Papers - ICHIGE Koichi
about 108-
2-Step robust DNN model for RSSI-based indoor localization
Kosaka, T; Wandale, S; Ichige, K
IEICE Communications Express 13 ( 12 ) 513 - 516 2024.12 [Reviewed]
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>In this paper, we introduce a novel approach called the 2-Step Robust Deep Neural Network (DNN), designed specifically for indoor localization utilizing received signal strength indicator (RSSI) data. This method represents an advancement over the previously proposed 2-Step Extreme Gradient Boosting (XGBoost), aiming to enhance estimation precision by leveraging a single coordinate (<i>x</i> or <i>y</i>) as a feature. The pivotal alterations involve transitioning from XGBoost to DNN and refining the training data to develop a resilient learning model for positional coordinates. Through comprehensive simulations, we demonstrate that the proposed 2-Step Robust DNN attains superior estimation accuracy while preserving the absence of constraints on the dataset.</p>
-
An Edge-Enhanced Branch for Multi-Frame Motion Deblurring
Moriyama, S; Ichige, K
IEEE Access 12 156929 - 156938 2024.11 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Video Reflection Removal by Modified EDVR and 3D Convolution
S. Moriyama, K. Ichige, Y. Hori, M.Tachi
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E107A ( 8 ) 1430 - 1434 2024.8 [Reviewed]
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>In this paper, we propose a method for video reflection removal using a video restoration framework with enhanced deformable networks (EDVR). We examine the effect of each module in EDVR on video reflection removal and modify the models using 3D convolutions. The performance of each modified model is evaluated in terms of the RMSE between the structural similarity (SSIM) and the smoothed SSIM representing temporal consistency.</p>
-
Millimeter-Wave Radar-Based Vehicle In-Cabin Occupancy Detection Using Explainable Machine Learning
K. Sato, S. Wandale, K. Ichige, K. Kimura, R. Sugiura
IEEE Sensors Journal 24 ( 15 ) 24288 - 24298 2024.8 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Versatile Dataset Generation System for Hand Gesture Recognition Utilizing FMCW-MIMO Radar
K. Kashiwagi, K. Ichige
IEEE Transactions on Radar Systems 2 561 - 572 2024.5 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Single Work
Other Link: https://ieeexplore.ieee.org/document/10541921/
-
Investigation of the Use of Map Images for Stochastic Path Loss Estimation Model
HAGIWARA Rento, ICHIGE Koichi, NAGAO Tatsuya, HAYASHI Takahiro
J107-B ( 3 ) 146 - 154 2024.3 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
In recent years, many path loss estimation models using machine learning have been proposed, but in many cases, high generalization performance has not been achieved. In this paper, we propose a method of feature extraction from images using the Hough transform for path loss estimation to create highly accurate models. By comparing the performance of this method and the conventional method using CNN, we consider effective feature extraction methods.
-
RSSI-based indoor localization using two-step XGBoost
Kosaka, T; Wandale, S; Ichige, K
IEICE Communications Express 12 ( 12 ) 647 - 650 2023.12 [Reviewed]
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>In this letter, we propose a Received Signal Strength Indicator (RSSI)-based indoor localization method using two-step extreme gradient boosting (XGBoost). The proposed two-step XGBoost leverages one of the location coordinates (<i>x</i> or <i>y</i>) as a feature to enhance the estimation accuracy. Simulation examples confirm that the proposed two-step XGBoost approach could improve the estimation accuracy while maintaining low computational complexity.</p>
-
Transformer Model Preprocessing and Loss Function Improvement for Accurate ECG Waveform Reconstruction
ANZAI Ren, ICHIGE Koichi
J106-B ( 11 ) 756 - 759 2023.11 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
In this paper, we propose a method of ECG (ElectroCardioGram) signal reconstruction using a transformer, which is a kind of deep learning model. By improving the loss function and preprocessing of the transformer model, we propose a method that can reconstruct the signal even under the condition of high amplitude noise, which has been a problem in conventional methods.
-
xMISC: Improved Sparse Linear Array via Maximum Inter-Element Spacing Concept
Steven Wandale, Koichi Ichige
IEEE Signal Processing Letters 30 1327 - 1331 2023.9 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Low-Cost Learning-Based Path Loss Estimation Using Correlation Graph CNN
Keita IMAIZUMI, Koichi ICHIGE, Tatsuya NAGAO, Takahiro HAYASHI
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E106.A ( 8 ) 1072 - 1076 2023.8 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
A Deep-Learning Method for Path Loss Prediction Using Geospatial Information and Path Profiles
Takahiro Hayashi, Koichi Ichige
IEEE Transactions on Antennas and Propagation 71 ( 9 ) 7523 - 7537 2023.7 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Depth Estimation from a Single Image Using a Non-Hierarchical Encoder-Decoder Network with Pixel Shuffle
TOYODA Yuma, ICHIGE Koichi
J106-A ( 4 ) 171 - 174 2023.4
Language:Japanese Publishing type:Research paper (scientific journal) Publisher:The Institute of Electronics, Information and Communication Engineers Joint Work
We propose an accurate and lightweight depth estimation method from a single image using non-hierarchical encoder-decoder network with pixel shuffle. Performance of the proposed method is evaluated through simulation.
-
Contactless Biological Sensing and ECG Waveform Reconstruction Using FMCW Radar and Transformer
ANZAI Ren, TODA Daiki, ICHIGE Koichi
J106-B ( 3 ) 208 - 216 2023.3 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
In this paper, we propose a waveform reconstruction method for ECG (ElectroCardioGram) signals using a transformer, a kind of deep learning model, for biological signals acquired by FMCW radar without contact. Although ECG signals are commonly used for heart rate monitoring, they have some disadvantages such as discomfort due to contact with the sensor during measurement. Therefore, a non-contact method using radar is attracted attention. In order to realize a highly accurate ECG waveform reconstruction method, a waveform reconstruction method using CNN (Convolutional Neural Network) and a deep learning method specializing in removing environmental noise from biological signals have been studied. In this paper, we propose a waveform reconstruction method for ECG signals by applying a transformer to the biological signals acquired by the FMCW radar for the purpose of further improving the accuracy. As a result, highly accurate waveform restoration was possible even under conditions where sinusoidal noise was added, confirming the superiority of the transformer-based method.
-
A Generalized Extended Nested Array Design via Maximum Inter-Element Spacing Criterion
Wandale Steven, Ichige Koichi
IEEE SIGNAL PROCESSING LETTERS 30 31 - 35 2023.1 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
ECG Signal Reconstruction Using FMCW Radar and a Convolutional Neural Network for Contactless Vital-sign Sensing
Daiki Toda, Ren Anzai, Koichi Ichige, Ryo SAITO, Daichi UEKI
IEICE Trans. Communications E106-B ( 1 ) 65 - 73 2023.1 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Single Work
-
Flexible Extended Nested Arrays for DOA Estimation: Degrees of Freedom Perspective
Steven Wandale, Koichi Ichige
Signal Processing 201 ( 108710 ) 2022.12 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Single Work
-
Path Loss Estimation Using Spatial Data and Neural Networks
INOUE Kazuya, IMAIZUMI Keita, ICHIGE Koichi, NAGAO Tatsuya, HAYASHI Takahiro
J105-B ( 11 ) 872 - 879 2022.11 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
In this paper, we peopose a path loss estimation method using spatial data and neural networks. The present authors have already proposed some path loss estimation methods, but there were some problems which lead bad estimation accuracy in some difficult situations. We develop a new method which enhances path loss estimation accuracy by reconsidering input data and neural network mode. Performance of the proposed method is evaluated through simulation using the radio propagation channel database provided by IEICE technical committee on antennas and propagation.
-
Low-Light Image Enhancement Using Curve Map Estimation with Multiscale Inputs
SUZUKI Yuma, ICHIGE Koichi
J105-A ( 9 ) 106 - 110 2022.9 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Publisher:The Institute of Electronics, Information and Communication Engineers Joint Work
We propose an accurate low-light image enhancement method using curve map estimation and multiscale input image features. Performance of the proposed method is evaluated through simulation of enhancing low-light images.
-
Characterization of modal interference in multi-core polymer optical fibers and its application to temperature sensing
Toda Kanon, Kishizawa Kazuya, Toyoda Yuma, Noda Kohei, Lee Heeyoung, Nakamura Kentaro, Ichige Koich … Show more authors
Toda Kanon, Kishizawa Kazuya, Toyoda Yuma, Noda Kohei, Lee Heeyoung, Nakamura Kentaro, Ichige Koichi, Mizuno Yosuke Hide authors
APPLIED PHYSICS EXPRESS 15 ( 7 ) 2022.7 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Accurate Source-Number Estimation Using Denoizing Preprocessing and Singular Value Decomposition
Shohei Hamada, Koichi Ichige, Katsuhisa Kashiwagi, Nobuya Arakawa, Ryo Saito
IEICE Transactions on Communications E105-B ( 6 ) 766 - 774 2022.6 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Single Work
-
Learning-Based Prediction Method for Radio Wave Propagation Using Images of Building Maps
Inoue Kazuya, Ichige Koichi, Nagao Tatsuya, Hayashi Takahiro
IEEE ANTENNAS AND WIRELESS PROPAGATION LETTERS 21 ( 1 ) 124 - 128 2022.1 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Adaptive Beamforming by Extension and Phase Restoration of Sparse Array Input Signal
MORIMOTO Shinya, IWAZAKI Sho, ICHIGE Koichi
J104-A ( 12 ) 250 - 257 2021.12 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Publisher:The Institute of Electronics, Information and Communication Engineers Joint Work
In this paper, we propose an adaptive beamforming method for received signals from sparse array antennas and a demodulation method for virtual signals. Previously, it has been confirmed that the direction of arrival (DOA) estimation performance can be improved by using the Khatri-Rao (KR) product expansion process on the received signals of real arrays. However, when virtual signals are used in communication systems that employ digital modulation, the processing in the real array region cannot be directly adopted because of the unique properties of virtual signals. Therefore, in this paper, we propose a beamforming method for the extended virtual signal and try to improve the extended array system by recovering the phase information during the demodulation of the virtual signal. The performance of the proposed array system is evaluated by computational simulation.
-
Simulated Annealing Assisted Sparse Array Selection Utilizing Deep Learning
Wandale Steven, Ichige Koichi
IEEE ACCESS 9 156907 - 156914 2021.11 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Optimization of Microwave Circuit Parameters by CMA-ES Method
Kosuke Hayashi, Koichi Ichige
IEICE Communications Express 10 ( 9 ) 681 - 687 2021.5 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
-
FMCW radar with multiple initial frequencies for robust source number estimation
Saito Ryo, Kashiwagi Katsuhisa, Arakawa Nobuya, Hamada Shohei, Ichige Koichi
IEICE COMMUNICATIONS EXPRESS 10 ( 9 ) 698 - 703 2021.5 [Reviewed]
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>We propose a novel method to estimate source number used in Direction Of Arrival (DOA) estimator for Frequency Modulated Continuous Wave - Multiple-Input Multiple-Output (FMCW-MIMO) radar. The main principle is that the phase of the intermediate signals can be modified by the initial frequency of transmitted signals. We confirmed that our method can distinguish true and spurious sources when the number of sources is larger than the number of true sources.</p>
Other Link: https://ci.nii.ac.jp/naid/130008082843
-
Design of Sparse Arrays via Deep Learning for Enhanced DOA Estimation
Steven Wandale, Koichi Ichige
EURASIP Journal of Advances in Signal Processing 2021 ( 1 ) 17-1 - 17-14 2021.4 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:Springer Joint Work
-
NAKAMURA Shogo, IWAZAKI Sho, ICHIGE Koichi
IEICE Transactions on Communications 104 ( 4 ) 401 - 409 2021.4 [Reviewed]
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>This paper presents a method to optimize 2-D sparse array configurations along with a technique to interpolate holes to accurately estimate the direction of arrival (DOA). Conventional 2-D sparse arrays are often defined using a closed-form representation and have the property that they can create hole-free difference co-arrays that can estimate DOAs of incident signals that outnumber the physical elements. However, this property restricts the array configuration to a limited structure and results in a significant mutual coupling effect between consecutive sensors. In this paper, we introduce an optimization-based method for designing 2-D sparse arrays that enhances flexibility of array configuration as well as DOA estimation accuracy. We also propose a method to interpolate holes in 2-D co-arrays by nuclear norm minimization (NNM) that permits holes and to extend array aperture to further enhance DOA estimation accuracy. The performance of the proposed optimum arrays is evaluated through numerical examples.</p>
Other Link: https://ci.nii.ac.jp/naid/130008014020
-
Automatic Piano Transcription by CNN Based on Frequency Band Division
TODA Daiki, ICHIGE Koichi
J104-A ( 4 ) 110 - 113 2021.4 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Publisher:The Institute of Electronics, Information and Communication Engineers Joint Work
In this paper, we propose a method for automatic piano transcription using a convolutional neural network (CNN). The piano rolls, which are CNN outputs, are divided into appropriate frequency bands, and the CNNs improve the accuracy of the estimation result.
-
Modified MODE for increasing the maximum number of sources in DOA estimation
Hamada Shohei, Ichige Koichi
IEICE COMMUNICATIONS EXPRESS 10 ( 7 ) 391 - 397 2021.4 [Reviewed]
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>This paper presents a modified version of the method of direction estimation (MODE) that can estimate a greater number of sources than the original MODE. It is well-known that <i>M</i>-element arrays can basically estimate up to (<i>M</i>-1) direction of arrivals (DOAs), whereas MODE can only estimate up to <i>M</i>/2 DOAs because of its error-sensitive computation procedure. We propose a modified version of MODE that can estimate up to (<i>M</i>-1) DOAs. The performance of the proposed method was evaluated through computer simulation.</p>
Other Link: https://ci.nii.ac.jp/naid/130008060771
-
A Multiple-Music Learning Method for Supervised Sound Source Separation Using Bayesian NMF
KUDO Kai, ICHIGE Koichi
J104-A ( 3 ) 106 - 109 2021.3 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Publisher:The Institute of Electronics, Information and Communication Engineers Joint Work
This paper presents a multiple-music learning method using bayesian non-negative matrix factorization (BNMF) for supervised audio source separation. Separation accuracy was improved by using multiple training data and combinatorial optimization.
-
Single Image Haze Removal Using Iterative Ambient Light Estimation with Region Segmentation
ARAKI Yuji, MITA Kentaro, ICHIGE Koichi
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences 104 ( 2 ) 550 - 562 2021.2 [Reviewed]
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>We propose an iterative single-image haze-removal method that first divides images with haze into regions in which haze-removal processing is difficult and then estimates the ambient light. The existing method has a problem wherein it often overestimates the amount of haze in regions where there is a large distance between the location the photograph was taken and the subject of the photograph; this problem prevents the ambient light from being estimated accurately. In particular, it is often difficult to accurately estimate the ambient light of images containing white and sky regions. Processing those regions in the same way as other regions has detrimental results, such as darkness or unnecessary color change. The proposed method divides such regions in advance into multiple small regions, and then, the ambient light is estimated from the small regions in which haze removal is easy to process. We evaluated the proposed method through some simulations, and found that the method achieves better haze reduction accuracy even than the state-of-the art methods based on deep learning.</p>
Other Link: https://ci.nii.ac.jp/naid/130007978990
-
Extended Beamforming by Restored Phase Information of Virtual Array Input Signal
Shinya Morimoto, Sho Iwazaki, Koichi Ichige
Proceedings of the International Symposium on Antennas and Propagation 2021.1 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Robust Source Number Estimation using Annihilating Filter and Downsampling Scheme
Shohei Hamada, Koichi Ichige, Katsuhisa Kashiwagi, Nobuya Arakawa, Ryo Saito
Proceedings of the International Symposium on Antennas and Propagation 2021.1 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
2D Sparse Array Selection via Deep Leaning
Steven Wandale, Koichi Ichige
Proceedings of the International Symposium on Antennas and Propagation 2021.1 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Radio Propagation Prediction Using Neural Network and Building Occupancy Estimation
Kazuya Inoue, Koichi Ichige, Tatsuya Nagao, Takahiro Hayashi
Proceedings of the International Symposium on Antennas and Propagation 2021.1 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Robust Source Number Estimation Based on FMCW Radar with Multiple Initial Frequencies
Ryo Saito, Katsuhisa Kashiwagi, Nobuya Arakawa, Shohei Hamada, Koichi Ichige
Proceedings of the International Symposium on Antennas and Propagation 2021.1 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Accurate Estimation of Analog Circuit Parameters by CMA-ES Method
Kosuke Hayashi, Koichi Ichige
Proceedings of the International Symposium on Antennas and Propagation 2021.1 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Accurate Source-Number Estimation Using Denoising Preprocessing and Singular Value Decomposition
HAMADA Shohei, ICHIGE Koichi, KASHIWAGI Katsuhisa, ARAKAWA Nobuya, SAITO Ryo
IEICE Transactions on Communications advpub ( 0 ) 766 - 774 2021
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>This paper proposes two accurate source-number estimation methods for array antennas and multi-input multi-output radar. Direction of arrival (DOA) estimation is important in high-speed wireless communication and radar imaging. Most representative DOA estimation methods require the source-number information in advance and often fail to estimate DOAs in severe environments such as those having low signal-to-noise ratio or large transmission-power difference. Received signals are often bandlimited or narrowband signals, so the proposed methods first involves denoising preprocessing by removing undesired components then comparing the original and denoised signal information. The performances of the proposed methods were evaluated through computer simulations.</p>
-
A Nested Array Geometry with Enhanced Degrees of Freedom and Hole-Free Difference Coarray
Wandale Steven, Ichige Koichi
29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021) 1905 - 1909 2021
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
Radio propagation prediction using deep neural network and building occupancy estimation
Inoue Kazuya, Ichige Koichi, Nagao Tatsuya, Hayashi Takahiro
IEICE COMMUNICATIONS EXPRESS 9 ( 10 ) 506 - 511 2020.10 [Reviewed]
DOI Web of Science CiNii Research
Language:Japanese Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>In this paper, we propose a radio propagation prediction method using machine learning and building occupancy estimation. There have been learning-based researches using aerial photographs and building occupancy images as spatial information. However, the availability of building occupancy images are often limited to urban areas. We assume the situation that only the aerial photographs are available, and aim to improve radio propagation prediction accuracy by estimating building occupancy images from the given aerial photographs.</p>
Other Link: https://ci.nii.ac.jp/naid/130007921372
-
DOA-Based Weighted Spatial Filter Design for Sum and Difference Composite Co-Array
Iwazaki Sho, Nakamura Shogo, Ichige Koichi
IEICE TRANSACTIONS ON COMMUNICATIONS E103B ( 10 ) 1147 - 1154 2020.10 [Reviewed]
DOI Web of Science CiNii Research
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
<p>This paper presents a weighted spatial filter (WSF) design method based on direction of arrival (DOA) estimates for a novel array configuration called a sum and difference composite co-array. A sum and difference composite co-array is basically a combination of sum and difference co-arrays. Our configuration can realize higher degrees of freedom (DOF) with the sum co-array part at a calculation cost lower than those of the other sparse arrays. To further enhance the robustness of our proposed sum and difference composite co-array we design an optimal beam pattern by WSF based on the information of estimated DOAs. Performance of the proposed system and the DOA estimation accuracy of close-impinging waves are evaluated through computer simulations.</p>
Other Link: https://ci.nii.ac.jp/naid/130007920558
-
CNNおよび畳み込みLSTMを用いた単一画像の反射除去
三田健太郎, 市毛弘
電子情報通信学会論文誌A J103-A ( 9 ) 218 - 221 2020.9 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
Robust Source Number Estimation Based on Denoising Preprocessing
Koichi Ichige, Shohei Hamada, Katsuhisa Kashiwagi, Nobuya Arakawa, Ryo Saito
Proceedings of Sensor Signal Processing for Defence Conference 2020.9 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
畳み込みニューラルネットワークと切断核ノルム最小化による人物の関節位置推定
吉村海, 市毛弘一
電子情報通信学会論文誌A J103-A ( 7 ) 152 - 155 2020.7 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
Extended Beamforming by Optimum 2-D Sparse Arrays
Nakamura Shogo, Iwazaki Sho, Ichige Koichi
IEICE Communications Express 9 ( 6 ) 200 - 206 2020.6 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電子情報通信学会 Joint Work
Other Link: https://ci.nii.ac.jp/naid/130007800685
-
A Note on The Maximum Number of Sources in DOA Estimation by MODE
Shohei Hamada, Koichi Ichige
Proceedings of IEEE Sensor Array and Multichannel Signal Processing Workshop 2020.6 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
On the DOA Estimation Performance of Optimum Arrays Based on Deep Learning
Steven Wandale, Koichi Ichige
Proceedings of IEEE Sensor Array and Multichannel Signal Processing Workshop 2020.6 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Location Estimation Accuracy of Augmented Arrays for Millimeter-Wave FMCW-MIMO Radar
K. Ichige, R. Saito, T. Sugiyama, N. Arakawa, K. Kashiwagi, A. Yuasa
Proceedings of International Radar Conference ( 92 ) 2019.9
Language:English Publishing type:Research paper (international conference proceedings) Publisher:RADAR Joint Work
-
Extended Beamforming by Sum and Difference Composite Co-Array for Real-Valued Signals
Sho IWAZAKI, Koichi ICHIGE
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Vol.E102-A ( 7 ) 918 - 925 2019.7 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEICE Joint Work
-
Optimum 2D Sparse Array and its Interpolation via Nuclear Norm Minimization
Shogo Nakamura, Sho Iwazaki, Koichi Ichige
2019 IEEE International Symposium on Circuits and Systems (ISCAS) 2019.5
Language:English Publishing type:Research paper (research society, symposium materials, etc.) Publisher:IEEE Joint Work
Date of Conference: 26-29 May 2019
Date Added to IEEE Xplore: 01 May 2019
Print ISBN: 978-1-7281-0397-6
Print ISSN: 2158-1525
INSPEC Accession Number: 18815736
DOI: 10.1109/ISCAS.2019.8702741
Publisher: IEEE
Conference Location: Sapporo, Japan, JapanOther Link: https://ieeexplore.ieee.org/abstract/document/8702741
-
Super Nested Sparse Circular Array for High Resolution DOA Estimation
Steven Wandale, Thomas Basikolo, Koichi Ichige
2019 IEEE International Symposium on Circuits and Systems (ISCAS) 2019.5
Language:English Publishing type:Research paper (research society, symposium materials, etc.) Publisher:IEEE Joint Work
Date of Conference: 26-29 May 2019
Date Added to IEEE Xplore: 01 May 2019
Print ISBN: 978-1-7281-0397-6
Print ISSN: 2158-1525
INSPEC Accession Number: 18815515
DOI: 10.1109/ISCAS.2019.8702389
Publisher: IEEE
Conference Location: Sapporo, Japan, JapanOther Link: https://ieeexplore.ieee.org/abstract/document/8702389
-
Phase-Difference Compensation and Nonuniform Pulse Transmission for Accurate Real-Time Moving Object Tracking
Koichi ICHIGE,Nobuya ARAKAWA,Ryo SAITO,Osamu SHIBATA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences E102-A ( 1 ) 211 - 218 2019 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Kawashima Takeo, Ichige Koichi
電気学会論文誌C(電子・情報・システム部門誌) 139 ( 10 ) 1106 - 1112 2019 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:一般社団法人 電気学会 Joint Work
<p>In this paper, we propose novel automatic piano music transcription methods which improve multi-pitch estimation accuracy. The conventional multi-pitch estimation method using low-rank non-negative matrix factorization (LR-NMF) cannot achieve a good accuracy because the method cannot detect true spectrum and analyze nonlinearity in sound. In the proposed method, the nonlinearity is analyzed using the convolutional neural network (CNN) or the convolutional denoising autoencoder (CDAE) as a post processing of LR-NMF. After the processing, we further improve the accuracy by the Hadamard product of the output from LR-NMF and that from CNN or CDAE. The performance of the proposed method is evaluated through computer simulation.</p>
Other Link: https://ci.nii.ac.jp/naid/130007722364
-
Super Nested Sparse Circular Array for High Resolution DOA Estimation
Wandale Steven, Basikolo Thomas, Ichige Koichi
2019 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS) 2019 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
Optimum 2D Sparse Array and Its Interpolation via Nuclear Norm Minimization
Nakamura Shogo, Iwazaki Sho, Ichige Koichi
2019 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS) 2019 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEEE Joint Work
-
Single Image Haze Removal Using Ambient Light Estimation and Region Segmentation
Y. Araki, K. Ichige
Proc. International Symposium Intelligent Signal Processing and Communication Systems (ISPACS) 70 - 75 2018.11
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Automatic Piano Music Transcription using Low Rank NMF and Convolutional Neural Network
T. Kawashima, K. Ichige
Proc. International Symposium Intelligent Signal Processing and Communication Systems (ISPACS) 475 - 480 2018.11
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
An Optimum2D Sparse Array Configuration with Reduced Mutual Coupling
S. Nakamura, S. Iwazaki, K. Ichige
Proc. International Symposium on Antennas and Propagation (ISAP) 617 - 618 2018.10
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Effect of Signal Correlation in FMCW-MIMO Radar with Augmented Array
R. Saito, K. Ichige
Proc. International Symposium on Antennas and Propagation (ISAP) 615 - 616 2018.10
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Nested Circular Array and Its Concentric Extension for Underdetermined Direction of Arrival Estimation
T. Basikolo, K. Ichige, H. Arai
IEICE Transactions on Communications E101-B ( 4 ) 1076 - 1084 2018.4
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
A Novel Mutual Coupling Compensation Method for Underdetermined Direction of Arrival Estimation in Nested Sparse Circular Arrays
T. Basikolo, K. Ichige, H. Arai
IEEE Transactions on Antenna and Propagation 66 ( 2 ) 909 - 917 2018.2
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
A Note on CRLB Formulation for Underdetermined DOA Estimation in Circularly Configured Planar Arrays
Thomas Basikolo, Koichi Ichige, Hiroyuki Arai
IEICE Electronics Express 15 ( 6 ) 20180193 2018 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Underdetermined Direction of Arrival Estimation by Sum and Difference Composite Co-Array
Sho Iwazaki,Koichi Ichige
2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS) 2018 [Reviewed]
Language:English Publishing type:Research paper (international conference proceedings) Joint Work
-
Fast Intra Mode Decision Method Based on Outliers of DCT Coefficients and Neighboring Block Information for H.265/HEVC
Ogata Jun, Ichige Koichi
2018 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS) 2018
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
Extension of Nested Array for Large Aperture and High Degree of Freedom
Y. Iizuka, K. Ichige
IEICE Communication Express 6 ( 6 ) 381 - 386 2017.9 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Fast Intra Mode Decision Algorithm Based on Outliers of DCT Coefficients and Neighboring Block Information for H.265/HEVC
Trans. IEICE Japan A J-100A ( 9 ) 350 - 353 2017.9 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Adaptive Beamforming by Array Antenna via Using Feedback Section
Trans. IEICE Japan A J-100A ( 1 ) 70 - 78 2017.1 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
複数の受信アンテナおよびマルチパス波を利用した屋内位置推定手法
荒川暢哉,市毛弘一
電子情報通信学会ソサイエティ大会講演論文集 ( B-1-152 ) 2016.9 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
屋内における低コスト端末位置推定手法において,複数の受信アンテナおよびマルチパス波を利用することで高精度な推定が可能となることを実証した.
-
クラスタ画像における連続的な構造の再現性を利用したインペインティング手法
村上祐亮,市毛弘一
電子情報通信学会ソサイエティ大会講演論文集 ( A-8-10 ) 2016.9 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
画像の欠損領域情報を復元するインペインティング手法において,クラスタ画像における連続的な構造の再現性を利用した手法を考案した.
-
Optimum Linear Array Geometry with Minimum Redundancy for 2q-th Order Cumulant-Based Array Processing
Y.Iizuka, K.Ichige
Proceedings of IEEE International Workshop on Compressed Sensing Theory and its Applications (Cosera) 198 - 201 2016.9 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Direction of Arrival Estimation for Quasi-Stationary Signals using Nested Circular Array
T.Basikolo, K.Ichige, H.Arai
Proceedings of IEEE International Workshop on Compressed Sensing Theory and its Applications (Cosera) 212 - 216 2016.9 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEEE Joint Work
-
MS-SSIA: Multiple Snapshot Spatial Smoothing with Improved Effective Array Aperture for High-Resolution DOA Estimation
Y. Iizuka, K. Ichige
IEICE Communication Express 5 ( 9 ) 309 - 315 2016.9 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEICE Joint Work
-
Weighted Shooting Method for High-Resolution DOA Estimation Based on Sparse Spectrum Fitting
K.Ichige, N.Yotsueda
Proceedings of European Signal Processing Conference (EUSIPCO) 1068 - 1072 2016.8 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Array Correlation Matrix Element Properties and Their Application to Low-Cost DOA Estimation
K. Ichige, Y. Iwabuchi
IEICE Transactions on Communications E99-B ( 8 ) 1859 - 1866 2016.8 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG Joint Work
We study the correlation matrix element properties in array signal processing and apply them to a Direction-Of-Arrival (DOA) estimation problem of coherent or highly-correlated sources for a Uniform Linear Array (ULA). The proposed algorithm is generally based on the relation between the elements of the array correlation matrix and does not need an eigendecomposition, iteration, or angular peak-search. The performance of the proposed method was evaluated through a computer simulation.
-
Real-Time Moving Object Tracking Using Phase-Difference Compensation and Nonuniform Pulse Transmission
K.Ichige, N.Arakawa, O.Shibata
Proceedings of IEEE International Symposium on Circuits and Systems (ISCAS) 2647 - 2650 2016.5 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEEE Joint Work
-
An Efficient Direction-Of-Arrival Estimation Method for Uniform Rectangular Array Based on Array Covariance Matrix Element Properties
K.Ichige, Y.Iwabuchi
Proceedings of IEEE workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP) 357 - 360 2015.12 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Pyramidal Shaped Array Antenna for 2-D DOA Estimation
Trans. IEICE Japan B J97-B ( 9 ) 752 - 761 2014.9 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
High Resolution 2-D DOA Estimation by Low-Cost Antenna Array Based on Synthesized Covariance Matrix via Antenna Switching
Y. Doi, H. Moriya, K. Ichige, H. Arai, T. Hayashi, H. Matsuno, M. Nakano
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E96-A ( 10 ) 1962 - 1971 2013.10 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG Joint Work
-
Improving Elevation Estimation Accuracy in DOA Estimation: How Planar Arrays Can Be Modified into 3-D Configuration
H. Moriya, K. Ichige, H. Arai, T. Hayashi, H. Matsuno, M. Nakano
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E95-A ( 10 ) 1658 - 1666 2012.10 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG Joint Work
-
Successive Optimization of Zeros of Reflection Characteristics for Automated Microwave Filter Tuning
K. Ichige, Y. Takeuchi, K. Miyamoto, Y. Ebine
NOLTA, IEICE 3 ( 3 ) 375 - 385 2012.7 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Automated Microwave Filter Tuning Based on Successive Optimization of Phase and Amplitude Characteristics
Y. Takeuchi, K. Ichige, K. Miyamoto, Y. Ebine
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E94-A ( 2 ) 617 - 624 2011.2 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG Joint Work
-
Efficient Heterodyne Digital Receiver with Direct RF-to-Digital Conversion for Software Defined Radio
M. Kim, T. Moteki, K. Ichige, H. Arai
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E92-A ( 4 ) 1056 - 1062 2009.4 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Publisher:IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG Joint Work
-
High Resolutuion DOA Estimation Using Unwrapped Phase Information of MUSIC-based Noise Subspace
Kazuhiko Saito, Hiroyuki Arai
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E91-A ( 8 ) 2008.8 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Direction of Arrival Detection System for Radio Source Surveillance of the Cellular System at 900MHz
J91-B ( 5 ) 2008.5 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
The Design of Phoneme Grouping for Coarse Phoneme Recognition
K. Nakadai, R. Sumiya , M. Nakano, K. Ichige, Y. Hirose, H. Tsujino
Lecture Notes in Computer Science 4570 2007.7 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
High Resolutuion DOA Estimation Using Second-Order Differential of MUSIC Spectrum
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E90-A ( 3 ) 546 - 552 2007.3 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Filter Effect on Low-IF Multichannel Receiver: How a Simple Filter Improves Digital Communication Quality
IEICE Transactions on Communications E89-B ( 12 ) 3471 - 3474 2006.12 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Accurate Source Number Detection Using Pre-Estimated Signal Subspace
IEICE Transactions on Communications E89-B ( 12 ) 3257 - 3265 2006.12 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
An Efficient Signed-Power-of-Two Term Allocation for Filter Coefficients in Digital Communication System
IEICE Transactions on Communications E89-B ( 12 ) 3266 - 3268 2006.12 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Hand Shape Analysis and Recognition by Masking and Standardization of Extracted Hand Images
Trans. IEICE Japan D-II J89-D ( 6 ) 1369 - 1378 2006.6 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Experimental Study of Jitter Effect on Digital Downconversion Receiver with Undersampling Scheme
IEICE Transactions on Information and Systems E88-D ( 7 ) 1430 - 1436 2005.7 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Implementation of FPGA Based Fast Unitary MUSIC DOA Estimator
IEICE Transactions on Electronics E87-C ( 9 ) 1485 - 1494 2004.9 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
A DOA Estimation System in 900MHz by T-type Array Antennas
Trans. IEICE Japan B J86-B ( 10 ) 2153 - 2165 2003.10 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
A Fast Algebraic Approach to the Eigenproblems of Correlation Matrices in DOA Estimation
IEICE Transactions on Communications E86-B ( 2 ) 865 - 869 2003.2 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Design of Jacobi EVD processor Based on CORDIC for DOA estimation with MUSIC Algorithm
IEICE Transactions on Communications E85-B ( 12 ) 2648 - 2655 2002.12 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
A Computationally Efficient Algorithm for Exponential B-splines Based on Difference/IIR Filter Approach
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E85-A ( 6 ) 1265 - 1273 2002.6 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
An Efficient Algorithm for Decomposition and Reconstruction of Images by Box Splines
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E84-A ( 8 ) 1883 - 1891 2001.8 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Experiments of DOA Estimation by DBF Array Antenna at 2.6GHz
IEICE Transactions on Communications E84-B ( 7 ) 1871 - 1875 2001.7 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Concept and Evaluation of A 2-D FDTD Formulation Based on Expanded Wave Equation Approach
IEICE Transactions on Electronics E84-C ( 7 ) 981 - 993 2001.7 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
A New Formulation for Discrete Box Splines Reducing Computational Cost and Its Evaluation
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E84-A ( 3 ) 884 - 892 2001.3 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Accurate Estimation of Minimum Filter Length for Optimum FIR Digital Filters
IEEE Transactions on Circuits and Systems II 47 ( 10 ) 1008 - 1016 2000.10 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Schur Stability of Weighted Diamond Polynomials
Trans. IEICE Japan A J82-A ( 3 ) 482 - 486 1999.3 [Reviewed]
Language:Japanese Publishing type:Research paper (scientific journal) Joint Work
-
Properties of the Frequency Transformation Matrices for IIR Digital Filters
EURASIP Signal Processing 71 ( 3 ) 227 - 233 1998.12 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
A Simple Scheme of Decomposing and Reconstructing Continuous-time Signals by B-Splines
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E81-A ( 11 ) 2391 - 2399 1998.11 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
A Simple Discrete Version of B-Splines
International Journal of Systems Science 29 ( 3 ) 335 - 340 1998.3 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
An Approximation for Discrete B-Splines in Time Domain
IEEE Signal Processing Letters 4 ( 3 ) 82 - 84 1997.3 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
An Automatic Design Procedure of IIR Digital Filters from an Analog Low-pass Filter
EURASIP Signal Processing 57 ( 3 ) 223 - 231 1997.3 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work
-
Quadratic Spline Interpolator
International Journal of Systems Science 27 ( 10 ) 977 - 983 1996.10 [Reviewed]
Language:English Publishing type:Research paper (scientific journal) Joint Work