检索结果-内蒙古大学图书馆

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Kamma, Vidya Wbaid, Saef Sudhakar, K. Nisha, A. Saravanan, T. Neil Gogte Institute of Technology Department of Computer Science and Engineering Rangareddy Hyderabad India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Data Science Bengaluru India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Computer Science and Engineering Mamallapuram India New Prince Shri Bhavani College of Engineering and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331529246

In recent years, toxic comment detection evolved as important in detecting hatred and harmful content present in user-generated content. However, a few challenges are raised in detecting toxic comments like context sensitivity and missing toxic content. To overcome these issues, improved Bi-directional Long Short-Term Memory (Bi-LSTM) is proposed for toxic comment detection. Initially, data is preprocessed with lemmatization and stop words removal methods for converting the texts to its base form and eliminates the common words respectively. Then, the Word to Vector (Word2Vec) technique converts the words into a dense vector representation by capturing semantic relationships and contextual meanings. Finally, improved Bi-LSTM is employed for detecting the toxic comments by capturing both past as well as future context with its bidirectional architecture and focuses on important words within the context dynamically. From the results, proposed Improved Bi-LSTM model attained better outcomes in terms of accuracy (acc) of 94.32%, precision (pr) of 98.07%, and recall of 95.98% compared to existing Convolutional Neural Networks (CNN)-BiLSTMs. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Analysis of Synthetic Data Generation Techniques in Diabetes Prediction 2nd

Analysis of Synthetic Data Generation Techniques in Diabet...

引用

2nd International Conference on Big Data, Machine Learning, and Applications, BigDML 2021

作者： Das, Sujit Kumar Roy, Pinki Kumar Mishra, Arnab Department of Computer Science and Engineering National Institute of Technology Silchar Assam788010 India

ISBN: (纸本)9789819934805

The problem of inadequate and class imbalanced data is one of the major problems in the classification tasks. Therefore applying synthetic data generation (SDG) approaches to handle class imbalances can be useful in improving Machine Learning (ML) classifier’s performance. The aim of this work is to explore various SDG approaches to improve diabetes prediction using Pima Indian Diabetes Dataset (PIDD). We have also proposed a hybrid approach of SDG by combining the idea of popularly used SDG techniques Synthetic Minority Oversampling TEchnique (SMOTE) and SVM-SMOTE (Support Vector Machine-Synthetic Minority Oversampling TEchnique), named as SSVMSMOTE. The idea is to divide training data into equal halves and apply SMOTE and SVM-SMOTE separately to sub-training samples. The approach has successfully overcome the limitation of SMOTE and SVM-SMOTE. A set of classifiers namely Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (KNN), Logistic Regression (LR), Gaussian Naive Bayes (GNB), AdaBoost (AB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), and Light Gradient Boosting (LGM) are trained on the combined resampled training data and tested on hold out testset. The experiment shows that boosting classifiers, XGB, and GB outperformed other considered classifiers. Further, the XGB classifier, with the help of the proposed SDG technique, achieved the highest average accuracy of 0.9415. The proposed approach also achieved promising results in terms of other important evaluation metrics such as F-Scores, AUC, Sensitivity, and specificity. Therefore, such an impressive result of the proposed approach suggests its applicability in the real-life decision-making process. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

UAV Object Detection and Tracking in Video using YOLOv3 and Deepsort

UAV Object Detection and Tracking in Video using YOLOv3 and ...

引用

2024 IEEE International Conference on Emerging Technologies in computer science for Interdisciplinary Applications, ICETCS 2024

作者： Gandhi, Rahulkumar Nirma University Institute of Technology Department of Computer Science and Engineering Gujarat Ahmedabad India

ISBN: (纸本)9798350372502

The popularity of unmanned aerial vehicles (UAVs), also referred to as drones, is growing quickly, raising questions about their misuse as they become more widely available. This escalating trend underscores the urgency for effective drone detection mechanisms to prevent unlawful intrusions and ensure public safety. To bridge the existing gap in technology, There's a deliberate attempt to develop sophisticated deep-learning models capable of accurately recognizing drones of varying shapes and forms, including those that resemble birds. In our quest to address this challenge, we have adopted a comprehensive approach by utilizing the YOLOv3 object detection model alongside OpenCV. Through meticulous training on a diverse dataset encompassing images of drones, including bird-like variations, we have achieved an impressive accuracy rate of 96.98% at 0.5 mAP. Moreover, our integration of DeepSORT with YOLO enhances the system's tracking capabilities, enabling efficient monitoring and tracking of identified drones. In conclusion, our endeavor not only fills a crucial void in current drone detection technology but also underscores our commitment to safeguarding against potential threats posed by drone misuse. Through continuous advancements in deep-learning methodologies and innovative integration techniques, we aim to establish robust frameworks for automated UAV detection, ensuring the security and integrity of airspace operations. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Trustworthy Diabetes Prediction Model 16

Machine Learning-Based Trustworthy Diabetes Prediction Model

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Aruna Devi, B. Karthik, N. National Institute of Technology Puducherry Department of Computer Science and Engineering Puducherry Karaikal India

ISBN: (纸本)9798350383119

Diabetes is a condition that develops when the blood sugar is above average level. Diabetes shoots up the risk of eye, kidney, nerve, and heart problems. By adopting suitable measures to prevent or manage blood sugar level may reduce the chances of getting diabetes-related health issues. Medical data collection is not done on a regular basis but is determined by the patient's condition and other clinical or administrative factors. A trustworthy model is free from missing values, faulty data and makes reliable predictions. Factors like data quality, anomalies, and model selection play a significant role in building a trustworthy model. Hence, this work concentrates on the prediction of diabetes by considering the following issues: 1) missing values in the dataset, 2) an imbalanced dataset and the presence of anomalies, and 3) diabetes prediction using Machine learning (ML) algorithm. The main objective of this work is to propose a trustworthy diabetes prediction model for an incomplete and imbalanced dataset using ML-based imputation, techniques for balancing datasets, and anomaly detection. © 2024 IEEE.

关键词： anomalies diabetes imbalanced dataset missing values

来源：评论

学校读者我要写书评

暂无评论

Incorporating 5G NR Sidelink with MQTT to Maximize Energy Efficiency in IoT-Enabled Microgrids 1

Incorporating 5G NR Sidelink with MQTT to Maximize Energy Ef...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Neelamegam, G. Ashforn, Hermina J.M. Raja, Mohamed S. Priyadharshini, J. Akshya, J. Choudhry, Mani Deepak Sundarrajan, M. Vsb College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Erode India Kalaignarkarunanidhi Institute of Technology Department of Computer Science and Engineering Coimbatore India K. Ramakrishnan College of Engineering Department of Information Technology Trichy India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India Srm Institute of Science and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798350377002

IoT for smart microgrids is an innovative disruption at the cutting edge of energy management, relying on interconnectedness provided by smart sensors and devices to enhance power generation and distribution precision in metropolitan areas. The problems of the real-time operational capabilities required for efficient energy resource management thus progress, inhibit rapid control and management. The main goal of this research proposal consists of to use of the advanced technology of 5G NR Sidelink combined with MQTT to conduct a revolutionary communication system of Microgrid running through the IoT devices. The 5G NR (New Radio) Sidelink enables direct D2D communication, which leads to a dramatic lowering of the latency in the absence of traditional network infrastructures for communication, while the MQTT protocol improves the communication efficiency among networks of numerous IoT devices. The introduction of this system was followed by a 15% decrease in energy transmission losses and by 20% improvement in response times in comparison to conventional models specified in the quantitative evaluation thus increasing operational efficiency by far. These efficiencies not only reduce operating expenses and power consumption but also increase the solution's scalability, pointing out the possibility of building the solution for bigger urban microgrid implementations. In consideration of that, the suggested mechanism with 5G NR Sidelink along with MQTT overcomes elaborate barriers of IoT-based microgrids and establishes a new potency in advanced energy management in smart cities which could make the distribution network in the urban areas on the edge of the verge of a change. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

Driver Assistance System Based on Real-Time Dehazing 4

Driver Assistance System Based on Real-Time Dehazing

引用

4th International Conference on Computation, Automation and Knowledge Management, ICCAKM 2023

作者： Pradhan, Soumen Balaji Reddy, Adamala Sai Aman, Mritunjay Mukherjee, Shyamapada National Institute of Technology Silchar Department of Computer Science and Engineering Silchar India National Institute of Technology Rourkela Department of Computer Science and Engineering Rourkela India

ISBN: (纸本)9798350393248

Weather conditions such as Haze, Fog reduce visibility making it difficult to observe the surrounding environment. This makes drivers prone to accidents in such situations. Most of the existing methods for dehazing use models that work upon single-image dehazing. Dehazing in real-time proves a much bigger challenge as it demands efficient handling of the constant stream of frames, as well as a lightweight dehazing algorithm. Further, there is the need for some decision-making parameter that determines whether dehazing is needed. This paper provides a novel framework that works at dehazing in real-time using Dark Channel Prior (DCP), and is able to work on minimal hardware such as smartphones. © 2023 IEEE.

关键词： Automobile drivers

来源：评论

学校读者我要写书评

暂无评论

Likelihood Ratio Based Voice Comparison Using Cepstral Coefficients and GAN 2

Likelihood Ratio Based Voice Comparison Using Cepstral Coeff...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Kruthika, S.G. Nagavi, Trisiladevi C. Mahesha, P. Department of Computer Science and Engineering S.J. College of Engineering JSS Science & Technology University Karnataka Mysore India

In order to identify suspects in digital forensics, Forensic Voice Comparison (FVC) entails comparing trace voices with known suspect voice samples. The FVC uses semi-automatic approaches to identify speakers using acoustic features. Two Australian datasets such as forensic evaluation dataset 1 & English dataset 2 were used. The current research on FVC samples is noise-reduced using a stationary noise reduction algorithm within a likelihood ratio-based framework. To demonstrate the power of knowledge representation, acoustic features like Mel Frequency Cepstral Coefficients(MFCC) and Linear Predictive Cepstral Coefficients (LPCC) were extracted. The suspect is then identified by classifying the model using the Generative Adversarial Network(GAN) and Artificial Neural Network (ANN). The accuracy is 80% & 90% for MFCC for dataset 1 & 2. Similarly, accuracy is 20% & 40% for LPCC for dataset 1 & 2. The overall comparison of acoustic features with two different datasets the MFCC performs better accurate results for Australian English dataset 2 with varying sample sizes. © 2024 Elsevier B.V.. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An effective object detection via BS2ResNet and LTK-Bi-LSTM

引用

Multimedia Tools and Applications 2025年 1-20页

作者： V, Arulalan V, Premanand Kumar, Dhananjay Department of Computing Technologies SRM Institute of Science and Technology Chengalpattu District Tamil Nadu Kattankulathur603203 India Department of Computer Science and Engineering Vellore Institute Technology Chennai Campus Tamil Nadu Chennai India Department of Information Technology Anna University MIT Campus Tamil Nadu Chennai India

Video analytics faces complex challenges in object detection and classification. Deep learning based approaches have achieved remarkable success in past decade. However, existing object identification models that utilize backbone’s core features still present challenges due to their lack of semantic information. To address these issues, a novel object detection and classification framework utilizing Batch normalization and Softswish activation adapted ResNet (BS2ResNet) and Logistic Tanh Kaiming Bi-directional Long Short Term Memory (LTK-Bi-LSTM) techniques was proposed. The framework employs frame conversion, noise removal, and contrast elevation during frame pre-processing, followed by background subtraction using the Supreme Distance-centered Fuzzy C-Means (SD-FCM) clustering algorithm, and edge detection using the Hyperbolic Tangent Kernel Canny Edge Detector (HTKCED). BS2ResNet is then used for object detection, and features are extracted and passed to the LTK-Bi-LSTM neural network for object classification. The proposed system was found to improve object detection and classification accuracy, outperforming existing techniques. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

引用

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

作者： Arunakumari, B.N. Swain, Vikas Sharan, K. Bms Institute of Technology and Management Department of Computer Science and Engineering Bengaluru560064 India

ISBN: (纸本)9798350370249

Efficiently finding similar items in large datasets is a crucial task with applications in various domains. This abstract presents a survey of algorithms and techniques designed for this purpose. Notable approaches include Minhashing, which employs hash signatures to estimate set similarity;Locality-Sensitive Hashing (LSH), a family of hash functions grouping similar items into common buckets;Cosine Similarity for Vector Spaces, suitable for data represented as vectors;Random Projection, a dimensionality reduction technique preserving pairwise distances;Word Embeddings, leveraging pre-trained embeddings for measuring similarity in text data;Bloom Filters, space-efficient structures for set-membership testing;Tree-based Methods like KD-trees and Ball-trees for efficient nearest neighbor searches;and SimHash, a method generating hash codes to represent similarity. To choose an algorithm the factors such as data characteristics, dataset size, and the desired balance between accuracy and computational efficiency should be considered. Experimentation with different techniques is recommended to determine the most effective approach for specific use cases. © 2024 IEEE.

来源：评论

学校读者我要写书评

暂无评论

Software engineering Metrics For Sifting Android Malicious Applications 1

Software Engineering Metrics For Sifting Android Malicious A...

引用

1st International Conference on Innovative engineering sciences and Technological Research, ICIESTR 2024

作者： Alam, Shahid Demir, Alper Kamil Adana Alparslan Turkes Science and Technology University Department of Computer Engineering Adana Turkey

ISBN: (纸本)9798350348637

Software engineering metrics are used to predict the effort/cost and quality of software applications. Measuring software quality helps us find defects and bugs, which in turn leads us to find software vulnerabilities. In addition, these metrics find the structural and behavioral properties of a software program and hence help find clones/variants of the original software program. New malware programs are commonly written by creating clones/variants of the original malware. Software engineering metrics can be effectively used to find such malware. None of the previous research works have employed these metrics for finding Android malicious applications. In this paper, we propose the first such system that uses software engineering metrics for sifting and finding Android malicious applications. We extract these metrics for each reachable method in an Android application. Some of the metrics are, API types, API call in/out, control flow graph size, lines of code, number of branches, and number of invocations. When tested with real Android malware applications our proposed system shows promising results indicating the effectiveness of these features. © 2024 IEEE.

关键词： Android malware

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：