, and proved that our method is able to reach 95.83% accuracy, which is really helpful for the improvement of the system’s user experience.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125037558","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":"Asynchronous Domino Binary search Digital LDO","authors":"Wei-Bin Yang, S. Ku, Chun-Wei Wang, Li-Lun Chu","doi":"10.1109/ISPACS51563.2021.9651071","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651071","url":null,"abstract":"This paper proposes asynchronous binary search digital low-dropout regulator (ADLDO) with domino control mechanism and the adjustable bidirectional asynchronous loop. The domino binary search is used to achieve fast settling time. After domino binary search completed, the adjustable bidirectional asynchronous loop goes to fine tracking region. Additionally, the double edge-triggered comparator enhances the detection of load transients. The proposed ADLDO is implemented in TSMC 90nm 1P9M. With VIN=350mV and 50mV dropout, the proposed LDO can support maximum output current of 2.4mA with 99.87% current efficiency and settling time is 61ns. Therefore, the proposed LDO is suitable for fast tracking ultra-low supply voltage applications.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122031593","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":"Fusing Multi-Modality Information for 3D Road Obstacle Detection","authors":"Yu-Quan Wang, Yi-Ting Chen, Man Wu, Ching-Hsiang Ko, Hao-Wei Hwang, Yung-Yao Chen","doi":"10.1109/ISPACS51563.2021.9650995","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9650995","url":null,"abstract":"Considerable resources have been devoted to developing self-driving systems in industry and academia, for which three-dimensional object detection is critical. The commonly used LiDAR-based methods, in which point clouds serve as the input representation, are marred by the problems of sparsity and inhomogeneity, which make small or distant objects difficult to detect. Accordingly, we propose a LiDAR-based road obstacle detection method assisted by RGB images, which operates as follows. First, a depth completion network is used to transform RGB images into dense depth maps that can be used to create a pseudo–point cloud through matrix operations. Subsequently, both pseudo point cloud and real point cloud are transformed into a pillar form for a pillar-wise feature encoder; this is executed to generate a two-dimensional (2D) feature tensor. Finally, a standard 2D convolutional neural network detection architecture is used to learn features. This method increases the number of point features to remedy the sparsity and inhomogeneity of the original point cloud. Our method had an improvement compared with its LiDAR-based counterpart in experiments.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125304393","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":"Comparisons of Classification Models on COASTSAT","authors":"Sun Wei-hao, Shih-Huan Tseng","doi":"10.1109/ISPACS51563.2021.9651114","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651114","url":null,"abstract":"Due to rapid climate change, the task to observe and quantify shoreline position is important to coastal protection and management. CoastSat is a time-series shoreline detection system that using artificial neural network ANN on image classification. This paper further compared 4 image classification models such as decision tree classifier DTC, non-linear support vector machine (SVM), k-nearest neighbors (KNN) and linear SVM with stochastic gradient descent (SGD) on the Qijn images from the satellite, Landsat 8. The experimental results demonstrate accuracies, F1 scores and precision-recall curves on different models. Finally, the work shows that ANN is the best model in CoastSat image classification.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125918272","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":"Hand-detection with Transferrable Design for Smart Factories","authors":"Guan-Ting Liu, Ching-Hu Lu, Syu-Huei Huang","doi":"10.1109/ISPACS51563.2021.9651134","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651134","url":null,"abstract":"Nowadays, a smart factory in Industry 4.0 often must produce a variety of products, so its assemblers need to learn different assembly processes and post-inspections. Smart cameras that leverage edge computing (hereinafter referred to as edge cameras) can now incorporate deep neural networks (DNNs) and have been widely used in smart factories. However, in response to the demand for rapid learning and deployment of DNNs across different assembly lines, which has not been addressed in previous studies, we propose \"Knowledge Transfer across Multiple Assembly Lines\" (KTaMAL) to transfer learned knowledge across different assembly lines. The experimental results show that the model prediction accuracy of KTaMAL is improved by 8% compared with non-transfer-learning based approaches and the training time can be significantly reduced by approximately 80%.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128563955","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}
Kenta Mori, Eiki Kayama, Taichi Maebou, Yuan-ying Chen, H. San, T. Matsuura, M. Hotta
{"title":"A Low-voltage Non-binary Cyclic ADC using Fully Differential Ring Amplifier","authors":"Kenta Mori, Eiki Kayama, Taichi Maebou, Yuan-ying Chen, H. San, T. Matsuura, M. Hotta","doi":"10.1109/ISPACS51563.2021.9651059","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651059","url":null,"abstract":"This paper presents a non-binary cyclic analog-to-digital converter (ADC) with fully differential ring amplifier in 65nm SOTB CMOS technology for low power supply voltage applications. By utilizing substrate voltage control technique of SOTB CMOS, high gain dynamic amplifier is realized at low supply voltage. In a cyclic ADC with proposed fully differential ring amplifier, the number of reset mode can be reduced because the reset mode is provided only once per AD conversion instead of each conversion step. And hence, offset cancellation capacitors in the multiplying digital-to-analog converter (MDAC) with ring amplifier switched-capacitor (SC) circuits can be removed. As the results, not only the active area for capacitors, but also input referred noise of MDAC can be reduced. Proposed non-binary cyclic ADC with fully differential ring amplifier can be realized at supply voltage as low as Vdd =0.75V. SPICE simulation results confirm the feasibility and reliability of proposed technique to realize a high-resolution ADC at low supply voltage.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"122 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131244695","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":"Image Restoration from Low Bit-Rate Quantization Based on Reinforcement Learning","authors":"Yi-Rung Lin, H. Lin","doi":"10.1109/ISPACS51563.2021.9650984","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9650984","url":null,"abstract":"The image restoration is an important issue in some application scenarios where only the limited storage or bandwidth are available. In this paper, we present a method using pixelwise reinforcement learning to restore the uniformly quantized images. The results are evaluated using various metrics, including SSIM, PSNR and HDR-VDP-3, and the performance comparison with other techniques is provided. The experimental results demonstrate the better visual effect and image quality of the proposed method. It also shows the potential to deal with more complicated high dynamic range imaging problems.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130150923","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}
Chien-Wu Lan, Shih-Sung Lin, Chi-Ting Ku, Bo-Sian Chen, M. Lo, Mu-Ching Chien
{"title":"Design and Development of a Biped Robot for a Knee Exoskeleton Analysis","authors":"Chien-Wu Lan, Shih-Sung Lin, Chi-Ting Ku, Bo-Sian Chen, M. Lo, Mu-Ching Chien","doi":"10.1109/ISPACS51563.2021.9650992","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9650992","url":null,"abstract":"Recently, exoskeleton has gradually diversified and are used in various walks of life. However, how to systematically analyze the performance of exoskeleton has always been a problem. In this research, a biped robot platform is developed for the performance analysis of active knee exoskeleton. The biped robot platform includes metal skeletons, detachable and realistic 3D printed leg contour, actuators which can transmit position, speed and current information, and inertial measurement units. In addition, a graphical human-machine interface is also developed for motion control and data acquisition on the biped robot platform. By wearing the knee exoskeleton on the biped robot platform, repeatable motion analysis of the knee exoskeleton can be realized. For more, by analyzing the position trajectory and current changes provided by the actuator of biped robot platform during the test motion, the performance of the exoskeleton can be evaluated directly.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121326753","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":"Design of Battery Management System For Electric Vehicles","authors":"Tsung-hsun Wu, Tzu-Yang Pai, Chih-Hsing Liu, Pei-Yin Chen","doi":"10.1109/ISPACS51563.2021.9650999","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9650999","url":null,"abstract":"The battery management system is one of the key technologies for electric vehicles. This system is mainly used to monitor the status of the battery, improve the efficiency and reliability of the battery, prevent the battery from overcharge and over discharge, and to extend the battery life. This research uses NUVOTON's Coretex-M4 chip M487SIDAE as the control core to construct a set of \"low-cost and high-efficiency battery management system\", for the electric vehicles. With self-designed battery monitoring and sensing circuits to measure various important parameters of the battery module, A set of C# real-time monitoring screens is constructed on the computer interface to facilitate the monitoring of the personnel, and to make the battery information in real time. Recording and data accumulation are convenient for users to perform subsequent battery health status diagnosis and analysis offline, which can be used to effectively judge the battery life.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121213720","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}