Pub Date : 2025-12-04DOI: 10.23919/comex.2025COF0001
IEICE Communications Express (ComEX) has continued to issue a special cluster annually in conjunction with the IEICE General Conferences since 2019. This year's special cluster is based on the papers presented at the IEICE General Conference 2025, which was held at the Setagaya Campus of Tokyo City University in March 2025. Since October 1, 2023, all accepted letters in ComEX have been published in IEEE Xplore to improve the visibility of letters.
{"title":"Special Cluster in Conjunction with IEICE General Conference 2025","authors":"","doi":"10.23919/comex.2025COF0001","DOIUrl":"https://doi.org/10.23919/comex.2025COF0001","url":null,"abstract":"IEICE Communications Express (ComEX) has continued to issue a special cluster annually in conjunction with the IEICE General Conferences since 2019. This year's special cluster is based on the papers presented at the IEICE General Conference 2025, which was held at the Setagaya Campus of Tokyo City University in March 2025. Since October 1, 2023, all accepted letters in ComEX have been published in IEEE Xplore to improve the visibility of letters.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"14 12","pages":"419-419"},"PeriodicalIF":0.3,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11278568","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-14DOI: 10.23919/comex.2025XBL0113
Cho Thet Htar;Takafumi Fujimoto;Chai-Eu Guan
This research proposes a wideband printed MIMO antenna, based on two printed inverted-F antennas introduced by authors in past studies. These antennas are connected by isolation and impedance matching section, comprising a crank element, two L-shaped elements and two small rectangular elements. The detachment structure serves as a radiation element, causing resonance to improve isolation and impedance bandwidth. The measured 2-VSWR bandwidth is approximately 97.9% (2.4 GHz −7.0 GHz) with antenna spacing of $0.125 lambda_{l}$, where $lambda_{l}$ is the wavelength in free space at the lowest frequency. The transmission coefficient in the frequency band is below −17 dB.
{"title":"A Wideband Printed Inverted-F Antenna for MIMO Application","authors":"Cho Thet Htar;Takafumi Fujimoto;Chai-Eu Guan","doi":"10.23919/comex.2025XBL0113","DOIUrl":"https://doi.org/10.23919/comex.2025XBL0113","url":null,"abstract":"This research proposes a wideband printed MIMO antenna, based on two printed inverted-F antennas introduced by authors in past studies. These antennas are connected by isolation and impedance matching section, comprising a crank element, two L-shaped elements and two small rectangular elements. The detachment structure serves as a radiation element, causing resonance to improve isolation and impedance bandwidth. The measured 2-VSWR bandwidth is approximately 97.9% (2.4 GHz −7.0 GHz) with antenna spacing of <tex>$0.125 lambda_{l}$</tex>, where <tex>$lambda_{l}$</tex> is the wavelength in free space at the lowest frequency. The transmission coefficient in the frequency band is below −17 dB.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"15 1","pages":"5-8"},"PeriodicalIF":0.3,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11249779","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145847775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-14DOI: 10.23919/comex.2025XBL0124
Shogo Kurimoto;Hirofumi Suganuma;Fumiaki Maehara
In sixth-generation (6G) mobile communication systems, the development of non-terrestrial networks utilizing low Earth orbit (LEO) satellite communication (SATCOM) is expected to promote connectivity in diverse environments, including mountainous regions and maritime areas. To enhance the capacity of LEO SATCOM, the application of multiuser multiple-input multiple-output has recently garnered significant attention. Conventional studies have mainly evaluated linear precoding (LP) or Tomlinson-Harashima precoding (THP) separately, without exploring adaptive schemes that dynamically switch between them under a wide range of received carrier-to-noise ratio (CNR) conditions peculiar to SAT-COM. We propose a method to maximize system capacity by appropriately selecting between THP and LP based on the received CNR, evaluating its effectiveness through computer simulations. The proposed method was validated by comparing its system capacity performance with those of LP-only and THP-only schemes, demonstrating superior performance across varying CNR conditions.
{"title":"Adaptive Precoding Selection Between LP and THP for Enhanced System Capacity in MU-MIMO-Based LEO SATCOM Systems","authors":"Shogo Kurimoto;Hirofumi Suganuma;Fumiaki Maehara","doi":"10.23919/comex.2025XBL0124","DOIUrl":"https://doi.org/10.23919/comex.2025XBL0124","url":null,"abstract":"In sixth-generation (6G) mobile communication systems, the development of non-terrestrial networks utilizing low Earth orbit (LEO) satellite communication (SATCOM) is expected to promote connectivity in diverse environments, including mountainous regions and maritime areas. To enhance the capacity of LEO SATCOM, the application of multiuser multiple-input multiple-output has recently garnered significant attention. Conventional studies have mainly evaluated linear precoding (LP) or Tomlinson-Harashima precoding (THP) separately, without exploring adaptive schemes that dynamically switch between them under a wide range of received carrier-to-noise ratio (CNR) conditions peculiar to SAT-COM. We propose a method to maximize system capacity by appropriately selecting between THP and LP based on the received CNR, evaluating its effectiveness through computer simulations. The proposed method was validated by comparing its system capacity performance with those of LP-only and THP-only schemes, demonstrating superior performance across varying CNR conditions.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"15 1","pages":"13-16"},"PeriodicalIF":0.3,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11249778","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145847802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-14DOI: 10.23919/comex.2025XBL0074
Mubarak S. Ellis;David Amoako;Elijah Atiigah;Derrick Dompreh;Christian Agyekum;George A. Prah;Kwame O. Gyasi;Kingsford S.O. Kwakye;Abdul R. Ahmed;Jerry J. Kponyo
This research presents a design of a printed monopole antenna that is miniaturized with end-fire radiation, and has high gain. The antenna begins with a rectangular monopole antenna that is split into two sides using a narrow rectangular slot. The ground plane is then connected to one side of the split-radiator using a stub. By doing so, the omnidirectional radiation of the antenna changes to an end-fire radiation. Hence, a low gain unidirectional radiation is realized. The gain performance is enhanced by placing a parasitic conductor next to the other split radiator. The peak gain is more than doubled this way. Measurements show that the antenna has an S11 < −10 dB bandwidth of 2.38 – 6.35 GHz (90.9%) and a good front - to - back ratio (F/B) > 10dB across this band. The antenna has a small physical size of 20×35 mm2, 0.04λ02 miniature area, 10 dBi peak gain, and stable main beam directions. It doesn't have reflective structures and ground plane extensions, making it compact and easily implemented.
{"title":"A Miniaturized Shorted Radiator-Ground Monopole Antenna with High Gain End-Fire Radiation Pattern","authors":"Mubarak S. Ellis;David Amoako;Elijah Atiigah;Derrick Dompreh;Christian Agyekum;George A. Prah;Kwame O. Gyasi;Kingsford S.O. Kwakye;Abdul R. Ahmed;Jerry J. Kponyo","doi":"10.23919/comex.2025XBL0074","DOIUrl":"https://doi.org/10.23919/comex.2025XBL0074","url":null,"abstract":"This research presents a design of a printed monopole antenna that is miniaturized with end-fire radiation, and has high gain. The antenna begins with a rectangular monopole antenna that is split into two sides using a narrow rectangular slot. The ground plane is then connected to one side of the split-radiator using a stub. By doing so, the omnidirectional radiation of the antenna changes to an end-fire radiation. Hence, a low gain unidirectional radiation is realized. The gain performance is enhanced by placing a parasitic conductor next to the other split radiator. The peak gain is more than doubled this way. Measurements show that the antenna has an S<inf>11</inf> < −10 dB bandwidth of 2.38 – 6.35 GHz (90.9%) and a good front - to - back ratio (F/B) > 10dB across this band. The antenna has a small physical size of 20×35 mm<sup>2</sup>, 0.04λ0<sup>2</sup> miniature area, 10 dBi peak gain, and stable main beam directions. It doesn't have reflective structures and ground plane extensions, making it compact and easily implemented.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"15 1","pages":"17-20"},"PeriodicalIF":0.3,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11249777","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145847840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, the Internet of Things (IoT) has been increasingly deployed in various domains. Message Queuing Telemetry Transport (MQTT), which features low overhead, has been adopted as a communication protocol for IoT to replace conventional HTTP. MQTT is a representative protocol of the publish/subscribe (Pub/Sub) communication model and enables high-speed, low-latency data transmission. However, in wireless environments, transmission errors and handovers may cause packet loss, thereby degrading the communication quality. This paper investigates the impact of such wireless transmission impairments on IoT communications in mobile environments using the Gilbert-Elliott model, a well-known model for characterizing bursty transmission errors in wireless channels.
{"title":"Analysis of Performance on MQTT Over Wireless Transmission Link","authors":"Ayumu Ito;Atsuko Yokotani;Koichi Ishibasi;Tetsuya Yokotani","doi":"10.23919/comex.2025COL0007","DOIUrl":"https://doi.org/10.23919/comex.2025COL0007","url":null,"abstract":"In recent years, the Internet of Things (IoT) has been increasingly deployed in various domains. Message Queuing Telemetry Transport (MQTT), which features low overhead, has been adopted as a communication protocol for IoT to replace conventional HTTP. MQTT is a representative protocol of the publish/subscribe (Pub/Sub) communication model and enables high-speed, low-latency data transmission. However, in wireless environments, transmission errors and handovers may cause packet loss, thereby degrading the communication quality. This paper investigates the impact of such wireless transmission impairments on IoT communications in mobile environments using the Gilbert-Elliott model, a well-known model for characterizing bursty transmission errors in wireless channels.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"14 12","pages":"453-456"},"PeriodicalIF":0.3,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11249781","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-14DOI: 10.23919/comex.2025XBL0122
Ke Peng;Qiang Chen
This letter addresses the performance degradation of reflectarrays (RAs) in practical operation due to aperiodic arrangement and mutual coupling between units, and proposes a reflection-coefficient extraction method based on the mean scattered electric field obtained from full-wave simulations. The method can accurately quantify the impact of an aperiodic environment on the amplitude and phase of the reflection coefficient at the scale of a single RA unit, while avoiding the modeling bias introduced by the conventional periodic-environment assumption. A 3×3 unit model is established to systematically analyze the influence of various environment-unit states on the reflection coefficient of the central unit. Furthermore, in a 20×20 1-bit RA design example, the proposed approach is integrated with a simulated-annealing algorithm to optimize the unit-size distribution, achieving a gain improvement of approximately 2 dB. The results demonstrate that the aperiodic arrangement effect is not only a potential source of performance degradation but can also be transformed into a usable design degree of freedom in optimization, thereby providing a new method and perspective for high-accuracy RA modeling and performance enhancement.
{"title":"Reflection-Coefficient Extraction and Gain Enhancement of Reflectarrays Under Aperiodic Arrangement","authors":"Ke Peng;Qiang Chen","doi":"10.23919/comex.2025XBL0122","DOIUrl":"https://doi.org/10.23919/comex.2025XBL0122","url":null,"abstract":"This letter addresses the performance degradation of reflectarrays (RAs) in practical operation due to aperiodic arrangement and mutual coupling between units, and proposes a reflection-coefficient extraction method based on the mean scattered electric field obtained from full-wave simulations. The method can accurately quantify the impact of an aperiodic environment on the amplitude and phase of the reflection coefficient at the scale of a single RA unit, while avoiding the modeling bias introduced by the conventional periodic-environment assumption. A 3×3 unit model is established to systematically analyze the influence of various environment-unit states on the reflection coefficient of the central unit. Furthermore, in a 20×20 1-bit RA design example, the proposed approach is integrated with a simulated-annealing algorithm to optimize the unit-size distribution, achieving a gain improvement of approximately 2 dB. The results demonstrate that the aperiodic arrangement effect is not only a potential source of performance degradation but can also be transformed into a usable design degree of freedom in optimization, thereby providing a new method and perspective for high-accuracy RA modeling and performance enhancement.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"15 1","pages":"9-12"},"PeriodicalIF":0.3,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11249782","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145847819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-14DOI: 10.23919/comex.2025COL0012
Tomohiro Ishida;Nozomi Okada;Toshiyuki Nishibori
This study obtained the far-field radiation pattern of a reflector antenna from the near-field amplitude distribution using the Phase Retrieval (PR) method in the plane perpendicular to the axis tilted from the optical axis. The PR method usually uses the near-field amplitude distribution in the plane perpendicular to the optical axis of the antenna. However, due to the design of the measurement system and antenna, the measurements had to be made in a plane perpendicular to an axis tilted from the optical axis. Since the literature has not reported such cases, this study investigated the determination of phase retrieval from the near-field amplitude distribution in a tilted plane by simulation.
{"title":"Phase Retrieval Method Under Tilted Near-Field Conditions in 480 GHz Band","authors":"Tomohiro Ishida;Nozomi Okada;Toshiyuki Nishibori","doi":"10.23919/comex.2025COL0012","DOIUrl":"https://doi.org/10.23919/comex.2025COL0012","url":null,"abstract":"This study obtained the far-field radiation pattern of a reflector antenna from the near-field amplitude distribution using the Phase Retrieval (PR) method in the plane perpendicular to the axis tilted from the optical axis. The PR method usually uses the near-field amplitude distribution in the plane perpendicular to the optical axis of the antenna. However, due to the design of the measurement system and antenna, the measurements had to be made in a plane perpendicular to an axis tilted from the optical axis. Since the literature has not reported such cases, this study investigated the determination of phase retrieval from the near-field amplitude distribution in a tilted plane by simulation.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"14 12","pages":"457-459"},"PeriodicalIF":0.3,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11249780","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-13DOI: 10.23919/comex.2025XBL0101
Fumiyuki Adachi;Ryo Takahashi
In this paper, we derive analytical expressions for the cumulative distribution function (CDF) of channel capacity achievable by suboptimal joint transmit-receive diversity (JTRD) for perfectly correlated and uncor-related fading cases in a strongly asymmetric MIMO channel. The derived CDF of channel capacity is validated by Monte-Carlo numerical computation. It is confirmed that in a strongly asymmetric MIMO channel, the fading correlation has a favorable impact on suboptimal JTRD based on maximal-ratio diversity (MRD), while it only slightly degrades suboptimal JTRD based on selection diversity (SD). The fading correlation has also a favorable impact on optimal JTRD, which is confirmed by investigating the behavior of eigenmode transmission by using Monte-Carlo numerical computation.
{"title":"Further Investigation of Impact of Fading Correlation on Joint Transmit-Receive Diversity","authors":"Fumiyuki Adachi;Ryo Takahashi","doi":"10.23919/comex.2025XBL0101","DOIUrl":"https://doi.org/10.23919/comex.2025XBL0101","url":null,"abstract":"In this paper, we derive analytical expressions for the cumulative distribution function (CDF) of channel capacity achievable by suboptimal joint transmit-receive diversity (JTRD) for perfectly correlated and uncor-related fading cases in a strongly asymmetric MIMO channel. The derived CDF of channel capacity is validated by Monte-Carlo numerical computation. It is confirmed that in a strongly asymmetric MIMO channel, the fading correlation has a favorable impact on suboptimal JTRD based on maximal-ratio diversity (MRD), while it only slightly degrades suboptimal JTRD based on selection diversity (SD). The fading correlation has also a favorable impact on optimal JTRD, which is confirmed by investigating the behavior of eigenmode transmission by using Monte-Carlo numerical computation.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"14 12","pages":"460-463"},"PeriodicalIF":0.3,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11202644","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Image overlay uplink screen camera communication consists of a small screen with LED backlight modulation and a rolling shutter telephoto camera. In a previous study on symbol synchronization, object detection deep neural network (DNN) detected the screen, and autocorrelation detected the preamble separately. However, both object detection DNN and autocorrelation can detect the preamble. First, in this study, object detection DNN detects the screen and preamble. Next, autocorrelation precisely detects the preamble assisted with object detection DNN, improving the efficiency and accuracy of preamble detection. Also, preamble pattern suitable for object detection DNN is revealed.
{"title":"DNN-Assisted Autocorrelation-Based Preamble Detection for Symbol Synchronization of Image Overlay Screen Camera Communication","authors":"Wataru Chujo;Keima Takechi;Hayate Ohtani;Kentaro Kobayashi","doi":"10.23919/comex.2025XBL0116","DOIUrl":"https://doi.org/10.23919/comex.2025XBL0116","url":null,"abstract":"Image overlay uplink screen camera communication consists of a small screen with LED backlight modulation and a rolling shutter telephoto camera. In a previous study on symbol synchronization, object detection deep neural network (DNN) detected the screen, and autocorrelation detected the preamble separately. However, both object detection DNN and autocorrelation can detect the preamble. First, in this study, object detection DNN detects the screen and preamble. Next, autocorrelation precisely detects the preamble assisted with object detection DNN, improving the efficiency and accuracy of preamble detection. Also, preamble pattern suitable for object detection DNN is revealed.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"14 12","pages":"481-485"},"PeriodicalIF":0.3,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11202646","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-13DOI: 10.23919/comex.2025XBL0088
Tsung-Cheng Wu
This study applies Bayesian learning techniques, specifically Variational Inference (VI) and Monte Carlo Dropout (MC Dropout) to Automatic Modulation Classification (AMC). Both methods are built upon a Convolutional Neural Network (CNN) framework and are capable of detecting certain out-of-domain (OOD) modulations through threshold-based decision making. The results indicate that the confidence scores assigned to OOD modulations are influenced by their proximity to the trained indomain classes. Higher confidence scores are typically observed for modulation types that closely resemble known modulation classes. This approach enables effective classification by training only on essential modulation types, thereby reducing the need for exhaustive class coverage and supporting the constraints of edge computing environments.
{"title":"Automatic Modulation Classification based on Bayesian Learning","authors":"Tsung-Cheng Wu","doi":"10.23919/comex.2025XBL0088","DOIUrl":"https://doi.org/10.23919/comex.2025XBL0088","url":null,"abstract":"This study applies Bayesian learning techniques, specifically Variational Inference (VI) and Monte Carlo Dropout (MC Dropout) to Automatic Modulation Classification (AMC). Both methods are built upon a Convolutional Neural Network (CNN) framework and are capable of detecting certain out-of-domain (OOD) modulations through threshold-based decision making. The results indicate that the confidence scores assigned to OOD modulations are influenced by their proximity to the trained indomain classes. Higher confidence scores are typically observed for modulation types that closely resemble known modulation classes. This approach enables effective classification by training only on essential modulation types, thereby reducing the need for exhaustive class coverage and supporting the constraints of edge computing environments.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"14 12","pages":"477-480"},"PeriodicalIF":0.3,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11202647","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}