检索结果-内蒙古大学图书馆

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Reidy, Brendan Tabrizchi, Sepehr Mohammadi, Mohammadreza Angizi, Shaahin Roohi, Arman Zand, Ramtin Department of Computer Science and Engineering University of South Carolina ColumbiaSC United States School of Computing University of Nebraska-Lincoln LincolnNE United States Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ United States

ISBN: (纸本)9798400706011

With the rise of tiny IoT devices powered by machine learning (ML), many researchers have directed their focus toward compressing models to fit on tiny edge devices. Recent works have achieved remarkable success in compressing ML models for object detection and image classification on microcontrollers with small memory, e.g., 512kB SRAM. However, there remain many challenges prohibiting the deployment of ML systems that require high-resolution images. Due to fundamental limits in memory capacity for tiny IoT devices, it may be physically impossible to store large images without external hardware. To this end, we propose a high-resolution image scaling system for edge ML, called HiRISE, which is equipped with selective region-of-interest (ROI) capability leveraging analog in-sensor image scaling. Our methodology not only significantly reduces the peak memory requirements, but also achieves up to 17.7× reduction in data transfer and energy consumption. © 2024 Copyright held by the owner/author(s).

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

An Elite Archive-Assisted Multi-Objective Evolutionary Algorithm for mRNA Design 13

An Elite Archive-Assisted Multi-Objective Evolutionary Algor...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Hong, Wenjing Chen, Cheng Zhu, Zexuan Tang, Ke Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9798350308365

Messenger RNA (mRNA) vaccines have emerged as highly effective strategies in the prophylaxis and treatment of diseases. mRNA design, a key to the success of mRNA vaccines, in-volves finding optimal codons and increasing secondary structure stability to lengthen mRNA half-life, ultimately enhancing protein expression. Despite receiving widespread attention, most methods primarily rely on manual design, which is time-consuming and labor-intensive. While optimization approaches can alleviate this issue, existing methods still exhibit critical limitations caused by conflicts between codon usage and mRNA structural stability, compounded by the vast design space of mRNA resulting from the presence of synonymous codons. In this paper, a novel multi-objective evolutionary optimization-based mRNA design method is proposed. We first formulate the mRNA design problem as a multi-objective optimization problem and then develop an Elite Archive-Assisted Multi-Objective Evolutionary algorithm for mRNA Design, namely EAA-MOED, by incorporating a novel elite archive-assisted method into a weighted optimization framework to improve search efficiency. Experimental studies, involving two state-of-the-art mRNA design methods and five well-known MOEAs, show the competitiveness of the proposed EAA-MOED in mRNA design. © 2024 IEEE.

关键词： Vaccines

来源：评论

学校读者我要写书评

暂无评论

Paddy Plant Disease Detection using Hybrid Deep Learning Algorithms 8

Paddy Plant Disease Detection using Hybrid Deep Learning Alg...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Suguna, R. Deepa, S. Kanimozhi, T. Chandru, M. Arun, G. Harshini, M. Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam Tamilnadu Erode638401 India Kongu Engineering College Perundurai Department of Computer Technology - Pg Tamilnadu Erode638060 India Sri Eshwar College of Engineering Department of Artificial Intelligence and Data Science Coimbatore641202 India College Department of Computer Science Erode India Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai India Kongu Engineering College Tamilnadu Perundurai Erode638060 India

ISBN: (纸本)9798350367904

Agriculture is the backbone of India's economy, supporting a large portion of the population and establishing the country as a key global player in food production. India ranks as the second-largest producer of both paddy and wheat. However, agricultural productivity is highly susceptible to various plant diseases, which can significantly reduce crop yields and quality. Paddy, one of the most important staple crops, is particularly vulnerable to diseases caused mainly by viral and bacterial related diseases. The climate conditions are also play a vital role in paddy plant diseases. This research work proposes a deep learning-based approach for early detection and classification of paddy diseases. The proposed research devises a hybrid model that combines the VGG19 and ResNet50 algorithms, the system analyses images of both healthy and disease-affected paddy leaves, sourced from the Kaggle repository. This research focuses on predicting four major paddy diseases that can cause yield losses of up to 80%, and in severe cases, can destroy an entire crop: (i) Paddy Blast, (ii) Bacterial Leaf Blight, (iii) Sheath Blight, and (iv) Ufra Disease. The proposed model achieves a high accuracy rate of 98% in predicting paddy diseases and offers a rapid classification process, showcasing the potential of advanced image processing and deep learning techniques to mitigate the impact of paddy plant diseases on agricultural productivity. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

A Non-Adaptive Algorithm for the Quantitative Group Testing Problem 37

A Non-Adaptive Algorithm for the Quantitative Group Testing ...

引用

37th Annual Conference on Learning Theory, COLT 2024

作者： Soleymani, Mahdi Javidi, Tara Halıcıoğlu Data Science Institute University of California San Diego United States Department of Electrical and Computer Engineering University of California San Diego United States

Consider an n dimensional binary feature vector with k non-zero entries. The vector can be interpreted as the incident vector corresponding to n items out of which k items are defective. The quantitative group testing (QGT) problem aims at learning this binary feature vector by queries on subsets of the items that return the total number of defective items. We consider this problem under the non-adaptive scenario where the queries on subsets are designed collectively and can be executed in parallel. Most of the existing efficient non-adaptive algorithms for the sublinear regime where k = nα with 0 3). In this work, we present a concatenated construction method yielding a non-adaptive algorithm with the decoding complexity of O(n2α + n log2 n). The probability of decoding failure is analyzed by establishing a connection between the QGT problem and the so-called balls into bins problem. Our algorithm reduces the gap between the information-theoretic and computational bound for the number of required queries/tests from log k to log log k. This narrows the gap in number of tests for non-adaptive algorithms within the class of algorithms with o(n2) decoding complexity. Moreover, although our algorithm exhibits a log log k gap in terms of the number of tests, it is surpassed by the existing asymptotically optimal construction only in scenarios where k is exceptionally large for moderate values of α, such as k > 1027 for α = 0.7, thereby highlighting the practical applicability of our proposed concatenated construction. © 2024 M. Soleymani & T. Javidi.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

IPL data Analysis and Visualization for Team Selection and Profit Strategy 7

IPL Data Analysis and Visualization for Team Selection and P...

引用

7th International Conference on computing Methodologies and Communication, ICCMC 2023

作者： Saranya, G. Swaminathan, Aravind Joel Benjamin, J. Surendran, R. Nelson, Leema Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai campus Chennai India Data Science Middlesex University Dubai United Arab Emirates Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science and Engineering Chitkara University Institute of Engineering & Technology Chitkara University Punjab India

ISBN: (纸本)9781665464086

Day by day, the role of data science and machine learning in cricket is increasing due to the large amount of data generated from a single player on a whole line. The field of data science is the intensive study of data to extract insights and knowledge from the data and apply the acquired knowledge and actionable insights. These available data and statistics are used to predict things like the team's first-innings score and the probability of winning the second team, etc. This study works on Indian Premier League (IPL) data Analysis 2022 and data Visualization for the duration (2008-2020) using Python. This application modules are followed by preprocessing, data analysis, and visualization, and finally create a model that predicts the team's overall score and the probability of winning. When building models, python algorithms such as Numpy is used for S cientific computing, Pandas used to perform data Analysis, and finally Matplotlib and S eaborn to enable data Visualization. Finally, this paper helps the trainers and owners of the team during the auction to select an emerging player to win the matches in the entire season and to win the trophy and to get profit to the owners by the profit strategy done in this analysis report. © 2023 IEEE.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Harnessing Blockchain and Deep Learning for Enhanced Energy Analytics in Photovoltaic Systems

Harnessing Blockchain and Deep Learning for Enhanced Energy ...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Subbulakshmi, G. Sujatha, S. Saraswathi, V. Hemamlini, Ranganathan Rani St Joseph's College of Engineering and Technology Department of Artificial Intelligence and Data Science Engineering Chennai India Bit Campus Anna University Department of Computer Appication Tiruchirappalli India Chennai Institute of Technology Department of Computer Science Engineering Chennai India St. Peter's Institute of Higher Education and Research Department of Electrical and Elctronics Engineering Chennai India

ISBN: (纸本)9798331510022

The rapid evolution of solar energy in industrial sectors has sparked a growing interest in renewable energy, particularly within the context of smart grids and systems. The effective detection and management of energies within photovoltaic (PV) systems stand as crucial tasks in this landscape. This abstract introduces a proposed model aimed at exploring the integration of blockchain networks within large-scale solar energy infrastructures. The primary objective is to establish a framework that enables the distribution of solar energy in a decentralized manner to end-users while ensuring secure energy transactions between producers and consumers. Blockchain technology serves as the cornerstone of this model, encompassing intelligent techniques to address energy mitigation challenges within the solar energy network. By leveraging blockchain, the detection of energies within solar power plants becomes shared knowledge accessible to all users connected to the solar power network. The research within this framework emphasizes the exploration and application of diverse Deep Learning (DL) architectures, including autoencoders, Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, Deep Stacking Networks (DSNs), and Deep Belief Networks (DBNs). Furthermore, this research extends beyond conventional machine learning approaches, incorporating knowledge-driven methodologies. It incorporates generative models such as adversarial networks and transfer learning, elevating the scope of machine learning in optimizing energy detection, distribution, and consumption within the block chain-based solar energy infrastructure. This interdisciplinary approach signifies a significant stride in fortifying renewable energy systems. By amalgamating blockchain's decentralized nature with sophisticated DL architectures and knowledge-driven models, it establishes a resilient and efficient renewable energy infrastructure capable of meeting escalating demands for sustainabl

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Image Analysis to Track Vehicles 2

Deep Learning-Based Image Analysis to Track Vehicles

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Prabakaran, P. Jayasudha, R. Sandhu, Mukta Gupta, Sandeep School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Department of Computer Applications Chennai India Dr.N.G.P.Institute of Technology Department of Mathematics Coimbatore India Shri Vishwakarma Skill University Skill Department of Computer Science and Engineering Haryana Palwal India Department of Electrical Engineering Dehradun India

ISBN: (纸本)9798350371055

There are many ways to track the traffic conditions on roads. With the rise of AI-based image processing technology, there has been a surge in interest in developing traffic monitoring systems that rely on camera vision data. An improved road monitoring system may be derived from the data collected in this research by placing a camera at a junction. The technique detects and classifies vehicles using a deep-learning-based methodology (YOLOv4). By comparing the positions of the vehicle with the map HD, lane-by-lane trajectories of the vehicle may be approximated. The predicted vehicle trajectories are used to calculate each lane's wait lengths and traffic volumes, broken down by travel direction. This technique was evaluated using five distinct metrics: vehicle detection rates, trajectory prediction, type of vehicle categorization, traffic volume estimate, and queue length assessment. Thousands of samples were used to assess its performance. Based on the findings, it is acceptable to assume that the system can identify vehicles with a 98% success rate and an error rate of less than 25% regarding lane-by-lane trip volume estimation and vehicle type classification. Therefore, this study's approach reveals the viability of collecting comprehensive traffic information from a camera set up at a junction. Current traffic monitoring schemes have a reasonable likelihood of being developed by this study's significant contribution, which is a strategy that combines AI with HD map approaches. © 2024 IEEE.

关键词： Artificial Intelligence HD Map Traffic Monitoring System Vehicle Type Classification YOLOv4

来源：评论

学校读者我要写书评

暂无评论

Investigating customer churn in banking:a machine learning approach and visualization app for data science and management

引用

data science and Management 2024年第1期7卷 7-16页

作者： Pahul Preet Singh Fahim Islam Anik Rahul Senapati Arnav Sinha Nazmus Sakib Eklas Hossain Institute for Artificial Intelligence and Data Science University at BuffaloThe State University of New YorkAmherst14068United States Department of Mechanical Engineering Khulna University of Engineering&TechnologyKhulna9203Bangladesh Department of Information Technology Kennesaw State UniversityMarietta30067United States Department of Electrical and Computer Engineering Boise State UniversityBoise83725United States

Customer attrition in the banking industry occurs when consumers quit using the goods and services offered by the bank for some time and,after that,end their connection with the ***,customer retention is essential in today’s extremely competitive banking ***,having a solid customer base helps attract new consumers by fostering confidence and a referral from a current *** factors make reducing client attrition a crucial step that banks must *** our research,we aim to examine bank data and forecast which users will most likely discontinue using the bank’s services and become paying *** use various machine learning algorithms to analyze the data and show comparative analysis on different evaluation *** addition,we developed a data Visualization RShiny app for data science and management regarding customer churn *** this data will help the bank indicate the trend and then try to retain customers on the verge of attrition.

关键词： Bank customer attrition Churn prediction Machine learning XGboost Random forest

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wound Care in Healthcare Systems with Logistic Regression for Infection Detection 1

Enhancing Wound Care in Healthcare Systems with Logistic Reg...

引用

1st International Conference on Innovations in Communications, electrical and computer engineering, ICICEC 2024

作者： Ramalingam, L. Amarnath, Raveendra N. Arun, V. Sendhilkumar, N.C. Ravi, Rupavathy Srinivasan, C. Loyola Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Mphasis Corporation MelissaTX United States SRM Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computing Technologies Tamil Nadu Chennai India Sri Indu College of Engineering and Technology Department of Electronics and Communication Engineering Hyderabad India Agni College of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376517

In healthcare systems, wound care management is essential for reducing infections and promoting faster recovery. To improve wound care, this paper proposes a data-driven method that combines machine learning (ML), more particularly, Logistic Regression (LR), with Internet of Things (IoT) sensors to identify early infections. The system provides real-time data streams to healthcare providers by continually monitoring important wound parameters, including temperature, moisture, pH levels, and exudate presence via IoT-enabled sensors. Using LR, the system predicts the potential of wound infections based on these physiological indicators, allowing for more effective patient care and early treatments. When tested for accuracy and dependability in infection prediction, the proposed model shows significant detection skills with few false positives. This approach optimizes clinical processes by reducing the need for manual wound examination, enhancing patient safety, and lowering the possibility of complications from infections. Wound care management might improve patient outcomes and expedite infection control measures in medical institutions. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Large Model for Small data: Foundation Model for Cross-Modal RF Human Activity Recognition 24

Large Model for Small Data: Foundation Model for Cross-Modal...

引用

22nd ACM Conference on Embedded Networked Sensor Systems, SenSys 2024

作者： Weng, Yuxuan Wu, Guoquan Zheng, Tianyue Yang, Yanbing Luo, Jun Department of Computer Science and Engineering Southern University of Science and Technology China Smart City Center Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology China College of Computer Science Sichuan University China College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400706974

Radio-Frequency (RF)-based Human Activity Recognition (HAR) rises as a promising solution for applications unamenable to techniques requiring computer visions. However, the scarcity of labeled RF data due to their non-interpretable nature poses a significant obstacle. Thanks to the recent breakthrough of foundation models (FMs), extracting deep semantic insights from unlabeled visual data become viable, yet these vision-based FMs fall short when applied to small RF datasets. To bridge this gap, we introduce FM-Fi, an innovative cross-modal framework engineered to translate the knowledge of vision-based FMs for enhancing RF-based HAR systems. FM-Fi involves a novel cross-modal contrastive knowledge distillation mechanism, enabling an RF encoder to inherit the interpretative power of FMs for achieving zero-shot learning. It also employs the intrinsic capabilities of FM and RF to remove extraneous features for better alignment between the two modalities. The framework is further refined through metric-based few-shot learning techniques, aiming to boost the performance for predefined HAR tasks. Comprehensive evaluations evidently indicate that FM-Fi rivals the effectiveness of vision-based methodologies, and the evaluation results provide empirical validation of FM-Fi's generalizability across various environments. © 2024 Copyright is held by the owner/author(s).

关键词： Zero-shot learning

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：