检索结果-内蒙古大学图书馆

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Afaq, Shajal Singh, Nanhay Netaji Subhas Institute of Technology Department of Computer Science and Engineering New Delhi110031 India

ISBN: (纸本)9798350368109

Breast cancer is a leading cause of morbidity for women all over the world, BC, or breast cancer, affects many women globally. It ranks fourth in fatality among colon, brain, and cervical malignancies. New BC cases are predicted to rise 70% in the following two decades. Thus, early identification and accurate breast cancer diagnosis improve prognosis and long-term survival. Machine learning methods like "Support Vector Machines"(SVM) and Nearest Neighbor have shown promising but limited efficacy in recognizing BC. This study introduced a "Convolutional Neural Network"(CNN) model of utilizing deep neural networks to diagnose BC using the Wisconsin BC database. The research demonstrates the application of DL technology for diagnosing BC using the Kaggle Dataset. The research method involves data acquisition, data preprocessing and using the dataset to train the CNN model and assess its performance using four key metrics: precision, recall, accuracy, and F-measure. CNN model accuracy is 95.57%, precision is 97.70%, recall is 98.64%, and F-measure is 98.14%. This approach outperforms standard models, proving its effectiveness in detecting BC. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Abstractive Text Summarization Techniques

A Comprehensive Survey of Abstractive Text Summarization Tec...

引用

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Kumar, Nikesh Soni, Rayirth Adhikari, Tarun Kumar, Suresh Netaji Subhas University Of Technology Department Of Computer Science Engineering Delhi India

ISBN: (纸本)9798350366846

Abstractive text summarization [16] leverages advanced machine learning and deep neural networks to generate entirely new text that encapsulates the essence of the input text. It differs from extractive summarization [20], which mechanically concatenates text segments. Abstractive summarization is needed to address information overload and enhance content creation. However, it faces challenges such as maintaining consistency, capturing subtle nuances, and striking a balance between conciseness and comprehensiveness. Various approaches to abstractive summarization are presented, including the seq2seq model [17], attention mechanism [18], pointer-generator network [10], and copy mechanism. These approaches have different strengths and weaknesses depending on the application. Abstractive summarization finds practical applications in news summarization, research paper summarization, legal document summarization, customer support, and e-commerce product descriptions. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Regret Detection on Social Media using BERT-BiLSTM Model 1

Regret Detection on Social Media using BERT-BiLSTM Model

引用

1st International Conference on Advanced Computing and Emerging Technologies, ACET 2024

作者： Sharma, Renuka Nagpal, Sushama Sabharwal, Sangeeta Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350367720

Regret is a common and fundamental emotion in everyone life. It is defined as the feeling that arises when we realize or believe that our current circumstances could have been better if different decisions had been made. It is accompanied by negative emotions such as remorse, self-blame, and disappointment, often shared by many users who regularly express their emotional experiences on the social web. Detecting the actual regret emotion of a sentence is complex because of its multifaceted nature. This article introduced the following steps for detecting regret content from English text: (i) topic modeling and automatic labeling using average agreement between Latent Dirichlet Allocation (LDA) and the K-mean clustering method, (ii) using pre-trained BERT base uncased embedding and TFIDF word vectorization for feature representation enables contextual analysis and assesses the relevance of terms, and (iii) Implementing a Bi-LSTM model stacked with word embedding techniques, and incorporating a single dense layer for regret text classification. The experimental findings demonstrate that the proposed learning approach (BERT-BiLSTM) has superior performance in identifying regretful sentences compared to other models. We evaluate the performance of the proposed model by assessing its precision, recall, F1 score, and accuracy metrics. © 2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning with Mobile Net for Brain Tumor Detection in Neuroimaging 8th

Transfer Learning with Mobile Net for Brain Tumor Detection ...

引用

8th International Conference on Intelligent Technologies, ICIT 2023

作者： Verma, Neha Bohat, Vijay Kumar Department of Computer Science & Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (纸本)9789819738588

Brain tumor detection is crucial for early diagnosis and treatment planning in the field of medical image analysis, particularly in neuroimaging. Deep learning techniques, including transfer learning, have shown great promise in this regard. This research investigates the effectiveness of utilizing the MobileNet architecture for brain tumor detection in neuroimaging. MobileNet is a lightweight convolutional neural network designed for efficient deployment on resource-constrained and mobile devices. Its focus on both accuracy and computational efficiency makes it a promising option for medical image analysis. In this methodology, pretrained MobileNet models, previously trained on extensive image datasets, are fine-tuned using a carefully curated neuroimaging dataset. The experiments cover various neuroimaging modalities, such as MRI and CT scans, demonstrating MobileNet’s ability to adapt to brain tumor characteristics despite limited annotated data through transfer learning. A comprehensive evaluation using publicly available benchmark datasets is conducted, and the results are compared to established architectural approaches. This study highlights the potential of transfer learning with MobileNet for brain tumor detection, emphasizing the advantages of using pretrained architectures to address data scarcity in medical imaging. Ultimately, this approach contributes to enhancing the accuracy and efficiency of brain tumor detection pipelines, aiding medical professionals in making timely diagnoses and improving patient care. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancing ADHD diagnosis: using machine learning for unveiling ADHD patterns through dimensionality reduction on IoMT actigraphy signals

引用

International Journal of Information technology (Singapore) 2024年 1-13页

作者： Misgar, Muzafar Mehraj Bhatia, M.P.S. Department of Computer Science & amp Engineering Netaji Subhas University of Technology New Delhi India

Mental health is an integral component of overall well-being, profoundly influencing the lives of individuals, families, and communities worldwide. As our understanding of mental health has evolved, so too has our awareness of the myriad conditions that impact it. Attention-Deficit Hyperactivity Disorder (ADHD) emerges as a substantial and intricate mental health concern, classified as a neurodevelopmental disorder with a pronounced impact on an individual’s capacity to concentrate, manage impulses, and modulate their activity levels. That is why the actigraphy measurements from wrist actigraphy provide a non-invasive monitoring method and diagnosis too. This paper proposes a methodology employing dimensionality reduction for feature extraction from time series actigraphy data signals and Machine learning (ML) classifiers for classifying control subjects from ADHD patients. Three dimensionality reduction techniques UMAP (Uniform Manifold Approximation and Projection), t-SNE (t-Distributed Stochastic Neighbour Embedding), and PCA (Principal Component Analysis) were applied to the actigraphy sample of length 1440 (24-h recordings). A Set of 10 ML classifiers (Medium Tree, Efficient Logistic Regression, Gaussian Naïve Bayes, Quadratic SVM, Cubic SVM, Fine kNN, Ensemble Boosting, Ensemble bagging, Medium NN, and Kernel SVM) were trained on three reduced feature sets. On UMAP features Cubic SVM outshines with remarkable accuracy of 99.2%, on t-SNE features Medium Tree classifier achieves an impressive accuracy of 98.3%, and on PCA. The Medium Tree classifier stands out with exceptional accuracy at 99.7%. Quadratic SVM shows Consistent Performance by maintaining the highest accuracy across UMAP (97.5), t-SNE (89.9), and PCA (98.8). This research contributes to advancing our understanding of ADHD through objective, data-driven methodologies. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： ADHD Dimensionality Reduction Machine Learning Motor Activity

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis and Optimization of Spam Filtration Techniques Using Natural Language Processing

Comparative Analysis and Optimization of Spam Filtration Tec...

引用

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Mehta, Aditya Kumar Kumar, Suresh Netaji Subhas University Of Technology Department Of Computer Science & Engineering Delhi India

ISBN: (纸本)9798350366846

Spam emails, messages, and content remain a persistent nuisance in the digital landscape, demanding effective and efficient classification methods. This paper presents an exploration of several techniques for spam classification using Natural Language Processing (NLP) techniques, we aimed to optimize the performance of spam filtration algorithms Through rigorous experimentation and analysis. In Spam classification, the spam Text is converted into a machine-readable form by NLP preprocessing tasks such as Tokenization, stemming, Lemmatization. After preprocessing the dataset is converted into a transformed text on which we will train our model to detect spam and ham messages using various classifiers. We trained our dataset on different Machine Learning (ML)classification models like Naive bayes, Random Forest, Extra trees classifier. We were able to achieve 96.7% accuracy and 100% precision using Extra trees classifier and 97.1% accuracy using multinomial Naïve bayes model. We also explored spam classification using pretrained 'BERT' model Which can predict spam or ham messages with contextual understanding, our spam detector model using BERT could classify spam messages with 86.0% accuracy on UCI spam messages dataset. This research contributes to the ongoing efforts to combat spam by presenting a comprehensive exploration of optimization techniques in the context of NLP-based spam classification. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithms for Traffic Flow Prediction in Intelligent Transportation Systems 4

Comparative Analysis of Machine Learning Algorithms for Traf...

引用

4th International Conference on Technological Advancements in Computational Sciences, ICTACS 2024

作者： Yadav, Mahima Kumar, Bijendra Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350387490

As human society advances, the limitations of current transportation systems become more apparent, prompting a growing desire to leverage advanced technology for intelligent transportation solutions. However, low identification rates and complicated processing plague many of the vehicle detection techniques used in video analytics today. This paper gives a comparative analysis of multiple machine learning algorithms for traffic flow prediction in order to improve Intelligent Transportation Systems (ITS). Using an extensive dataset of historical traffic flow and environmental variables, we evaluate the performance of several methods: Linear Regression (LR), Support Vector Machine (SVM), Decision Trees, Random Forests (RF) and deep Neural Networks (DNN). Numerous Variables are taken into account in the evaluation, including scalability, computing efficiency, and forecast accuracy. The findings show that while algorithms like RF and SVM give good performance with less computational overhead, DNN obtain the maximum accuracy. The work offers valuable information on the disadvantages of various machine learning (ML) techniques, which may be used to select suitable models for the prediction of traffic movement in real-world ITS. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Deep Transfer Learning based Speech Recognition for Low Resource Hindi Language

Deep Transfer Learning based Speech Recognition for Low Reso...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Singh, Shivangi Bhatt, Shobha Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350378092

Automatic speech recognition (ASR) stands out as a pivotal technique, steadily gaining prominence by facilitating seamless communication between humans and technology. Due to a shortage of substantial speech datasets for model training, ASR systems for most languages lack acceptable performance, despite achieving human-like performance for a limited number of languages. In this study, we leverage the Hugging Face ecosystem to fine-tune state-of-the-art Whisper Speech architecture to showcase the efficacy of transfer learning technique in ASR tasks, yielding momentous enhancements in accuracy and performance compared to conventional training methods. Our findings underscore the potential of transfer learning to advance ASR technologies and provide insights for future research endeavors in this dynamic domain. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Predicting Stress Using Time-Domain Feature engineering via Smartphone Soft-Typing Data

Predicting Stress Using Time-Domain Feature Engineering via ...

引用

2024 International Conference on Artificial Intelligence and Emerging technology, Global AI Summit 2024

作者： Sakshi Bhatia, M.P.S. Chakraborty, Pinaki Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350379716

People with significant intellectual disabilities frequently struggle to articulate their stress, which makes timely carer reactions difficult. Stress, a frequent problem in modern life, is often overlooked, emphasising the importance of early detection. Smartphones, which are continually used, generate a variety of behavioural data, making them perfect for stress detection. This paper offers an autonomous real-time stress detection system that use wearable sensors to capture physiological signals and machine learning to detect stress-related changes. Our study uses data from smartphone sensors, including linear acceleration, gravity, gyroscope, and touchscreen sensors, to detect stress through soft keyboard typing behaviours. We capture nuances in phone interactions under stress by extracting statistical time domain features from raw sensor data, such as mean, variance, standard deviation, and energy. Using feature selection techniques, we reduced the dataset to the most significant features, minimizing model complexity and improving accuracy. We applied advanced machine learning methods like bagging, boosting, and stacking classifiers. The AdaBoost classifier achieved a 94.21% accuracy, a 5.58% improvement using the selected feature subset compared to the full feature set. The optimized model also significantly reduced the model-building time to 1.73 seconds, demonstrating the efficiency and practicality of our approach for real-time stress detection. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Optimization of Sentiment Analysis using BERT

Optimization of Sentiment Analysis using BERT

引用

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Kewalramani, Bhaskar Kumar, Suresh Netaji Subhas University Of Technology Department Of Computer Science & Engineering Delhi India

ISBN: (纸本)9798350366846

This study presents a comprehensive exploration of a sentiment analysis algorithm enhanced by the BERT (Bidirectional Encoder Representations from Transformers) model. The BERT model's integration into our sentiment analysis algorithm has resulted in performance that surpasses traditional methods, including Support Vector Machines (SVM), Logistic Regression (LR), and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. The findings of this research are poised to contribute significantly to the field of sentiment analysis, providing a robust framework for future applications in understanding customer feedback. © 2024 IEEE.

关键词： Sentiment analysis

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：