检索结果-内蒙古大学图书馆

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Mohammad Aman Sohel Raghupatruni Sai Madhukar Sai Muralidhar Batchu Jyotsna C. Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru India

Recognizing human emotions is a multifaced field that uses the technology, especially deep learning and Convolutional neural networks, to recognize and understand emotions such as happiness, sadness, anger, disgust and fear. Convolutional Neural Networks are designed for visual data explorations and they are effectively capture facial expressions for emotion recognition. The process involves the collection of labeled data, and also preprocesses it, creating an appropriate deep neural network, training the model with constant updates, and assessing its performance using metrics on a testing dataset. Proposed work tackles emotion detection in irregularly distributed datasets of preprocessed 48x48 grayscale emotion images. Significant performance gains are achieved through targeted data augmentation for marginalized classes, giving valuable insights for robust emotion recognition models. Optimizing hyperparameters enhances the model, enabling its deployment in real-world scenarios by ensuring integration, data handling, and real-time functionality. The proposed model primarily focuses on offline image and video capturing for emotion detection, and highlighting on video-emotion recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Framework for Personality Prediction for E-Recruitment Using Machine Learning Algorithms

A Framework for Personality Prediction for E-Recruitment Usi...

引用

International Conference on Confluence The Next Generation Information Technology Summit (Confluence)

作者： Lakshyajit Thapa Aniket Pandey Deepanshu Gupta Ayush Deep Rakesh Garg Dept. of computer science and engineering Amity University Uttar Pradesh India

With rapid advancements in technology, the process of recruitment has evolved from traditional methods to online and automated methods known as e-recruitment. While e-recruitment streamlines the initial screening process, assessing the personality and suitability of candidates continues to remain a challenge. In this paper, we propose a framework for online personality prediction to aid the e-recruitment process. The framework utilizes machine learning algorithms to analyze user data from multiple online sources like resumes, social media profiles, and responses to psychometric tests, and predict their personality type based on established psychological theories. Four popular personality prediction models - Big Five, Myers Briggs, HEXACO, and Enneagram are discussed. State-of-the-art natural language processing and deep learning techniques like BERT are explored for feature extraction from text data. Popular supervised machine learning algorithms like logistic regression, Naive Bayes, k-nearest neighbors, support vector machines, random forest, XGBoost, and LSTM are compared to build predictive models. The proposed framework can help recruiters shortlist candidates better matched to job requirements, leading to increased hiring satisfaction and productivity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction Of Pulmonary Fibrosis Disease

Prediction Of Pulmonary Fibrosis Disease

引用

Control Instrumentation System Conference (CISCON)

作者： Disha Jain Palak Khurana Sakshi Yadav Seema Sharma Dept. of Computer Science and Engineering Amity University Uttar Pradesh India

ISBN: (数字)9798350375480

ISBN: (纸本)9798350375497

The progressive and potentially fatal lung illness pulmonary fibrosis (PF) is represented by permanent scarring in a lung tissue. A successful treatment of pulmonary function decline requires early diagnosis and close observation. For people with Pulmonary fibrosis (PF), forced vital capacity (FVC), a measurement of maximal exhaled air volume, is an essential marker of lung function. In order to improve PF diagnosis, this work investigates the viability of using deep learning and machine learning models to predict FVC. A set of three models were developed namely the Long Short Term- Memory (LSTM) network to identify sequential patterns in data from clinical trials, a Huber regression model for reliable management of outliers, and a Support Vector Regression (SVR). For model training and assessment, a dataset of 200 patients was used. In the training set, baseline Computed Tomography (CT) scan and the entire history of FVC measurements are provided and, in the testing, set baseline CT scan and only the initial FVC measurements are used. Each model's effectiveness was compared using three performance metrics- Mean Absolute Error, Mean Squared Error and Root Mean Squared Error. The findings showed that all three of the models had potential for predicting FVC, with the SVR be the most efficient in predicting the FVC values as it has the lowest Mean squared error (MSE) which is 0.029. This work demonstrates the potential of deep learning and machine learning for non-invasive FVC prediction, which may allow for early PF detection and prompt intervention for improved clinical results.

关键词： Training Deep learning Analytical models Computed tomography Computational modeling Atmospheric modeling Lung Predictive models Metadata Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Malware Detection in Android: A Practical Approach

Machine Learning based Malware Detection in Android: A Pract...

引用

Applied Intelligence and Computing (AIC), IEEE World Conference on

作者： Toshi Tyagi Madhu Gautam Dept. of Computer Science and Engineering KIET Group of Institutions Ghaziabad India

ISBN: (数字)9798350384598

ISBN: (纸本)9798350384604

Today's society heavily depends on online communities, which host a wide variety of social networks and public and private services. These demands led to the creation of Android, the world's most popular mobile operating system. The wide range of features and capabilities offered by freely installable third-party apps is largely responsible for this success. While focusing on the positive aspects of technology use, it is vital to keep in mind the potential negative consequences like privacy breaches, data theft, and malware infections that could compromise personal information and device security, especially if negligence or overuse of technology is present. This article discusses a systematic review of ML-based Android malware detection techniques. It provides a critical analysis of a number of carefully selected articles, highlighting their methods and conclusions. To support this study, we also present our own analysis and findings, for which an evaluation of diverse ML models with 123,453 applications and 5,560 malware samples from the DREBIN dataset was done to classify apps as malicious and benign. Preprocessing was done on the dataset to address missing values and perform label encoding. To cope with the issue of class imbalance, we used SMOTE an efficient ML technique that handles imbalance issues efficiently. We have applied five different ML algorithms, The results show that among all the techniques, Decision Tree (DT), Support Vector Machines (SVM) with various kernels (linear, polynomial, RBF), Sequential Neural Network (NN), K-Nearest Neighbours (KNN), and Logistic Regression (LR), the sequential neural network model outperformed other methods with 99% accuracy. Additionally, the process identifies areas for future research and improvement in ML-based Android malware detection techniques.

关键词： Support vector machines Analytical models Technological innovation Accuracy Social networking (online) Artificial neural networks Feature extraction Malware Robustness Security

来源：评论

学校读者我要写书评

暂无评论

Real-Time Gaze Tracking for Online Examination

Real-Time Gaze Tracking for Online Examination

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Preyanshu Bisht Suresh Kumar Dept. of Computer Science and Engineering Netaji Subhas University of Technology Delhi India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

The exponential growth in online education has increased the demand for automated systems to ensure academic integrity during online examinations. A real-time proctoring system addresses this need by monitoring a student's eye gaze and head movements during an exam. This system leverages Dlib's pre-trained frontal face detector and 68-point facial landmark predictor to detect facial features and track the direction of eye movement and head position. By analyzing these metrics, the system can flag behaviors associated with potential cheating, such as looking away from the screen for extended periods. This paper discusses the design and implementation of the proctoring system, details the detection algorithms, and evaluates its effectiveness for real-time monitoring.

关键词： Measurement Tracking Education Gaze tracking Detectors Real-time systems Detection algorithms Monitoring Facial features Faces

来源：评论

学校读者我要写书评

暂无评论

DivLog: Log Parsing with Prompt Enhanced In-Context Learning 24

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

引用

44th ACM/IEEE International Conference on Software engineering, ICSE 2024

作者： Xu, Junjielong Yang, Ruichun Huo, Yintong Zhang, Chengyu He, Pinjia The Chinese University of Hong Kong Dept. of Computer Science & Engineering Hong Kong Eth Zurich Switzerland School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China

ISBN: (纸本)9798400702174

Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing super-vised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose Di-vLog, an effective log parsing framework based on the in-context learning (ICL) ability of large language models (LLMs). Specifically, before log parsing, DivLog samples a small amount of offline logs as candidates by maximizing their diversity. Then, during log parsing, DivLog selects five appropriate labeled candidates as examples for each target log and constructs them into a prompt. By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner. In addition, we design a straightforward yet effective prompt format to extract the output and enhance the quality of the generated log templates. We conducted experiments on 16 widely-used public datasets. The results show that DivLog achieves (1) 98.1% Parsing Accuracy, (2) 92.1% Precision Template Accuracy, and (3) 92.9% Recall Template Accuracy on average, exhibiting state-of-the-art performance. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Privacy preserving data mining techniques using a denoising Auto Encoder (DAE) for medical images

SSRN

引用

SSRN 2024年

作者： Kalshetty, Jagadevi N. Pareek, Piyush Kumar Dept. of Computer Science and Engineering Nitte Meenakshi Institute of Technology India

The p proposed article a new reversible privacy-preserving data hiding approach for medical imaging. Our method uses a Denoising Autoencoder (DAE) to successfully incorporate sensitive information inside medical images, ensuring data integrity and reversible. This method concentrates on patient privacy while keeping medical images useful for diagnostic purposes. Our method uses a Denoising Autoencoder (DAE) to successfully incorporate sensitive information inside medical images, ensuring data integrity and reversible. This method concentrates on patient privacy while keeping medical images useful for diagnostic purposes. © 2024, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Applications of AI in Preservation of Kumaoni Culture Through Digital Archival

Applications of AI in Preservation of Kumaoni Culture Throug...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Vaishali Dev Ansh Dhingra Shashi Kumar Sharma Nishant Koturiya Dept. of Computer Science and Engineering Graphic Era Hill University Bhimtal India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Culture represents a society with human values and ethics. Without civilization there can be no culture. Thus it is very important to preserve our culture as it represents our values and ethics. Each region has its own characteristics culture which separates it from other regions not just geographically but in terms of traditions, art and literature. The Kumaon region in the Indian state of Uttarakhand lies in the eastern part of the state. It is blessed with a rich culture heritage and nature. The preservation of culture is done through traditional methods. The focus of this study is to use modern Artificial Intelligence techniques to achieve the preservation of culture. The Artificial Intelligence techniques which are used in this paper range from Convolutional Neural Networks, augmentation of data and fine tuning of models. To preserve it is necessary to archive the cultural elements so that it can be easily accessible in the future. The archival process can help in cataloguing the cultural items. By culture we mean traditional arts, such as Aipan, local literature texts and historical structures. The archival process seamlessly integrates the Artificial Intelligence methods to effectively preserve the cultural elements. This process can be further enhanced by fine tuning the Convolutional Neural Networks. This makes the model more robust and accurate than the existing model. The dataset quality can be further improved by using data augmentation techniques. This allows to generate more data from existing dataset. However, with the process comes some challenges like accountability and validity. This study explores these challenges which can help existing researchers in the field of culture and arts.

关键词： Ethics Art Accuracy Linguistics Data augmentation Data models Cultural differences Convolutional neural networks Artificial intelligence Tuning

来源：评论

学校读者我要写书评

暂无评论

Impact of Novel Pre-Processing Techniques on Retinal Images

Impact of Novel Pre-Processing Techniques on Retinal Images

引用

Disruptive Technologies (ICDT), International Conference on

作者： Deepti Sahu Mandeep Kaur Dept. of Computer Science & Engineering Sharda University Greater Noida India

Glaucoma, a gradually developing eye condition that can damage the optic nerve, is one of the leading causes of irreversible blindness worldwide. The detection of glaucoma is required in its initial phases for the prevention of the disease. Several machine learning and deep learning models have been developed to detect the disease. These models require a preprocessed structured data set for better efficiency and accuracy of detection. The image datasets used for this purpose have been found with several issues of outliers and noise that limit the accuracy of the results. Hence, proper handling of the dataset in terms of pre-processing is vital. This paper presents a novel pre-processing technique for better glaucoma detection as it is necessary to remove outliers from the retinal images. The proposed “EMF” model for pre-processing comprises Enhancement, Morphology, and Filtering of the images to get better results on the Retina. Drishti dataset has been used to evaluate the efficiency of the proposed technique. This dataset has several outliers that limit the accuracy, making it difficult to diagnose glaucoma. However, with the usage of the proposed technique, the dataset could be efficiently utilized for glaucoma detection. Compared to current state-of-the-art techniques, the findings from the proposed approach were shown to be better in terms of MSE, PSNR, and entropy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RBFN-Augmented DDoS Detection with CNN-GRU Fusion

RBFN-Augmented DDoS Detection with CNN-GRU Fusion

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： E Elakkiya Rohit Bahadur Bista Chandan Shah Ankit Rajput Ashish Kumar Gupta Raj Chaudhary Dept of Computer Science Engineering SRM-University AP Guntur Andhra Pradesh

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Distributed denial-of-service (DDoS) assaults represent a substantial menace in contemporary security of networks, demanding effective detection mechanisms to mitigate their escalating impact. Despite notable progress in related research, the diverse attack modes and fluctuating scale of malicious traffic continue to challenge the development of detection methods with optimal accuracy. This paper addresses this gap by proposing a comprehensive DDoS attack detection approach leveraging deep learning methodologies. The NSL-KDD Dataset serves as the experimental foundation for training, testing, and validating deep learning algorithms. The proposed method integrates the Minimum Redundancy Maximum Relevance (MRMR) feature selection algorithm, enhancing model performance, mitigating overfitting, and reducing computational complexity. The classifier comprises Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) components. CNN excels at object detection and localization within images or videos, while the GRU provides a dynamic mechanism for selectively updating the network’s hidden state, effectively managing flow information. The experimental results demonstrate the efficacy of the proposed approach in achieving improved detection accuracy and robust performance against DDoS attacks.

关键词： Deep learning Training Accuracy Computational modeling Telecommunication traffic Logic gates Denial-of-service attack NSL-KDD Convolutional neural networks computer crime

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：