检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2872-2883页

作者： Bhardwaj, Nishit Pal, Anupriya Bhumika Das, Debasis Indian Institute of Technology Jodhpur Department of Computer Science and Engineering Rajasthan 343020 India Samsung Semiconductor India Research Karnataka560048 India Verint Systems Karnataka560005 India

Traffic accidents are common urban events that pose significant risks to human safety, traffic management, and economic stability;consequently, the research community is paying increasing attention toward accident risk prediction. However, accident risk prediction is a challenging problem because accident occurrences are sparse and influenced by multiple contextual factors (e.g., POI, road structure, road type, hour of the day, and month). Therefore, in this article, we propose a novel architecture named Topographic-Weighted Context Category (TWCCnet) that adapts heterogeneous contextual category weights based on spatial-temporal correlations across sectors. Specifically, the framework consists of two parallel components: one uses convolution and stacked bidirectional gated recurrent unit (Bi-GRU) to capture spatial-temporal relationships between neighborhood sectors, while the other uses multiple graph convolution network (GCN) over resemblance graphs to capture spatial-temporal relationships between semantic sectors. At last, temporal attention is utilized on top of parallel components to learn important spatiotemporal features that have a substantial impact on traffic accidents. The extensive experiments on two publicly available citywide datasets, i.e., New York City and Chicago demonstrate the effectiveness of the proposed approach and showed (7.21, 10.7) Root Mean Squared Error (RMSE), (34.09, 20.75) Mean Average Precision (MAP), and (0.19, 0.09) Recall approximately over both datasets, respectively, outperforming baseline as well as state-of-the-art models. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

IPH2O: Island Parallel-Harris Hawks Optimizer-Based CLSTM for Stock Price Movement Prediction

引用

Annals of Data science 2024年第6期11卷 1959-1974页

作者： Joel, Linda Parthasarathy, S. Venkatesan, P. Nandhini, S. Department of Mathematics SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai89 India Research and Statistics Sri Ramachandra Medical College and RI Sri Ramachandra University Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

Stock price movement forecasting is the process of predicting the future price of a financial and company stock from chaotic data. In recent years, many financial institutions and academics have shown interest in stock market forecasting. The accurate and successful predictions of the future price of stock yield a substantial profit. However, the current approaches are a major challenge due to the dynamic, chaotic, high-noise, non-linear, highly complex, and nonparametric characteristics of stock data. Furthermore, it is not sufficient to consider only the target firms' information because the stock prices of the target firms may be influenced by their related firms. Significant profits can be made by correct forecasting of stock prices, while poor forecasts can cause huge problems. Thus, we propose a novel Island Parallel-Harris Hawks Optimizer (IP-HHO)-optimized Convolutional Long Short Term Memory (ConvLSTM) with an autocorrelation model to predict stock price movement. Then, using the IP-HHO algorithm, the hyperparameters of ConvLSTM are optimized to minimize the Mean Absolute Percentage Error (MAPE). Four different types of financial time series datasets are utilized to validate the performance of the evaluation measures such as root mean square error, MAPE, Index of Agreement, accuracy, and F1 score. The results show that the IP-HHO-optimized ConvLSTM model outperforms others by improving the prediction rate accuracy and effectively minimizing the MAPE rate by 19.62%. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Mitigating Racial Bias in Facial Expression Recognition Using Enhanced Data Diversification Techniques 15

Mitigating Racial Bias in Facial Expression Recognition Usin...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Sidana, Sagar Thakur, Sujata Negi Kumar, Sandeep Gomathi, R.D. Sinha, Anurag Saini, Arshroop Singh Raj, Petheru Dixit, Karan Kumar, Vikas Al-Khayyat, Ahmed Department of computer science and engineering Maharshi Dayanand University Haryana Rohtak India Department of computer science and engineering Graphic Era Hill University India Department of computer science and engineering Aryan Institute of Technology India Department of English Kongu Engineering College Perundurai Tamil Nadu Erode India School of Computing and information Science IGNOU India New Delhi India Secondary education Emerald Heights School India Reliance Jio Platforms Ltd Bangalore India Department of computer science and engineering Kiet Group of Institutions India Department of computer science and engineering Islamic University Iraq

ISBN: (纸本)9798350370249

With countless new methods and further advancements in computer vision, applying the technology to the everyday lives of people has become inevitable. One such use of computer vision models is recognizing facial patterns and expressions. However, as recent studies have indicated, many models interpreting facial expressions have developed biases towards certain races. This is likely a result of skewed training data;the model may have been trained with more images of a certain race than others. Overall, this can cause inaccuracy when the model is presented with people from different backgrounds. To promote a diverse group of data that the model can process, I present a way to balance biases. First, I fine-tuned a hybrid facial recognition model of state-of-the-art convolutional neural network (CNN) models called DeepFace on the emotion recognition dataset FER2013 to recognize the emotions on people’s faces. Next, using FairFace, which is modeled after the large-scale CNN ResNet-34, I extrapolated the races and facial structures for each type of individual, which I then used to determine the bias and skew within the dataset. I did this by comparing the model’s accuracy when applied to different races. Then, I used a user-instructed stable diffusion model called InstructPix2Pix to modify the images and create a more well-represented and diverse dataset. With this method, I was able to balance the dataset effectively and reduce bias in the image recognition model. However, due to issues with the FER2013 dataset images, many of the transformed images were disfigured, meaning the emotion data within the images was lost. This caused the overall accuracy of the model to drop significantly. Future research can evaluate this method using InstructPix2Pix on different computer vision tasks or with different datasets. © 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

Advanced BERT and CNN-Based Computational Model for Phishing Detection in Enterprise Systems

引用

computer Modeling in engineering & sciences 2024年第12期141卷 2165-2183页

作者： Brij B.Gupta Akshat Gaurav Varsha Arya Razaz Waheeb Attar Shavi Bansal Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India University Centre for Research and Development(UCRD) Chandigarh UniversityChandigarh140413India Computer Engineering Ronin InstituteMontclairNJ 07043USA Department of Business Administration Asia UniversityTaichung413Taiwan Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon College of Business Administration Management DepartmentPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Research and Innovation Insights2TechinfoJaipur302001India Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)Hong Kong518031China

Phishing attacks present a serious threat to enterprise systems,requiring advanced detection techniques to protect sensitive *** study introduces a phishing email detection framework that combines Bidirectional Encoder Representations from Transformers(BERT)for feature extraction and CNN for classification,specifically designed for enterprise information ***’s linguistic capabilities are used to extract key features from email content,which are then processed by a convolutional neural network(CNN)model optimized for phishing *** an accuracy of 97.5%,our proposed model demonstrates strong proficiency in identifying phishing *** approach represents a significant advancement in applying deep learning to cybersecurity,setting a new benchmark for email security by effectively addressing the increasing complexity of phishing attacks.

关键词： Phishing BERT convolutional neural networks email security deep learning

来源：评论

学校读者我要写书评

暂无评论

Strengthening Authentication: The Role of Multi-Level Hashing in OSPA Protocol 5

Strengthening Authentication: The Role of Multi-Level Hashin...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Hariharasudhan, S. Varghese, Vineetha Malarvizhi, K. Santhoshkumar, S.P. Nalini, T. Vikram, D. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai Avadi India Rathinam Technical Campus Department of Computer Science and Engineering Coimbatore India Jct College of Engineering and Technology Department of Computer Science Al Business Systems Coimbatore India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai Avadi India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Saveetha University Department of Computer Science and Engineering Chennai India Rathinam Technical Campus Department of Artificial Intelligence Data Science Coimbatore India

ISBN: (纸本)9798331518097

Authentication is a crucial step in the cyber security process that confirms user identities. Even though they are widely used, traditional password based techniques are frequently vulnerable to attacks like guessing and password theft. This study presents the Optimal Strong Password Authentication (OSPA) protocol, which uses USB sticks to provide safe user authentication in order to address these issues. The Multi-Level Hashing Algorithm (MLHA), which dynamically picks hash functions during authentication to generate many layers of hashed passwords, is a key component of OSPA's effectiveness. By preventing eavesdropping efforts and reducing the possibility of unwanted access through guessing attacks, this method strengthens security. This protocol provides strong authentication procedures, protecting confidential data and improving overall cyber security posture by integrating MLHA into the OSPA architecture. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

IoT based deep learning approach for online fault diagnosis against cyber attacks

IoT based deep learning approach for online fault diagnosis ...

引用

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

作者： Felix, A. Yovan Sharmila, V. Devi, S. Nandhini Deena, S. Yadav, Ajay Singh Jeyalakshmi, K. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering R.M.D. Engineering College Tamil Nadu Kavaraipettai India Department of Computer Science and Engineering VSB Engineering College Tamil Nadu Karur India Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham Tamil Nadu Chennai India Department of Mathematics SRM Institute of Science and Technology Delhi-NCR Campus Modinagar Uttar Pradesh Ghaziabad India Department of Physics PSNA College of Engineering and Technology Tamil Nadu Dindigul India

ISBN: (纸本)9781032669663

The Internet of Things (IoT) connects systems, software, cloud computing, activities and could provide new access points for cyber-attacks. Virus attacks and unauthorized downloading are the two main risks to IoT security at the moment. These dangers run the risk of obtaining private information, damaging their reputation and their finances. A frame is employed in this paper’s deep learning to identify threat avoidance in IoT. The cyber security detection systems following database has to be built, after which the benchmark variables are chosen and assessed in order to establish a cyber-security alert system in a large data set. The deep learning strategy to identifying threat avoidance was described for the simulation of this scenario. From the Mailing database, malware samples have been gathered for analysis. The research results demonstrate that the proposed method for assessing risks to cyber security in IoT provides highest accuracy to current approaches. Because of this, Deep Convolution Neural Network (DCNN) is utilized in IoT to detect attack avoidance. © 2024 The Author(s).

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Adaptive Indoor People-Counting System Based on Edge AI computing

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2024年第1期8卷 255-263页

作者： Yen, Mao-Hsu Lin, Bor-Shyh Kuo, Yu-Lun Lee, I-Jung Lin, Bor-Shing National Taiwan Ocean University Department of Computer Science and Engineering Keelung City202301 Taiwan National Yang Ming Chiao Tung University Institute of Imaging and Biomedical Photonics Tainan71150 Taiwan Chi Mei Medical Center Department of Medical Research Tainan71004 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237303 Taiwan National Taipei University College of Electrical Engineering and Computer Science New Taipei City237303 Taiwan

Since the outbreak of COVID-19 in 2019, people counting in confined spaces has become essential for controlling the flow of people and reducing viral spread. Many people-counting systems use a fisheye lens to achieve a wide viewing range. However, the images captured with a fisheye lens can have different sizes and deformations due to different camera heights, which consequently affects the accuracy of people counting. In this study, a Raspberry Pi 4 development board attached to a fisheye lens was used to construct an edge computing platform for people counting by using artificial intelligence. A modified You Only Look Once (YOLO) model, which has three output layers and a spatial pyramid pooling module, is proposed to recognize people in images captured at various heights. For efficiently running this deep learning model on the proposed edge computing platform, a TensorFlow Lite framework was used to reduce the model size. The final experimental results indicated that the mean average error and mean squared error of the modified tiny version of the YOLO v4 model were 0.249 and 0.292, respectively, and the detection speed of the platform was 2 frames per second. The results indicate that the proposed edge computing platform can efficiently and accurately count the number of people. Because the proposed system uses edge computing, it can effectively solve personal privacy and transmission bandwidth problems. © 2017 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A New S-Box Design System for Data Encryption Using Artificial Bee Colony Algorithm

引用

computers, Materials & Continua 2023年第10期77卷 781-797页

作者： Yazeed Yasin Ghadi Mohammed SAlshehri Sultan Almakdi Oumaima Saidani Nazik Alturki Fawad Masood Muhammad Shahbaz Khan Department of Computer Science Al Ain UniversityAbu Dhabi112612United Arab Emirates Department of Computer Science College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Electrical Engineering Institute of Space TechnologyIslamabad4400Pakistan School of Computing Engineering and the Built EnvironmentEdinburgh Napier UniversityEdinburghEH105DTUK

Securing digital image data is a key concern in today’s information-driven *** encryption techniques are required to protect sensitive image data,with the Substitution-box(S-box)often playing a pivotal role in many symmetric encryption *** study introduces an innovative approach to creating S-boxes for encryption *** proposed S-boxes are tested for validity and non-linearity by incorporating them into an image encryption *** nonlinearity measure of the proposed S-boxes is *** qualities significantly enhance its resistance to common cryptographic attacks,ensuring high image data ***,to assess the robustness of the S-boxes,an encryption system has also been proposed and the proposed S-boxes have been integrated into the designed encryption *** validate the effectiveness of the proposed encryption system,a comprehensive security analysis including brute force attack and histogram analysis has been *** addition,to determine the level of security during the transmission and storage of digital content,the encryption system’s Number of Pixel Change Rate(NPCR),and Unified Averaged Changed Intensity(UACI)are *** results indicate a 99.71%NPCR and 33.51%*** results demonstrate that the proposed S-boxes offer a significant level of security for digital content throughout its transmission and storage.

关键词： S-box chaos artificial bee colony image encryption

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multi-Model Gradient Boosting Techniques for Workforce Enablement: A Transparent Framework for Task Management and Issue Resolution

Leveraging Multi-Model Gradient Boosting Techniques for Work...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Rithani, M. Kumar, Mahendira S. Kumar, Sudeesh V. Kumar, Praveen S. Priyadharshan, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Information and Technology SRM Institute Of Science and Technology Ramapuram Chennai India

ISBN: (纸本)9798350374933

In the rapidly shifting workplace environment, fostering an inspiring and dynamic atmosphere is essential for organizational success. This paper introduces an innovative Workforce Enhancement Platform designed to improve transparency, teamwork, and communication within the team. The platform employs state-of-the-art techniques for analyzing textual data, utilizing Gradient Boosting Machines (GBM) such as XGBoost, LightGBM, and CatBoost, to evaluate and categorize worker-submitted issues. It features a comprehensive data cleaning procedure to remove extraneous elements like markup and special symbols, followed by converting the processed text into actionable features using methods such as term frequency and inverse document frequency. Central to the system is the application of GBM algorithms, which detect and classify the emotional tone of the reports, distinguishing between positive and negative sentiments. Furthermore, the platform incorporates advanced data visualization tools to provide an in-depth analysis of model performance, including accuracy metrics, confusion matrices, and feature importance evaluations. By optimizing the identification and classification of workplace issues, the platform facilitates effective resolution, fostering a setting of innovation and teamwork. The main goal of the platform is to boost staff engagement and support by addressing challenges proactively, thereby promoting both individual growth and collective progress. This comprehensive approach ensures that team members’ feedback is acknowledged and valued, ultimately contributing to a more positive and productive organizational environment. © 2024 IEEE.

关键词： Empowerment of personnel

来源：评论

学校读者我要写书评

暂无评论

Analysis of COVID-19 Datasets Using Statistical Modelling and Machine Learning Techniques to Predict the Disease

引用

SN computer science 2024年第1期5卷 1-18页

作者： Nramban Kannan, Senthil Kumar Kolla, Bhanu Prakash Sengan, Sudhakar Muthusamy, Rajendiran Manikandan, Raja Patel, Kanubhai K. Dadheech, Pankaj Department of Computer Science and Engineering School of Computing Institute of Science and Technology (Deemed to Be University) Vel Tech Rangarajan Dr. Sagunthala R&D Tamil Nadu Chennai 600062 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur 522302 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli 627152 India Department of Computer Science and Engineering Panimalar Engineering College Chennai 600123 India Department of Electronics and Communication Engineering K. Ramakrishnan College of Technology Tamil Nadu Trichy 621112 India Charotar University of Science and Technology Gujarat 388421 India Department of Computer Science and Engineering Management and Gramothan (SKIT) Swami Keshvanand Institute of Technology Rajasthan Jaipur 302017 India

Sustainable development is crucial for a prosperous future, but epidemic diseases like Coronavirus Disease 2019 (COVID-19) pose real and complex challenges. The global pandemic, declared by the WHO on March 11, 2020, has led to significant loss of life and challenges in public health, economy, food systems, and social life. This research article aims to develop a Machine Learning (ML) model to predict a patient’s COVID-19 diagnosis, as early diagnosis is fundamental for controlling the spread of COVID-19. An investigation of the literature and a research study is conducted to find suitable mathematical methods and measure how they impact prediction models. This paper analyses COVID-19 pandemic deaths, confirmed cases, and recovered individuals using Time Series Analysis (TSA) to study the disease's impacts and understand the TAS. A forecasting model can predict future COVID cases by analyzing trends in time-series and connecting global changes with government restrictions. Since higher predictive accuracy is the limitation of ensemble learning algorithms, better ML approaches are proposed here. Autocorrelation plots clearly showed the results executed for the considered objectives. The hybrid ARIMA algorithm proposed in this work proved adequate results. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Analysis and visualization Autocorrelation COVID-19 Machine learning Time-series analysis Time-series forecasting

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：