检索结果-内蒙古大学图书馆

作者： Liang, Chulong Ma, Xiao Bai, Baoming Department of Electronics and Communication Engineering Sun Yat-sen University Guangzhou510006 China Department of Electronic Engineering City University of Hong Kong Hong Kong School of Data and Computer Science Sun Yat-sen University Guangzhou510006 China State Key Laboratory of Integrated Services Networks Xidian University Xi'an710071 China

In this paper, we propose a simple procedure to construct (decodable) good codes with any given alphabet (of moderate size) for any given (rational) code rate to achieve any given target error performance (of interest) over additive white Gaussian noise channels. We start with constructing codes over groups for any given code rates. This can be done in an extremely simple way if we ignore the error performance requirement for the time being. Actually, this can be satisfied by repetition (R) codes and uncoded (UN) transmission along with time-sharing technique. The resulting codes are simply referred to as RUN codes for convenience. The encoding/decoding algorithms for RUN codes are almost trivial. In addition, the performance can be easily analyzed. It is not difficult to imagine that the RUN code usually performs far away from the corresponding Shannon limit. Fortunately, the performance can be improved as required by spatially coupling the RUN codes via block Markov superposition transmission (BMST), resulting in the BMST-RUN codes. Simulation results show that the BMST-RUN codes perform well (within around 1 dB away from Shannon limits) for a wide range of code rates and outperform the BMST with bit-interleaved coded modulation scheme. © 2016 IEEE.

关键词： White noise

来源：评论

学校读者我要写书评

暂无评论

Cross-Layer Optimization Strategies for Energy-Efficient and Reliable Machine-Type Communication in LPWANs

Cross-Layer Optimization Strategies for Energy-Efficient and...

引用

Emerging Research in Computational Science (ICERCS), International Conference on

作者： M. Amanullah J. Manoranjini V. Helen Sathiya P. Prabbu Sankar Department of Computer Science & Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Engineering Chennai India Department of Computer Science & Engineering Panimalar Engineering College Chennai India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

In the massive Machine-Type Communication (mMTC), the exponential growth of Internet of Things (IoT) devices over Low Power Wide Area Networks (LPWANs) presents substantial issues regarding energy efficiency and stability. The existing frameworks frequently fails in the the intricate relationships among the MAC-layer and physical parameters. To enhanced cross-layer evaluation methodology that integrates adaptive data rate (ADR) optimization, real-time energy consumption monitoring, and dynamic downlink message handling to address the problems. To maintain stability and performance with the network situations, the framework makes use of a Control-Lyapunov function. To enable effective resource allocation uses the Successive Convex Approximation that improve the effects of various transmission systems under quasi-static and dynamic channel conditions. To verify the cross-layer interactions and it impacts the energy efficiency, the proposed method begins with the data collection and it moves to payload size and packet length, are regularly changed to examines the affect throughput and energy consumption. The findings show the high-density node situations, energy consumption that reduced while retaining reliable communication. Furthermore, the results show the interdependencies among network parameters, highlighting the necessity of an integrated strategy. This framework helps to ensure the mMTC scenarios that optimized by improving the long-term viability and dependability of IoT networks.

关键词： Energy consumption Cross layer design Scientific computing Scalability Throughput Energy efficiency Reliability Internet of Things Optimization Low-power wide area networks

来源：评论

学校读者我要写书评

暂无评论

A multidimensional time series data on wireless network to improve the detection performance of unsupervised learning algorithms

A multidimensional time series data on wireless network to i...

引用

2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2022

作者： Paul, Chayan Ranjith, S. Vijayashanthi, R.S. Begam, R. Benazir Sabitha, R. KoneruLakshmaiah Education Foundation Department of Artificial Intelligence and Data Science AP Vaddeswaram India Jeppiaar Engineering College Semmenchery Department of Electronics and Communication Engineering Chennai600119 India S.A. Engineering College Department of Electronics and Communication Engineering Poonamallee Avadi Road Tamil Nadu Thiruverkadu600077 India Rajalakshmi Engineering College Department of ECE Tamil Nadu Chennai602105 India SIMATS Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai602105 India

ISBN: (数字)9781665474139

ISBN: (纸本)9781665474139

In recent years, only with developments of cellular networking technologies as well as the implementation of 4G LTE networks, the skills and options provided to end-users had expanded to a level that seems to be limitless. Smart phone users who travel by public transportation rely on high-speed internet infrastructure and expect to have a stable, greater connectivity for the length of their journey. Because of the high requirements placed on wireless networks and the regular changes in the fundamental radio channel, customers frequently encounter rapid and surprising alterations in the connectivity reliability of their connections. The old traditional process of evaluating and inspecting infrastructure cellular technology should be no longer sufficient to fulfill the demands of the manufacturing industry. Consequently, an accurate mobile network cellular irregularity diagnostic method is required to monitor for problems that lead and to improving the effectiveness of device construction and operation. It is estimated that there are thousands of mistakes and exclusions in the current single-dimensional abnormality identification technique, and also that the present multifunctional abnormality diagnostic technique has a poor detection accuracy on multifunctional time series analysis. Multidimensional statistics depending on network service device abnormality classification optimization approach described in this work is predicated on machine learning that use limited of information to support in the instruction of tremendous unmonitored techniques, thereby enhancing the detection accuracy of unsupervised classification techniques. This paper conducts experimental studies to validate the functionality of the optimization techniques, and it shows a significant progress over the four generally used unmonitored techniques, that can greatly enhance the abnormality detection performance of the existing techniques, according to the authors. © 2022 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

MBFusion: Multi-modal balanced fusion and multi-task learning for cancer diagnosis and prognosis

引用

computers in Biology and Medicine 2024年 181卷 109042-109042页

作者： Zhang, Ziye Yin, Wendong Wang, Shijin Zheng, Xiaorou Dong, Shoubin Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510641 China

Pathological images and molecular omics are important information for predicting diagnosis and prognosis. The two kinds of heterogeneous modal data contain complementary information, and the effective fusion of the two modals can better reveal the complex mechanisms of cancer. However, due to the different representation learning methods, the expression strength of different modals in different tasks varies greatly, so that many multimodal fusions do not achieve the best results. In this paper, MBFusion is proposed, to achieve multiple tasks such as prediction of diagnosis and prognosis through multi-modal balanced fusion. The MBFusion framework uses two kinds of specially constructed graph convolutional network to extract the features of molecular omics data, and uses ResNet to extract the features of pathological image data and retain important deep features by using attention and clustering, which effectively improves both kinds of the features representation, making their expressive ability balanced and comparable. The features of these two modal data are then fused through cross-attention Transformer, and the fused features are used to learn both tasks of cancer subtype classification and survival analysis by using multi-task learning. In this paper, MBFusion and other state of the art methods are compared on two public cancer datasets, and MBFusion shows an improvement of up to 10.1% by three kinds of evaluation metrics. In the ablation experiment, MBFusion explores the contribution of each modal data and each framework module to the performance. Furthermore, the interpretability of MBFusion is explained in detail to show the value of application. © 2024 Elsevier Ltd

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Online Affinity of Instructing Methods for Using Personal-Efficacy and Reading Capacious During Covid-19 5th

Online Affinity of Instructing Methods for Using Personal-Ef...

引用

5th International Conference on Communication, Device and Networking, ICCDN 2021

作者： PremaLatha, V. Sreedevi, E. Sivakumar, S. Nayak, Soumya Ranjan Bhoi, Akash Kumar Ghosh, Uttam Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation K L University Guntur Vaddeswaram522502 India Department of Computer Applications Faculty of Science and Humanities SRM Institute of Science and Technology Kattankulathur603203 India Amity School of Engineering and Technology Amity University Uttar Pradesh Noida India KIET Group of Institutions Delhi-NCR Ghaziabad201206 India Directorate of Research Sikkim Manipal University Sikkim Gangtok737102 India Department of Computer Science and Data Science Meharry School of Computational Sciences Nashville NashvilleTN United States

ISBN: (纸本)9789811920035

Now a days in EFL procedure of education the ability of reading became as significant belief and personal-efficacy reading as a basic understanding for students. By monitoring the acknowledged participates under the ballpark figure of large studying and methods of understanding, the impact of their observation is premeditated on reading of each one’s personal-efficacy. On a daily routine all these things are comparatively considered which are put into effect by teachers of handful in number. Approach towards exhibiting Extensive reading (ER) is inspected to be "more expensive, difficult, and time-consuming". Method of recognition of elements in a various way for effective impact in putting its efforts to utilize for its empowerment. Paper has been segregated into two contexts: Association with attitude is considered as primary one and attitude is considered as secondary one. Whether knowledge work is understood by student or not is considered as the impact of ER by the first review. Procedure which are convenient is taken as the observations of student and is analysed as second one. The examinations are quantifiable to utilize the observations as information in terms of subjective way taken from students who belong to first academic year of reading course in a systematic way and 603 details of undergraduate students from KLEF of Guntur were chosen as participants for extant examination. In ER programme of includes and excludes "comprehension reading work" is treated as fundamental in the proposal of disclosures. In case of any, "the programme appeared to positively affect contributing students". Techniques of classification like "decision tree and Mixed Model database Miner (MMDBM)" are employed in this paper which leads to improvements of post-test to pre-test in ER group. Observations of students in ER results as optimistic and algorithm of MMDBM which leads to accuracy in higher rate in pre-test and post-test detection. © 2023, The Author(s), under exclusive lice

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Alternating Differentiation for Optimization Layers

arXiv

引用

arXiv 2022年

作者： Sun, Haixiang Shi, Ye Wang, Jingya Tuan, Hoang Duong Poor, H. Vincent Tao, Dacheng School of Information Science and Technology ShanghaiTech University China School of Electrical and Data Engineering University of Technology Sydney Australia Department of Electrical and Computer Engineering Princeton University United States School of Computer Science The University of Sydney Australia JD Explore Academy China

The idea of embedding optimization problems into deep neural networks as optimization layers to encode constraints and inductive priors has taken hold in recent years. Most existing methods focus on implicitly differentiating Karush–Kuhn–Tucker (KKT) conditions in a way that requires expensive computations on the Jacobian matrix, which can be slow and memory-intensive. In this paper, we developed a new framework, named Alternating Differentiation (Alt-Diff), that differentiates optimization problems (here, specifically in the form of convex optimization problems with polyhedral constraints) in a fast and recursive way. Alt-Diff decouples the differentiation procedure into a primal update and a dual update in an alternating way. Accordingly, Alt-Diff substantially decreases the dimensions of the Jacobian matrix especially for optimization with large-scale constraints and thus increases the computational speed of implicit differentiation. We show that the gradients obtained by Alt-Diff are consistent with those obtained by differentiating KKT conditions. In addition, we propose to truncate Alt-Diff to further accelerate the computational speed. Under some standard assumptions, we show that the truncation error of gradients is upper bounded by the same order of variables’ estimation error. Therefore, Alt-Diff can be truncated to further increase computational speed without sacrificing much accuracy. A series of comprehensive experiments validate the superiority of Alt-Diff. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Walkie-Talkie: Motion-Assisted Automatic Key Generation for Secure On-Body Device Communication

Walkie-Talkie: Motion-Assisted Automatic Key Generation for ...

引用

International Symposium on Information Processing in Sensor Networks (IPSN)

作者： Weitao Xu Girish Revadigar Chengwen Luo Neil Bergmann Wen Hu School of Information Technology and Electrical Engineering University of Queensland Brisbane Australia CSIRO Data61 Australia School of Computer Science and Engineering University of New South Wales Sydney Australia College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Ubiquity of wearable and implantable devices sparks a new set of mobile computing applications that leverage the prolific information of sensors. For many of these applications, to ensure the security of communication between legitimate devices is a crucial problem. In this paper, we design Walkie-Talkie, a shared secret key generation scheme that allows two legitimate devices to establish a common cryptographic key by exploiting users' walking characteristics (gait). The intuition is that the sensors on different locations of the same body experience similar accelerometer signal when the user is walking. However, the accelerometer also captures motion signal produced by other body parts (e.g., swinging arms). We address this issue by employing Blind Source Separation (BSS) technique to extract the informative signal produced by the unique gait pattern. Our experimental results show that the keys generated by two independent devices on the same body are able to achieve up to 100% bit agreement rate. To demonstrate the feasibility, we implement the proposed key generation scheme on modern smartphones. The evaluation results show that the proposed scheme can run in real-time on modern mobile devices and incurs low system overhead.

关键词： Acceleration Legged locomotion Sensors Authentication Smart phones Source separation

来源：评论

学校读者我要写书评

暂无评论

SCD-NAS: Towards Zero-Cost Training in Melanoma Diagnosis

SCD-NAS: Towards Zero-Cost Training in Melanoma Diagnosis

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Hongyan Xu Xiu Su Arcot Sowmya Ian Katz Dadong Wang School of Computer Science and Engineering University of New South Wales Australia Data61 The Commonwealth Scientific and Industrial Research Organisation School of Computer Science Faculty of Engineering The University of Sydney Australia Southern Sun Pathology Pty Ltd

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Diagnosing melanoma remains challenging despite advances in Convolutional Neural Networks (CNNs) for skin cancer detection. Their application in clinical settings is often limited by differences between natural and clinical images. To address this, we introduce the Skin Cancer Detection Neural Architecture Search (SCD-NAS) framework. In our method, Large Language Model (LLM) is leveraged as a proxy, which helps SCD-NAS achieve cost-free training. Additionally, to maximize the benefits of various architectural design spaces, we introduce a Search Space Expansion (SSE) methodology. This effectively combines the merits of diverse architectural configurations, thereby enhancing model performance. We conducted experiments on the ISIC 2020, MedMNISTv2, CIFAR-10 and CIFAR-100 datasets. Our SCD-NAS-derived ResNet50 model achieved an Area Under the Curve (AUC) of 91.23% on the ISIC 2020 dataset, improving the baseline by 5.93%. It also exceeded the CIFAR-10 benchmark by 2.45% in accuracy.

关键词： Training Accuracy Navigation Large language models Melanoma Benchmark testing Convolutional neural networks Medical diagnostic imaging Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Price Prediction of Seasonal Items Using Time Series Analysis

引用

computer Systems Science & engineering 2023年第7期46卷 445-460页

作者： Ahmed Salah Mahmoud Bekhit Esraa Eldesouky Ahmed Ali Ahmed Fathalla Faculty of Computers and Informatics Zagazig UniversitySharkeya44523Egypt Information Technology Department the University of Technology and Applied SciencesIbriOman School of Electrical and Data Engineering University of Technology SydneySydney2007Australia College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Computer Science Department Faculty of Computers and InformaticsSuez Canal UniversityIsmailia41522Egypt Higher Future Institute for Specialized Technological Studies Cairo3044Egypt Department of Mathematics Faculty of ScienceSuez Canal UniversityIsmailia41522Egypt

The price prediction task is a well-studied problem due to its impact on the business *** are several research studies that have been conducted to predict the future price of items by capturing the patterns of price change,but there is very limited work to study the price prediction of seasonal goods(e.g.,Christmas gifts).Seasonal items’prices have different patterns than normal items;this can be linked to the offers and discounted prices of seasonal *** lack of research studies motivates the current work to investigate the problem of seasonal items’prices as a time series *** proposed utilizing two different approaches to address this problem,namely,1)machine learning(ML)-based models and 2)deep learning(DL)-based ***,this research tuned a set of well-known predictive models on a real-life *** models are ensemble learning-based models,random forest,Ridge,Lasso,and Linear ***,two new DL architectures based on gated recurrent unit(GRU)and long short-term memory(LSTM)models are ***,the performance of the utilized ensemble learning and classic ML models are compared against the proposed two DL architectures on different accuracy metrics,where the evaluation includes both numerical and visual comparisons of the examined *** obtained results show that the ensemble learning models outperformed the classic machine learning-based models(e.g.,linear regression and random forest)and the DL-based models.

关键词： Deep learning price prediction seasonal goods time series analysis

来源：评论

学校读者我要写书评

暂无评论

Towards deployment-centric multimodal AI beyond vision and language

arXiv

引用

arXiv 2025年

作者： Liu, Xianyuan Zhang, Jiayang Zhou, Shuo van der Plas, Thijs L. Vijayaraghavan, Avish Grishina, Anastasiia Zhuang, Mengdie Schofield, Daniel Tomlinson, Christopher Wang, Yuhan Li, Ruizhe van Zeeland, Louisa Tabakhi, Sina Demeocq, Cyndie Li, Xiang Das, Arunav Timmerman, Orlando Baldwin-McDonald, Thomas Wu, Jinge Bai, Peizhen Al Sahili, Zahraa Alwazzan, Omnia Do, Thao N. Suvon, Mohammod N.I. Wang, Angeline Cipolina-Kun, Lucia Moretti, Luigi A. Farndale, Lucas Jain, Nitisha Efremova, Natalia Ge, Yan Varela, Marta Lam, Hak-Keung Celiktutan, Oya Evans, Ben R. Coca-Castro, Alejandro Wu, Honghan Abdallah, Zahraa S. Chen, Chen Danchev, Valentin Tkachenko, Nataliya Lu, Lei Zhu, Tingting Slabaugh, Gregory G. Moore, Roger K. Cheung, William K. Charlton, Peter H. Lu, Haiping Centre for Machine Intelligence University of Sheffield Sheffield United Kingdom School of Computer Science University of Sheffield Sheffield United Kingdom The Alan Turing Institute London United Kingdom Department of Metabolism Digestion and Reproduction Imperial College London London United Kingdom Department of Applied AI Simula Research Laboratory Oslo Norway Information School University of Sheffield Sheffield United Kingdom NHS England Leeds United Kingdom Institute of Health Informatics University College London London United Kingdom Department of Engineering King’s College London London United Kingdom Department of Computing Science University of Aberdeen Aberdeen United Kingdom School of Informatics University of Edinburgh Edinburgh United Kingdom School of Engineering Mathematics and Technology University of Bristol Bristol United Kingdom Department of Informatics King’s College London London United Kingdom Department of Earth Sciences University of Cambridge Cambridge United Kingdom Department of Computer Science University of Manchester Manchester United Kingdom Department of Computer Science Queen Mary University of London London United Kingdom Digital Environment Research Institute Queen Mary University of London London United Kingdom Department of Computer Science University of Bath Bath United Kingdom Department of Classics King’s College London London United Kingdom School of Electrical Electronic and Mechanical Engineering University of Bristol Bristol United Kingdom School of Engineering University of the West of England Bristol United Kingdom Cancer Research UK Scotland Institute Glasgow United Kingdom School of Business and Management Queen Mary University of London London United Kingdom City St George’s University of London London United Kingdom British Antarctic Survey Cambridge United Kingdom School of Health and Wellbeing University of Glasgow Glasgow United Kingdom Chief Data & AI Office Lloyds Banking Group Lo

Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most multimodal AI advances focus on models for vision and language data, while their deployability remains a key challenge. We advocate a deployment-centric workflow that incorporates deployment constraints early to reduce the likelihood of undeployable solutions, complementing data-centric and model-centric approaches. We also emphasise deeper integration across multiple levels of multimodality and multidisciplinary collaboration to significantly broaden the research scope beyond vision and language. To facilitate this approach, we identify common multimodal-AI-specific challenges shared across disciplines and examine three real-world use cases: pandemic response, self-driving car design, and climate change adaptation, drawing expertise from healthcare, social science, engineering, science, sustainability, and finance. By fostering multidisciplinary dialogue and open research practices, our community can accelerate deployment-centric development for broad societal impact. © 2025, CC BY.

关键词： Decision making

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：