{"title":"Optimization of Video Repetitive Action Counting for Efficient Inference on Edge Devices","authors":"Hyunwoo Yu, Yubin Cho, Jong Pil Yun, S. Kang","doi":"10.1109/ITC-CSCC58803.2023.10212477","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212477","url":null,"abstract":"Repetitive actions are prevalent in both natural and man-made environments, offering valuable insights into the analysis of action units and underlying phenomena. Video repetition counting task aims to predict the count and frequency of the repetitive actions. Deep learning models have been developed for this task, enabling the recognition of repetitive motions without physical contact with the moving object. However, these models often perform unnecessary operations during inference due to inefficient data pre-processing. To address this issue, we propose an optimized data frame pre-processing method that minimizes redundant operations, ensuring fast and accurate inference. Furthermore, in order to enable video repetition counting on edge devices, we employ quantization for model compression, allowing the deployment of lightweight models suitable for various applications.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123084283","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 Low-Complexity Patch Segmentation in the V-PCC Encoder","authors":"Y. Kim, Yong-Hwan Kim","doi":"10.1109/ITC-CSCC58803.2023.10212807","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212807","url":null,"abstract":"The video-based point cloud compression(V-PCC) is the compression standard of the dynamic dense point cloud established by ISO/IEC MPEG-I in 2021. It is designed to achieve significant data size reduction for the dynamic dense point cloud. However, the patch generation process in the V-PCC encoding is computationally very complex. To solve this problem, we propose a fast algorithm for patch partitioning using a look-up table instead of the k-d tree search. Experimental results show the reduction of the computational complexity of the patch segmentation process by over 40% while achieving the same encoding results as the original method.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125850303","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}
Takuro Manabe, Shota Kanzawa, Md. Arshad Ali, Y. Nogami, Yuta Kodera, Takuya Kusaka
{"title":"A Proposal of Eliminating Fruitless Cycle for Efficient Pollard's Rho Method by Adding a Constant Rational Point","authors":"Takuro Manabe, Shota Kanzawa, Md. Arshad Ali, Y. Nogami, Yuta Kodera, Takuya Kusaka","doi":"10.1109/ITC-CSCC58803.2023.10212808","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212808","url":null,"abstract":"The security of elliptic curve cryptography is based on the ECDLP. The Pollard's rho method is known to be the most efficient attacking for ECDLP. In addition, the Pollard's rho method with skew Frobenius mapping, which is even more efficient version of the Pollard's rho method, however the number of fruitless cycle increases significantly. In this paper, the authors have succeeded in reducing them by adding an operation of addition and subtraction of constant rational points to Pollard's rho method with the skew Frobenius mapping.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114884251","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}
Ignasi Piqu´e Muntan´e, M. J. Fern´andez-Getino, Fern´andez-Getino Garc´ıa
{"title":"Parametric Model and Estimator Classifier for Optimal Averaging in Mobile OFDM Systems with Superimposed Training","authors":"Ignasi Piqu´e Muntan´e, M. J. Fern´andez-Getino, Fern´andez-Getino Garc´ıa","doi":"10.1109/ITC-CSCC58803.2023.10212534","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212534","url":null,"abstract":"Superimposed training (ST) is an attractive technique for channel estimation in orthogonal frequency division multiplexing (OFDM) modulation. However, its main challenge is the intrinsic interference due to the joint transmission of pilot and data symbols, which can be mitigated by averaging the received signal. Previous works analyzed the mean square error (MSE) of the channel estimation, for both least squares (LS) and minimum MSE (MMSE) estimators, and showed that, under realistic channel models, the optimum number of averaged symbols could be computed by solving a transcendental equation. In this paper, as a practical implementation proposal, these optimum averaging values are parametrically approximated with a multilinear regression model. Also, it is proposed an accurate classifier that, under delay and performance tolerances, is able to select the most suitable estimator between LS and MMSE.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115015761","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":"Graph Fourier Transform Based Image Zero-Watermarking","authors":"Yusuke Sao, Hodaka Yamanouchi, T. Uto","doi":"10.1109/ITC-CSCC58803.2023.10212615","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212615","url":null,"abstract":"In this paper, we propose an image zero watermarking method using the graph Fourier transform (GFT). We introduce new elements such as sampling suitable for images, convolution of surrounding pixels, and definition of adjacency matrices based on sampling results. To extract features of a host image, a graph signal is produced with an adjacency matrix that depends on the distance from neighboring pixels. Then, the coefficients after the GFT are encoded into binary information using the K-means method. Finally, XOR operation is performed between the obtained features and watermark to achieve zero watermarking. Simulations show that the proposed method works more effectively than a comparative method in resisting a variety of common attacks.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128228891","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}
Thearrawit Ngenjaroendee, W. Phakphisut, Thongchai Wijitpornchai, Poonlarp Areeprayoonkij, Tanun Jaruvitayakovit, N. Puttarak
{"title":"Reference Signal Received Power Prediction Using Convolutional Neural Network with Residual Loss","authors":"Thearrawit Ngenjaroendee, W. Phakphisut, Thongchai Wijitpornchai, Poonlarp Areeprayoonkij, Tanun Jaruvitayakovit, N. Puttarak","doi":"10.1109/ITC-CSCC58803.2023.10212448","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212448","url":null,"abstract":"In this paper, LTE measurement reports collected from user equipments are used to generate the residual loss, which can represent the loss value of each grid. The residual loss and geospatial data are used in the learning process of convolutional neural network (CNN). We also use the site configuration and three-dimensional antenna pattern. Thus, the neural network and convolutional neural network are proposed to construct deep learning to predict the reference signal received power (RSRP) in Bangkok, Thailand. The results show that residual loss can improve the efficiency of prediction.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128383458","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}
Shunsuke Inoue, Takumi Hayashi, T. Yamashita, T. Kumaki
{"title":"Proposal of Flicker-Based QR Code with Invisible Information Display Lighting Device","authors":"Shunsuke Inoue, Takumi Hayashi, T. Yamashita, T. Kumaki","doi":"10.1109/ITC-CSCC58803.2023.10212942","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212942","url":null,"abstract":"This paper proposes a special QR code by using a LED-based display Stego-panelV. This QR code is invisible to the human eyes. On the otherhand, this can be recognized by a camera equipped with a CMOS image sensor. However, at this time, shutter speed of the camera must be adjusted appropriately. Therefore, by using this system, it is possible to improve the security by making it difficult to duplicate the QR code and secretly photograph it. To achieve this, we develop Stego-panelV, which has a special LED control mechanism and is operated by dedicated software, and conducted an experiment to evaluate the effectiveness of the OR code.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123924327","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 0.75V 30.1 ppm/°C 300nW Bandgap Reference and Low Power Low-dropout Regulator with Hybrid form of Resistors as Size Reduction Technique","authors":"Jiteck Jung, Hyun Oh Song, Jungeun Park, H. Kim","doi":"10.1109/ITC-CSCC58803.2023.10212763","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212763","url":null,"abstract":"This paper proposes a low-power bandgap reference(BGR) and low-dropout regulator(LDO) circuit that apply size reduction technique. Using stacked-MOS transistors in triode region as resistors occupies less layout area than poly resistors with the same resistance. Although the resistance of MOS transistors has wider PVT variations than that of poly resistors, The hybrid form of both MOS resistors and poly resistors can have acceptable PVT variation of resistance with noticeable size reduction. The proposed BGR and LDO with the size reduction technique have the layout size of 0.034mm2 total, which could be 0.050mm2 with poly resistors only. The layout size saving effect is 0.016mm2, which is 31.36% of the total. The proposed BGR produces 0.75V reference voltage with temperature coefficient of 30.1[ppm/°C] over temperature range of −40°C∼125°C. The power consumption is 300nW with layout size of 0.025mm2. The proposed LDO has 0.9V output voltage with input voltage of 2∼3.6V. The operating current is 260nA. The layout size of the LDO is 0.009mm2.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128141884","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":"Proposal and Quality Evaluation of Skin Imaging Using Smartphone and Ring Light with Polarizing Film","authors":"Aika Kuramoto, M. Hasegawa","doi":"10.1109/ITC-CSCC58803.2023.10212896","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212896","url":null,"abstract":"A method for skin image acquisition for cosmetic purposes using a smartphone camera is discussed. A simple construction using a commonly available ring light and a polarizing film is used to create an inexpensive method for capturing images comparable to those of expensive beauty and medical cameras. The use of a ring light stabilizes the light source, and a polarizing film mounted orthogonally to the ring light and lens eliminates skin reflection. Image quality was evaluated using the non-reference image quality evaluation model (Naturalness Image Quality Evaluator). We show that the proposed method provides resolution and image quality comparable to beauty and medical cameras.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121762710","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":"Link Quality-Aware Geographic Predictive Routing for V2V Network Based on GPSR","authors":"M. Harayama, Masahiro Mishioka","doi":"10.1109/ITC-CSCC58803.2023.10212525","DOIUrl":"https://doi.org/10.1109/ITC-CSCC58803.2023.10212525","url":null,"abstract":"In recent years, advances in automotive IoT technology have not only improved automated driving and driving convenience but have also led to a diminishing number of traffic accidents. Vehicle Ad-hoc Networks (VANETs) have attracted much attention because automotive IoT is based on wireless communications. Ad-hoc routing protocols that apply the characteristics of vehicle-to-vehicle (V2V) networks are needed. One of them is Greedy Perimeter Stateless Forwarding (GPSR), a routing protocol using geographic information. It uses Global Positioning System (GPS) information for routing. However, GPSR may increase the packet drop rate due to radio attenuation and fading. Therefore, C. Li et al. proposed to select the next hop by evaluating the link quality. However, due to the large moving speed of the node, the next hop may be out of the radio propagation range at the communication timing. Therefore, in this study, we propose a new routing method that combines the future location prediction proposed by Z.S. Houssaini et al. The effectiveness of the method is demonstrated by simulations using ns-3 with traffic data acquired by SUMO.","PeriodicalId":220939,"journal":{"name":"2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115926602","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}