检索结果-内蒙古大学图书馆

Model-to-Circuit Cross-Approximation for Printed Machine Learning Classifiers

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2023年第11期42卷 3532-3544页

作者： Armeniakos, Giorgos Zervakis, Georgios Soudris, Dimitrios Tahoori, Mehdi B. Henkel, Jorg Karlsruhe Institute of Technology Karlsruhe76131 Germany National Technical University of Athens School of Electrical and Computer Engineering Athens15780 Greece University of Patras Computer Engineering and Informatics Department Patras26504 Greece Karlsruhe Institute of Technology Department of Computer Science Karlsruhe76131 Germany

Printed electronics (PEs) promises on-demand fabrication, low nonrecurring engineering costs, and subcent fabrication costs. It also allows for high customization that would be infeasible in silicon, and bespoke architectures prevail to improve the efficiency of emerging PE machine learning (ML) applications. Nevertheless, large feature sizes in PE prohibit the realization of complex ML models in PE, even with bespoke architectures. In this work, we present an automated, cross-layer approximation framework tailored to bespoke architectures that enable complex ML models, such as multilayer perceptrons (MLPs) and support vector machines (SVMs), in PE. Our framework adopts cooperatively a hardware-driven coefficient approximation of the ML model at algorithmic level, a netlist pruning at logic level, and a voltage overscaling at the circuit level. Extensive experimental evaluation on 12 MLPs and 12 SVMs and more than 6000 approximate and exact designs demonstrates that our model-to-circuit cross-approximation delivers power and area optimal designs that, compared to the state-of-the-art exact designs, feature on average 51% and 66% area and power reduction, respectively, for less than 5% accuracy loss. Finally, we demonstrate that our framework enables 80% of the examined classifiers to be battery-powered with almost identical accuracy with the exact designs, paving thus the way toward smart complex printed applications. © 1982-2012 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

A Review on Leveraging Language Agnostic Automated Text Data Augmentation with Explainable Semantic Integrity 5

A Review on Leveraging Language Agnostic Automated Text Data...

引用

5th International Conference on Advanced Research in Computing, ICARC 2025

作者： Wijesundera, Sarith Peiris, Suresh Michael University of Westminster Department of Computer Science and Engineering London United Kingdom Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798331530983

Data Augmentation (DA) is an effective strategy to increase model generalisation. In Natural Language Processing (NLP), DA remains in its early stages, primarily due to the inherent sensitivity of textual data, which complicates the augmentation process. These complexities are further increased in multilingual contexts, as DA techniques effective in one language may not yield comparable results in others. As a result, manually identifying optimal DA techniques that preserve semantic integrity and are language agnostic remains a significant challenge. It emphasises the necessity for automating the text DA process with Explainable Artificial Intelligence (XAI), which offers a promising approach by calculating word importance scores to effectively guide the augmentation. In this paper, a comprehensive review of existing approaches in auto-text DA is presented, beginning with an exploration of the concept of auto-text DA, followed by a discussion on its cross-lingual applications, and concluding with the integration of XAI for semantic preservation. The paper highlights the critical need for further research to enhance the effectiveness and applicability of XAI in auto-text DA, enabling its use across diverse languages. © 2025 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Elevating Cystic Fibrosis Detection in Lungs using HRCT Images with a Cutting-Edge CNN-Based Approach 2

Elevating Cystic Fibrosis Detection in Lungs using HRCT Imag...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Ganjam, Amrutha Sriya Reddy C, Kishor Kumar Radhika, D. Ganjam, Karthik Singh.t, Monika Akuthota, Keerthi Sai Stanley College of Engineering and Technology for Women abids Department of Computer Science Hyderabad India University of Edinburgh Department School of Informatics MSc Data Science Edinburgh United Kingdom Stanley College of Engineering and Technology for Women Deptartment. of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331519056

The creation of an algorithm for recognizing pathological abnormalities in cystic fibrosis is investigated in this paper using the CNN model with a modified psp-net. Currently, Decision Trees, Random Forests, PSP Nets, and Neural Networks are utilized in the diagnosis of cystic fibrosis. Since convolutional neural networks (CNNs) can process complicated picture data rapidly and efficiently, the goal of this study is to use CNNs for the detection of anomalies associated with cystic fibrosis. The method groups distinct annotated images into a simple and efficient structure, runs the set of images through a multiscale CNN procedure, and precisely locates the lung region affected by cystic fibrosis. The result of this paper demonstrated that differences in the training dataset can impact performance, but annotating CT images and categorizing them in terms of similar pathologies can improve the accuracy of the model. The proposed CNN model achieved an Accuracy of 84 %, Precision of 74%, Recall of 79%, F1-Score of 72%, error rate of 16% Which is better when compared with existing approaches. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Machine Learning Algorithms Using Recursive Feature Elimination For Student Performance Prediction

Enhancing Machine Learning Algorithms Using Recursive Featur...

引用

2024 International of Seminar on Application for Technology of Information and Communication, iSemantic 2024

作者： Wijiyanto Marjuni, Aris Fanani, Ahmad Zainul Basuki, Ruri Suko Dian Nuswantoro University Department of Informatics Engineering Semarang Indonesia Duta Bangsa University Fakulty of Computer Science Surakarta Indonesia

ISBN: (纸本)9798350366648

Prediction systems for students' performance are crucial in improving educational outcomes in higher education institutions. Big data can be sourced from various channels, such as examination centers, academic systems, registration departments, and e-learning platforms. Extracting meaningful insights from educational data is challenging, necessitating data dimensionality reduction. This study introduces an enhanced recursive feature elimination (RFE) algorithm as a wrapper feature selection technique. We adopt machine learning by combining the proposed RFE with five different classifiers, including Gradient Boosting Classifier (GB), Random Forest Classifier (RF), Support Vector Classifier (SVC), K-Neighbors Classifier (KNN), and Decision Tree Classifier (DT). The dataset was originally intended to influence factors in dropout students, and it has 329 records and 9 features. The AUC score improved by 8% compared to the model tested without the proposed feature selection method by testing the proposed methodology with the Decision Tree Classifier. Educators and academic institutions can utilize this information to develop targeted intervention strategies, tailored learning experiences, and personalized recommendations for students, ultimately promoting a more effective learning environment and improving overall educational outcomes. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Digital Twin Empowered PV Power Prediction

引用

Journal of Modern Power Systems and Clean Energy 2024年第5期12卷 1472-1483页

作者： Xiaoyu Zhang Yushuai Li Tianyi Li Yonghao Gui Qiuye Sun David Wenzhong Gao the School of Information Science and Engi neering Northeastern UniversityShenyang 110004China the Department of Informatics Universi ty of OsloOslo 0316mNorway the Department of Computer Science Aalborg UniversityAal borg 9220Denmark the Electrification and Energy Infrastructures Division Oak Ridge National LaboratoryOak RidgeTN 37830USA the Department of Electrical and Computer Engineering University of DenverDenverCO 80208USA

The accurate prediction of photovoltaic(PV)power generation is significant to ensure the economic and safe operation of power *** this end,the paper establishes a new digital twin(DT)empowered PV power prediction framework that is capable of ensuring reliable data transmission and employing the DT to achieve high accuracy of power *** this framework,considering potential data contamination in the collected PV data,a generative adversarial network is employed to restore the historical dataset,which offers a prerequisite to ensure accurate mapping from the physical space to the digital ***,a new DT-empowered PV power prediction method is ***,we model a DT that encompasses a digital physical model for reflecting the physical operation mechanism and a neural network model(i.e.,a parallel network of convolution and bidirectional long short-term memory model)for capturing the hidden spatiotemporal *** proposed method enables the use of the DT to take advantages of the digital physical model and the neural network model,resulting in enhanced prediction ***,a real dataset is conducted to assess the effectiveness of the proposed method.

关键词： Photovoltaic power prediction digital twin hybrid prediction data recovery

来源：评论

学校读者我要写书评

暂无评论

Real-Time-Based Blood Wastage Management Using IoT and Blockchain Technology

引用

SN computer science 2024年第3期5卷 310页

作者： Kumar, Ajay Chatterjee, Indranath Pallavi Sharma, Komal Thakur, Muskan Department of Computer Science and Informatics Central University of Himachal Pradesh Dharamshala India Department of Computer Engineering Tongmyong University Busan South Korea Department of Computing and Mathematics Manchester Metropolitan University Manchester United Kingdom

The rapid shift in population density increased the need for blood in medical treatments, emphasizing the importance of appropriate blood supply chain management. Most countries have institutions that run centralized blood management information networks. However, these centralized solutions are limited as they do not provide complete blood information. In the healthcare industry, supply chains are crucial, ranging from the prompt delivery of vital medications to patients to the traceability of these medications. To address the limitations of current systems, we recommend the use of Blockchain technology to offer real-time information on donors and patients. The primary advantage of Blockchain is that information is secure and less susceptible to tampering. The blood supply chain uses private Blockchain solutions, ideal for commercial transactions due to the limited number of participants, who are both rapid and trustworthy. This article also explores how the Internet of Things (IoT) can be used to store blood information in QR codes. These codes, attached to blood packets, provide easy access to critical data such as blood group, cell count, etc. The proposed method aims to reduce blood waste, facilitate real-time identification of suitable donors, and improve the distribution of blood units to all needed locations. Ultimately, implementing this approach will be beneficial for both donors and patients. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Blockchain Internet of Things Smart contracts Supply chain

来源：评论

学校读者我要写书评

暂无评论

A Novel Drone-Station Matching model in Smart Cities based on Strict Preferences

引用

无人系统（英文） 2023年第3期11卷 261-271页

作者： Debolina Nath Anjan Bandyopadhyay Ankit Rana Tarek Gaber Aboul Ella Hassanien Department of Computer Science and Engineering Amity University Kolkata KolkataWest BengalIndia Department of Computer Science and Engineering Gitam University BangaloreKarnatakaIndia School of Science Engineeringand Environment University of SalfordUK Faculty of Computers and Informatics Suez Canal UniversityIsmailiaEgypt Scientific Research Group in Egypt(SRGE) Egypt Faculty of Computer and Artificial Intelligence Cairo UniversityCairoEgypt Scientific Research Group in Egypt(SRGE) Egypt

There has been a considerable increase in the use of drones,or unmanned aerial vehicles(UAVs),in recent times,for a wide variety of purposes such as security,surveillance,delivery,search and rescue operations,penetration of inaccessible or unsafe areas,*** increasing number of drones working in an area poses a challenge to finding a suitable charging or resting station for each drone after completing its task or when it goes low on its *** classical methodology followed by drones is to return to their pre-assigned charging station every time it requires a *** approach is found to be inefficient as it leads to an unnecessary waste of time as well as power,which could be easily saved if the drone is allotted a nearby charging station that is ***,we propose a drone-allocation model based on a preference matching algorithm where the drones will be allotted the nearest available station to land if the station is *** problem is modeled as three entities:Drones,system controllers and charging *** matching algorithm was then used to design a Drone-Station Matching *** simulation results of our proposed model showed that there would be considerably less power consumption and more time saving over the conventional *** would save its travel time and power and ensure more efficient use of the drone.

关键词： Unmanned Aerial Vehicle(UAV) stable matching resource allocation smart city matching algorithm

来源：评论

学校读者我要写书评

暂无评论

UNet Based onMulti-Object Segmentation and Convolution Neural Network for Object Recognition

引用

computers, Materials & Continua 2024年第7期80卷 1563-1580页

作者： Nouf Abdullah Almujally Bisma Riaz Chughtai Naif Al Mudawi Abdulwahab Alazeb Asaad Algarni Hamdan A.Alzahrani Jeongmin Park Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Information Technology Department College of Computing and InformaticsSaudi Electronic UniversityRiyadh13316Saudi Arabia Department of Computer Engineering Korea Polytechnic UniversitySiheung-siGyeonggi-do237Republic of Korea

The recent advancements in vision technology have had a significant impact on our ability to identify multiple objects and understand complex *** technologies,such as augmented reality-driven scene integration,robotic navigation,autonomous driving,and guided tour systems,heavily rely on this type of scene *** paper presents a novel segmentation approach based on the UNet network model,aimed at recognizing multiple objects within an *** methodology begins with the acquisition and preprocessing of the image,followed by segmentation using the fine-tuned UNet ***,we use an annotation tool to accurately label the segmented *** labeling,significant features are extracted from these segmented objects,encompassing KAZE(Accelerated Segmentation and Extraction)features,energy-based edge detection,frequency-based,and blob *** the classification stage,a convolution neural network(CNN)is *** comprehensive methodology demonstrates a robust framework for achieving accurate and efficient recognition of multiple objects in *** experimental results,which include complex object datasets like MSRC-v2 and PASCAL-VOC12,have been *** analyzing the experimental results,it was found that the PASCAL-VOC12 dataset achieved an accuracy rate of 95%,while the MSRC-v2 dataset achieved an accuracy of 89%.The evaluation performed on these diverse datasets highlights a notably impressive level of performance.

关键词： UNet segmentation blob fourier transform convolution neural network

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning to Identify and Categorize Personally Identifiable Information and Payment Card Industry Data in Textual Content 4

Using Machine Learning to Identify and Categorize Personally...

引用

4th International Conference on Advanced Research in Computing, ICARC 2024

作者： Arambawela, Milinda Aponso, Achala University of Westminster Computer Science and Engineering London United Kingdom Informatics Institute of Technology Department of Computing Colombo Sri Lanka

ISBN: (纸本)9798350384864

The advent of the Internet has significantly stream-lined daily tasks through the rapid increase of online services. Everyday activities, such as purchasing goods and scheduling appointments with healthcare professionals, have become more speedy, efficient and user-friendly with the integration of the Internet. The continuous improvement of online services has led to many people moving towards digital activities. As a result, it has heightened the recording of personal and payment transaction data across various storage mediums, including databases and log files. The protection and regulation of this sensitive data are imperative, aligning with the guidelines outlined in GDPR and PCI-DSS compliances. Recognizing exposed personal data poses a considerable challenge. This research introduces a novel approach to identifying payment card industry data (PCI) and personally identifiable information (PII). The research project proposes a machine learning-based text classification model utilizing the Convolutional Neural Network (CNN) model to discern PII and PCI data within a given text. The CNN model has been constructed and compared against Naive Bayes, Gradient Boost, Random Forest, and Support Vector Machine (SVM) models. The CNN model achieved the highest accuracy at 0.96 (96%). Additionally, the F1 scores for each class were significant, with PII scoring 0.94, PCI scoring 0.95, and Normal scoring 0.99. Following the model's construction and training, it was employed with the saved tokenizer's word indexes and label encoders in the developed classification tool. This tool successfully delivered the promised results, identifying exposed PII and PCI data. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Conflict Between Artificial Intelligence and Traditional Designers: How Artificial Intelligence Transforms the Design Process 3rd

Conflict Between Artificial Intelligence and Traditional Des...

引用

3rd International Conference on Emerging Trends in Expert Applications and Security, ICE-TEAS 2024

作者： Gupta, Keshav Dev Pandey, Rishi Pathak, Devendra Nath Ranjan, Rakesh Gupta, Vijay Department of Computer Science Engineering Poornima College of Engineering Rajsthan Jaipur India Department of Animation & Multimedia Birla Institute of Technology Ranchi Mesra India Department of Computer Science & Engineering Poornima College of Engineering ISI-6 RIICO Institutional Area Sitapura Rajasthan Jaipur India Department of Computer Science & Engineering Babu Banarasi Das University Lucknow India Department of Computer Science International School of Informatics and Management Sector 12 Mahaveer Marg Jaipur Mansarovar India

ISBN: (纸本)9789819739905

The development of technology, especially the use of resources provided by artificial intelligence (AI), has advanced in areas where business is gaining importance and is an important fear of economic growth. The use of technical skills in the creation of products and services is not unique to design. In today's world, artificial intelligence (AI) has become an industry in many countries, and design is no exception. However, the lines of work performed by humans and machines are changing rapidly, and as a result, the global market is also changing a lot. This is the result of very rapidly developing technology. This raises the question of how this progress has and will continue to influence the future work of designers. What skills do designers need to enter or stay in this industry? The purpose of this article is to provide a summary of research findings on the impact of intelligence on the performance of designers, as well as an analysis that includes an evaluation of the potential and benefits of intelligent design solutions. Case studies and other scientific studies are used to analyze the applications and benefits of AI-based solutions. Studies can be theoretical or empirical. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： International trade

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：