Hayoung Kim, Gihoon Kim, Jongwon Park, Kyushik Min, Dongchan Kim, K. Huh
{"title":"Action Conditioned Response Prediction with Uncertainty for Automated Vehicles","authors":"Hayoung Kim, Gihoon Kim, Jongwon Park, Kyushik Min, Dongchan Kim, K. Huh","doi":"10.1109/ISPACS48206.2019.8986322","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986322","url":null,"abstract":"Interaction-aware prediction is a critical component for realistic path planning that prevents automated vehicles from overly cautious driving. It requires to consider internal states of other driver such as driving style and intention, which the automated vehicle cannot directly measure. This paper proposes a probabilistic driver model for response prediction given the planned future actions of automated vehicle. The drivers internal states are considered in an unsupervised manner. The prediction model utilizes mixture density network to estimate future acceleration and yaw-rate profile of interacting vehicles. The proposed method is evaluated by using real-world trajectory data.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"8 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80361057","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":"Alveolar fricative consonants detection with easily interpretable feature for speech training","authors":"Kouki Furuya, A. Kawamura, Y. Iiguni","doi":"10.1109/ISPACS48206.2019.8986317","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986317","url":null,"abstract":"In this study, we conducted feature extraction for speech training by hearing-loss people alone. We targeted alveolar frictional consonant (/ s, z/), which is particularly error prone, and divided its features into three parts: fricativeness, articulation point, and voicing. The indicators created by these features are easily interpretable and help correct incorrect pronunciation.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"147 3","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91512822","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":"Classification of Environmental Sounds Using Convolutional Neural Network with Bispectral Analysis","authors":"Katsumi Hirata, T. Kato, R. Oshima","doi":"10.1109/ISPACS48206.2019.8986304","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986304","url":null,"abstract":"To realize a useful acoustic environmental recognition system, we propose a new method that classifies sound signals using a slice bispectrogram, which is a third-order version of a spectrogram. The classified sound was used as input data for a convolutional neural network. We conducted a fundamental classification experiment using UrbanSound8k, which was an open dataset consisting of 10 classes of environmental sounds. Our proposed method gave high accuracy and stability. Furthermore, a relationship between the accuracy and non-Gaussianity of sound signals was confirmed.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"54 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84832436","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":"Residual Concatenated Network for ODBTC Image Restoration","authors":"A. Wicaksono, Heri Prasetyo, Jing-Ming Guo","doi":"10.1109/ISPACS48206.2019.8986408","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986408","url":null,"abstract":"This paper proposes Residual Concatenated Network (RCN) for improving the quality of Ordered Dither Block Truncation Coding (ODBTC) decoded image. This method inherits the effectiveness of Convolutional Neural Networks (CNN) for suppressing the impulsive noise occurred in decoded image. It suppresses the noise by applying a series of convolutional operations. The network directly performs learning process via an end-to-end mapping approach. The experimental results reveal that the proposed approach yields a promising result in the ODBTC image restoration.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"136 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82259242","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":"AIoT Solution Survey and Comparison in Machine Learning on Low-cost Microcontroller","authors":"Hoang-The Pham, Minh-Anh Nguyen, Chi-Chia Sun","doi":"10.1109/ISPACS48206.2019.8986357","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986357","url":null,"abstract":"Neural Networks, especially Convolutional Neural Network [1] are becoming increasingly popular in IoT edge devices today for executing data analytics right at the source without transmitting to Cloud Computing centers. So that it will be reduced latency as well as energy consumption for data communication. In this paper, we will compare CMSIS-NN and uTensor: low energy consumption microcontrollers. Most classification tasks have always-on, and real-time requirements, which limits the total number of operations per neural network inference. So that, with image classification model, microcontrollers will execute lower frame per second than GPU and embedded CPU. CMSIS-NN is a collection of efficient kernels which was developed to maximize the performance and minimize the memory footprint of Neural Network applications. Allow deploy machine learning models on ARM Cortex-M processors for intelligent IoT edge devices.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"37 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85665163","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}
Rintaro Yoshii, Yoshiki Tsukamoto, Takuya Takahashi, H. Kubo
{"title":"A Differential Multiple Single Carrier Modulation Scheme for Underwater Acoustic Communications and Its Actual Evaluation Results","authors":"Rintaro Yoshii, Yoshiki Tsukamoto, Takuya Takahashi, H. Kubo","doi":"10.1109/ISPACS48206.2019.8986343","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986343","url":null,"abstract":"This paper discusses actual evaluation results of a differential multiple single carrier (MSC) modulation scheme for underwater acoustic communications (UWACs). UWACs suffer from severe doubly-selective channels and inter-carrier interference due to non-uniform frequency offset. In addition, assuming image data communications, UWACs require improved frequency efficiency. To resolve these issues, this paper proposes a wireless transmission scheme that employs differential MSC modulation scheme. Next, this paper investigates the parameters for 8kbps-UWACs and 64kbps-UWACs aiming at wireless control of autonomous underwater vehicles and image data communications, respectively. Finally, two actual evaluation results in an acoustic experimental pool and an actual shallow-sea environment confirm that the UWAC MODEMs have excellent performance on severe doubly-selective channels.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"38 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86171717","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}
Shoya Oohara, Hirotaka Oka, M. Muneyasu, Soh Yoshida, M. Nakashizuka
{"title":"Image Regularization with Morphological Gradient Priors Using Optimal Structuring Elements for Each Pixel","authors":"Shoya Oohara, Hirotaka Oka, M. Muneyasu, Soh Yoshida, M. Nakashizuka","doi":"10.1109/ISPACS48206.2019.8986309","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986309","url":null,"abstract":"As an image prior for image restoration, the use of the sum of the morphological gradient for an image has been proposed. In this paper, we propose a method of optimizing the structuring element (SE) for each pixel, in particular, by greatly reducing the computational burden for optimization by adopting a new evaluation method for the SE in simulated annealing. By optimizing the SE for each pixel, edges of the image can be faithfully evaluated, and the improvement of restoration accuracy can be expected. An experimental result shows the effectiveness of the proposed method.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"6 3 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76484103","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":"Detection of Dangerous Objects By Pan-tilt Camera","authors":"Yurika Fujii, M. Fukumi, S. Ito, Momoyo Ito","doi":"10.1109/ISPACS48206.2019.8986233","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986233","url":null,"abstract":"Security cameras have increased in public facilities. The number of crimes has decreased by security cameras, but we will have too much data of cameras. In this paper, we have aim of security improvement. First, we search whether there are humans in images by OpenPose. We then obtain position of human's hands. Finally, we detect dangerous objects around the hands by image classification.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"9 2 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89804115","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}
Takahiro Matsumoto, H. Torii, Y. Ida, S. Matsufuji
{"title":"A Generation Method of a Two-Dimensional Optical ZCZ Sequence with the Zero-Correlation Zone (4n – 2) × (4n – 2)","authors":"Takahiro Matsumoto, H. Torii, Y. Ida, S. Matsufuji","doi":"10.1109/ISPACS48206.2019.8986247","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986247","url":null,"abstract":"In this paper, we propose a new generation method of a two-dimensional (2D) optical zero-correlation zone (ZCZ) sequence with the size of ZCZ (4n – 2) × (4n – 2). The 2D optical ZCZ sequence consists of pairs of a binary sequence which takes 1 or 0 and a bi-phase sequence which takes 1 or −1, and has a zero-correlation zone in the two-dimensional correlation function. Because of these properties, the 2D optical ZCZ sequence can be used for optical code-division multiple access (OCDMA) system using an LED array having a plurality of light-emitting elements arranged in a lattice pattern. The OCDMA system using the 2D optical ZCZ sequence can increase the data rate and can suppress interference by the light of adjacent LEDs. By using the proposed generation method, we can improve the peak value of the autocorrelation function of the sequence. This means that the BER performance of the OCDMA system using the sequence can be imnroved.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"156 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74896295","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}
S. Duangsuwan, Anna Chusongsang, C. Teekapakvisit, S. Promwong
{"title":"BER Detection of A2G Wireless Communication in Rician K-Factor Fading Channel for Massive IoT Connectivity Network","authors":"S. Duangsuwan, Anna Chusongsang, C. Teekapakvisit, S. Promwong","doi":"10.1109/ISPACS48206.2019.8986353","DOIUrl":"https://doi.org/10.1109/ISPACS48206.2019.8986353","url":null,"abstract":"In this paper, we present a performance of bit error rate detection in air-to-ground (A2G) wireless communication over Rician K-factor fading channel for massive the internet of things (IoT) connectivity network. The massive IoT connectivity deploys to the cyber-physical system (CPS). We analyze the BER by using the asymptotic simulation of zero-forcing (ZF) and minimum mean square error (MMSE) detection. The system model employs the effect of Rician K-factor channel between the transmitter antenna (drone) and IoT users. Finally, we discuss the performance of BER curves.","PeriodicalId":6765,"journal":{"name":"2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"4 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75913658","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}