检索结果-内蒙古大学图书馆

2nd International Conference for Innovation in Technology, INOCON 2023

作者： Reddy, B. Ajay Chandrasekhar Chandra, Girish Kumar Sisodia, Dilip Singh Anuragi, Arti National Institute of Technology Department of Computer Science and Engineering Raipur India

ISBN: (纸本)9798350320923

On social media networks like Twitter, Facebook, and Tumblr, people frequently share information. However, these platforms are also notorious for the spread of hate speech and insults, often posted anonymously. Hate speech involves using violent, abusive, or aggressive language towards a particular group based on factors such as gender, race, religion, or region. The prevalence of hate speech on these websites is a major concern, and manually detecting it can be time-consuming. To address this issue, this study presents an automated hate speech detection model that is evaluated on a publicly available Twitter dataset. The proposed method emphasizes data pre-processing, including stemming, term frequency-inverse document frequency (TF-IDF) for feature extraction, and various sampling techniques (random sampler, synthetic minority over-sampling technique (SMOTE), and ALL-KNN) to balance an imbalanced dataset. The logistic regression, support vector machine (SVM), and k-nearest neighbor (k-NN) machine learning classifiers were trained and tested using hold-out cross-validation to reduce overfitting and evaluate performance. The performance was evaluated using metrics such as accuracy, precision, and confusion matrix. The results showed that the logistic regression classifier using the SMOTE approach had the best performance, with an accuracy of 82%, a macro average of precision, recall, and an F1-score of 80%, 82%, and 79%, respectively. © 2023 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Bus Dwell Time Forecasting using Machine Learning Models 7

Bus Dwell Time Forecasting using Machine Learning Models

引用

7th International Conference on Trends in Electronics and Informatics, ICOEI 2023

作者： Aswini, B.P. Savithramma, R.M. Sumathi, R. Siddaganga Institute of Technology Department of Computer Science and Engineering Tumakuru India

ISBN: (纸本)9798350397284

Bus Dwell Time (BDT) is a vital and most important contributing part of Bus Travel Time (BTT). Forecasting BDT is key for applications that predict the arrival time of buses at bus stops and intersections. With aim of aiding the BTT prediction, the objectives of the current work are to (i) Develop machine learning models using archived location data of buses to predict dwell times at all the bus stops of a route and (ii) Compare the performances of the models developed with a base model through error metrics. Multiple machine learning algorithms namely;k-Nearest Neighbors, Gradient Boosting and Extreme Gradient Boosting (XGBoost) regressor, Random Forest Regressor, and One- Dimensional Convolutional Neural Network models are identified and implemented based on the literature survey and compared with the Historic Average as the base model. The location logs of Tumakuru city service buses, Tumakuru, India are preprocessed, trained, and tested. Among the implemented models, XGBoost demonstrated better performance. The mean absolute percentage of errors demonstrated by the implemented models is above 20% indicating the need to improve the performance of the models as a future study. © 2023 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection System for Defending against DoS Attacks in the IoMT Ecosystem 4

Intrusion Detection System for Defending against DoS Attacks...

引用

4th International Conference on Communication, Computing and Industry 6.0, C216 2023

作者： Puthin Krishna, M. Kumar, Suvidha Rupesh Palani Thanaraj, K. School of Computer Science & Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350327328

This paper endeavors to enhance healthcare security in the Internet of Medical Things (IoMT) by developing an Intrusion Detection System (IDS) focused on countering Denial of Service (DoS) attacks. Leveraging machine learning algorithms including Support Vector Machine (SVM), Random Forest (RF), Linear Discriminant Analysis (LDA), and k-Nearest Neighbors (k-NN), the IDS is trained on Wireshark-simulated data to identify and mitigate DoS threats. By filling critical gaps in IoMT cybersecurity literature and providing a dataset for IoMT-based DoS attacks, this work fortifies the resilience of IoMT infrastructure, safeguarding health data, healthcare service continuity, and patient safety in our increasingly interconnected healthcare landscape. © 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

VANET Handoff from IEEE 80.11p to Cellular Network Based on Discharging with Handover Pronouncement Based on Software Defined Network (DHP-SDN) 22nd

VANET Handoff from IEEE 80.11p to Cellular Network Based on ...

引用

22nd International Conference on Hybrid Intelligent Systems, HIS 2022 and the 18th International Conference on Information Assurance and Security, IAS 2022

作者： Sarvavnan, M. Narayanan, R. Lakshmi Kavitha, K. Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Networking and Communications SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Kongu Engineering College Erode India

ISBN: (纸本)9783031274084

In Vehicular Adhoc Network (VANET) is an emerging domain with high dynamic mobility and disrupted network in Discharging with Handover Pronouncement based on Software Defined Network (DHP-SDN) with advance predictive management tool described in this work for discharging of vehicle-to-infrastructure communication with Software Defined Network (SDN) architecture. Various parameters were addressed in research articles like maintaining connectivity, identifying appropriate intermediate node for carrying signal and transferring of data but in the proposed model SDN monitors the discharging signal based on the speediness, terrestrial location, nearby vehicle RSU from the vehicle which has cellular and IEEE 802.11p network boundary. SDN regulator computes when the due time is to settle on a choice, chooses whether it is appropriate or not have the vehicle to handoff from cell organization to the ahead IEEE 802.11p organization. The simulation results that using DHP-SDN method maintains the networking quality by reducing the load and traffic congestion. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Using ARO and LSTM Algorithms

引用

SN computer science 2025年第1期6卷 1-11页

作者： Bhagat, Amit Dangi, Dharmendra Suman, Vaibhav Dixit, Dheeraj Kumar Sharma, Suvarna Department of Computer Applications MANIT Madhya Pradesh Bhopal India Department of Information Technology IIIT Madhya Pradesh Bhopal India Department of Computer Science & Engineering LNCT University Madhya Pradesh Bhopal India Department of Computer Science & Engineering MITS Madhya Pradesh Gwalior India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

There has been an exponential increase in social media content over the past few years due to the popularity of social media platforms. However, this has also resulted in the dissemination of intentionally false information, or fake news, which can have significant negative effects on society. As a result, detecting fake news has become an important issue that requires attention. Promoting trust in the global community is crucial to preventing the spread of false information in mass media. A study report suggests a reliable technique for identifying false news in order to remedy this. The author has thoughtfully chosen two distinct datasets: the Buzzfeed dataset, which is an assortment of news articles from Buzzfeed News, and the ISOT dataset, which is a collection of social media postings and articles from other sources. The author thoroughly analyzed a variety of content kinds and assessed the efficacy of various approaches and methods for processing and categorizing them using the datasets. The study found that these datasets have accuracy rates of 99% and 97.8% respectively. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： ARO algorithm Fake news detection LSTM Pre-processing

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Deep Learning for Leaf Disease Detection: Integrating Visual and Non-Visual Data Sources 6

Multi-Modal Deep Learning for Leaf Disease Detection: Integr...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Ilavendhan, A. Sreenidhi, R. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350394702

In this paper, a novel technique is presented for detecting leaf diseases using multi-modal deep learning methods that incorporate both visual and non-visual data. The approach involves combining leaf image data with information from environmental sensors, soil moisture levels, and weather data to enhance the accuracy of our models. A vast dataset of leaf images is gathered and associated with non-visual data from various locations and environments, which is used to develop a multi-modal deep learning model capable of effectively integrating both types of data sources to accurately identify leaf diseases. This approach will considerably enhance the accuracy of leaf disease detection and enable effective management of plant diseases. By utilizing multi-modal data sources, we can achieve a more comprehensive understanding of the factors that contribute to leaf diseases and develop more precise models for detecting them. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Image Captioner: Captioning for Visual Impact 1

Image Captioner: Captioning for Visual Impact

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Aryan, Shabareesh Subrahmanya, S. Jagtap, Pahel Mani, Leander Sowmya, M.R. Nitte Meenakshi Institute of Technology Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350316469

Image captioning is the process of generating a textual description that accurately represents the features of an image. In the realm of deep learning, this task is of utmost significance and has a wide range of uses. Image captioning involves converting an image, represented as a sequence of pixels, into a sequence of words that are relevant to the image. It can be seen as an end-to-end and sequence-to-sequence challenge, as both the language and visual aspects need to be processed. In this regard, recurrent neural networks are employed for the language processing, while convolutional neural networks are used to extract feature vectors from the images. The findings of this study highlight the effectiveness of this method and show how diverse applications in image processing and description generation are possible. This work promotes the incorporation of these methods into actual image captioning systems in order to provide more precise and contextually appropriate image descriptions. © 2023 IEEE.

关键词： BLEU: Bilingual Evaluation Understudy convolutional neural networks Image captioning long short-term memory pooling recurrent neural networks unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Tracking of Food Waste in Food Supply Chain Using Machine Learning

Tracking of Food Waste in Food Supply Chain Using Machine Le...

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent engineering, ICECONF 2023

作者： Sriman, B. Santhosh, R. Guru, R. Santhosh Raju, V. Saras Prasad Prasad, H. Ruma Sailendiran, R. Computer Science and Engineering Rajalakshmi Institute of Technology TamilNadu Chennai India

ISBN: (纸本)9798350334357

In India, annually, 67 million tonnes of food are wasted, costing the country roughly 92000 crores. The motivation behind recycling food waste is the desire to divert waste from landfills. This study aims to manage food wastage in regional Food Supply 7hChains (FSC). In this model, we use modern generation machine learning techniques to track the amount of food waste in FSCs and redirect it for productive usage. The future recommended model is inferred to be effective across a number of areas based on the numerous studies that were conducted. © 2023 IEEE.

关键词： Land fill

来源：评论

学校读者我要写书评

暂无评论

Multiclass Identification and Classification of Diabetic Retinopathy using Transfer Learning: A Comprehensive Approach for Enhanced Diagnostic 9

Multiclass Identification and Classification of Diabetic Ret...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Sharma, Gunjan Anand, Vatsala Chauhan, Rahul Pokhariya, Hemant Singh Gupta, Sheifali Sunil, G. Chitkara University Institute of Engineering And Technology Chitkara University Punjab India Computer Science And Engineering Graphic Era Hill University Uttarakhand Dehradun India Computer Science And Engineering Graphic Era Deemed To Be University Uttarakhand Dehradun India Sr University School of Computer Science & Artificial Intelligence Warangal India

ISBN: (纸本)9798350394474

Diabetic retinopathy, a commonly observed disorder associated with diabetes mellitus, is distinguished by the emergence of irregularities in the retina that adversely affect visual capabilities. In the absence of timely identification, the condition above has the potential to advance and result in compromised visual function. While proven to be effective, the process of manual diagnosis conducted by ophthalmologists is characterized by time-consuming procedures, labor-intensive efforts, significant costs, and a susceptibility to misdiagnosis. On the other hand, computer-aided diagnosis procedures provide a highly efficient and precise alternative. The utilization of deep learning techniques, namely in medical picture interpretation, has demonstrated improved effectiveness. This study introduces an innovative deep-learning methodology for detecting and classifying diabetic retinopathy automatically. This study proposes the utilization of a Convolutional Neural Network model based on ResNet50 architecture to identify and classify retinal pictures into five distinct categories, which correspond to different phases of diabetic retinopathy. The model demonstrates a validation accuracy of 95.01% and a training accuracy of 98.70%, accompanied by a Cohen Kappa score of 0.96 with negligible loss. The efficiency of the proposed model is assessed by utilizing the Diabetic Retinopathy Detection dataset, demonstrating its capability to automatically identifying diabetic retinopathy. This research has the potential to be applied within the healthcare domain, specifically to diagnose retinal complications in individuals with diabetes. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Streamlining Machine Learning Model Execution Time with Hyperparameter Optimization 3

Streamlining Machine Learning Model Execution Time with Hype...

引用

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Dhivya, P. Jegavardhini, M. Chandru, M. Vaigunth, Krishnan Harish Kumar, S. Rahul, S. Computer Science and Engineering Bannari Amman Institute of Technology Erode India

ISBN: (纸本)9798350343632

Breast cancer is a common disease that mostly affects women. It can be fatal if not detected early. Early detection and accurate diagnosis can lead to a longer survival rate for patients. Various classification models have been used to identify breast cancer, including logistic regression, decision trees, random forests, k-nearest neighbors, and gradient-boosting algorithms. A Parameterized Random Forest (PRF) classifier has been proposed that chooses the best parameter for classification based on the highest probability of a particular value in the parameters. The proposed model achieves an accuracy of 98.25% with a false negative rate of 1%. It is also more accurate (95.31%) than other classification algorithms when applied to the Hepatitis C dataset. The PRF classifier is a promising new tool for the early detection and accurate diagnosis of breast cancer. It is more accurate than other classification algorithms and can be used to reduce the time required to choose the best parameter value. © 2023 IEEE.

关键词： Artificial Intelligence Benign Malignant Random Forest Receiver Operating Characteristics Tuning

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：