检索结果-南通市图书馆

TP-MobNet: A Two-pass Mobile Network for Low-complexity Classification of Acoustic Scene

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第11期73卷 3291-3303页

作者： Soonshin Seo Junseok Oh Eunsoo Cho Hosung Park Gyujin kim ji-hwan kim NAVER Corporation Seongnam13561Korea Department of Computer Science and Engineering Sogang UniversitySeoul04107Korea

Acoustic scene classification(ASC)is a method of recognizing and classifying environments that employ acoustic *** ASC approaches based on deep learning have been developed,with convolutional neural networks(CNNs)proving to be the most reliable and commonly utilized in ASC systems due to their suitability for constructing lightweight *** using ASC systems in the real world,model complexity and device robustness are essential *** this paper,we propose a two-pass mobile network for low-complexity classification of the acoustic scene,named *** inverse residuals and linear bottlenecks,TPMobNet is based on MobileNetV2,and following mobile blocks,coordinate attention and two-pass fusion approaches are *** log-range dependencies and precise position information in feature maps can be trained via coordinate *** capturing more diverse feature resolutions at the network’s end sides,two-pass fusions can also train ***,the model size is reduced by applying weight quantization to the trained *** adding weight quantization to the trained model,the model size is also *** TAU Urban Acoustic Scenes 2020 Mobile development set was used for all of the *** has been confirmed that the proposed model,with a model size of 219.6 kB,achieves an accuracy of 73.94%.

关键词： Acoustic scene classification low-complexity device robustness two-pass mobile network coordinate attention weight quantization

Subcarrier BD with Cooperative Communication for MIMO-NOMA System

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第9期72卷 5807-5821页

作者： Jung-In Baik ji-hwan kim Beom-Sik Shin ji-Hye Oh Hyoung-Kyu Song Department of Information and Communication Engineering and Convergence for Intelligent DroneSejong UniversitySeoul05006Korea

With the rapid evolution of Internet of things(IoT),many edge devices require simultaneous connection in 5G communication *** afford massive data of IoT devices,multiple input multiple output non-orthogonal multiple access(MIMO-NOMA)method has been considered as a promising ***,there are numerous drawbacks due to error propagation and inter-user ***,proposed scheme aims to improve the reliability of the MIMO-NOMA system with digital beamforming and intracluster cooperative multi point(CoMP)to efficiently support IoT *** the conventional MIMO-NOMA system,user entities are grouped into *** diagonalization(BD)is applied to efficiently eliminate the inter-cluster interference of the MIMO-NOMA ***,since the channel path of the data stream from a single antenna to a single cluster doesn’t hold other cluster’s data,the system can’t fully utilize the selective subcarrier channel *** indicates that there can be better channel paths for a data stream at a certain subcarrier ***,proposed scheme allocates data streams to antennas adaptively considering selective channel ***,intra-cluster CoMP method is adjusted to enhance the reliability of the system in the *** simulation results show that the proposed scheme improves BER and throughput performance compared to the conventional MIMO-NOMA system.

关键词： 5G MIMO-NOMA CoMP BD interference

Language Model Using Differentiable Neural Computer Based on Forget Gate-Based Memory Deallocation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第7期68卷 537-551页

作者： Donghyun Lee Hosung Park Soonshin Seo Changmin kim Hyunsoo Son Gyujin kim ji-hwan kim Department of Computer Science and Engineering Sogang UniversitySeoul04107Korea

A differentiable neural computer(DNC)is analogous to the Von Neumann machine with a neural network controller that interacts with an external memory through an attention *** DNC’s offer a generalized method for task-specific deep learning models and have demonstrated reliability with reasoning *** this study,we apply a DNC to a language model(LM)*** LM task is one of the reasoning problems,because it can predict the next word using the previous word ***,memory deallocation is a problem in DNCs as some information unrelated to the input sequence is not allocated and remains in the external memory,which degrades ***,we propose a forget gatebased memory deallocation(FMD)method,which searches for the minimum value of elements in a forget gate-based retention *** forget gatebased retention vector indicates the retention degree of information stored in each external memory *** experiments,we applied our proposed NTM architecture to LM tasks as a task-specific example and to rescoring for speech recognition as a general-purpose *** LM tasks,we evaluated DNC using the Penn Treebank and enwik8 LM *** it does not yield SOTA results in LM tasks,the FMD method exhibits relatively improved performance compared with DNC in terms of *** the speech recognition rescoring tasks,FMD again showed a relative improvement using the LibriSpeech data in terms of word error rate.

关键词： Forget gate-based memory deallocation differentiable neural computer language model forget gate-based retention vector

Stretchable and colorless freestanding microwire arrays for transparent solar cells with flexibility

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2019年第1期8卷 47-59页

作者： Sung Bum Kang ji-hwan kim Myeong Hoon Jeong Amit Sanger Chan Ul kim Chil-Min kim Kyoung jin Choi Department of Materials Science and Engineering Ulsan National Institute of Science and Technology(UNIST)Ulsan 44919Republic of Korea Department of Emerging Materials Science Daegu Gyeongbuk Institute of Science and Technology(DGIST)Daegu 42988Republic of Korea

Transparent solar cells(TSCs)are emerging devices that combine the advantages of visible transparency and light-toelectricity ***,existing TSCs are based predominantly on organics,dyes,and perovskites;however,the rigidity and color-tinted transparent nature of those devices strongly limit the utility of the resulting TSCs for realworld ***,we demonstrate a flexible,color-neutral,and high-efficiency TSC based on a freestanding form of n-silicon microwires(SiMWs).Flat-tip SiMWs with controllable spacing are fabricated via deep-reactive ion etching and embedded in a freestanding transparent polymer *** light transmittance can be tuned from ~10 to 55% by adjusting the spacing between the *** TSCs,a heterojunction is formed with a p-type polymer in the top portion of the n-type flat-tip *** contact with an indium-doped ZnO film occurs at the bottom,and the side surface has an Al2O3 passivation ***,slanted-tip SiMWs are developed by a novel solventassisted wet etching method to manipulate light ***-difference time-domain simulation revealed that the reflected light from slanted-tip SiMWs helps light-matter interactions in adjacent *** TSC based on the slanted-tip SiMWs demonstrates 8%efficiency at a visible transparency of 10% with *** efficiency is the highest among Si-based TSCs and comparable with that of state-of-the-art neutral-color TSCs based on organic–inorganic hybrid perovskite and ***,unlike others,the stretchable and transparent platform in this study is promising for future TSCs.

关键词： transparent transparency spacing

Long Short-Term Memory Recurrent Neural Network-Based Acoustic Model Using Connectionist Temporal Classification on a Large-Scale Training Corpus

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2017年第9期14卷 23-31页

作者： Donghyun Lee Minkyu Lim Hosung Park Yoseb Kang Jeong-Sik Park Gil-jin Jang ji-hwan kim Department of Computer Science and Engineering Sogang University Department of Information and Communication Engineering Yeungnam University School of Electronics Engineering Kyungpook National University

A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.

关键词： acoustic model connectionisttemporal classification large-scale trainingcorpus long short-term memory recurrentneural network

Hybridization of different types of exceptional points

在线全文

学校读者我要写书评

暂无评论

Photonics Research 2019年第12期7卷 1473-1478页

作者： jiNHYEOK RYU SUNJAE GWAK JAEWON kim HYEON-HYE YU ji-hwan kim ji-WON LEE CHANG-hwan YI CHIL-MIN kim Department of Emerging Materials Science DGISTDaegu 42988South Korea Institut fur Physik Technische Universitat IlmenauD-98693 IlmenauGermany Samsung Electro-Mechanics Suwon 16674South Korea

A large number of different types of second-order non-Hermitian degeneracies called exceptional points(EPs)were found in various physical systems depending on the mechanism of coupling between *** show that these EPs can be hybridized to form higher-order EPs,which preserve the original properties of the initial EPs before *** a demonstration,we hybridize chiral and supermode second-order EPs,where the former and the latter are the results of intra-disk and inter-disk mode coupling in an optical system comprised of two Mie-scale microdisks and one Rayleigh-scale *** high sensitivity of the resulting third-order EP against external perturbations in our feasible system is emphasized.

关键词： exceptional coupling system

Impact of non-Hermitian mode interaction on inter-cavity light transfer

在线全文

学校读者我要写书评

暂无评论

Photonics Research 2022年第5期10卷 1232-1237页

作者： HYEON-HYE YU SUNJAE GWAK jiNHYEOK RYU HYUNDONG kim ji-hwan kim JUNG WAN RYU CHIL-MIN kim CHANG hwan YI Department of Emerging Materials Science DGISTDaegu 42988Republic of Korea Center for Theoretical Physics of Complex Systems Institute for Basic Science(IBS)Daejeon 34126Republic of Korea

Understanding inter-site mutual mode interaction in coupled physical systems is essential to comprehend large compound systems,as this local interaction determines the successive multiple inter-site energy transfer *** the present study,we demonstrate that only the non-Hermitian coupling can correctly account for the light transfer between two coupled optical *** also reveal that the non-Hermitian coupling effect becomes crucial as the system dimension *** results provide important insight for handling general-coupled devices in the subwavelength regime.

关键词： interaction transfer coupling

Aligned Ion Conduction Pathway of Polyrotaxane‑Based Electrolyte with Dispersed Hydrophobic Chains for Solid‑State Lithium–Oxygen Batteries

在线全文

学校读者我要写书评

暂无评论

Nano-Micro Letters 2025年第2期17卷 169-186页

作者： Bitgaram kim Myeong‑Chang Sung Gwang‑Hee Lee Byoungjoon hwang Sojung Seo ji‑Hun Seo Dong‑Wan kim Department of Materials Science and Engineering Korea University145 Anam‑RoSeongbuk‑GuSeoul 02841Republic of Korea School of Civil Environmental and Architectural EngineeringKorea University145 Anam‑RoSeongbuk‑GuSeoul 02841Republic of Korea Materials Science and Chemical Engineering Center Institute for Advanced Engineering(IAE)Yongin 17180Republic of Korea

A critical challenge hindering the practical application of lithium–oxygen batteries(LOBs)is the inevitable problems associated with liquid electrolytes,such as evaporation and safety *** study addresses these problems by proposing a modified polyrotaxane(mPR)-based solid polymer electrolyte(SPE)design that simultaneously mitigates solvent-related problems and improves ***-SPE exhibits high ion conductivity(2.8×10^(−3)S cm^(−1)at 25℃)through aligned ion conduction pathways and provides electrode protection ability through hydrophobic chain *** this mPR-SPE into solid-state LOBs resulted in stable potentials over 300 *** situ Raman spectroscopy reveals the presence of an LiO_(2)intermediate alongside Li_(2)O_(2)during oxygen *** situ X-ray diffraction confirm the ability of the SPE to hinder the permeation of oxygen and moisture,as demonstrated by the air permeability *** present study suggests that maintaining a low residual solvent while achieving high ionic conductivity is crucial for restricting the sub-reactions of solid-state LOBs.

关键词： Solid polymer electrolyte Lithium-oxygen batteries Polyrotaxane ion conductivity Hydrophobic chain

Role of glutathione transferase in phase separation of FUS and TAF15 in neurons

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第7期20卷 1999-2000页

作者： Kiyoung kim Department of Medical Science Soonchunhyang UniversityAsanKorea

Amyotrophic lateral sclerosis(ALS)is a progressive neurodegenerative disorder characterized by the degeneration of motor neurons in the brain and spinal cord,leading to muscle weakness,paralysis,and ultimately death(Cleveland and Rothstein,2001).Frontotemporal lobar degeneration(FTLD)is a neurodegenerative disease affecting the frontal and temporal lobes of the brain,leading to changes in behavior,personality,and language(Van Langenhove et al.,2012).Both ALS and FTLD are classified as proteinopathies in which abnormal protein aggregation and accumulation in neurons contribute to the disease *** in sarcoma(FUS)is a DNA/RNA-binding protein involved in various cellular processes,including transcriptional regulation,RNA splicing,and DNA *** in the FUS gene have been linked to familial ALS,highlighting the importance of FUS in the disease pathogenesis(Vance et al.,2009).In ALS and FTLD,aberrant post-translational modifications(PTMs)of FUS,such as phosphorylation,acetylation,and methylation,have been implicated in the promotion of FUS aggregation and neurotoxicity(Choi et al.,2023).Therefore,understanding the regulatory mechanisms of FUS PTMs is crucial for developing targeted therapies against these diseases.

关键词： degeneration FUS aggregation