检索结果-内蒙古大学图书馆

Alzheimer's Disease Classification via Pre-trained Convolutional Neural Network Variants Utilizing Multi-level Thresholding based on Kapur's Entropy 2

Alzheimer's Disease Classification via Pre-trained Convoluti...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Mahendran, Nivedhitha Durai Raj Vincent, P.M. Srm Institute of Science and Technology School of Computing Technologies Department of Networking and Communications Kattankulathur Chennai India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350372892

Neurological diseases are the disorders of brain and the nerves that run throughout the human body. There is a range of symptoms that arise as a result of chemical, structural, or electrical modifications in the regions of brain. One such neurological disease is the Alzheimer's Disease (AD), is considered as a slow and progressive disease that majorly affects the cognitive abilities of the individual. It is most common forms of dementia without any proper cure. However, early diagnosis and treatment might slow down the symptoms and improve the lifestyle of the individual. The most common techniques to identify the neurological disorders are imaging of the brain regions, namely, CT, MRI, PET, etc. The learning approaches, such as Deep Learning and Machine Learning are identified to be effective in analyzing these images to provide better accuracies in detecting the AD. In this study, four versions of Convolutional Neural Networks (CNN) are used to classify AD and Control cases. Further, the Kapur's thresholding technique is also implemented to segment the images for improving the classification accuracy of AD. From the results shown in the study, the inference shows that the VGG16 of CNN provides considerable improvement than the other deep learning models before and after the implementation of thresholding. © 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

Topic Modeling Based Clustering of Disaster Tweets Using BERTopic

Topic Modeling Based Clustering of Disaster Tweets Using BER...

引用

2024 MIT Art, Design and technology School of Computing International Conference, MITADTSoCiCon 2024

作者： Rachel J, Julanta Leela Bhuvaneswari, A. Kumudha, M. Vellore Institute of Technology School of Computer Science and Engineering Chennai India T.John Institute of Technology Dept. of Information Science and Engineering Bangalore India

ISBN: (纸本)9798350362879

The essence of catastrophe management is in the capacity to promptly and effectively addressing unforeseen circumstances, as well as to implement premeditated and flexible strategies in accordance with established protocols and norms. Twitter has become a prominent means of disaster communication, particularly in nations where it has a substantial presence. Twitter can provide valuable information regarding the effects of infrastructure on emergency management in the event of significant disasters. However, the process of sifting through numerous unrelated tweets can be laborious and time-consuming. Prior research has successfully recognized the various categories of communications present on social media platforms during times of disaster. However, there is a dearth of recommended methodologies aimed at effectively extracting valuable information from these messages. In this study, we propose a framework that may be efficiently utilized to promptly deliver disaster effect information derived from social media sources. The methodology involves the application of certain techniques to process the unprocessed Twitter data by employing keyword filtering, location-based filtering, and analysis of tweet properties. Subsequently, Bidirectional Encoder Representations from Transformers (BERT) technique is utilized to categorize the tweets originating from disaster-Affected regions into distinct subjects that are relevant and valuable for emergency management. BERT analysis yielded a total of 376 themes within the dataset. Among these topics, a significant proportion of 196 were found to be closely associated with the impacts of disasters. These impacts encompassed many aspects such as outages, closures, flooded roadways, and damaged infrastructure. © 2024 IEEE.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Semantic Segmentation Approaches for Polyp and Lesion Detection in Medical Imaging 2

Benchmarking Semantic Segmentation Approaches for Polyp and ...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Pandiyaraju, V. Sunil, Meghana Shravya, V. Venkatraman, Shravan Kannan, A. Vellore Institute of Technology School of Computer Science and Engineering Chennai India Anna University Department of Information Science and Technology Chennai India

ISBN: (纸本)9798331534950

In medical imaging, semantic segmentation is essential because it can precisely locate and isolate regions of interest, such lesions or tumours, from intricate anatomical systems. Deep learning (DL) has led to a substantial evolution in segmentation approaches, which have improved medical diagnostics' accuracy and efficiency. The performance of six cutting-edge models is assessed in this paper: LinkNet, U-Net with ResNet50, LinkNet with ResNet50, FPN Net, Simple U-Net, and SegNet-Transformer across four segmentation tasks - polyp detection, lung lesion segmentation from Computed Tomography (CT) scans, breast lesion detection from ultrasound images, and Segmenting brain tumours with magnetic resonance imaging (MRI). With results like 0.9618 for brain tumour segmentation and 0.9483 for lung lesion segmentation, SegNet-Transformer consistently obtained the highest Dice Coefficient across all tests, demonstrating superior ability in capturing intricate boundaries. Other models, such as U-Net with ResNet50, performed competitively with Dice scores of 0.9375 for lung lesion segmentation and 0.9472 for brain tumors but required slightly more memory and longer training times. This study underscores that model performance varies across different tasks, revealing specific strengths and weaknesses. Ultimately, while SegNet-Transformer demonstrates robustness, the choice of model should be informed by the unique requirements of each segmentation task, balancing accuracy, efficiency, and computational demands. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

LPCC Based Music Genrefication Using Hybrid Computational Model 7

LPCC Based Music Genrefication Using Hybrid Computational Mo...

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Sul, Astha Sarda, Harshit Billa, Aishwarya Mishra, Tusar Kanti School of Computer Science and Engineering Vellore Institute of Technology Vellore India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Dept. of Computer Science and Engineering Manipal India

ISBN: (纸本)9798350304268

This work deals with spontaneous music genrefication through computational models which in the recent times has been gaining importance rapidly. Through these hybrid computational models implemented users get an enhanced level of satisfaction when their choice of music files genre with least latency is gained. The paper includes the use of LPCC attributes to obtain the features of the music files along with robust classification models such as neural networks. For this purpose, one thousand audio files are taken as the sample set. The input audio file is pre-processed and suitable LPCC features are computed and stored into final vector. The pool of vectors of numerous audio samples are finally utilized to train a neural model. The proposed work trains the model for ten very distinct categories of music such as hip-hop, jazz, metal, pop, blues, classical, country, disco, reggae, and rock. Further, a comparison is also made between all the classifiers such as SVM, ANN and random forest (RF). Comparatively the best accuracy rate of 85.53\% has been achieved for the proposed work that validates its effectiveness. © 2023 IEEE.

关键词： ANN gtzan dataset LPCC Music Genre

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Personality Classification for Carpooling Application

Machine Learning Based Personality Classification for Carpoo...

引用

2023 International Conference on Intelligent Systems for Communication, IoT and Security, ICISCoIS 2023

作者： Anas, Mohd Gunavathi, C. Kirubasri, G. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Sona College of Technology Department of Computer Science and Engineering Tamil Nadu Salem India

ISBN: (纸本)9798350335835

Sharing a ride in vehicle is known as carpooling and many businesses are adapting this system. Carpooling is an effective way to control air pollution since it decreases the number of automobiles on busy roads. It also helps to reduce traffic roadways, allowing automobiles to drive faster. Carpooling reduces the pollution even further because vehicles use less gas when they travel without much stopping in the traffic. People may also drive their automobiles whenever they choose, with no need for cheaper maintenance and parking charges for each vehicle. According to studies, each car in a carpooling system takes up to 11 vehicles off the road. This cuts yearly pollution by 13 metric tonnes. In India, if carpooling done correctly, one single car will take around 25 automobiles off the road. To make carpooling easier, in this work, a machine learning (ML) model is utilized to identify the personality types of customers based on the tweets and to group them for the same car with similar personalities. The idea intends to break down this barrier between people who don't like to travel with the people who have different personality. In this model, Natural Language Processing (NLP) is used to deal with the dataset before passing it to the model to train. The proposed work is done using XG-Boost, Decision Tree Classifier, Support Vector Machine, and Stochastic Gradient Decent optimizer. Pre-processing the dataset employed the NLP techniques such as Tokenization, Lemmatization and Stemming. After evaluating all the algorithms, we found out that XG-Boost is outperforming all the remaining three algorithms by achieving 68% accuracy easily with 5-fold cross validation. © 2023 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Query-Driven Video Summarization for Long Video Footage Analysis Using Faster-RCNN and Determinantal Point Processes

引用

Procedia computer science 2025年 258卷 3989-3999页

作者： Maitrey M. Bhute Sanskar S. Tare Sridhar Raj S School of Computer Science and Engineering Vellore Institute of Technology Vellore India

With ever growing volume of video content, video summarization becomes crucial for efficiently condensing lengthy videos into informative representations. This paper introduces a novel approach for video summarization by combining object identification with Determinantal Point Processes (DPP). Object identification, powered by advanced computer vision techniques, tracks and recognizes objects across video frames (Convolutional Neural Network/computer Vision), allowing for identification and prioritization of frames with key objects and respective interactions. The proposed algorithm leverages DPP and R-CNN concurrently to select frames while avoiding redundancy and preserving diversity Extensive experiments using diverse video datasets demonstrates that this method performs competitively with existing summarization techniques while tested on TVSum dataset [12], a popular baseline. The results highlight the efficacy of the proposed algorithm in striking a balance between information retention and summary length. It provides accuracy of 84.34% and recall of 13.09%. This research contributes to the field of multimedia content analysis, with potential applications in video indexing, retrieval, and content recommendation systems. Through integration of object identification and DPP, this work introduces an innovative dimension to video summarization. The proposed approach holds promise for generating more informative and visually coherent video summaries. This work holds the potential to advance the state-of-the-art in video summarization techniques, benefiting various multimedia applications by aiding content analysis and user experience.

关键词： Video Summarization Query-Based personalization Determinantal Point Process Faster R-CNN Object Detection

来源：评论

学校读者我要写书评

暂无评论

Sketch to Image synthesis using attention based contextual GAN 14

Sketch to Image synthesis using attention based contextual G...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Sudharson, S. Kumar, R. Prasanna Nawab Mudassir, Shaik Vellore Institute of Technology Computer Science and Engineering Chennai India Chennai India

ISBN: (纸本)9798350335095

Generating realistic and high-quality images from sketches remains a challenging task in the fields of computer vision and graphics. Although deep learning approaches, specifically Generative Adversarial Networks (GANs), have showed promise in generating images in this area, issues such as image quality and diversity persist. In this study, a novel approach for generating human faces from sketches was proposed by leveraging a contextual GAN with attention mechanisms and ResNet-50 feature extraction. Proposed method aims to enhance image quality by incorporating attention mechanisms. Specifically, we extract relevant features from the input sketch using the ResNet-50 feature extraction technique, which are then utilized to guide the image synthesis process. To evaluate the model's performance, a comparison is made with existing approaches using the CHUK dataset, assessing the results based on the Structural Similarity Index (SSIM) score. The proposed technique achieves an impressive SSIM score of 0.78, outperforming other methods in generating realistic and faithful representations of the original images. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Development of Judgment Classification Models using Machine Learning

Development of Judgment Classification Models using Machine ...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Ganti, Shashank Anirudh, Mantha Vellore Institute of Technology Computer Science and Engineering Department Hyderabad India Gandhi Institute of Technology and Management Computer Science and Engineering Department Hyderabad India

ISBN: (纸本)9798350322309

With the world becoming more and more reliant on technology, we are transitioning from a society that values rational evaluation over intuitive thinking to one in which both of those methods coexist. AI devices rely solely on rational evaluation and machine learning allows us to focus on intuition. The task of intelligence is to deduce which method should be relied upon when solving various problems via the establishment of realistic judgments, according to what kind it identifies as being best for that particular problem. However, human judgments cannot simply be quantitatively compared and ranked by a computer according to conditions set by algorithms because certain difficult-to-measure criteria are not easily passable through algorithm systems such as ethics and common sense. In this research, the authors focus on developing judgment classification models using random forest and support vector machine. The authors attempt to test the effectiveness of sentiment proportions as features in judgment classification models. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Fractal dimension analysis for improved decision-making in non-stationary multi-arm bandit problems: a machine learning approach

引用

The European Physical Journal Special Topics 2025年 1-16页

作者： Nandhini, S. Kala Pandian, J. Arun Department of Computer Applications School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

In this research, we propose a novel approach to addressing the exploration–exploitation dilemma in multi-armed bandit (MAB) algorithms using fractal dimensions. The fractal dimension is used in the algorithms to represent the reward distributions of arms which represents the uncertainty of the arm in receiving the reward. The fractal dimension of the reward distribution is implemented in the most popular MAB optimization algorithms, such as Epsilon-Greedy, Upper Confidence Bound (UCB), Exponential-weight algorithm for Exploration and Exploitation (EXP3), and Thompson Sampling in this study. The algorithm prefers to choose arm with the least fractal dimension, as a lower fractal dimension represents less uncertainty of the arm. The performance of the fractal-enhanced MAB optimization algorithms is compared with traditional algorithms in non-stationary environments with various numbers of arms. The proposed approach provides a novel way to quantify and utilize the uncertainty of each arm in MAB problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dog Tracking Through Dynamic Geofencing and Environmental Awareness 5

Enhancing Dog Tracking Through Dynamic Geofencing and Enviro...

引用

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

作者： Saikrupa, P.A. Dhaarini, G. Sanjai, R. Sri Sairam Institute of Technology Department of Information Technology Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518097

With the development of smart technologies, tracking businesses have evolved as tracking collars are now becoming the most crucial piece of safety equipment as well as monitoring tools for dogs. Various solutions like Fi Smart Collar and SpotOn have promising features such as geofencing and activity tracking but integrate with their smart product with less features lacking dynamic geofencing environmental awareness, as well as intelligent system connectivity. The paper proposed a new dog tracking collar system that integrates the use of GPS, Bluetooth, Wi-Fi, and environmental sensors all together onto a unified platform. The system employs an adaptive geofencing module which is dynamic and responds to changes in the environment, including weather and time, as well as different behaviors of pets, keeping it safe within the intended zones. The other advantage with this collar is the maximization of battery life, as it has used low power GPS tracking and intelligent algorithms to adjust the frequency of tracking in line with the assessment of the movement and risk of the pet. The system further integrates into smart home technology and will notify and automatically respond in real-time to changes that might be detected within the pet's environment. The comparative analysis of the current technologies for pet tracking shows significant improvement in accuracy, battery efficiency, and responsiveness to dynamic conditions. The proposed collar was tested and validated by controlled trials and real-time performance assessments, for which considerable results evidenced the reliability and effectiveness for real-time applications. This proposed framework thus would eventually be able to act as a potential future solution that integrates advanced technologies for enhanced pet welfare and with real-time dynamic geofencing and AI in order to create a whole system of pet monitoring. © 2024 IEEE.

关键词： Environmental monitoring

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：