检索结果-内蒙古大学图书馆

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Samudrala, Sai Santhoshi Haneesha Thambi, Jaishitha Vadluri, Sai Rishisri Mahalingam, Anand Pati, Peeta Basa Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350381931

Parkinson's disease (PD) is a progressive neurological disorder that affects movement, posture, hand writing and speech. This disease often manifests speech related symptoms, including reduced vocal intensity, articulatory imprecision, making speech analysis a potential diagnostic tool. This paper focus on speech analysis of individuals to diagnose PD using different classifiers such as Logistic Regression (LR), Gradient Boosting classifier (GBC), Random Forest (RF), SVM, Decision Tree (DT), AdaBoost. SHAP and LIME are implemented toevaluate each feature's significance. It's observed that the optimal subset with 7 important features, identified with SHAP, an accuracy of 98% is attained. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Modeling Plants vs Zombies Gameplay using Finite automata 3

Modeling Plants vs Zombies Gameplay using Finite automata

引用

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Archana Reddy, P. Divya Jyothi, G. Varshita, Velumury Akshitha, Chennupati Radha, D. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350364569

Playing video games on personal computers is known as PC gaming. PC games are available in a variety of genres, offer both single-player and multiplayer options, and have spawned an international e-sports industry. Modding communities are active, digital distribution systems are essential, and hardware can be customized. Future developments in gaming, such as virtual reality, cloud gaming, and artificial intelligence, portend more innovation in the industry. The game, Plants vs Zombies is represented by Finite Automata and it is ruled by DFAs and NFAs which describe the actions and behaviours of both the plants and the zombies and the result of their actions. In the proposed work you can notice how the NFA will be converted to DFA and vice versa due to its handy functions. Overall, "Plants vs Zombies"is a fun and interactive way for players to explore computational thinking while learning about the complex ideas of NFA and DFA in Automata Theory. The advantages are Synchronize State Management, Consistent State Transitions, Easier Development, and Unambiguous Animation Staging. © 2024 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

AMOSI:Attention-Based Multimodal Sentiment Intensity Analysis with LSTM-CNN Architecture for Online Opinion Videos 15

AMOSI:Attention-Based Multimodal Sentiment Intensity Analysi...

引用

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

作者： Sree, V. V. V. Bhagya Bharathi Mohan, G. Prasanna Kumar, R. Rithani, M. Pallavi, Gundala Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350370249

Through online video sharing websites, people share their thoughts, experiences, and reviews on a daily basis. Researching the subjectivity and sentiment in these opinion videos is becoming more and more popular among academics and industry professionals. Although sentiment analysis works well for text, there isn't much research done on it when it comes to videos and other multimedia. The largest obstacles to research in this area are the absence of appropriate methodology, baselines, datasets,and statistical analysis of the relationships between data from various modality sources. The Multimodal Opinionlevel Sentiment Intensity dataset (MOSI), the first opinion-level annotated corpus of sentiment and subjectivity analysis in online videos, is presented to the scientific community in this paper. With labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, the dataset is meticulously annotated. User-generated opinion videos are increasingly prevalent, necessitating advanced sentiment analysis techniques. We present an attention-based LSTM-2D CNN model for multimodal sentiment intensity prediction. Our contributions are three-fold: 1) We collect new annotations of visual gestures and acoustic effects in online videos to augment the MOSI dataset. 2) We design an end-to-end neural architecture to model textual, visual and acoustic modalities. Bi-directional LSTMs capture temporal dependencies in text and audio. 2D CNNs extract spatial visual features. A hierarchical attention mechanism identifies important utterances and frames. 3) Extensive experiments demonstrate 74.7% accuracy, outperforming prior BC-LSTM models by 1.7%. Ablation studies validate the impact of multimodal fusion and attention. Our work provides an improved neural baseline on MOSI, with detailed analysis of multi-view sequential modelling for opinion videos. The additional annotations and strong results will aid future research in this emerging domain. © 2024

关键词： AMOSI Attention CNN LSTM MultiModal

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-based AI for COVID-19 detection: a comprehensive review of public and private lung ultrasound datasets and studies

引用

Multimedia Tools and Applications 2025年 1-55页

作者： Morshed, Abrar Al Shihab, Abdulla Jahin, Md Abrar Al Nahian, Md Jaber Hossain Sarker, Md Murad Ibne Wadud, Md Sharjis Uddin, Mohammad Istiaq Imtiaz Siraji, Muntequa Anjum, Nafisa Shristy, Sumiya Rajjab Rahman, Tanvin Khatun, Mahmuda Rubel Dewan, Md Hossain, Mosaddeq Sultana, Razia Chakma, Ripel Emon, Sonet Barua Islam, Towhidul Hussain, Mohammad Arafat Department of Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka1208 Bangladesh Department of Electrical and Telecommunication Engineering Daffodil International University Dhaka1216 Bangladesh Khulna9203 Bangladesh Okinawa904-0412 Japan Department of Information and Communication Technology Bangladesh University of Professionals Dhaka1216 Bangladesh Department of Information and Communication Technology Comilla University Cumilla3506 Bangladesh Department of Biomedical Physics and Technology University of Dhaka Dhaka1000 Bangladesh Department of Computer Science and Engineering International Islamic University Chittagong Chittagong4318 Bangladesh Department of Electrical and Electronic Engineering Islamic University of Technology Gazipur1704 Bangladesh Department of Electronics and Telecommunication Engineering Chittagong University of Engineering and Technology Chittagong4349 Bangladesh Department of Computer Science and Engineering Notre Dame University Bangladesh Dhaka1000 Bangladesh Department of Electrical and Electronic Engineering Khulna University of Engineering & Technology Khulna9203 Bangladesh Department of Computer Science and Engineering Institute of Science and Technology Dhaka1209 Bangladesh Department of Electronics and Communication Engineering Institute of Science and Technology Dhaka1209 Bangladesh Department of Mathematics Jahangirnagar University Dhaka1342 Bangladesh Department of Electrical and Electronic Engineering Daffodil International University Dhaka1216 Bangladesh Department of Electrical and Electronic Engineering Dhaka University of Engineering and Technology Gazipur1707 Bangladesh Department of Computer Science and Telecommunication Engineering Noakhali Science and Technology University Noakhali3814 Bangladesh Department of Computer Science and Engineering Northern University Bangladesh Dhaka1230 Bangladesh Boston Children’s Hospital Harvard Medical School BostonMA02

The COVID-19 pandemic has affected millions of people globally, with respiratory organs being strongly affected in individuals with comorbidities. Medical imaging-based diagnosis and prognosis have become increasingly popular in clinical settings for detecting COVID-19 lung infections. Among various medical imaging modalities, ultrasound stands out as a low-cost, mobile, and radiation-safe imaging technology. In this comprehensive review, we focus on AI-driven studies utilizing lung ultrasound (LUS) for COVID-19 detection and analysis. We provide a detailed overview of both publicly available and private LUS datasets and categorize the AI studies according to the dataset they used. Additionally, we systematically analyzed and tabulated the studies across various dimensions, including data preprocessing methods, AI models, cross-validation techniques, and evaluation metrics. In total, we reviewed 60 articles, 41 of which utilized public datasets, while the remaining employed private data. Our findings suggest that ultrasound-based AI studies for COVID-19 detection have great potential for clinical use, especially for children and pregnant women. Our review also provides a useful summary for future researchers and clinicians who may be interested in the field. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Identifying Sentiment in Legal Case Judgments using Random Forest Classifier 9

Identifying Sentiment in Legal Case Judgments using Random F...

引用

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

作者： Pavani, Bhupathi Vishva Mahitha, Desham Prabhakar, Priyanka Pati, Peeta Basa Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350394474

This paper explores sentiment analysis in legal judgments using machine learning techniques. Six machine learning models, including Naïve Bayes, K Nearest Neighbors, Logistic Regression, Support Vector Machine, Random Forest, and Decision Tree, are used along with three data embeddings namely T5, RoBerta, and LegalBert. The study aims to evaluate the effectiveness of these models in sentiment analysis tasks tailored to legal documents. Each model is trained and evaluated based on the unique characteristics of legal texts. Hyperparameter tuning has also been performed for all the models. The focus is on achieving high accuracy, F1 score and understanding the interpretability of the models' predictions. The highest accuracy achieved was by Random Forest of 67.5%. The study aims to provide insights into the applicability of various machine learning algorithms and data embeddings for sentiment analysis in the legal domain. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Inference of Missing Attributes in Multilevel Complex Network 5

Inference of Missing Attributes in Multilevel Complex Networ...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Nettem, Nikhil Chowdary Nukala, Aashish Gopal Kaushal, Siruguppa Vishnu Sai Deepthi, L.R. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350379945

Social networks exhibit a hierarchical structure where users are grouped at multiple levels based on communities, interests, or behaviors. The attributes associated with users provide additional information for various social network analysis tasks. However, the attributes may be missing for multiple reasons: incomplete data collection, or privacy concerns. Inferring missing attribute values within a hierarchical social network poses a challenge for accurate analysis and modeling. The state-of-the-art algorithm infers the attributes in a single level and less focus is given to infer the attributes at multiple levels. In this paper, the missing attributes are inferred by employing hierarchical clustering followed by CNN and Hierarchical Graph Neural Network. Our method's accuracy of attribute inference is compared with traditional machine learning models, including Logistic Regression, Random Forest, XGBoost, K-Nearest Neighbors (KNN), and Gaussian Naive Bayes. The results demonstrate that the hierarchical clustering with the CNN approach consistently outperforms traditional machine learning models in terms of attribute inference accuracy. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Real-Time Malware Detection for IoT Traffic Streams: A Comparative Study of Concept Drift Detection Techniques 5

Adaptive Real-Time Malware Detection for IoT Traffic Streams...

引用

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

作者： Bharani, D. Lakshmi Priya, V. Saravanan, S. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331518097

As IoT expands dynamically, cybersecurity threats are evolving with time;thus, classical malware detection systems are no more appropriate, due to the phenomenon of concept drift and the necessity of handling large amount of data while detecting malware. Concept drift is used to refer to the statistical properties of malware that change over time as the malware behavior changes. We henceforth propose a real-time system to detect malware within a large-scale network traffic streams in the presence of concept drift. The system is capable of processing continuous large volumes of IoT traffic in real-time as it is implemented using Apache Spark and Apache Kafka. The proposed system also compares the performance of six different concept drift detection techniques: KS test, CUSUM, ADWIN, KSWIN, DDM, Page Hinkley on NSL-KDD and IoT -23 datasets. The comparison results show that KS test correctly identified concept drift in both the datasets. The proposed system makes an IoT environment with better malware detection capabilities by integrating the adaptive mechanism in real-time data processing tools apart from achieving high performance and scalability. © 2024 IEEE.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

Hand-Written Bramhi Script Recognition using Deep Learning

Hand-Written Bramhi Script Recognition using Deep Learning

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Swaroop, Bandi Vishnu Prasad, Angala Hari Reddy, Busa Thanuj Sathwik Vardhan, Puvvadi Harsha Singh, Rimjhim Padam Palaniswamy, Suja Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350374933

This work involves the classification of handwritten script using deep learning with a special interest in the comparison of different pre- trained models. As one of the oldest writing systems in the world, derived from the Dravidian and southeast Semitic scripts that were developed 4,500 years ago in India and Central America, Brahmi script also has variability due to the hand-written accented forms. To address these obstacles, different pre-trained models viz., Vision Transformer (ViT), MobileNetV2, VGG16, ResNet50, DenseNet, and EfficientNet with the CNN are implemented and compared. The result of the implementation infers that all of these pre- trained models yield a higher accuracy than the custom CNN traditional CNN approach, with a peak improvement in performance shown by MobileNetV2. This lays the ground for future utilization of deep learning architectures which have the capability of preserving and understanding handwritten symbolic scripts. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MediLocker: Centralized Electronic Health Records System 2

MediLocker: Centralized Electronic Health Records System

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Harini, N. Karishma, R.S. Pranav, M. Duvvuri, Ananya Akhil, Marrivada Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350371314

The transition from traditional paper-based patient records to advanced digital formats has not been without its challenges. While Electronic Health Records (EHRs) offer instantaneous access to detailed patient health information, there are drawbacks too. One significant drawback that was identified from the literature survey was the lack of interoperability and uniformity in patients' medical information across different healthcare facilities. This fragmentation hampers communication and collaboration among healthcare providers, leading to inefficiencies and gaps in patient care. Additionally, concerns about the security and privacy of patient data in EHRs persist, with instances of data breaches and unauthorized access raising alarm within the healthcare community. In response to these challenges, this paper proposes the development of a secure, privacy-ensuring Medilocker system aimed at investigating electronic health management systems comprehensively by assessing the status of EHR systems and efficiently managing electronic health records while safeguarding patient data. The implementation of role-based access control, coupled with data anonymization for preserving confidentiality, results in the development of a cohesive solution that facilitates the systemization, integration, and fortification of the healthcare system, while ensuring prompt access to information in compliance with privacy and security standards. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Sapota Quality: Bruise Detection and Shelf Life Prediction 5

Sapota Quality: Bruise Detection and Shelf Life Prediction

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Raviteja, Mellacheruvu Reddy, Vanguru Venkata Varun Kumar Aqibuddin, Shaik Soppa, Mithil Teja Sarath, S. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9798350379945

The shelf life and consumer appeal of sapota, a tropical fruit, are influenced by fluctuations in its freshness and flavor over time. Apart from classifying bruises, this study looks into the application Using thermal imaging to estimate the shelf life and identify maturity of sapota. This research study intends to predict the shelf life of the sapota, maturity of the sapota and bruises detection for this we collected dataset using fluke thermal camera of 60 sapota fruits, each day for 5 days in order to capture the life cycle of sapota from unripe to ripen state. The weights are monitored for further analysis. Further, a seperate dataset is collected for bruise detection by intentionally damaging the fruit for bruise detection part. The dataset consists of ripen and unripen images together with the number of days that have passed since the photo was taken, along with weights on particular day. For these tasks, various convolutional neural networks CNN ResNet, VGG16 and MobileNet are used. In terms of ripeness classification, shelf life prediction and sapota bruise detection, the efficiencies of the models are assessed and accuracy we got is 93 percent for the best model. These findings suggest that the thermal imaging in combination with deep learning techniques for non-destructive quality Evaluation of sapota fruit may assist in reducing food waste. © 2024 IEEE.

关键词： Shelf life

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：