检索结果-内蒙古大学图书馆

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Abhishek Tiwari Jiya Sehgal Mukhtiar Singh Ashutosh Mishra Dept. of Computer Science Engineering Chandigarh University Mohali Punjab India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

This paper presents a model that detects emotions in English-Punjabi code-mixed social media posts. The pervasiveness of multilingual code-mixed communication on social media platforms poses a significant challenge for sentiment and emotion analysis. Our work addresses this gap by developing a logistic regression-based emotion detection system that classifies posts into three divisions: positive, negative, and neutral. The data set used for this study comprises 37,805 training posts and 10,307 test posts, each labeled with an emotion. The model was trained and evaluated after preprocessing the code-mixed text data, including cleaning, stopword removal, and vectorization. The model attained an accuracy of 92% on the test dataset, exhibiting its effectiveness in handling code-mixed content. Furthermore, we implemented a real-time web interface using Streamlit, which allows users to classify the emotions of mixed English-Punjabi code posts. The promising results suggest that this approach can be beneficial in various implementations such as mental health tracking and sentiment analysis in multilingual contexts.

关键词： Sentiment analysis Emotion recognition Accuracy Social networking (online) Mental health Machine learning Real-time systems Cleaning Multilingual Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Accident Detection Approaches

A Comprehensive Study on Accident Detection Approaches

引用

2022 IEEE Delhi Section Conference, DELCON 2022

作者： Donepudi, Harshini S Saxena, Mayank Yun, Yeo Xiong Jansirani, Preethaa Sethi, Simardeep Singh Banik, Barnali Gupta Andhra University Dept. of Computer Science Sys Engineering Andhra Pradesh Visakhapatnam India University of Allahabad Dept. of Computer Science and Engineering Uttar Pradesh Allahabad India National University of Singapore Dept. of Engineering Science Singapore Singapore College of Engineering Guindy Anna University Dept. of Electronics and Comm. Engineering Chennai India Guru Tegh Bahadur Institute of Technology Dept. of Computer Science and Engineering New Delhi India C. R. Rao Advanced Institute of Mathematics Statistics Computer Science University of Hyderabad Telangana India

ISBN: (纸本)9781665458832

Accident-prone detection predicts the likelihood of a vehicle getting into an accident. Major contributing factors to road accidents include distracted driving, unsafe road infrastructures, and social sensitivity features, but not only these factors. The data collected by monitoring the traffic is used to model and test the detection systems. This behaviour is usually identified utilising exploratory data analysis of historical data based on previous accidents, traffic patterns, the infrastructure of the roads and other miscellaneous factors. In this paper, existing techniques are studied in detail to weigh the benefits and costs of implementing different detection models. This study aims to determine how various model(s) can be implemented to ensure a safe commute that can eventually lead to real-time alerts to prevent fatal accidents. The notion of lane-less and lane-based traffic is also considered. Specifically, a Long Short-Term Memory (LSTM) network has been reviewed, and notable enhancements have been suggested. After arriving at the conclusions, the future scope has also been discussed. © 2022 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Elastic Vertical Memory Management for Container-based Stateful Applications in Kubernetes 25

Elastic Vertical Memory Management for Container-based State...

引用

40th Annual ACM Symposium on Applied Computing, SAC 2025

作者： Kang, Taeshin Yu, Heonchang Dept. of Computer Science and Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798400706295

Cloud service providers offer horizontal auto-scaling to prevent wasting resources by overprovisioning containers. However, this approach struggles to respond immediately to unexpected spikes in resource usage and has limitations in optimizing resource utilization. Vertical auto-scaling overcomes these limitations. Vertical elasticity has become increasingly important in recent years to provide instant resource elasticity for stateful and real-time critical applications. Nevertheless, vertical elasticity is not actively researched and implemented due to limitations in achieving it. This paper proposes Elastic Vertical Memory Management (EVMM) for stateful applications in the Kubernetes environment, which is the de facto standard in the container orchestration space. We compared EVMM to an existing Kubernetes environment without vertical elasticity and found that it reduced the total execution time of container workflows by up to 35% and memory resource utilization on nodes improved by 1.5x. Copyright © 2025 held by the owner/author(s).

关键词： auto-scaling

来源：评论

学校读者我要写书评

暂无评论

Privacy-Enhanced Image Restoration in Remote Sensing via Federated Learning

TechRxiv

引用

TechRxiv 2024年

作者： Khan, Muhammad Jahanzeb Rath, Suman Zaib, Muhammad Hassan Dept. of Computer Science and Engineering University of Nevada Reno Reno United States Dept. of Computer Science Air University Islamabad Pakistan

This research addresses the dual challenges of image restoration quality and data privacy in optical remote sensing. Traditional restoration methods often fall short due to the complex nature of remote sensing images, and data privacy concerns further complicate the use of advanced techniques. By integrating the Deep Memory Connected Neural Network (DMCN) with the Data-Decoupled Federated Learning (DDFL) framework, our approach enables significant improvements in image restoration without requiring direct access to sensitive raw data. This method not only enhances data privacy by leveraging federated learning principles but also incorporates advanced techniques like Gaussian image denoising to maintain high restoration quality despite potential noise introduced by the federated process. The performance of the federated DMCN, particularly on the UCMERCED dataset, demonstrates minimal accuracy degradation, even in the presence of noise, while the strategic use of Downsampling Units within DMCN optimizes computational efficiency. Our comprehensive evaluations reveal the effectiveness of this approach in balancing data privacy with the need for high-quality image restoration, suggesting a promising direction for future advancements in remote sensing applications. © 2024, CC BY.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Insights: a Visual Comparative Analysis of Fundus Images Across Diverse Datasets

Glaucoma Insights: a Visual Comparative Analysis of Fundus I...

引用

Smart Systems for applications in Electrical sciences (ICSSES), International Conference on

作者： Chunduri Yoshitha G Vishwa Prakashini Neha S Aiswariya Milan K Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru India

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

Glaucoma is a major global health issue that can lead to irreversible vision loss if untreated. Early diagnosis and continuous monitoring are crucial to mitigating its impacts. Fundus images are necessary to evaluate, diagnose glaucoma and offer an in-depth perception of retinal structures and features indicative of the condition. The project aims to compare the features of fundus images from three widely recognized datasets, they are REFUGE, ODIR, and DRONIS-DB focusing on analyzing critical metrics such as pixel intensity, brightness, image channel analysis, edge mean, and saturation means. Advanced visualizations are employed to ensure a comprehensive analysis of the features. The main objective of the work is to provide a structured data-driven approach for feature extraction and visualization, enhancing our understanding. This project contributes to advancing diagnostic precision, supporting clinical decision-making, and enabling researchers to explore innovative solutions in ophthalmology by bridging the gap between medical imaging data and actionable insights.

关键词： Glaucoma Visualization Decision making Data visualization Feature extraction Smart systems Retina Ophthalmology Biomedical imaging Resistance heating

来源：评论

学校读者我要写书评

暂无评论

Integrating Fuzzy Logic with Supply Chain Management

Integrating Fuzzy Logic with Supply Chain Management

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： Afrah Fathima. S Muqaddam Aaqil Sheriff Addepalli Raja Vyshnavi Jananee V Dept of Computer Science Rajalakshmi Engineering College

Supply chain management concepts are of great importance in the current era. It is also famously quoted that "Whoever controls the spice, controls the whole world". Transportation of goods from one place to another and at the right time is very essential. The two major Parties playing huge roles in the whole concept are the suppliers and the manufacturers. The supplier is the one who is responsible for supplying raw materials to the manufacturer. The manufacturer has to hunt down for suppliers which is a tedious task. The success of the supply chain as a whole has a significant impact on the success of a manufacturing firm. The demand for specific goods is determined by all supply chain participants, who subsequently supply the raw materials needed to make those goods and complete consumer orders. The chain as a whole could be in danger if one link breaks or becomes weak. On the other hand Artificial Intelligence plays a very important role in automating and taking right decisions. Without the role of Artificial Intelligence(Fuzzy Logic) our lives could be unpredictable on really different levels. Primarily the type of Intelligence which is portrayed by machines in contrast to that of human beings. The Data that the AI model has could be of great significance to SCM specialists. These two concepts can be put into use and certain major problems that SCM specialists face can be solved with the help of Artificial Intelligence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Kidney Stone Detection with Vision Transformers and CNNs: A Transfer Learning Strategy

Optimizing Kidney Stone Detection with Vision Transformers a...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Supritha Kulkarni Suhaas Rao S Tushar Kumar Chopra Yeshwanth S P Bhanushree K J Suneetha K R Dept. of Computer Science and Engineering Bangalore Institute of Technology Bengaluru India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Kidney stones are a common and impactful urological condition, with timely and accurate diagnosis being critical to prevent complications such as renal damage and avoid invasive treatments. This study explores the use of advanced deep learning models, including Vision Transformers (ViT), Swin Transformer and Convolutional Neural Networks (CNNs)—specifically XResNet-50, VGG-16, MobileNetV2 and AlexNet—to enhance kidney stone detection from CT scan images. Leveraging a robust dataset of annotated CT scans in JPG format, the approach employs transfer learning which leverages features learnt from the ImageNet dataset to optimize model performance, focusing on classifying cases as either "Kidney Stone Present" or "Kidney Stone Absent". To further improve diagnostic reliability, the Grad-CAM (Gradient-weighted Class Activation Mapping) identifies and localizes kidney stones within CT images, enhancing understanding of the model’s decision-making and supporting interpretability. Addressing challenges related to dataset imbalance, model interpretability, and generalizability across healthcare settings. By refining these models for kidney stone detection, the main objective of this work is to build a reliable diagnostic tool that aids in clinical judgement and treatment planning, ultimately enhancing patient outcomes and encouraging broader clinical adoption.

关键词： computer vision Visualization Accuracy Computed tomography Transfer learning Medical services Transformers Data models Reliability Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automail AI: Intelligent Voice-Controlled Email Generator

Automail AI: Intelligent Voice-Controlled Email Generator

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Kavitha Jayaram Samarth Mandagere Sampriti Gopisetti Sahit S Dept. of Computer Science and Engineering BNM Institute of Technology Bengaluru India

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

The complexity of contemporary communication further emphasizes the need to automate monotonous work to increase efficiency and effectiveness. This paper introduces a new advance, voice-controlled Automail AI, in the form of an email generation tool that automatically sends an email according to end-user-specified keywords. Automail AI utilizes NLP, ML, and Speech Recognition to differentiate formal emails from informal ones and draft appropriate responses as the situation demands. It has been tuned with Naive Bayes Classifier that yields a better level of accuracy as compared to models such as Decision Tree, SVM, and Logistic Regression. Setting the benchmark for Automated Communication tools, Automail AI combines diverse technologies like SMTP to guarantee secure Email delivery, Google Text-to-Speech or GTTS for auditory feedback, and a module providing an interface for speech recognition that offers the possibility to use the tool with no hands.

关键词： Support vector machines Logistic regression Accuracy Speech recognition Machine learning Natural language processing Real-time systems Electronic mail Internet Decision trees

来源：评论

学校读者我要写书评

暂无评论

Towards Touchless Interaction: Implementing Hand Gesture Recognition for Presentation and Media Control

Towards Touchless Interaction: Implementing Hand Gesture Rec...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Shailaja Uke Atifa Shaikh Harshada Rayate Anjali Kamble Sanavi Rahane Dept. Computer Science and Engineering Vishwakarma Institute of Technology Pune India

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

The integration of hand gesture recognition with modern multimedia systems offers a novel and intuitive interface for users to interact with. This research implements a reliable framework for gesture-based control of slide presentations and media functionalities, using real-time hand detection and tracking through computer vision technologies such as OpenCV and cvzone. Recognizing individual hand gestures, the system allows for smooth navigation through slides in a presentation, annotating on slides, changing the brightness, managing windows like window minimization and maximization, and controlling media playback. The solution uses machine learning-based hand pose estimation along with optimal gesture mappings to make the recognition highly accurate and responsive. This research is meant to represent the possibility of hands-free interaction in professional and academic settings. The approach also studies applications in remote work scenarios, thereby increasing the incorporation of gesture recognition technology into everyday computing work. Moreover, the system is flexible and scalable and has the potential to integrate with virtual reality systems, remote learning platforms, and interactive kiosks. The proposed system, under controlled conditions, achieves an average accuracy of about 85 percent to 90 percent. It recognizes predefined hand gestures for navigation and interaction. When multiple gestures are shown at the same time, the system might experience temporary lags, but it recovers functionality within a few seconds. Thus, this research underlines the role of gesture recognition technology in transforming the way a user experience is provided.

关键词： Hands Productivity computer vision Technological innovation Accuracy Navigation Gesture recognition Media Real-time systems Windows

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Deep Learning Based Approaches for DeepFake Identification 6

A Comparative Analysis of Deep Learning Based Approaches for...

引用

6th International Conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 2024

作者： Duhan, Krity Kajal, Abhishek Dept. of Computer Science and Engineering GJUS and T Hisar125001 India

One of the major concerns in the present global environment is the creation and utilization of deepfakes. In this work, we have examined the issues and challenges that are created by the deepfake in the security and surveillance mechanisms. Deepfakes are used for by passing the facial identification or biometrics system that are normally used as surveillance mechanisms. Previously the only issue was to find the authentic person through the photographs that they have put on their identity proofs but nowadays it is extended to find the forged pics that are manipulated with the usage of AI based methods like deepfakes. Deepfakes are used in the current environments for bypassing the security by impersonation and providing false information and thus become a source of danger especially in the politics arena and entertainment landscape. Deep learning has the tendency to mitigate the impact of deepfakes to considerable extent by incorporating the same in the techniques develop for the identification of deepfakes. This paper provides the comprehensive review of the deepfake related work that has been done by researchers with the usage of deep learning approaches which could identify the fake images, videos to significant extent in various contexts along with the mechanism used for deepfake creation and identification in general. Moreover, the comparative analysis of the existing techniques has been done considering a range of factors like dataset used, technique used, accuracy, AUC, data type used for deepfake identification etc. It has been inferred that majority of the researchers have used the FaceForensics++, Celeb-DF, DFDC dataset and have utilized CNN technique for the deepfake identification primarily on images. © 2025 The Author(s). Published by Elsevier B.V.

关键词： Deep learning

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：