检索结果-内蒙古大学图书馆

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Bhatt, Chandradeep Rai, Sumit Chauhan, Rahul Dua, Deepika Kumar, Mukesh Sharma, Sanjay Graphic Era Hill University CSE Department Dehradun India Computer Science and Engineering Graphic Era Hill University Dehradun India Uttranchal University Department of School of Computing Dehradun India Computer Application Department SGRRITS Dehradun India

ISBN: (纸本)9798350303360

Photo caption generators had gained huge recognition recently from the areas of NLP and computer vision. These generators produce captions that explain an image's content using deep learning algorithms. A sizable collection of image-caption pairs is used to train the algorithm. The photos are fed into a pre-trained CNN after the dataset has undergone preprocessing to extract its visual properties. Along with the picture features, the necessary captions are tokenized and supplied to the LSTM decoder. In order to accelerate the caption generation process, the LSTM decoder is trained to utilize beam search and maximum likelihood estimation methods. To assess the effectiveness of the suggested model, several metrics such as BLEU and METEOR are employed. The suggested CNN-LSTM image caption generator has a lot of promise for use in a variety of contexts, such as picture comprehension, information retrieval, and assistive technology for the blind. Combining CNN and LSTM models takes advantage of each architecture's capabilities, allowing the model to produce insightful and contextually appropriate captions for a variety of images. We also explore present difficulties and potential directions for additional investigation in this area. This research study concludes by presenting an innovative method for creating image captions that combines the strength of CNN and LSTM. The experimental outcomes demonstrate the efficacy and reliability of the suggested model, highlighting its potential to advance the field of image captioning and contribute to the creation of intelligent systems that can comprehend visual content and produce precise and insightful textual descriptions. © 2023 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Building Safety Through Machine Learning-Based Smoke Detection 5

Enhancing Building Safety Through Machine Learning-Based Smo...

引用

5th IEEE International Conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Mohamed, Sulaiman Syed Judeson Antony Kovilpillai, J. Pragya Mir, Mahmood Hussain Golda Brunet, R. Mir, Tawseef Ahmad Alliance School of Advanced Computing Alliance University Bangalore India Government College of Engineering Department of Computer Science & Engineering Thanjavur India

ISBN: (纸本)9798350356236

Smoke detection in surveillance systems plays a crucial role in ensuring the safety and security of various environments, including buildings, forests, and industrial sites. In this paper, a comprehensive analysis of machine learning algorithms applied to smoke detection is presented. The proposed technique is validated using the Smoke Detection Dataset from Kaggle. The dataset comprises a diverse collection of images captured in different scenarios, including both smoke and non-smoke instances. The performance of various machine learning classifiers was evaluated. This included ensemble methods Random Forest (RF), Gradient Boosting (GB), AdaBoost (AB), linear models Logistic Regression (LR), kernel methods Support Vector Machine (SVM), decision-based methods Decision Tree (DT), and nearest neighbor methods K-Nearest Neighbors (KNN). Their precision, recall, AUC-ROC score, and Intersection over Union (IoU) are measured to assess their effectiveness in smoke detection. The results highlight that classifiers such as RF, DT, KNN, GB and AdaBoost achieve outstanding performance, with perfect scores in multiple metrics. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

LGDB-Net: Dual-Branch Path for Building Extraction from Remote Sensing Image 30

LGDB-Net: Dual-Branch Path for Building Extraction from Remo...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Zhang, Ronghuan Zhao, Jing Li, Ming Zou, Qingzhi Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Shandong University of Traditional Chinese Medicine School of Intelligence and Information Engineering Jinan China

ISBN: (纸本)9798331515966

Extracting buildings from remote sensing images using deep learning techniques is a widely applied and crucial task. Convolutional Neural Networks (CNNs) adopt hierarchical feature representation, showcasing powerful capabilities in extracting local information but facing challenges in capturing global features. Transformers can address this limitation, but they perform poorly in extracting local features and significantly increase memory requirements and computational complexity. To overcome these challenges, we propose a method for building extraction from remote sensing images called LGDB-Net (Local-Global Dual-Branch Network), employing a dual-branch approach. Firstly, inspired by Swin Transformer, we designed GB-Former(Global Branch-Former) as the backbone network to model global information. We use a linear multi-head self-attention mechanism to reduce time and memory complexity while maintaining a large global receptive field. Additionally, we replace the traditional multi-layer perceptron with a convolution-enhanced multi-layer perceptron to improve channel feature representation, reduce model parameters, and enhance segmentation performance. Secondly, we use multiple Depth-wise Conv3×3 + LN (Layer Normalization) + GeLU (Gaussian Error Linear Unit) modules as the auxiliary branch for local detailed feature extraction. Finally, we adopt a multi-scale feature fusion strategy to integrate feature information from both branches. We conduct a series of experiments on three datasets: WHU, Massachusetts, and Inria. The experimental results demonstrate that the proposed method not only effectively improves segmentation accuracy with lower building omission and commission rates but also significantly reduces model parameters and computational complexity. © 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

A Scenario-Based Data Catalogue for Autonomous Driving Assistance Systems Using Clustering 5

A Scenario-Based Data Catalogue for Autonomous Driving Assis...

引用

5th IEEE International Conference on Advances in Electronics, computers and Communications, ICAECC 2023

作者： Selvaraj, Surendhar Muthu Kumar, I. Bhaskaran, Sreebha Karthik, R. Balamurugan, Sabari Continental Automotive India Data Solutions Bengaluru India Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Dept of Computer Science & Engineering India Continental Automotive India Bengaluru India

ISBN: (纸本)9798350305449

Autonomous driving assistance systems (ADAS) are developing quickly in terms of the safety of persons and vehicles. Test scenarios are essential for development, simulation, and validation in a typical AD sensor & safety function. As a result, the fleet car of the automobile firm collected the real-world raw data across between 1-2 million kilometers for each sensor generation. Therefore, exact data (i.e., precise data for diverse scenarios like traffic, parking lot, bridge, crossroads, etc.) is essential for carrying out development and validation. To find the precise data among millions of kilometers collected data, automated analytics solutions are enabled such as detection environmental scenes, static & dynamic road participants, scenario detection, etc. and Data catalogue will be formed for the respective scenarios based the output got from the (scenario or object detection) using clustering algorithm. The clustering is performed on the raw text data output got from the scene detection and clustered the scenarios based on the similarity. At the end data catalogue is formed for various ADAS scenarios that used to cater various development and validation requirements of higher level of autonomy. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Credit Card Fraud Detection Using Machine Learning- A Comprehensive Review

Credit Card Fraud Detection Using Machine Learning- A Compre...

引用

Delhi Section Conference (DELCON), IEEE

作者： T. Venkata Jaswant G. Sai Manoj V. Vamisdhar A. Aravind S. Vasudeva Reddy Jagdish Chandra Patni Nilesh Bahadure Rohit Kumar Dept. of Computer Science Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Science and Engineering School of Technology GSFC University Gujarat India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

Credit card fraud is an omnipresent threat in the digital era that cannot be effectively managed without complex detection and prevention strategies. Machine learning has become instrumental for the industry, principally, due to providing tools to analyze transactional information and identify patterns of fraud. The article dwells on the methods, problems, and prospects of their future use. The algorithms are analyzed according to their potential applicability, scalability, and interpretability for fraud detection. This study includes convolutional neural networks and recurrent neural networks are used for utilization of anomaly exposure detection methods to detect unseen fraud with models.

关键词： Training Machine learning algorithms Recurrent neural networks Reviews Scalability Machine learning Credit cards Real-time systems Vectors Fraud

来源：评论

学校读者我要写书评

暂无评论

Navigating Challenges in Creating Effective Chatbots with Natural Language Processing 15th

Navigating Challenges in Creating Effective Chatbots with Na...

引用

15th International Conference on Soft computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired computing, NaBIC 2023

作者： Sathwik, Abbaraju Sai Rao, A. Koteswara Saiteja, Bheri Madhavi, K. Reddy Doppalapudi, Asutosh Amudha, P. VIT-AP University Amaravati India Department of Computer Science and Engineering Andhra Loyola Institute of Engineering and Technology Vijayawada India AI&ML School of Computing Mohan Babu University Tirupati India Coimbatore Ayya Avinashilingam Nagar641108 India

ISBN: (纸本)9783031889912

A conversational agent, also referred to as a chatbot, is computer software that can communicate with users in natural language. Because of a number of issues, developing a successful chatbot model is still difficult. First, understanding the nuances and context of human language remains a complex task, especially when dealing with slang, dialects, or ambiguous expressions. Second, maintaining engaging and coherent conversations over extended periods can be a hurdle, as chatbots need to adapt to changing topics and user moods. Third, ensuring ethical and responsible behavior in chatbots, such as avoiding biased or harmful responses, requires continuous monitoring and refinement. Lastly, staying up-to-date with the evolving field of NLP and AI is essential to incorporate the latest advancements and provide users with increasingly sophisticated conversational experiences. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

EmoSync: Facial Emotion Detection for Adaptive Music Playback 3

EmoSync: Facial Emotion Detection for Adaptive Music Playbac...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Devarajan, Devikanniga Rajkumar, K. GITAM Deemed to be University Computer Science and Engineering Nagadenahalli Doddabalpur Karnataka Bangalore561203 India SRM Institute of Science and Technology Department of Data Science and Business Systems School of Computing Tamil Nadu Kattankulathur603 203 India

ISBN: (纸本)9798350372120

This work investigates using Convolutional Neural Networks (CNN) and VGGNet architecture, for realtime emotion detection. Raw data from the FER-2013 dataset is transformed from CSV format into organized image directories, segmented by distinct emotions. The resulting model, equipped with convolutional, pooling, and dense layers, effectively classifies emotions from 48x48 grayscale images. In application, the model overlays detected emotions onto a webcam stream. An integrated music player module synchronizes music with the subject's emotions. Overall, this research explores a comprehensive interactive system focused on recognizing and responding to human emotions. Without further training data, our model, to the best of our understanding, achieves modern single-network accuracy of 74.57% on FER2013 © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

To Enhance a System for Predicting Cardiovascular Disease Using Feature Selection

To Enhance a System for Predicting Cardiovascular Disease Us...

引用

2023 International Conference on IoT, Communication and Automation Technology, ICICAT 2023

作者： Gupta, Shubham Mishra, Vikas Prasad Gawade, Sandhya Sharma, Vibhor Thapliyal, Madhur Shivalik College of Engineering Department of Computer Science & Engineering Dehradun India Ies University Department of Agriculture Sciences Madhya Pradesh Bhopal India Madhyanchal Professional University Department of Computer Science & Engineering Madhya Pradesh Bhopal India Hsst Swami Rama Himalayan University Jollygrant Department of Computer Science & Engineering Dehradun India School of Computing Graphic Era Hill University Dehradun India

ISBN: (纸本)9798350302820

Many individuals in India lack access to affordable, readily available, and high-quality medical treatment. Medical diagnostic and therapeutic aid in the early stage of disease is hampered by a lack of facilities in rural regions, resulting in delayed treatment and an increase in morbidity and death. Non-communicable disease mortality in India has risen dramatically during the previous two decades. Throughout the course of this time period, the percentage of fatalities attributable to CVDs rose from 15.2% to 28.1%. In addition to cardiovascular disease, other chronic illnesses' death rates have risen dramatically during the previous two decades. Present circumstances make it imperative to employ machine learning methods in order to make quality healthcare in India more accessible and cheap. The primary goal of this study is to enhance healthcare possibilities by utilizing machine learning methods. Using Chi-square, information gain, and principal component analysis, this paper provides a unique hybrid feature selection approach for filtering out superfluous data. The findings of this investigation are quite astonishing. Validation was achieved by comparing the outcomes to other feature selection techniques. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

An Entropy-Integrated Adaptive Coding and Scheduling Framework for Optimized Data Transmission in Fog-Cloud IoT Architectures

引用

IEEE Internet of Things Journal 2025年

作者： Lu, Yang Zang, Yuting Bian, Ziyi Zhao, Shuai Zheng, Yan Northeast Forestry University College of Computer and Control Engineering Harbin China Harbin Normal University College of Computer and Information Engineering Harbin China La Trobe University School of Computing Engineering and Mathematical Sciences MelbourneVIC Australia

Entropy-driven network coding has been used as a basis for optimizing data transmission and enhancing resource utilization in Fog-Cloud IoT architectures, including applications in smart cities, industrial automation, environmental monitoring, and healthcare. In Fog-Cloud IoT architectures, conventional data transmission protocols are inefficient because they cannot adapt to dynamic entropy levels, resulting in underutilized bandwidth, increased latency, and higher energy consumption. In this paper, we propose an Enhanced Entropy-Driven Network Coding (E-EDNC) framework to address these problems. Our framework integrates real-time entropy estimation with adaptive coding strategies and employs a hybrid evolutionary-reinforcement learning (HE-RL) algorithm to dynamically optimize coding parameters and scheduling decisions. Experimental results demonstrate that E-EDNC improves bandwidth utilization by 25%, reduces latency by 25%, and decreases energy consumption by 12%, thereby enhancing overall data transmission efficiency and reliability in Fog-Cloud IoT environments. © 2014 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Exploring 2D representation and transfer learning techniques for indoor localization

引用

Multimedia Tools and Applications 2025年 1-13页

作者： Kerdjidj, O. Himeur, Y. Atalla, S. Copiaco, A. Sohail, S.S. Amira, A. Fadli, F. Mansoor, W. Gawanmeh, A. Centre of Development of Advanced Techniques Algiers Algeria College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Department of Computer Science University of Sharjah Sharjah United Arab Emirates Institute of Artificial Intelligence De Montfort University Leicester United Kingdom School of Computing Science and Engineering VIT Bhopal University Kothri Kalan India Department of Architecture & Urban Planning Qatar University Doha2713 Qatar

Indoor localization (IL) plays a critical role in various applications, including asset tracking, emergency response, and indoor navigation. Traditional methods relying on one-dimensional (1D) representations of received signal strength indicator (RSSI) data often suffer from limitations such as low accuracy, environmental sensitivity, and susceptibility to interference. To overcome these challenges, this paper proposes Scalogram-Based Transfer Learning for Indoor Localization (STL-IL), a novel framework that significantly enhances localization performance. The proposed approach transforms 1D RSSI signals into two-dimensional (2D) representations using scalogram-based time-frequency analysis, coupled with advanced transfer learning (TL) techniques. By leveraging the scalogram method to generate image representations of the data and employing diverse wavelet types. Furthermore, pre-trained deep learning models, including GoogleNet and SqueezeNet, are utilized to achieve state-of-the-art performance. Experimental results demonstrate that the STL-IL system achieves remarkable accuracy levels of 95% and 96% for SqueezeNet and GoogleNet, respectively. The proposed framework not only improves localization accuracy but also enhances robustness in dynamic and challenging environments, making it a promising solution for real-world indoor localization applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

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：