{"title":"Interactive Evolutionary Design Method of Tile Shape by GAN Reflecting Adjectives","authors":"Mao Takegishi, K. Arakawa","doi":"10.1109/ISPACS51563.2021.9651018","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651018","url":null,"abstract":"A method of designing tile shapes using interactive evolutionary computing (IEC) with generative adversarial network (GAN) is proposed. Designing complex tile shape is difficult for ordinary people due to mathematical constraints and artistry requirements. The proposed method automatically generates shapes which reflect adjectives the user wants to express using GAN, and the shapes are refined by human interaction with IEC, so that the obtained shape becomes fully satisfactory to the user. Here, datasets of shapes are prepared for several adjectives first, and GAN is trained using random latent vectors to generate shapes for each adjective. The values in the latent vector are controlled by IEC to consider the user’s preference. The proposed method is shown to be effective in computer simulation and its subjective test.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"142 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":"116342242","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 Scan-Based Lower-Power Testing Architecture for Modern Circuits","authors":"J. Rau, Jia‐xiang Wang","doi":"10.1109/ISPACS51563.2021.9651069","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651069","url":null,"abstract":"Advances in Very-large-scale integration (VLSI) technology enable billions of logic gates to be integrated into a single chip. The rapid development of VLSI technology has created new difficulties for design and test engineers. The power consumption of the test is one of the important issues. This article describes a scanning architecture that enables high-quality and low-power testing by modifying test samples in test applications. When the test sample switches a large number of scan flip-flops in each shift, the stability of the circuit is lowered, the fault verification is difficult, the product yield is reduced, and the life is shortened, which is a serious problem. In the paper structure, part of the displacement power is solved. One method is to reduce the number of toggle triggers and reduce the switching activity caused by the move of test samples. The method calculates the switching activity of the scan trigger during the scan operation. Move to the appropriate scan path in the test sample.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"7 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":"126317709","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":"On the Upper Bound of Filter Length in the Design of Polynomial Graph Filter","authors":"C. Tseng, Su-Ling Lee","doi":"10.1109/ISPACS51563.2021.9651111","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651111","url":null,"abstract":"In this paper, the upper bound of filter length in the design of polynomial graph Alter is studied. First, the characteristic polynomial of graph Laplacian matrix is used to show that the upper bound of filter length is the number of vertex of graph. Then, two methods are presented to reduce the transfer matrix of graph filter if its length is greater than upper bound. One is degree reduction method, the other is long division method. Next, the numerical examples of cycle graph and path graph are illustrated to show the effectiveness of the proposed reduction methods. Finally, the lowpass graph filter design in the temperature data sensor network is applied to demonstrate the usefulness of proposed filter length reduction methods.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"39 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":"132318489","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}
Dinh-Thuan Dang, Jing-Wein Wang, Jiann-Shu Lee, Chou-Chen Wang
{"title":"Defect Classification System for Ski Goggle Lens","authors":"Dinh-Thuan Dang, Jing-Wein Wang, Jiann-Shu Lee, Chou-Chen Wang","doi":"10.1109/ISPACS51563.2021.9651116","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651116","url":null,"abstract":"In this work, we build the defect classification system for ski goggle lenses with machine learning. In the first step, we establish the image capturing model and data annotation. In the next step, we apply the classification model based on machine learning for classifying defects such as scratch, watermark, spotlight, border, stain, dust-line, and dust-spot. Besides, to increase the performance, the augmentation method is also applied in the training process. The classification rate achieves 94.34%, while the running time is short.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"43 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":"133304150","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":"DAH: Domain Adapted Deep Image Hashing","authors":"Pei-Jung Lu, Pao-Yun Ma, Ying-Ying Chang, Mei-Chen Yeh","doi":"10.1109/ISPACS51563.2021.9651027","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651027","url":null,"abstract":"With abundant labeled data, deep hashing methods have shown great success in image retrieval. However, these methods are often less powerful when applied to novel datasets. In this paper, we apply unsupervised domain adaptation techniques to improve a state-of-the-art deep hashing method, used in a cross-domain scenario where the model is trained with labeled source data and is evaluated with target data. Experiments show that the generalization capability of a supervised hashing method can be improved by the applied domain adaptation techniques.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"4 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":"133110992","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. Cross-Network Quality and Performance Measurement","authors":"Li-Chi Ku, Hui-Lan Lee, Min Chen","doi":"10.1109/ISPACS51563.2021.9650987","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9650987","url":null,"abstract":"In the era of 5G and future generation networks, cloud services take the dominant part of the network bandwidth usage. Therefore the quality and performance of the network between users and the cloud data centers dictate the perceived quality and responsiveness. Due to its distributed nature, the monitoring of the quality has to be made in a span-AS manner, into those networks we have almost no control. This paper introduces the way we developed to make long term measurement across different networks possible.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"41 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":"115103740","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 Doppler Effect Correction Method for APT Weather Satellite Image Reception","authors":"Shou-Sheu Lin, Yan-Zhou Song","doi":"10.1109/ISPACS51563.2021.9651104","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651104","url":null,"abstract":"To receive an useful APT image from the NOAA weather satellites usually spends at least 10 minutes. It suffers from Doppler shift and noise due to long receiving time. In this paper, we propose a linear regression method to estimate the length of each line of the APT image, then, apply the interpolation to mitigate the Doppler shift and noise. We develop a complete APT image reception and processing system based on low cost software defined radio RTL-SDR and Matlab. An APT image was received and decoded successfully.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"45 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":"116969670","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}
Weihao Liu, Yen-Ting Lai, Kai-Wen Liang, Jia-Ching Wang, P. Chang
{"title":"Dual-Masking Wind Noise Reduction System Based on Recurrent Neural Network","authors":"Weihao Liu, Yen-Ting Lai, Kai-Wen Liang, Jia-Ching Wang, P. Chang","doi":"10.1109/ISPACS51563.2021.9650991","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9650991","url":null,"abstract":"In this paper, we adopt the architecture of permutation invariant training (PIT) model. We take advantage of the dual mask features of the speech separation architecture and combine the results of the two masks to synthesize a better signal with a specific ratio. We use bidirectional gated recurrent unit (BGRU) to find appropriate weights for the features after short time Fourier transform (STFT). A mask finds the signal you want to keep. Another mask finds the unwanted signals. Compared with the traditional method for eliminating wind noise, our proposed method can achieve better noise reduction for non-stationary and non-periodic wind noise.","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":"129348880","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}
Jian-Ming Wu, Sian‐Wei Ke, Teng-Hao Hsu, Yuan-Chih Lin, Min-Lang Yang
{"title":"Study of Reducing Phase Error in QVCO RFIC Using Generalized Locking Equation","authors":"Jian-Ming Wu, Sian‐Wei Ke, Teng-Hao Hsu, Yuan-Chih Lin, Min-Lang Yang","doi":"10.1109/ISPACS51563.2021.9650975","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9650975","url":null,"abstract":"This paper concerns the accuracy of the quadrature phase that is generated by a S-band quadrature voltage control oscillator (QVCO) using a generalized locking equation. The main purpose of external injection is to reduce the phase error of the QVCO by suppressing the magnitude of the instantaneous beat frequency that is associated with a sinusoidal injection signal. The designed QVCO is based on a parallel-coupled QVCO with an integrated LC tank. The QVCO is implemented using the TSMC 0.18 μm CMOS standard process. Measurements of the injection-locked QVCO are made, revealing that the phase error are reduced from 2.44° to 0.32°. The reductions of the phase error is 2.12°. The supply voltage that is applied to the injection-locked QVCO is only 1.1 V and the power consumption is 20.5 mW.","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":"128946419","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":"Positioning Performance Improvement of RTK Using Kalman Filter for Autonomous Vehicles","authors":"Jiwoo Kang, Sungkwon Park","doi":"10.1109/ISPACS51563.2021.9651049","DOIUrl":"https://doi.org/10.1109/ISPACS51563.2021.9651049","url":null,"abstract":"Various researches for estimating the precise position of a vehicle are being actively conducted with increased interests in automotive vehicles and driver safety services. Currently, one of the most widely used technologies for estimating the position of a vehicle is a method using a Global Navigation Satellite System (GNSS). GNSS is one of the technologies to determine the outdoor position and uses the signals provided by artificial satellites to determine one’s position. However, due to different causes of error, general GNSS cannot estimate the precise position. To solve this problem, a Real-Time Kinematic (RTK) technology which can improve precision by using correction data provided by a base station has been developed. RTK can estimate a more precise position than GNSS. However, if the integer ambiguity cannot be precisely calculated, a precise position of the centimeter (cm) level cannot be estimated. In this paper, we propose a method for estimating a more precise position using the Kalman filter to improve the precision of the position estimated using RTK, and show the results of experiments.","PeriodicalId":359822,"journal":{"name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"116 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":"132510293","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}