检索结果-内蒙古大学图书馆

Annual Conference of Industrial Electronics Society

作者： Jaliya L. Wijayaraja Nimsiri Abhayasinghe Sasini Wellalage Department of Computer Systems Engineering Faculty of Computing SLIIT Malabe Sri Lanka Department of Electrical and Electronic Engineering Faculty of Engineering SLIIT Malabe Sri Lanka

Enhancing the performance and extending the life-cycle of older vehicles through retrofitting with improved systems presents an alluring opportunity. However, achieving accurate sensing of crucial parameters, such as engine revolutions per minute (RPM), poses challenges due to the need for mechanical manipulation and some designs, which may result in diminished accuracy in adverse settings. This study proposes using the primary ignition pulse signal to accurately determine engine speed without mechanical manipulation. We investigate the effectiveness of signal processing methods, including the RC filter, 2nd and 6th order Butterworth filter, to improve the accuracy of the readings. Our proposed method successfully collects data from conventional internal combustion engines, with simulated signal processing methods producing accurate detection of RPM and reduced fluctuations. The proposed method eliminated the noise, leading to accurate RPM measurements, while the maximum standard deviation observed for the RC filter implementation was 38.74. By accurately sensing key parameters, older vehicles can be retrofitted with improved systems, leading to enhanced performance and an extended lifecycle. The introduced methods can be practically implemented using custom electronics or embedded systems and can contribute to future research on automotive retrofitting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Decision Management: Multi-Modal Analytics in a Health Case Study 19

Data-Driven Decision Management: Multi-Modal Analytics in a ...

引用

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

作者： Agomuo, Okechukwu Clement Khan, Zohaib Otuomasirichi, Agomuo Ijeoma Uzoma, Agomuo Kingsley Muzamal, Junaid Hussain Department of Operations and Information Systems University of Utah Salt Lake City United States Dept. of Software Engineering FAST NUCES Lahore Pakistan Department of Agricultural Economics University of Nigeria Enugu Nigeria Center for Environmental Management and Green Energy University of Nigeria Enugu Nigeria Fast School of Computing Fast NUCES Lahore Pakistan

ISBN: (纸本)9798331507817

In an era where data is abundant yet underutilized, organizations across various sectors face challenges in extracting actionable insights from complex, multi-modal datasets. To address these challenges, this study proposes a versatile data analytics framework designed to enhance predictive accuracy and support informed decision-making. The framework integrates structured and unstructured data, leveraging advanced Transformer architectures to capture temporal dynamics and complex interactions within the data. In a healthcare use case, the framework demonstrated its effectiveness by achieving an Accuracy of 0.854, an F1-Score of 0.895, and an AUC-ROC of 0.930, significantly outperforming traditional models. By incorporating SHAP for interpretability, the framework ensures that its predictions are both accurate and transparent, making it a valuable tool for decision-makers. While healthcare is one application, the framework’s flexibility allows it to be adapted to a wide range of industries. Future work will focus on validating the framework across different sectors and integrating it into operational workflows to optimize decision-making and outcomes. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Classification using CNN and Transfer Learning (TL)

Skin Cancer Classification using CNN and Transfer Learning (...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Shashank Patel Mudita Pandey Rajeswari D Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

Skin cancer is a predominant and possibly lethal condition that distresses people across the world. Primary detection and precise finding are crucial for leveraging efficacious treatment and enhanced patient consequences. This research study explores the application off Artificial Intelligence (AI) resolutions for the primary finding and analysis of skin cancer. The study leverages a dataset of dermatological images and employs various ML methods, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and decision trees, to analyse the existence of skin cancer with a higher degree of accuracy. By utilizing a combination of image processing and feature extraction, the AI model demonstrates higher performance in classifying skin lesions into malignant or benign categories. The proposed model has achieved an accuracy rate of 98.52%, making the AI-based system a promising tool for dermatologists and healthcare professionals.

关键词： Support vector machines Technological innovation Dermatology Transfer learning Collaboration Medical services Skin

来源：评论

学校读者我要写书评

暂无评论

Disease Detection in Arecanut using Convolutional Neural Network

Disease Detection in Arecanut using Convolutional Neural Net...

引用

Advances in computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： V Arun Karthik Jatin Shivaprakash D Rajeswari Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Arecanut, also known as betel nut, is a tropical crop predominantly grown in India. The country holds the second position globally in terms of the production and consumption of arecanut. Throughout its life cycle, the areca nut plant is susceptible to a variety of diseases affecting its roots, trunk, leaves, and fruits. Some of these diseases are visible to the naked eye, while others are not. Farmers traditionally analyze every crop to detect any signs of disease, a process that is extremely *** this study, we propose an automatic system that aids in detecting the diseases of arecanut leaves using Convolutional Neural Networks (CNN) and deep learning algorithms. A Convolutional Neural Network is a Deep Learning algorithm that takes an image as input, assigns learnable weights and biases to various features in the image, and then learns from the results to distinguish one feature from another. This approach significantly reduces the manual effort required in disease detection and increases the efficiency of the process. A datset is developed with many photos of healthy and sick arecanut leaves in order to train and evaluate the CNN model. An 80:20 split of the dataset was made into training and testing data. The goal of training the model over multiple epochs was to maximize validation and test accuracy while minimizing loss. It was discovered that the suggested method for diagnosing arecanut illnesses was precise and successful. This study contributes to the ongoing efforts to leverage technology in agriculture, with the aim of improving crop health and productivity. This study indicate that the proposed system can accurately identify diseases in arecanut leaves with a good and best accuracy. The system was able to distinguish between healthy and diseased leaves, and suggest appropriate remedies for the detected diseases. These findings demonstrate the potential of using Convolutional Neural Networks and deep learning algorithms in the field of agriculture, par

关键词： Deep learning Training Productivity Plant diseases Accuracy Crops Agriculture

来源：评论

学校读者我要写书评

暂无评论

Learning Recovery Strategies for Dynamic Self-healing in Reactive systems

arXiv

引用

arXiv 2024年

作者： Sanabria, Mateo Dusparic, Ivana Cardozo, Nicolás Systems and Computing Engineering Department Universidad de los Andes Colombia School of Computer Science and Statistics Trinity College Dublin Ireland

Self-healing systems depend on following a set of predefined instructions to recover from a known failure state. Failure states are generally detected based on domain specific specialized metrics. Failure fixes are applied at predefined application hooks that are not sufficiently expressive to manage different failure types. Self-healing is usually applied in the context of distributed systems, where the detection of failures is constrained to communication problems, and resolution strategies often consist of replacing complete components. However, current complex systems may reach failure states at a fine granularity not anticipated by developers (for example, value range changes for data streaming in IoT systems), making them unsuitable for existing self-healing techniques. To counter these problems, in this paper we propose a new self-healing framework that learns recovery strategies for healing fine-grained system behavior at run time. Our proposal targets complex reactive systems, defining monitors as predicates specifying satisfiability conditions of system properties. Such monitors are functionally expressive and can be defined at run time to detect failure states at any execution point. Once failure states are detected, we use a Reinforcement Learning-based technique to learn a recovery strategy based on users’ corrective sequences. Finally, to execute the learned strategies, we extract them as Context-oriented Programming variations that activate dynamically whenever the failure state is detected, overwriting the base system behavior with the recovery strategy for that state. We validate the feasibility and effectiveness of our framework through a prototypical reactive application for tracking mouse movements, and the DeltaIoT exemplar for self-healing systems. Our results demonstrate that with just the definition of monitors, the system is effective in detecting and recovering from failures between 55% - 92% of the cases in the first application, and at pa

关键词： Functional programming

来源：评论

学校读者我要写书评

暂无评论

Comparing Fairness of Generative Mobility Models

arXiv

引用

arXiv 2024年

作者： Wang, Daniel McFarland, Jack Mashhadi, Afra Ugurel, Ekin Computing and Software Systems University of Washington Bothell United States Department of Civil & Environmental Engineering University of Washington Seattle United States

Crowd flow data serves as a foundation for predictive modeling, aiding in understanding of city structure [3], epidemics [12], and visitation patterns [9]. Extensive mobility studies have applied variety of models in this area, however there has been little work in quantifying the fairness of them in terms of the equity of their performance across geographical space. Indeed, as recent evidence from the broader machine learning domain has shown, the systematic discrimination in making decisions against different groups has been shifted from people to autonomous algorithms [6]. In many applications, discrimination may be defined by different protected attributes, such as race, gender, ethnicity, and religion, that directly prevent favorable outcomes for a minority group in societal resource allocation, education equality, employment opportunity, etc [8]. Similarly, in the context of spatiotemporal data, mobility demand prediction algorithms have been shown to offer higher service quality to neighborhoods with a larger Caucasian population [4]. However, in such contexts, only a handful of recent studies exist that examine the fairness of location-based systems [13], and to the best of our knowledge, no effort has yet been made in measuring the fairness of generative mobility models and their resulting synthetic traces. In this paper, we seek to measure and compare these models based on fairness performance across multiple datasets. We do so by introducing metrics for evaluating both the utility of a generative model and the quality and fairness of their resulting traces, where accuracy is measured in terms of Common Part of Commuters (CPC). This metric is based on the Sørensen-Dice index and measures the similarity between real flows and generated flows (Equation 1) (Equation presented). Where ŷ is the generated flow, and y is the real flow between location i and j. It is worth noting that, CPC is always positive and contained in the closed interval [0,1] where 1 is a

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Fraud Detection in Financial Transactions: A Machine Learning Approach

Fraud Detection in Financial Transactions: A Machine Learnin...

引用

International Conference on Science Technology engineering and Management (ICONSTEM)

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

Financial fraud presents substantial risks to individuals and financial institutions globally, necessitating efficient detection mechanisms to mitigate probable fatalities. In this study, the development and evaluation of machine learning (ML) models for detecting fraudulent activities in mobile money transactions are investigated. Using a synthetic dataset, realworld transaction scenarios involving a variety of transaction kinds and features are simulated. The effectiveness of many machine learning (ML) methods, such as LGBM, random forests, XGBoost, and logistic regression, in spotting fraudulent transactions is investigated through data preparation, feature engineering, and model-building procedures. Employing techniques such as SMOTE-Tomek resampling and hyperparameter tuning enhances the performance and robustness of our models. Our results reveal that the XGBoost classifier emerges as the top-performing model, exhibiting a remarkable accuracy of 99.95%. The findings underscore the potential of MLbased approaches to bolster security and trust in mobile financial services, contributing to the ongoing advancement of fraud detection methodologies in the financial sector.

关键词： Analytical models Accuracy Computational modeling Finance Data models Fraud Security

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Using Data Augmentation

Speech Emotion Recognition Using Data Augmentation

引用

Advances in computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Tanisha Kapoor Arnaja Ganguly D Rajeswari Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Speech emotion recognition (SER) is a vital aspect of human-computer interaction systems, enabling applications such as virtual assistants, affective computing, and mental health monitoring. In this work, deep learning methods to audio data to suggest a fresh approach to SER are applied. While still in its infancy, CNN is capable of accurately identifying emotions in human speech, but it requires careful study in order to produce reliable *** studywas done using a heterogeneous dataset that included recordings of different emotional states from many sources, such as TESS, RAVDESS, SAVEE, CREMAD, and others. A deep neural network model was built with many fully connected layers and ReLU activation functions after preprocessing and feature extraction. The suggested method’ s effectiveness was assessed using common performance indicators like F1-score, recall, accuracy, and precision. Our tests produced encouraging outcomes, with an accuracy of 84% on the test dataset. This demonstrates how well the suggested technique works to discern emotions from speech audio information.

关键词： Emotion recognition Accuracy Virtual assistants Speech recognition Mental health Feature extraction Recording

来源：评论

学校读者我要写书评

暂无评论

Beyond Success: Quantifying Demonstration Quality in Learning from Demonstration

Beyond Success: Quantifying Demonstration Quality in Learnin...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Muhammad Bilal Nir Lipovetzky Denny Oetomo Wafa Johal School of Computing and Information Systems The University of Melbourne Parkville Victoria Australia Department of Mechanical Engineering The University of Melbourne Parkville Victoria Australia

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Learning from Demonstration (LfD) empowers novice users to teach robots daily life tasks without writing sophisticated code, thereby promoting the democratization of robotics. However, novice users often provide sub-optimal demonstrations, which can potentially impact the robot’s ability to efficiently learn and execute the tasks. Prior research has assessed the quality of demonstrations by evaluating the robot’s task performance; however, the approach remains insufficient to qualify individual demonstrations, leaving the reason for classifying demonstrations as high- or low-quality unknown. Therefore, this simulation-based study aims to quantify the quality of individual demonstration at each step by incorporating motion-related quality features such as manipulability and joint-space jerk. To assess the efficacy of these features, we initially evaluated the given demonstrations—taking into account each quality feature—to rank them from high- to low-quality. Subsequently, we investigated the impact of demonstration’s quality on task performance and the quality of task execution. In this pursuit, we trained a series of LfD models for distinct manipulation tasks: cube lifting and pick-and-place of soda can. Our results illustrate a strong correlation between ranked demonstrations and the quality of task execution. Interestingly, we observed that the quality features have a significant impact on task performance, particularly when the provided demonstrations exhibit diversity in terms of quality. Overall, this analysis enables quantifying the quality of individual demonstrations based on motion-related quality features, thus improving learning from demonstration.

关键词： Training Correlation coefficient Iris Correlation Codes Computational modeling Writing Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Convolutional Autoencoder for Image Denoising: A Compositional Subspace Representation Perspective 3

Convolutional Autoencoder for Image Denoising: A Composition...

引用

3rd IEEE International Conference on Artificial Intelligence in engineering and Technology, IICAIET 2021

作者： Teow, Matthew Y. W. School of Engineering and Technology Sunway University Department of Computing and Information Systems Bandar Sunway Malaysia

ISBN: (纸本)9781665428996

This study explores a convolutional autoencoder for image denoising with a proposed compositional subspace method. This modeling approach presents a structural and rigorous mathematical abstraction to understand a convolutional autoencoder's functional computation layers. The theoretical basis is that the best way to model a complex learning function is by using a composition of simple functions to form a multilayer successive cascaded function for complex representation. The proposed method has experimented with the Fashion-MNIST dataset. Experimental results are discussed and were consistent with the theoretical expectation. © 2021 IEEE.

关键词： Image denoising

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：