检索结果-内蒙古大学图书馆

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Reddy, Thumu Rampraveen Vijaya Lakshmi, K.S. Nikhila, Lanke Koneru, Suvarnavani Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Science and Engineering Vijayawada India

ISBN: (纸本)9798350371314

Knee Osteoarthritis is one of the predominant types of arthritis, affecting joint tissues and afflicting millions of people globally. Currently, there are no curative medications exist for this condition, so there is a need to focus on early detection to manage disease progression. X-ray imaging serves as a primary method for osteoarthritis prediction, but manual prediction may sometimes be error-prone due to limited radiologist expertise. Recent studies have explored many machine learning systems for efficient osteoarthritis prediction from X-ray images, yet upgraded predictive accuracy is essential for early-stage detection. This study targets knee osteoarthritis detection and classification using Kellgren and Lawrence's grading scheme, utilizing an ensemble model combining Xception and InceptionResNetV2 architectures. The ensemble model excels with a 95.1% accuracy score, contributing to medical image analysis and providing clinicians with a robust tool for early diagnosis and treatment planning in knee osteoarthritis. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2023年第11期42卷 4038-4051页

作者： Tuli, Shikhar Jha, Niraj K. Princeton University Department of Electrical and Computer Engineering PrincetonNJ08544 United States

Self-attention-based transformer models have achieved tremendous success in the domain of natural language processing. Despite their efficacy, accelerating the transformer is challenging due to its quadratic computational complexity and large activation sizes. Existing transformer accelerators attempt to prune its tokens to reduce memory access, albeit with high compute overheads. Moreover, previous works directly operate on large matrices involved in the attention operation, which limits hardware utilization. In order to address these challenges, this work proposes a novel dynamic inference scheme, DynaTran, which prunes activations at runtime with low overhead, substantially reducing the number of ineffectual operations. This improves the throughput of transformer inference. We further propose tiling the matrices in transformer operations along with diverse dataflows to improve data reuse, thus, enabling higher energy efficiency. To effectively implement these methods, we propose AccelTran, a novel accelerator architecture for transformers. Extensive experiments with different models and benchmarks demonstrate that DynaTran achieves higher accuracy than the state-of-the-art top- k hardware-aware pruning strategy while attaining up to 1.2× higher sparsity. One of our proposed accelerators, AccelTran-Edge, achieves 330K × higher throughput with 93K × lower energy requirement when compared to a Raspberry Pi device. On the other hand, AccelTran-Server achieves 5.73× higher throughput and 3.69× lower energy consumption compared to the state-of-the-art transformer co-processor, Energon. The simulation source code is available at https://***/jha-lab/acceltran. © 1982-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Crime Type Prediction based on Various Occurrence using Parallel LSTM

Crime Type Prediction based on Various Occurrence using Para...

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Saradha, M. Nithesh Priyan, T. Shreeram, D.U. Viknesh, S. Faculty of Computer Science and Engineering K S Rangasamy College of Technology Department of Computer Science and Engineering Tiruchengode India Computer Science and Engineering K S Rangasamy College of Technology Department of Computer Science and Engineering Tiruchengode India

ISBN: (纸本)9798350333602

Crime is a widespread societal issue that has a negative impact on people's standard of living and the nation's prosperity. It's a major consideration for potential residents and tourists alike when deciding whether or not to settle in a given area. As crime rates rise, police departments have a growing need for cutting-edge GIS and data mining tools to enhance crime analytics and strengthen public safety. The suggested method includes preprocessing, feature selection, and evaluating the model's performance. We begin by cleaning up the raw crime statistics. For more predictable signals, this comprises both spatial and temporal regularization. Feature selection is performed using a rough spanning tree. To measure the effectiveness of the model, we employ parallel LSTM. When compared to two established approaches, the new strategy fares quite well. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks for Fraud Detection in E-commerce Transactions 1

Graph Neural Networks for Fraud Detection in E-commerce Tran...

引用

1st International Conference on Computing, Sciences and Communications, ICCSC 2024

作者： Goyal, Gauri Tyagi, Rashi Tyagi, Shiva Ajay Kumar Garg Engineering College Department of Computer Scienceand Engineering Ghaziabad India

ISBN: (纸本)9798350353648

E-commerce platforms face increasing fraud, resulting in significant financial losses, and traditional fraud detection approaches often fail to capture complex patterns. This paper proposes a Graph Neural Network approach to enhance fraud detection by modeling e-commerce data as a graph, where nodes represent consumers, sellers, and transactions, and edges represent interactions. By utilizing a multi-layer Graph Convolutional Network and message-passing algorithms, the GNN captures intricate relationships, uncovering hidden fraud patterns through local and global node interactions. Trained on a large-scale, real-world dataset, this method significantly outperforms traditional approaches like logistic regression and decision trees, demonstrating its superior ability to detect sophisticated fraud in e-commerce environments. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

DDoS Attacks Analysis with Cyber Data Forensics using Weighted Logistic Regression and Random Forest

DDoS Attacks Analysis with Cyber Data Forensics using Weight...

引用

2023 IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2023

作者： Tolanur, Jyoti Chaudhari, Shilpa Reva University Department of Computer Science and Engineering Bangalore India Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9781665474924

The internet has become an additional domain of warfare, alongside land, air, space, and sea, as technology has advanced. Cyberattacks can have a significant impact on both individual and national security, making the security of cyberspace a key concern for researchers. One prominent type of attack is the Distributed Denial of Service (DDoS) attack. DDoS attacks flood a targeted network or service with a high volume of traffic from multiple compromised systems, causing a denial of service for legitimate users. These attacks are a significant threat to cloud-based services. This paper presents a cyber forensics approach to analyze and classify these attacks by collecting benchmark network traffic datasets which fall under the Bigdata category. This is because DDoS attacks can generate a large amount of traffic in a short period of time. An exploratory data analysis approach in the Machine Learning Phase is proposed. Dask, an extensible parallel computing framework built on Python with machine learning, is used to uncover insights and understand patterns that may not be immediately obvious from the table. The proposed approach is evaluated using benchmark DDoS data and demonstrates its effectiveness in identifying attack characteristics and providing insight for defense. The results show the usefulness of cyber forensics in improving cloud security. © 2023 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of compressive strength of cement based material using deep learning technique

引用

Materials Today: Proceedings 2022年 69卷 1402-1407页

作者： Rajendran, Sasikumar Matheshwaran, P. Deepa, K. Department of Computer Science and Engineering K.Ramakrishnan College of Engineering Trichy India Department of Computer Science and Engineering K.Ramakrishnan College of Technology Trichy India Department of Computer Science and Engineering M. Kumarasamy College of Engineering Karur India

Although the widespread usage of mortars in construction over the last few decades, there is no published method for estimating their strength based on the mix parameters of the mortars themselves. This is owing to the fact that the mortar's compressive forte is very nonlinear in response to the mixture's components. Researchers in this research examined how artificial intelligence might be used to forecast compressive strength for cement-based mortars. In previous studies, artificial networks have been used to map the mechanical possessions of cement-based materials. Overfitting and the difficulty to explain decisions are some of the key drawbacks of this machine learning technique, which have been documented in the literature. This study therefore analyses if deep learning may be used to make predictions. Proposed methodology may accurately estimate mortar's strength when compared to experimental results, according to the results obtained from this study. As expected, machine learning predicted mortar compressive strength more accurately than provided model, however it was discovered during verification. To solve the problem of mortar compressive strength, the built deep learning model has been presented as the best predicting procedure. © 2022

关键词： Mortar

来源：评论

学校读者我要写书评

暂无评论

Challenges and Opportunities in Healthcare and Industrial IoT: A Comparative Analysis 1

Challenges and Opportunities in Healthcare and Industrial Io...

引用

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Berjis, Zaid Ameen, Siddeeq Y. Al-Jammas, Mohammed H. Electrical and Computer Engineering Department College of Engineering University of Duhok Duhok Iraq Energy Engineering Department College of Technical Engineering Duhok Polytechnic University Duhok Iraq Computer and Information Engineering Department College of Electronics Ninevah University Mosul Iraq

ISBN: (纸本)9798331533557

The Internet of Things (IoT) has changed many industries by enabling smart devices to transmit data, operate autonomously, and interact in real-time. Among its most prominent applications are in healthcare and industrial sectors, where IoT is classified into two classes: massive Machine-Type Communication (mMTC) and Ultra-Reliable Low Latency Communication (URLLC). While mMTC devices prioritize low energy consumption and can handle large-scale deployments with minimal data rates, URLLC devices are focused on mission-critical applications requiring ultra-low latency and high reliability. This paper examines the challenges and opportunities of IoT implementation in healthcare and industrial sectors, focusing on interoperability, data security, and scalability issues. The objective is to provide actionable solutions for the effective integration of IoT technologies. The investigation shows that in healthcare, mMTC is utilized for non-critical monitoring, while URLLC supports critical tasks like remote surgery. In industrial settings, mMTC improves processes like supply chain management, while URLLC enables automation and real-time control of machinery. Despite these opportunities, challenges such as data privacy, security, interoperability, and reliability remain. Addressing these issues is crucial for unlocking the full potential of IoT in healthcare and industrial sectors. © 2024 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Gauging Information Extracted from Smartphones Using Neutrosophic Logic

引用

Neutrosophic Sets and Systems 2025年 76卷 154-171页

作者： Abou Alzahab, R.M. Ismail, Amr Abd Elkhalik, S.H. Shams, M.Y. El-Bakry, H.M. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Department. of Communication and Computer Engineering Air Defense University Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Department of Information Systems. Faculty of Computer and Information Science Mansoura University Egypt

Smartphones contain a vast amount of information about their users, which can be used as evidence in criminal cases. However, the sheer volume of data can make it challenging for forensic investigators to identify and use the most relevant information. Neutrosophic logic is a generalization of fuzzy logic that allows for uncertainty and vagueness, making it a more potent tool for dealing with the ambiguity of real-world data. The proposed framework aims to identify and utilize the most relevant information for forensic investigators, making it easier to solve criminal cases using Neutrosophic logic. This novel approach provides a more powerful tool for dealing with the ambiguity of smartphone data, ultimately improving the accuracy and effectiveness of forensic investigations. Our research has utilized Neutrosophic logic to evaluate the degree of truth, falsity, or Indeterminacy of this information. Additionally, this study analyzes conversations between individuals using Excel’s fuzzy lookup add-in to determine the percentage of truth and false in each conversation. The results were compiled into a dataset and utilized a Neutrosophic Python code to evaluate the information. The results indicate the percentage of truth, false, and Indeterminacy in each conversation and which can be used to determine its admissibility as evidence and which not. © 2025, University of New Mexico. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Fruit disease detection and classification using convolution neural network

Fruit disease detection and classification using convolution...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Loganathan, V. Manasa, Chigarapalli Pavithra Devi, V. Nivetha, A. Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu Chennai India

ISBN: (纸本)9781032669663

The fruit industry is India’s largest industry. Due to carelessness and incorrect human inspection, the fruit disease results in significant losses in production, quality, and quantity. The manual examination is a laborious and time-consuming process. An image processing method is provided for the detection and classification of apple fruit diseases using various colour, texture, and shape feature combinations. The essential steps of the recommended approach include Fruit illness detection utilizing a typical neural network (CNN), where fruits are sorted, picture segmentation, feature extraction (color, texture, and shape), feature merging, and feature extraction into ill or healthy classifications. In the lab, our suggested technique was evaluated and confirmed. Using the suggested technique, 97% accuracy was attained. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

A heterogeneous soft-hard fusion framework on fog based private SaS model for smart monitoring of public restrooms

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第7期14卷 8957-8984页

作者： Gore, Rajasi Banerjea, Shashwati Tyagi, Neeraj Computer Science and Engineering Department MNNIT Allahabad Uttar Pradesh Prayagraj211004 India

Usage of public restrooms, provided by the Indian government under "Clean India Mission", is limited due to negligence in manual supervision. This paper proposes an Internet of Things-based smart application for sanitation to keep check on geographically distributed restrooms autonomously through soft-hard sensors. Due to a substantial increase in the number of sensing devices in recent years, the application aims to re-utilize data from hard sensors co-located near the restroom locations. A private Sensing as a Service (SaS) paradigm is proposed on the fog node that provides sensor data as a service at the network edge to reduce new sensor deployments. The data from re-utilized sensors is vendor-specific, and, therefore, have heterogeneous protocols and file formats, unknown to the application vendor. A soft-hard fusion framework is proposed to handle data heterogeneity of re-utilized data and perform time-series fusion of hard-sensor data (vendor-specific or application-specific) with uncertain soft sensor data at the fog node for having complete and accurate information about the toilet. The proposed framework takes approximately 0.145 s to resolve heterogeneity, handle soft uncertainty and perform fusion with low resource consumption. Moreover, it has a good system as well as network performance with increased classification accuracy in predicting the cleaning requirement of every toilet. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Fog

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：