检索结果-内蒙古大学图书馆

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Manasa, V.Gnana Sri Gopinath, M. Ram, M.Aditya Khan, Md.Sajid Velagapudi Ramakrishna Siddhartha Engineering College Dept. of Artificial Intelligence and Data Science Kanuru India

ISBN: (纸本)9798331529635

In the rapidly evolving landscape of cybersecurity, the classification of malware has become increasingly critical due to the exponential growth in the volume of malware, which poses significant security threats to financial institutions, businesses, and individuals. Traditional signature-based detection methods have struggled to keep up with the growing variety and complexity of new threats, making it necessary to use more advanced techniques. Among these, deep learning has emerged as a promising approach for malware detection, particularly through the classification of malware images by transforming binary files into grayscale representations. While previous research has predominantly utilized deep learning architectures for this task. However, in this research work, we developed a model with Mobilenet to enhance classification accuracy. The results of this research demonstrate the revolutionary potential of deep learning-based methods for malware family classification. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Ad Extension Augmentation through LSTM-NLP Synergy: A Deep Learning Approach 1

Ad Extension Augmentation through LSTM-NLP Synergy: A Deep L...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Reddy, Medarametla Varshitha Nikhitha, Nagalla R.M.K. Engineering College Department of Artificial Intelligence and Data Science 601206 India

ISBN: (纸本)9798350372748

In the dynamic realm of digital advertising, enhancing click-through and conversion rates within ad extensions remains a significant challenge for agencies. Ad extensions play a pivotal role in amplifying traditional text ads by providing added information and context, thereby elevating the ad's informativeness, visibility, and click-through rates. This research addresses the hurdles faced by ad-agencies constrained by manual ad extension creation, the evolution of customer web content, and resource-intensive monitoring. This study presents a data-driven solution to revolutionize ad extension effectiveness and campaign conversion rates. This approach initiates with the automation of ad extension creation, eradicating the inconsistencies of manual content generation. By harnessing real-time insights from website scraping, up-to-the-minute data about customer brand offerings can be acquired. The extracted data is processed using several Natural Language Processing (NLP) and clustering techniques. To effectively manage the dynamic nature of web content, Long Short-Term Memory (LSTM) neural networks are utilized. This deep learning model predicts word selection probabilities within ad extensions, facilitating the recommendation of terms in alignment with evolving web content. This solution also addresses the resource-intensive monitoring challenge through real-time sentiment analysis. This continual assessment provides timely insights for proactive adjustments, thus optimizing conversion rates. Hyperparameter tuning ensures optimal model accuracy. This model not only contributes to the digital advertising domain but also furnishes agencies with a transformative framework to surmount time-consuming manual processes, thereby enhancing their competitive edge and achieving accuracy of around 92%. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Food Recognition System with Calorie Estimation

Food Recognition System with Calorie Estimation

引用

2023 International Conference on Integration of Computational Intelligent System, ICICIS 2023

作者： Sarode, Ketaki Thakur, Aaryan Correa, Lyneshia Davare, Sarika Fr. Conceicao Rodrigues College of Engineering Artificial Intelligence and Data Science Thane India Fr. Conceicao Rodrigues College of Engineering Artificial Intelligence and Data Science Mumbai India

ISBN: (纸本)9798350318784

The quality of life, particularly in regards to food, has become a major focus in our rapidly developing society. With smart phones now ubiquitous, people are turning to mobile apps to simplify their daily routines. This report highlights the creation of a healthcare-focused app that uses computer vision algorithms to determine the caloric value of food. By analyzing the food's composition in a photo, the algorithm calculates the dish's nutritional content. The app then utilizes this data to create personalized nutritional profiles, recipes, and workout recommendations. Our goal is to create an app that identifies food through image processing and accurately estimates calorie intake. Our work is aimed at the development of an app that uses or determines the classification of food using image processing with the aim of determination/estimation of calorie intake. © 2023 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Graph Classification with GNNs: Optimisation, Representation & Inductive Bias 27

Graph Classification with GNNs: Optimisation, Representation...

引用

27th European Conference on artificial intelligence, ECAI 2024

作者： Kumar, P. Krishna Ramaswamy, Harish G. Department of Computer Science & Engineering IIT Madras India Department of Data Science & Artificial Intelligence IIT Madras India

ISBN: (纸本)9781643685489

Theoretical studies on the representation power of GNNs have been centered around understanding the equivalence of GNNs, using WL-Tests for detecting graph isomorphism. In this paper, we argue that such equivalence ignores the accompanying optimization issues and does not provide a holistic view of the GNN learning process. We illustrate these gaps between representation and optimization with examples and experiments. We also explore the existence of an implicit inductive bias (e.g. fully connected networks prefer to learn low frequency functions in their input space) in GNNs, in the context of graph classification tasks. We further prove theoretically that the message-passing layers in the graph, have a tendency to search for either discriminative subgraphs, or a collection of discriminative nodes dispersed across the graph, depending on the different global pooling layers used. We empirically verify this bias through experiments over real-world and synthetic datasets. Finally, we show how our work can help in incorporating domain knowledge via attention based architectures, and can evince their capability to discriminate coherent subgraphs. © 2024 The Authors.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based method for detection of copy-move forgery in videos

引用

Neural Computing and Applications 2025年第14期37卷 8451-8464页

作者： Elbarougy, Reda Abdelfatah, Osama Behery, G.M. El-Badry, Noha M. Department of Artificial Intelligence and Data Science College of Computer Science and Engineering University of Ha’il Ha’il81481 Saudi Arabia Department of Information Technology Faculty of Computer and Artificial Intelligence Damietta University New Damietta Kafr Saad Egypt Department of Computer Science Faculty of Computer and Artificial Intelligence Damietta University New Damietta Kafr Saad Egypt Department of Mathematics Faculty of Science Damietta University New Damietta Kafr Saad Egypt

Video forgery is one of the most serious problems affecting the credibility and reliability of video content. Therefore, detecting video forgery presents a major challenge for researchers due to the diversity of forgery types, the modernity of the programs used in forgery operations, and the abundance of information and content present in videos. The seriousness of this issue arises from the widespread use of videos in vital fields that require very high accuracy with no room for doubt or error, such as courtrooms, journalism, and others. Copy-move forgery is one of the most common and dangerous types of video forgery because of the difficulty in identifying it with the naked eye and the great diversity of forgery techniques involved in this particular type. One of the biggest challenges researchers have faced in the past is the complexity of the steps required to detect forgery in videos, leading to significant computational complexity and time consumption. The proposed method also aims to achieve better results than previous methods while reducing computational operations. Ultimately, forgery is detected with great efficiency. Compared to previous methods used for detecting copy-move forgery in the Rewind dataset, the proposed method achieves the highest F1, reaching 0.86, with a significant difference of 0.13 compared to the best result of the previous methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., 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

A New Concordance Correlation Coefficient based Fitness Function for Genetic Programming for Symbolic Regression 13

A New Concordance Correlation Coefficient based Fitness Func...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Xu, Jizhong Chen, Qi Xue, Bing Zhang, Mengjie Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

ISBN: (纸本)9798350308365

Coefficients learning has long been challenging in genetic programming based symbolic regression (GPSR). Recent GPSR methods employ Pearson correlation coefficient for fitness assessment with post-hoc linear scaling for coefficient learning. However, this approach often leads to sub-optimal coefficient learning and inadequate consideration of nonlinear relationships between input variables and outputs. To solve those issues, this study introduces an innovative approach to integrating the Concordance Correlation Coefficient (CCC) into GPSR. Unlike Pearson correlation, CCC can effectively assess both linear and non-linear agreements between two sets of variables. Experimental results on eight regression datasets highlight the potential of CCC as a promising fitness function for GPSR without the need of a more advanced coefficient optimisation method for linear scaling. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Accessibility for Recognizing Indian and American Sign Language through Deep Learning Techniques 4

Enhanced Accessibility for Recognizing Indian and American S...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Jayadharshini, P. Krishnasamy, Lalitha Santhiya, S. Harsine, K.U. Geetha, P. Logu, B. Kongu Engineering College Department of Artificial Intelligence Perundurai Tamil Nadu Erode India Nandha Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Erode India

ISBN: (纸本)9798331518981

Sign language detection, specifically for Indian Sign Language (ISL) and American Sign Language (ASL), plays a crucial role in bridging communication gaps between hearing impaired and normal people..This paper proposes a systematic methodology using different deep learning models to detect ISL and ASL from an image dataset of sign language gestures. The algorithms probed were 2D Convolutional Neural Networks (CNN), ResNet-50, Long Short Term Memory (LSTM) and VGG16. By using a dataset we conducted an extensive comparative analysis of these algorithms. The results portrayed LSTM as the best predictive classifier with an amazing 97.97% accuracy. This excellent result makes LSTM a strong model for the classification of sign languages with high accuracy. The target classes involved several signs from ISL and ASL are thus extensive for recognizing and interpreting both these languages by using a number of algorithms we make the predictive model more robust as it can handle multiple kinds of data patterns corresponding to different sign gestures. The outcomes of our investigation present the very first step towards an intelligent sign language detection system. A well-recognized and fast-emerging potential of deep learning is in the automatic detection of sign languages, which introduces a drastic positive change in communication efficiency as this research field grows exponentially. This could greatly improve the ability of a person to interact and the accessibility of an individual to sign languages. © 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

Cardiomegaly Detection Using Deep Learning 4

Cardiomegaly Detection Using Deep Learning

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Suganthi, S.U. Sivabalan, A. Akash, M.V. Barath, B. Goushik, G. Anto Akash, P. Sri Sairam Institute of Technology Dept. of Artificial Intelligence And Data Science Tamil Nadu Chennai India Sri Sairam Engineering College Dept. of Artificial Intelligence And Data Science Tamil Nadu Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

This research introduces an innovative method for forecasting cardiomegaly, a common heart condition marked by an enlarged heart, by combining deep learning and machine learning methods. Using the ResNet50 architecture, we examine chest X-ray images to identify cardiomegaly indications. At the same time, a Random Forest algorithm analyses clinical data in a table format, such as age, gender, and different cardiac indicators, to improve prediction accuracy. Our approach combines these models to use unstructured images and structured health data, resulting in a comprehensive diagnostic tool. The data, collected from public health databases, was carefully labelled to guarantee accurate training and validation. Preliminary results showed the promising accuracy of the hybrid model, surpassing individual approaches, and demonstrating the potential of integrated models to improve diagnostic capabilities in cardiology. This study helps improve medical imaging and predictive analytics in healthcare, providing a productive solution for early detection and management of cardiomegaly. The results highlight the promise of combining AI models to change diagnostic methods and enhance patient results. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Automating Product Classification in E-Commerce through Machine Learning and Natural Language Processing 2

Automating Product Classification in E-Commerce through Mach...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Jayadharshini, P. Krishnasamy, Lalitha Harshini, M. Arunachalam, M. Ajaykumar, N. Uvan, Hari Sri M. Department of Artificial Intelligence Kongu Engineering College Perundurai Tamil Nadu Erode India Department of Artificial Intelligence and Data Science Nandha Engineering College Tamil Nadu Erode India

ISBN: (纸本)9798331541217

An efficient product category classification has now emerged as a vital element of the rapidly developing world of e-commerce and online retail, providing better control over inventory and enabling customized presentations for each customer. This paper presents the investigation into using machine learning techniques to automatically classify products based on textual descriptions. Using a large, annotated dataset, authors collect information by extracting relevant information from product descriptions and use advanced methods in both machine learning and natural language processing in showing well the classification of categories of products. The study also includes the critically important data gathering, preprocessing, and feature extraction phases that are vital in harvesting subtle semantic-related information hidden in descriptions of products. The process involves careful selection and implementation of complex algorithms, such as Naive Bayes, Random Forest, and Linear SVM, best suited for dealing with product categorization-specific problems. Thus, training and validation procedures play a vital role in optimizing the model parameters so that the model can perform robustly on unseen data and hence generalize effectively to new products. The model, deployed on an e-commerce platform, provides real-time category prediction as new products are added into the system. It regularly updates and maintains itself so that any variations in the product catalog or changes in the structures of language used over time in describing products are incorporated within the model. It has addressed issues such as data incompleteness and inconsistency and therefore offers integrated methods that may lead to improving the accuracy of predictions. The system is flexible and adaptive and capable of learning and evolving over time, according to new categories that may arise and different contexts of operations. The results do reflect significant strides in creating large-scale, effic

关键词： Linear Support Vector Classifier (SVC) Machine Learning (ML) Algorithms Naive Bayes (NB) Product categorization Random Forest (RF)

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Late-Stage Supervised Contrastive Learning for Fine-Grained Action Recognition

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5912-5924页

作者： Pan, Yijun Zhao, Quan Zhang, Yueyi Wang, Zilei Sun, Xiaoyan Wu, Feng University of Science and Technology of China School of Artificial Intelligence and Data Science Hefei230026 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China University of Science and Technology of China National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application Hefei230026 China

Fine-grained action recognition typically faces challenges with lower inter-class variances and higher intra-class variances. Supervised contrastive learning is inherently suitable for this task, as it can decrease intra-class feature distances while increasing inter-class ones. However, directly applying it into fine-grained action recognition encounters two main problems. The first problem stems from the heavy training cost associated with supervised contrastive learning, which requires numerous training epochs, each involving double augmentation views per instance. To address this issue, we propose the late-stage supervised contrastive learning (late-SC) strategy, which effectively reduces the number of training epochs needed for the contrastive learning process. The second problem is that supervised contrastive loss does not explicitly consider the semantic distances between fine-grained actions when adjusting representation distances. This results in less reasonable and efficient adjustments to the representation space. To overcome this limitation, we introduce the semantic-aware temperature adaptation (STA) mechanism, enhancing the suitability of the supervised contrastive loss for fine-grained action recognition. We conduct experiments on several benchmark datasets for fine-grained action recognition, including Epic-Kitchens-55/100, SomethingSomething-V1, and Diving48-V2. The results demonstrate that our proposed method (referred to as LSC-STA) consistently enhances performance across various base feature extractors, without introducing additional inference overhead and incurring only a marginal increase in training expenses. © 1991-2012 IEEE.

关键词： Contrastive 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：