检索结果-内蒙古大学图书馆

Active terahertz beam steering based on mechanical deformation of liquid crystal elastomer metasurface

Light(Science & Applications) 2023年第1期12卷 118-127页

作者： Xiaolin Zhuang Wei Zhang Kemeng Wang Yangfan Gu Youwen An Xueqian Zhang Jianqiang Gu Dan Luo Jiaguang Han Weili Zhang Center for Terahertz Waves and College of Precision Instrument and Optoelectronics Engineering Key Laboratory of Optoelectronic Information TechnologyMinistry of EducationTianjin University300072 TianjinChina Department of Electrical and Electronic Engineering Southern University of Science and Technology518055 ShenzhenChina School of Electrical and Computer Engineering Oklahoma State UniversityStillwaterOK 74078USA

Active metasurfaces are emerging as the core of next-generation optical devices with their tunable optical responses and flat-compact *** for the terahertz band,active metasurfaces have been developed as fascinating devices for optical chopping and compressive sensing ***,performance regulation by changing the dielectric parameters of the integrated functional materials exhibits severe limitations and parasitic ***,we introduce a C-shape-split-ring-based phase discontinuity metasurface with liquid crystal elastomer as the substrate for infrared modulation of terahertz ***-focused infrared light is applied to manipulate the deflection of the liquid crystal elastomer substrate,enabling controllable and broadband wavefront steering with a maximum output angle change of 22°at *** as another control method is also investigated and compared with infrared *** further demonstrate the performance of liquid crystal elastomer metasurface as a beam steerer,frequency modulator,and tunable beam splitter,which are highly desired in terahertz wireless communication and imaging *** proposed scheme demonstrates the promising prospects of mechanically deformable metasurfaces,thereby paving the path for the development of reconfigurable metasurfaces.

关键词： tunable modulator beam

来源：评论

学校读者我要写书评

暂无评论

Improved electrical properties of micro light-emitting diode displays by ion implantation technology

引用

Discover Nano 2023年第1期18卷 1-11页

作者： Hsu, Yu-Hsuan Wang, Chi-Han Lin, Xin-Dai Lin, Yi-Hsin Wuu, Dong-Sing Horng, Ray-Hua Department of Photonics College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Xinzhu30010 Taiwan Institute of Electronics College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Xinzhu30010 Taiwan Department of Applied Materials and Optoelectronic Engineering National Chi Nan University Nantou54561 Taiwan

Generally, the inductively coupled plasma-reactive ion etching (ICP-RIE) mesa technology was used to remove p-GaN/MQWs and expose n-GaN for electrical contact in a fabricated micro light-emitting diode (μLED). In this process, the exposed sidewalls were significantly damaged which result in small-sized μLED presenting a strong size-dependent influence. Lower emission intensity was observed in the μLED chip, which can be attributed to the effect of sidewall defect during etch processing. To reduce the non-radiative recombination, the ion implantation using an As+ source to substitute the ICP-RIE mesa process was introduced in this study. The ion implantation technology was used to isolate each chip to achieve the mesa process in the μLED fabrication. Finally, the As+ implant energy was optimized at 40 keV, which exhibited excellent current–voltage characteristics, including low forward voltage (3.2 V @1 mA) and low leakage current (10–9 A@− 5 V) of InGaN blue μLEDs. The gradual multi-energy implantation process from 10 to 40 keV can further improve the electrical properties (3.1 V @1 mA) of μLEDs, and the leakage current was also maintained at 10–9 A@− 5 V. © 2023, The Author(s).

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Online Linear Regression in Dynamic Environments via Discounting 41

Online Linear Regression in Dynamic Environments via Discoun...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Jacobsen, Andrew Cutkosky, Ashok Department of Computing Science University of Alberta Edmonton Canada Department of Electrical and Computer Engineering Boston University BostonMA United States

We develop algorithms for online linear regression which achieve optimal static and dynamic regret guarantees even in the complete absence of prior knowledge. We present a novel analysis showing that a discounted variant of the Vovk-Azoury-Warmuth forecaster achieves dynamic regret of the form RT(u) ≤ O (d log(T ) ∨ √dPγT (u)T ), where PγT (u) is a measure of variability of the comparator sequence, and show that the discount factor achieving this result can be learned on-the-fly. We show that this result is optimal by providing a matching lower bound. We also extend our results to strongly-adaptive guarantees which hold over every sub-interval [a, b] ⊆ [1, T ] simultaneously. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cryptocurrency Portfolio Optimization by Neural Networks

Cryptocurrency Portfolio Optimization by Neural Networks

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Nguyen, Quoc Minh Tran, Dat Thanh Kanniainen, Juho Iosifidis, Alexandros Gabbouj, Moncef Tampere University Department of Computing Sciences Finland Aarhus University Department of Electrical and Computer Engineering Denmark

ISBN: (纸本)9781665430654

Many cryptocurrency brokers nowadays offer a va-riety of derivative assets that allow traders to perform hedging or speculation. This paper proposes an effective algorithm based on neural networks to take advantage of these investment products. The proposed algorithm constructs a portfolio that contains a pair of negatively correlated assets. A deep neural network, which outputs the allocation weight of each asset at a time interval, is trained to maximize the Sharpe ratio. A novel loss term is proposed to regulate the network's bias towards a specific asset, thus enforcing the network to learn an allocation strategy that is close to a minimum variance strategy. Extensive experiments were conducted using data collected from Binance spanning 19 months to evaluate the effectiveness of our approach. The backtest results show that the proposed algorithm can produce neural networks that are able to make profits in different market situations. © 2023 IEEE.

关键词： cryptocurrency decision making Deep learning financial engineering portfolio optimization

来源：评论

学校读者我要写书评

暂无评论

A Secure Framework for Blockchain Transactions Protection

引用

computer Systems Science & engineering 2023年第5期45卷 1095-1111页

作者： Wafaa N.Al-Sharu Majdi K.Qabalin Muawya Naser Omar A.Saraerh Department of Electrical Engineering Faculty of EngineeringThe Hashemite UniversityZarqa13133Jordan Department of Computer Science King Hussein School of Computing SciencesPrincess Sumaya University for TechnologyAmman11941Jordan

One of the most extensively used technologies for improving the security of IoT devices is blockchain *** is a new technology that can be utilized to boost the *** is a decentralized peer-to-peer network with no central *** nodes on the network mine or verify the data recorded on the *** is a distributed ledger that may be used to keep track of transactions between several *** one can tamper with the data on the blockchain since it is *** the blocks are connected by hashes,the transaction data is *** is managed by a system that is based on the consensus of network users rather than a central *** immutability and tamper-proof nature of blockchain security is based on asymmetric cryptography and ***,Blockchain has an immutable and tamper-proof smart contract,which is a logic that enforces the Blockchain’s *** is a conflict between the privacy protection needs of cyber-security threat intelligent(CTI)sharing and the necessity to establish a comprehensive attack chain during blockchain *** paper presents a blockchain-based data sharing paradigm that protects the privacy of CTI sharing parties while also preventing unlawful sharing and ensuring the benefit of legitimate sharing *** builds a full attack chain using encrypted threat intelligence and exploits the blockchain’s backtracking capacity to finish the decryption of the threat source in the attack *** contracts are also used to send automatic early warning replies to possible attack *** tests are used to verify the feasibility and efficacy of the suggested model.

关键词： Manuscript preparation typeset format

来源：评论

学校读者我要写书评

暂无评论

Detecting Concept Shifts Under Different Levels of Self-awareness on Emotion Labeling 27th

Detecting Concept Shifts Under Different Levels of Self-awa...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Choi, HyoSeon Choi, Dahoon Kaongoen, Netiwit Kim, Byung Hyung Department of Electrical and Computer Engineering Incheon Korea Republic of Department of Computer Engineering Incheon Korea Republic of Department of Artificial Intelligence Inha University Incheon Korea Republic of School of Computing KAIST Daejeon Korea Republic of

ISBN: (纸本)9783031782008

Generalizing deep learning for all requires individual self-assessment. However, the quality of ground-truth labels depends on the annotators’ self-awareness. Real-world datasets inevitably experience the Concept Shift problem. Recent advances in Out-of-distribution (OOD) detection have received much attention due to its ability to alleviate distribution shift problems by distinguishing between anomalous and in-distribution(ID) data samples. Existing approaches underlie pre-trained ID models learned with class-balanced data. However, this assumption makes the methods incapable when the ID models are trained with inter- and intra-class variance depending on user characteristics, such as gender, culture, and genetics. We present an OOD detection framework. Our system builds a generalized ID model by extracting high-quality data from high-dimensional neural activities considering individuals’ cognitive and perceptional ability to evaluate self-assessments. The proposed system detects and removes abnormal pairs of data and labels to enhance model performance by considering the maximum softmax probability approach. Experimental results on public EEG datasets in emotion recognition demonstrate the superiority of our method despite the non-stationary nature of EEG signals. The codes are available at https://***/affctivai/coglier. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An ensemble deep learning model for cyber threat hunting in industrial internet of things

引用

Digital Communications and Networks 2023年第1期9卷 101-110页

作者： Abbas Yazdinejad Mostafa Kazemi Reza M.Parizi Ali Dehghantanha Hadis Karimipour Cyber Science Lab School of Computer ScienceUniversity of GuelphOntarioCanada Department of Electrical Engineering Faculty of EngineeringShahed UniversityTehranIran College of Computing and Software Engineering Kennesaw State UniversityGAUSA School of Engineering University of GuelphOntarioCanada

By the emergence of the fourth industrial revolution,interconnected devices and sensors generate large-scale,dynamic,and inharmonious data in Industrial Internet of Things(IIoT)*** vast heterogeneous data increase the challenges of security risks and data analysis *** IIoT grows,cyber-attacks become more diverse and complex,making existing anomaly detection models less effective to *** this paper,an ensemble deep learning model that uses the benefits of the Long Short-Term Memory(LSTM)and the AutoEncoder(AE)architecture to identify out-of-norm activities for cyber threat hunting in IIoT is *** this model,the LSTM is applied to create a model on normal time series of data(past and present data)to learn normal data patterns and the important features of data are identified by AE to reduce data *** addition,the imbalanced nature of IIoT datasets has not been considered in most of the previous literature,affecting low accuracy and *** solve this problem,the proposed model extracts new balanced data from the imbalanced datasets,and these new balanced data are fed into the deep LSTM AE anomaly detection *** this paper,the proposed model is evaluated on two real IIoT datasets-Gas Pipeline(GP)and Secure Water Treatment(SWaT)that are imbalanced and consist of long-term and short-term dependency on *** results are compared with conventional machine learning classifiers,Random Forest(RF),Multi-Layer Perceptron(MLP),Decision Tree(DT),and Super Vector Machines(SVM),in which higher performance in terms of accuracy is obtained,99.3%and 99.7%based on GP and SWaT datasets,***,the proposed ensemble model is compared with advanced related models,including Stacked Auto-Encoders(SAE),Naive Bayes(NB),Projective Adaptive Resonance Theory(PART),Convolutional Auto-Encoder(C-AE),and Package Signatures(PS)based LSTM(PS-LSTM)model.

关键词： Internet of things IIoT Anomaly detection Ensemble deep learning Neural networks LSTM

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-Dialect End-to-End ASR Model Jointly with Beam Search Threshold Pruning and LLM

引用

SN computer Science 2025年第4期6卷 1-12页

作者： Shunmuga Priya, M.C. Karthika Renuka, D. Ashok Kumar, L. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Department of Information Technology PSG College of Technology Coimbatore India Department of Electrical and Electronics Engineering Thiagarajar College of Engineering Madurai India

This paper aims to develop a novel robust multi-dialect end-to-end ASR system with beam search threshold pruning. The efficacy of our proposed model is evaluated using word error rate (WER). Our key contributions are: (1) To develop an end-to-end ASR system using attention-based neural network architecture and analyze the effectiveness of two features such as MFCC and log mel filter bank energies on multiple speech dialect corpora including American, Britain, and Indian accents;(2) To integrate beam search threshold pruning as a decoding mechanism to reduce the decoding time (3) To conduct an experimental analysis to test the model performance and compare the results against baseline system. (4) Post processing analysis are carried out using Llama2-7B based large language model(LLM) for enhancing the performance of proposed ASR system. The proposed model significantly improves performance by 1.91% and 4.29% over clean and noisy speech in librispeech corpus. Similarly, for the Indian accented speech, the model attains an average WER of about 6.6%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Automatic speech recognition Beam search Decoding LLM Log Mel filter bank energies

来源：评论

学校读者我要写书评

暂无评论

Cross Feature Fusion of Fundus Image and Generated Lesion Map for Referable Diabetic Retinopathy Classification 17th

Cross Feature Fusion of Fundus Image and Generated Lesion ...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Mok, Dahyun Bum, Junghyun Tai, Le Duc Choo, Hyunseung Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9789819609000

Diabetic Retinopathy (DR) is a primary cause of blindness, necessitating early detection and diagnosis. This paper focuses on referable DR classification to enhance the applicability of the proposed method in clinical practice. We develop an advanced cross-learning DR classification method leveraging transfer learning and cross-attention mechanisms. The proposed method employs the Swin U-Net architecture to segment lesion maps from DR fundus images. The Swin U-Net segmentation model, enriched with DR lesion insights, is transferred to generate a lesion map. Both the fundus image and its segmented lesion map are used as complementary inputs for the classification model. A cross-attention mechanism is deployed to improve the model’s ability to capture fine-grained details from the input pairs. Our experiments, utilizing two public datasets, FGADR and EyePACS, demonstrate a superior accuracy of 94.6%, surpassing current state-of-the-art methods by 4.4%. To this end, we aim for the proposed method to be seamlessly integrated into clinical workflows, enhancing accuracy and efficiency in identifying referable DR. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

NDAS: Noise-Decomposed Abnormal Segmentation for Robust Medical Image Retrieval 19

NDAS: Noise-Decomposed Abnormal Segmentation for Robust Medi...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Kim, Ju-Chan Van Nguyen, Pham Le, Duc-Tai Choo, Hyunseung College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798331507817

This paper presents NDAS (Noise-Decomposed Abnormal Segmentation), an innovative framework for robust medical image retrieval and segmentation. By explicitly decomposing noise and abnormal features, NDAS enhances retrieval accuracy and segmentation precision. Experimental results on the BraTS 2019 dataset validate NDAS’s superiority over CBMIR and SBMIR methods, achieving the highest Top-5 accuracy and Dice coefficient. This demonstrates its effectiveness in handling noise, isolating pathological regions, and retrieving diagnostically relevant medical images. NDAS offers a significant advancement in medical imaging analysis, emphasizing its potential for clinical applications requiring precision and reliability. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：