检索结果-内蒙古大学图书馆

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Michael Appiah-Twum Xu Wenbo Cobbinah B. Mawuli Peter Atandoh School of Resources and Environment University of Electronic Science and Technology of China Chengdu Sichuan China Yangtze Delta Region Institute (Huzhou) University of Electronic Science and Technology of China Huzhou China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu Sichuan China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu Sichuan China

Remote sensing-based geological interpretation provides insight from numerous sensors. That notwithstanding, high-dimensional feature learning requires full-scale diagnosis of intrinsic geological features in remotely sensed datasets. This study proposes a multi-sensor fusion approach. Integrating Landsat-9 and ASTER spectral features with DenseNet for lithological classification, displaces RF and KNN by 2.12 % and surpasses ResNet50 and Xception with a classification accuracy of 83.89%. Furthermore, this study underscores the effectiveness of merging new and old generation sensors for geological interpretation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DNMDA: Deep Non-negative Matrix Factorization with Multi-level Integration for MiRNA-Drug Interaction Prediction

DNMDA: Deep Non-negative Matrix Factorization with Multi-lev...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yujie Qi Jiaxin Yang Yu-An Huang Zhu-Hong You Zimai Zhang Lun Hu Xi Zhou Pengwei Hu Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Xinjiang University The School of Software Urumqi China School of Engineering and Applied Science Columbia University NY USA School of Computer Science Northwestern Polytechnical University Xian China Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Urumqi China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Numerous studies have demonstrated that the interaction between miRNAs and drugs plays a pivotal role in regulating gene expression and cellular function. Therefore, predicting these interactions is crucial for the development of novel drugs and personalized therapies. Existing methods for predicting miRNA-drug interactions often fail to leverage the full spectrum of molecular and biological features and overlook complex high-dimensional patterns. Deep non-negative matrix factorization (DNMF) addresses these limitations by extracting higher-level representations, thereby enhancing prediction accuracy and robustness. Building on this, this paper proposes a model called DNMDA. In this model, we integrate multiple similarity networks for both miRNAs and drugs and then extract their features through three key modules. Moreover, autoencoders are used to combine various feature sets, allowing for the capture of complementary information and enhancing the model’s capacity for making precise and reliable predictions. The resulting features are consolidated into a unified feature vector for each miRNA-drug pair. Ultimately, these feature vectors and their associated labels are provided to the classifier for training. To verify the predictions, a five-fold cross-validation was conducted. The five-fold cross-validation demonstrated a clear advantage in DNMDA’s metrics, underscoring its reliability in predicting potential miRNA-drug interactions. This claim is further supported by the predictive results section in the paper, offering concrete evidence of DNMDA’s efficacy in this field.

关键词： Drugs Training Accuracy Biological system modeling Computational modeling Scalability Predictive models Feature extraction Vectors Data models

来源：评论

学校读者我要写书评

暂无评论

Band Prompting Aided SAR and Multi-Spectral Data Fusion Framework for Local Climate Zone Classification

Band Prompting Aided SAR and Multi-Spectral Data Fusion Fram...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haiyan Lan Shujun Li Mingjie Xie Xuanjia Zhao Hongning Liu Pengming Feng Dongli Xu Guangjun He Jian Guan College of Computer Science and Technology Harbin Engineering University Harbin China School of Astronautics Beihang University Beijing China School of Software Dalian University of Technology Dalian China State Key Laboratory of Space-Ground Integrated Information Technology Beijing China Independent Researcher

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Local climate zone (LCZ) classification is of great value for understanding the complex interactions between urban development and local climate. Recent studies have increasingly focused on the fusion of synthetic aperture radar (SAR) and multi-spectral data to improve LCZ classification performance. However, it remains challenging due to the distinct physical properties of these two types of data and the absence of effective fusion guidance. In this paper, a novel band prompting aided data fusion framework is proposed for LCZ classification, namely BP-LCZ, which utilizes textual prompts associated with band groups to guide the model in learning the physical attributes of different bands and semantics of various categories inherent in SAR and multi-spectral data to augment the fused feature, thus enhancing LCZ classification performance. Specifically, a band group prompting (BGP) strategy is introduced to align the visual representation effectively at the level of band groups, which also facilitates a more adequate extraction of semantic information of different bands with textual information. In addition, a multivariate supervised matrix (MSM) based training strategy is proposed to alleviate the problem of positive and negative sample confusion by completing the supervised information. The experimental results demonstrate the effectiveness and superiority of the proposed data fusion framework.

关键词： Training Visualization Semantics Data integration Signal processing Robustness Data mining Speech processing Synthetic aperture radar Meteorology

来源：评论

学校读者我要写书评

暂无评论

On-Chain Analysis-Based Detection of Abnormal Transaction Amount on Cryptocurrency Exchanges

SSRN

引用

SSRN 2022年

作者： Gu, Zhuoming Lin, Dan Wu, Jiajing School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China School of Software Engineering Sun Yat-sen University Zhuhai519000 China

Cryptocurrency exchanges play an indispensable role in the cryptocurrency market. However, some exchanges are suspected to be involved in various abnormal or malicious behaviors while providing services to users, such as money laundering, wash trading and even running away. Besides, these behaviors are reported to be often accompanied by an anomalous increase in the transaction amount. Therefore, it is a topic worthy of study to detect whether the abnormal transaction amount occurs in the exchange and when it occurs. This paper uses web crawler tools to collect a relatively complete dataset of exchanges and then conducts a correlation analysis to obtain the most important factors that influence the transaction amount of different exchanges. Then, the prediction model of the influence of various factors on the transaction amount is obtained based on deep learning. The deviation between the predicting transaction amount and the actual transaction amount is calculated to provide a basis for abnormal transaction amount detection. Finally, through a case study on the detection results, some abnormal transaction amounts are related to policy changes and industry events, while the others are suspected to be related to illegal behaviors. © 2022, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Identifying Dna-Binding Proteins Using Local Features Dpc-Pssm and Ab-Pssm with Primary Sequences Based on 2dcnn

SSRN

引用

SSRN 2024年

作者： Sikander, Rahu Rahu, Ali Ghulam Rahu, Mujeeb -Ur-Rehman Center for Computing Research Department of Computer Science and Software Engineering Jinnah University for Women Karachi Pakistan Information Technology Centre Sindh Agriculture University Sindh Tandojam Pakistan School of Information and Communication Engineering Guilin University of Electronic Technology Guilin China

DBPs, also known as DNA-binding proteins, play a crucial role in the evolutionary and genetic mechanisms of humans. Understanding the features of DNA-binding peptides might develop our comprehension of protein roles inside cellular genetic processes. Investigation on predicting the function of DNA-binding proteins can advance the study of drug proteins and facilitate the development of computer-assisted medications. Deep learning methods have become the major approach for protein prediction in recent years. While current approaches can yield impressive expect performance, further research is necessary to enhance this performance. This work proposed the prediction of DNA-binding proteins using two-dimensional Convolutional Neural Network (CNN) named 2DCNN-DBP. The prominent characteristics are obtained through innovative techniques, specifically position specific scoring matrix-dipeptide composition dipeptide composition (PSSM-DPC), Second, we employed Average Block novel approach to representing proteins using position-specific scoring matrices (AB-PSSM) in images. The DPC-PSSM feature extraction approach achieved a prediction accuracy of 0.9309% for the validation set, which is notably superior to the AB-PSSM. Based on the analysis, DPC-PSSM shown superior performance compared to the other two feature selection approaches in classification using 2DCNN. Specifically, AB-PSSM attained a higher accuracy level of 73.50% using independent test datasets and a training dataset accuracy score of 87.52%. The results demonstrate the superior performance of our innovative predictor compared to previous studies. Utilizing PSSM-DPC could lead to the development of more effective therapeutic approaches for the treatment of life-threatening diseases. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Understanding Wireless Charger Networks: Concepts, Current Research, and Future Directions

引用

IEEE Communications Surveys and Tutorials 2024年

作者： Ren, Meixuan Dai, Haipeng Liu, Tang Deng, Xianjun Dou, Wanchun Yang, Yuanyuan Chen, Guihai Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China Sichuan Normal University College of Computer Science Sichuan Chengdu610101 China Sichuan Normal University Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Sichuan Chengdu610068 China Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan430074 China Stony Brook University Department of Electrical and Computer Engineering NY11794 United States

Wireless Charger Network (WCN) emerges as a promising networking paradigm, employing wireless chargers with Wireless Power Transfer (WPT) technology to provide long-term and sustainable energy supply for future networks. Although extensive research has been conducted in this area over the last decade, there is currently no comprehensive survey to compile the latest literature and provide insights into future research directions. To fill this gap, our survey explores the recent developments in the active research area of WCNs. This paper starts by providing a framework of WCNs in detail, covering aspects of network architecture, various charging models, network design issues, and typical applications of WCNs. Then, we give an overview of charger deployment schemes, focusing on omnidirectional, directional, non-radiative, and heterogeneous charger deployments. We also provide an overview of charging scheduling schemes, encompassing power control, time allocation, energy beamforming, and multi-resource scheduling. Moreover, we explore communication optimization schemes, including Medium Access Control (MAC) protocols, routing protocols, broadcast transmission, and data collection. Finally, we highlight some future research directions and present corresponding open issues to advance the research on WCNs. © 1998-2012 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Mechanism Design for Exchange Markets

arXiv

引用

arXiv 2024年

作者： Zheng, Yusen Cheng, Yukun Xu, Chenyang Deng, Xiaotie CFCS School of Computer Science Peking University Beijing100871 China PKU-WUHAN Institute for Artificial Intelligence Wuhan430075 China School of Business Jiangnan University Wuxi214122 China Software Engineering Institute East China Normal University China

Exchange markets are a significant type of market economy, in which each agent holds a budget and certain (divisible) resources available for trading. Most research on equilibrium in exchange economies is based on an environment of completely free competition. However, the orderly operation of markets in reality also relies on effective economic regulatory mechanisms. This paper initiates the study of the mechanism design problem in exchange markets, exploring the potential to establish truthful market rules and mechanisms. This task poses a significant challenge as unlike auctioneers in auction design, the mechanism designer in exchange markets lacks centralized authority to fully control the allocation of resources. In this paper, the mechanism design problem is formalized as a two-stage game. In stage 1, agents submit their private information to the manager, who then formulates market trading rules based on the submitted information. In stage 2, agents are free to engage in transactions within these rules, ultimately reaching an equilibrium. We generalize the concept of liquid welfare from classical budget-feasible auctions and use market liquid welfare as a measure to evaluate the performance of the designed mechanism. Moreover, an extra concept called profitability is introduced to assess whether the market is money-making (profitable) or money-losing (unprofitable). Our goal is to design a truthful mechanism that achieves an (approximate) optimal welfare while minimizing unprofitability as much as possible. Two mechanisms for the problem are proposed. The first one guarantees truthfulness and profitability while approaching an approximation ratio of 1/2 in large markets. The second one is also truthful and achieves 1/2 approximation in general markets but incurs bounded unprofitability. Our aim is for both mechanisms to provide valuable insights into the truthful market design problem. Copyright © 2024, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

The Essence of Perceived Compatibility and Behavioral Intention in Mobile Money Use

The Essence of Perceived Compatibility and Behavioral Intent...

引用

Advanced Information Scientific Development (ICAISD), International Conference on

作者： Leni Susanti Siti Hajar Mohamad Mila Andria Savitri Karen Etania Saputra Doni Purnama Alamsyah Ahmad Setiadi Entrepreneurship Department BINUS Business School Bina Nusantara University Jakarta Indonesia Department of Business Management and Law Management and Science University Selangor Malaysia Interior Design Department School of Design Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Software Engineering Department Faculty of Information Technology Universitas Bina Sarana Informatika Jakarta Indonesia

ISBN: (数字)9798350392036

ISBN: (纸本)9798350392043

Today, financial technology is a part of consumer needs. Mobile payments are used to support daily transactions, so a study of factors that can support behavioral intention and mobile money use is conducted. This study examines the support of digital literacy, perceived security, and perceived compatibility of mobile payments in increasing behavioral intention and mobile money use. The research was conducted on mobile payment users in Bandung City (Indonesia), and 416 research participants were asked using a questionnaire. The research was conducted using a quantitative survey and was processed using the SmartPLS tool. Two tests, namely, the PLS Algorithm and Bootstrapping, were used to test the research model. Next, the research hypothesis testing was used to explain the results. The research results found positive support from digital literacy, perceived security, and perceived compatibility on mobile payment behavioral intention. However, only perceived compatibility can directly increase the use of mobile money. In line with the hypothesis test, behavioral intention can support increased mobile money use by digital payment users. The research findings explain the ability of behavioral intention to mediate support for digital literacy, perceived security, and perceived compatibility in mobile money use.

关键词： Surveys Online banking Fintech Urban areas Security Digital intelligence Testing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Domestic Garbage Detection Method Based on Improved YOLOv5 8th

Real-Time Domestic Garbage Detection Method Based on Improve...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Kan, Shengqi Fang, Wei Wu, Jiayi Sheng, Victor S. School of Computer and Software Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China State Key Laboratory of Severe Weather Chinese Academy of Meteorological Sciences Beijing100081 China Department of Computer Texas Tech University LubbockTX79409 United States

ISBN: (纸本)9783031067662

With the substantial improvement of people’s living standards, the amount of domestic garbage is increasing rapidly, and intelligent waste classification has become an urgent need in modern society. In this paper, we propose a real-time garbage detection model based on the improved YOLOv5 (you only look once version 5) algorithm. Firstly, mosaic data enhancement is introduced to enrich the background of the detection object and improve the robustness of the network. Secondly, Distance-IOU Non-Maximum Suppression is used to replace the traditional Non-Maximum Suppression to improve the suppression effect of prediction boxes. Finally, the network is further optimized from the aspect of activation function. The experimental results show that among the four versions of YOLOv5, their mean average precision(mAP) all reach more than 84%, The improved YOLOv5x has the best recognition effect, whose mAP reaches 89.4%, which is 2.1% higher than that of YOLOv5x and 5.3% higher than that of YOLOv5s. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

DCML: Boosting Applying Experience of NILM with Dilated Convolution and Multi-Task Learning

DCML: Boosting Applying Experience of NILM with Dilated Conv...

引用

IEEE International Conference on Communications in China (ICCC)

作者： ZhangMengru Zhao Fan Wu Huaqing Wu Tong Liu Conghao Zhou Jun Ma Yongmin Zhang Feng Lyu School of Computer Science and Engineering Central South University Changsha China Department of Electrical and Software Engineering University of Calgary Calgary AB Canada Big Data Institute Central South University Changsha China Department of Electrical and Computer Engineering University of Waterloo Waterloo Ontario Canada Hunan Energy Big Data Intelligence Limited Changsha China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

Non-intrusive load monitoring (NILM) is a promising approach for recognizing various electrical equipment energy usage patterns from aggregate load data. In this paper, we investigate the development of an NILM model to achieve high recognition accuracy, ensure a small model size for lightweight implementation, and enhance its adaptability to a wide range of appliance types. Specifically, we propose a framework named DCML, which employs dilated convolution to precisely control the receptive field, allowing efficient adjustments in feature extraction granularity to meet the specific requirements of different appliances. In addition, multi-task learning techniques are incorporated to allow simultaneous recognition of multiple appliances from a single model, saving model space while ensuring high recognition accuracy. Compared to the benchmark, our model reduces the recognition mean absolute error (MAE) by $36.8 \%, 16.8 \%$, and $43.8 \%$ for fridges, microwaves, and washing machines, respectively. Furthermore, the proposed DCML can significantly save the storage space of convolutional layers when simultaneously recognizing multiple appliances.

关键词： Adaptation models Accuracy Convolution Multitasking Data models Stability analysis Robustness

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：