检索结果-南通市图书馆

When AI meets sustainable 6G

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science China(information sciences) 2025年第1期 4-22页

作者： Xiaohu YOU Yongming HUANG Cheng ZHANG Jiaheng WANG Hao YIN Hequan WU National Mobile Communications Research Laboratory Southeast University Purple Mountain laboratories Chinese Academy of Military science China information Communication Technologies Group

Sixth-generation(6G) networks are anticipated to achieve transformative advancements, characterized by extreme connectivity, deep integration with artificial intelligence(AI) and sensing, and airground integration. The evolution of 6G exhibits two major trends: ubiquitous intelligence and sustainability. The former aims to embed state-of-the-art AI technology into the 6G network, from the physical layers to applications, while the latter emphasizes reducing energy consumption while enhancing network performance to address environmental concerns. Despite the amazing progress in recent years, AI advancements come with substantial increases in data and computational overhead, posing critical challenges for integrating AI into sustainable 6G networks. First, high energy consumption from large datasets and heavyweight AI models contradicts6G's green goals. Second, the precise collection of large datasets, message delivery latency, and inference delays in AI models pose challenges for real-time tasks in 6G. Third, the uninterpretability and unpredictability of AI models complicate meeting the stringent requirements for controllable transmission in dynamic wireless environments. Addressing these challenges and achieving sustainable 6G with ubiquitous intelligence calls for a revolutionary design of 6G architecture and AI frameworks. To this end, this paper introduces a novel and practical methodology for green, real-time, and controllable 6G native intelligence,starting with knowledge graph(KG) analysis to extract small but critical datasets, followed by the development of distributed lightweight AI models, and the use of digital twins(DTs) to create precise replicas of physical 6G networks. This leads to a pervasive multi-level(PML)-AI framework supported by a task-centric, three-layer 6G architecture. The AI framework operates through non-real-time and real-time cycles, leveraging three key technologies: wireless data KGs for efficient data management,lightweight AI mode

关键词：

A Novel Self-Supervised Learning Network for Binocular Disparity Estimation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & sciences 2025年第1期142卷 209-229页

作者： Jiawei Tian Yu Zhou Xiaobing Chen Salman A.AlQahtani Hongrong Chen Bo Yang Siyu Lu Wenfeng Zheng Department of Computer science and Engineering Major in Bio Artificial IntelligenceHanyang UniversityAnsan-si15577Republic of Korea School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA 70803USA Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11574Saudi Arabia School of Automation University of Electronic Science and Technology of ChinaChengdu610054China

Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical *** study proposes a novel end-to-end disparity estimation model to address these *** approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting *** study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and *** model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video *** results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing ***,the model exhibited faster convergence during training,contributing to overall performance *** study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.

关键词： Parallax estimation parallax regression model self-supervised learning Pseudo-Siamese neural network pyramid dilated convolution binocular disparity estimation

An Introduction to the Chinese Speech Recognition Front-End of the NICT/atr Multi-Lingual Speech Translation System

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua science and Technology 2008年第4期13卷 545-552页

作者：张劲松 Takatoshi Jitsuhiro Hirofumi Yamamoto 胡新辉 Satoshi Nakamura Knowledge Creating Communication Research Center National Institute of Information and Communications Technology 2-2-2 Keihanna Science City Kyoto 619-0288 Japan ATR Spoken Language Translation Research Laboratories 2-2-2 Keihanna Science City Kyoto 619-0288 Japan atr Knowledge science laboratories 2-2-2 Keihanna Science City Kyoto 619-0288 Japan Knowledge Creating Communication Research Center National Institute of Information and Communications Technology 2-2-2 Keihanna Science City Kyoto 619-0288 Japan

This paper introduces several important features of the Chinese large vocabulary continuous speech recognition system in the NICT/atr multi-lingual speech-to-speech translation system. The features include：（1） a flexible way to derive an information rich phoneme set based on mutual information between a text corpus and its phoneme set; （2） a hidden Markov network acoustic model and a successive state splitting algorithm to generate its model topology based on a minimum description length criterion; and （3） advanced language modeling using multi-class composite N-grams. These features allow a recognition performance of 90% character accuracy in tourism related dialogue with a real time response speed.

关键词： Chinese speech recognition mutual information phoneme set design hidden Markov network minimum description length successive state splitting multi-class composite N-grams

A K-/Ka-band planar shared-aperture beam-scanning array with a high-isolation for the emerging mm-Wave shared-aperture terminals

在线全文

学校读者我要写书评

暂无评论

science China(information sciences) 2023年第5期66卷 257-270页

作者： Zi-Jun GUO Zhang-Cheng HAO Zhuo-Wei MIAO Hao-Yu YIN Chen-Yu DING Hao-Jie GANG State Key Laboratory of Millimeter Waves School of Information Science and Engineering Southeast University Purple Mountain laboratories

A planar K-/Ka-band shared-aperture array with the steerable beam is proposed in this paper. The substrate-integrated coaxial line(SICL)-excited short-circuited-stub-loaded longitudinal slot and substrate-integrated double line(SIDL)-excited slot-loaded patches are employed to radiate K-/Ka-band waves, respectively. Then, to constitute the 1-D K-/Ka-band arrays, the center-fed SICL feed network and SIDL-based full diferential feed network are introduced to widen the bandwidth. Finally, the GCPW-toSICL and GCPW-to-SIW transitions are adopted to excite the proposed array, respectively. Both SICL and SIDL feed networks are located below the radiating aperture. Those arrays are interleaved and shared the same radiation aperture, as well as the shielding metallic-via-array for achieving a compact footprint. To excite the above radiating elements, the SICL center feed network and fully diferential feed network are introduced to widen the bandwidth. The channel isolation is improved by utilizing the fully diferential feed network and the filtering response of the SIW. Equivalent circuits are proposed for designing the proposed antenna. Thanks to the miniaturized geometries of K-/Ka-band arrays, the proposed antenna is able to scan up to 60? and 35? at K-/Ka-band, respectively. As an example, a shared-aperture array with a steerable beam is developed and fabricated by using a multilayer printed circuited board with the designed frequencies of 19 GHz(17.7–20.2 GHz) and 29 GHz(27.5–30 GHz). The aperture dimension of the array antenna is49.6 mm×40.75 mm. A good consistency between the simulation and measurement is acquired. The measured peak gains in K-/Ka-band are 16.6 and 17.6 d Bi. When the radiation beam points to 0?, the 3-d B gain bandwidth at K-band is 14.9%(17.4–20.2 GHz), while the 3 d B gain bandwidth at Ka-band covers from 27.6to 30.4 GHz, i.e., a bandwidth of 9.7%. When the radiation beams are deflected to 60? and 35?, the measured gains of the proposed antenna flu

关键词： shared-aperture high isolation beam-scanning substrate-integrated coaxial line substrate-integrated double line

NICT/atr Chinese-Japanese-English Speech-to-Speech Translation System

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua science and Technology 2008年第4期13卷 540-544页

作者： Tohru Shimizu Yutaka Ashikari Eiichiro Sumita 张劲松 Satoshi Nakamura Knowledge Creating Communication Research Center National Institute of Information and Communications Technology ATR Spoken Language Translation Research Laboratories 2-2-2 Keihanna Science City Kyoto 619-0288 Japan

This paper describes the latest version of the Chinese-Japanese-English handheld speech-tospeech translation system developed by NICT/atr, which is now ready to be deployed for travelers. With the entire speech-to-speech translation function being implemented into one terminal, it realizes real-time, location-free speech-to-speech translation. A new noise-suppression technique notably improves the speech recognition performance. Corpus-based approaches of speech recognition, machine translation, and speech synthesis enable coverage of a wide variety of topics and portability to other languages. Test results show that the character accuracy of speech recognition is 82%-94% for Chinese speech, with a bilingual evaluation understudy score of machine translation is 0.55-0.74 for Chinese-Japanese and Chinese-English

关键词： speech-to-speech translation speech recognition speech synthesis machine translation large-scale corpus

Searching a Polygonal Region by Two Guards

在线全文

学校读者我要写书评

暂无评论

Journal of Computer science & Technology 2008年第5期23卷 728-739页

作者：谭学厚蒋波 School of High-Technology for human Welfare Tokai University School of information science and Technology Dalian Maritime University

We study the problem of searching for a mobile intruder in a polygonal region P by two guards. The objective is to decide whether there should exist a search schedule for the two guards to detect the intruder, no matter how fast the intruder moves, and if so, generate a search schedule. During the search, the two guards are required to walk on the boundary of P continuously and be mutually visible all the time. We present a characterization of the class of polygons searchable by two guards in terms of non-redundant components, and thus solve a long-standing open problem in computational geometry. Also, we give an optimal O（n） time algorithm to determine the two-guard searchability in a polygon, and an O（n log n ＋ m） time algorithm to generate a search schedule, if it exists, where n is the number of vertices of P and m （≤ n^2） is the number of search instructions reported.

关键词： computational geometry robotics visibility polygon search problem two-guard problem

All-van der Waals stacking ferroelectric field-effect transistor based on In2Se3 for high-density memory

在线全文

学校读者我要写书评

暂无评论

science China(information sciences) 2023年第8期66卷 203-210页

作者： Xiaojie WANG Zeyang FENG Jingwei CAI Hao TONG Xiangshui MIAO Wuhan National Laboratory for Optoelectronics School of Optical and Electronic InformationHuazhong University of Science and Technology Hubei Yangtze Memory laboratories

High-density integration of ferroelectric field-effect transistors(Fe FETs) is hindered by factors such as interfacial states, short-channel effects, and ferroelectricity degradation in ultrathin films. Accordingly, the introduction of two-dimensional(2D) materials could effectively solve these problems. However,most current studies focus on the replacement of Si-based channels with 2D channels. Little progress has been made in addressing issues caused by bulk-phase ferroelectric gate layers, such as the unavoidable rough interfaces and the fading of ferroelectricity in ultrathin films. Herein, the 2D ferroelectric material In2Se3is introduced as the gate dielectric. Combined with 2D insulating h-BN and 2D channel Mo S2, an all-van der Waals(vd W) stacking Fe FET is fabricated to provide a straight solution for the abovementioned ***, the robust ferroelectric phase of In2Se3is verified in an ultrathin film case and a high-temperature case, which is outstanding among recently reported 2D ferroelectrics. Second, device-level out-of-plane ferroelectric polarization switching is achieved in the cross-structure device. Based on these results, In2Se3is adopted as the ferroelectric gate dielectric to fabricate all-vd W stacking Fe FETs. The subsequent transistor performance measurement on the fabricated Fe FETs indicates that the ferroelectric polarization of the In2Se3layer plays a dominating role in forming a counterclockwise hysteresis loop. Further pulse response measurements manifest the feasibility of nonvolatile channel conductance tuning of these devices with a proper pulse design. Our findings suggest that In2Se3is a suitable 2D ferroelectric gate material and that all-vd W stacking Fe FETs based on 2D ferroelectrics are promising in the application of high-density memory.

关键词： high-density memory ferroelectric field-effecttransistors two-dimensional ferroelectrics van der Waals In$_{2}$Se$_{3}$

W-band CMOS beamforming ICs and integrated phased-array antennas with 20+ Gb/s data rates

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science China(information sciences) 2024年第11期67卷 300-316页

作者： Dixian ZHAO Peigen YU Shan JIANG Weihan GAO Pingyang HE Huiqi LIU School of information science and Engineering Southeast University Purple Mountain laboratories Chengdu Xphased Technology Co. Ltd.

This article presents the design and implementation of W-band transmitter(TX) and receiver(RX) phased-array antennas, which leverage CMOS and printed circuit board(PCB) technologies to integrate the phased-array antennas with eight-channel beamforming ICs. The beamforming IC applies the variable gain amplifier(VGA) with fractional bits and the vector-modulated variable gain phase shifter(VGPS) for wide range and high precision of gain and phase shifting, providing moderate power gain. The phased-array board consists of 384 TX and 384 RX antenna elements, along with 48 TX and 48 RX beamforming *** also incorporates Wilkinson power dividers/combiners, a power management system, and a beamforming control module, all integrated into a cost-effective multi-layer PCB. Fabricated in 65-nm bulk CMOS, the IC achieves 3° RMS phase error for phase shifting and 0.5 d B RMS gain error for gain shifting, ensuring high precision of antenna pointing. The over-the-air(OTA) measurement of the proposed W-band phased-array antennas achieves a 64-QAM constellation with a symbol rate of 3.5 GS/s, resulting in raw data rates of21 Gb/s.

关键词： W-band phased array CMOS Gigabit wireless link antenna on PCB

Performance assisted enhancement based on change point detection and Kalman filtering

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Central South University 2013年第12期20卷 3528-3535页

作者：任孝平王健薛志超谷明琴 Division of Mechanics and Acoustics National Institute of Metrology Faculty of human Biology University of Copenhagen science & Research laboratories of Mychery

A performance assisted enhancement Kalman filtering algorithm(PAE-KF) for GPS/INS integration navigation in urban areas was presented in this work. The aim of this PAE-KF algorithm was to prevent "deep contamination" caused by error GPS data. This filtering algorithm effectively combined fault estimation of raw GPS data and nonholonomic constraint of vehicle. In fault estimation, a change point detection algorithm based on abrupt change model was proposed. Statistical tool was then used to infer the future bound of GPS data, which can detect faults in GPS raw data. If any kinds of faults were detected, dead reckoning mechanism begins to compute current position. Nonholonomic constraint condition of vehicle was used to estimate velocity of vehicle and change point detection was added into classic Kalman filtering structure. Experiment on vehicle shows that even when the GPS signals are unavailable for a period of time, this method can also output high accuracy data.

关键词： change point detection Kalman filtering nonholonomic constraint GPS/INS integrated navigation system