检索结果-内蒙古大学图书馆

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Wanjari, Ketan Verma, Prateek Department of Computer Science and Engineering Faculty of Engineering and Technology Maharashtra Wardha442001 India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

Modern image recognition has experienced dramatic improvements because of Machine Learning and Deep Learning algorithms together. This study investigates CNNs and SVMs for recognition enhancement while reviewing image recognition technologies extensively through literature. This paper demonstrates how the applications of healthcare and security systems and social media analysis influence society. New developments in technology have not resolved multiple unresolved obstacles such as data bias as well as computational complexity and privacy concerns together with real-time processing restrictions. The latest image processing techniques include ViTs alongside GANs and Few-Shot Learning but developers need to achieve better results in future improvements. The main goal of this research examines present-day advancements in ML and DL with a review of their capabilities as well as constraints before recommending future study paths to overcome problems encountered today. This paper evaluates both the future potential and benefits alongside drawbacks of ML and DL models applied to image recognition. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Encrypt Decrypt ReLU Activated UNet Prototype based Prediction of Leaf Disease Segmentation

Encrypt Decrypt ReLU Activated UNet Prototype based Predicti...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Shyamala Devi, M. Eswar, R. Hibban Rashid, M.D. Jai Harshan, J.H. Hari, P. Hemanth, S. Panimalar Engineering College Department of Computer Science and Engineering Tamilnadu Chennai India Panimalar Engineering College Department of Artificial Intelligence and Data Science Tamilnadu Chennai India

ISBN: (纸本)9798331540685

The issues of sustainable agriculture and climate change are intimately linked to the problem of effective leaf disease prevention. In practice, the primary method for identifying and detecting plant diseases is expert observation with the unaided eye. However, this necessitates for the ongoing supervision of specialists, which can be too costly for big farms. The automatic identification of leaf diseases is a significant area of research because it might be useful for monitoring vast agricultural fields and identify diseases based only on symptoms that occur on the leaves of the plants. This paper recommends ReLU Activated UNet (RAA-UNet) that categorizes the leaf diseases with high precision. The KAGGLE Leaf disease dataset that contains 2094 leaf images were used for implementation. The dataset consists of 1047 leaf image and 1047 respective leaf images that have been segmented. The proposed ReLU Activated UNet initiates by creating masked leaf images by masking the original image with a segmented leaf image. To classify the leaf disease, the masked leaf images are assigned to ReLU Activated UNet with contracting and expansion which was activated using Relu Activation function. The proposed ReLU Activated UNet and conventional CNN models are fitted to the masked leaf images. As demonstrated by the experiments, the proposed ReLU Activated UNet model works better with a high accuracy of 98.85% in the classification of leaf disease like leaf spot, blight and powdery mildew. © 2024 IEEE.

关键词： Accuracy Activation CNN ReLU Segmentation UNet

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Session-Based Recommendation System with Graph Neural Networks 24

A Dynamic Session-Based Recommendation System with Graph Neu...

引用

24th Conference Information Technologies - Applications and Theory, ITAT 2024

作者： Mahajan, Vrushali Birihanu, Ermiyas Tashu, Tsegaye Misikir ELTE Eötvös Loránd University Department of Data Science and Engineering Budapest Hungary Department of Artificial Intelligence Bernoulli Institute of Mathematics Computer Science and Artificial Intelligence University of Groningen Groningen Netherlands

Session-based recommendation systems provide personalized recommendations to users based on their session activities. Traditional recommendation algorithms often overlook temporal dependencies within user sessions, leading to suboptimal recommendations. To address this limitation, we proposed a Temporal Graph Neural Network (TemporalGNN) approach that leverages the temporal relationships between items in sessions to enhance recommendations. The proposed session-based recommendation system can effectively capture temporal dependencies within user sessions. The method consists of two temporal GNN layers designed to capture temporal dependencies within user sessions. A directed graph is constructed from session data, where each unique item in the dataset is a node, and directed edges are created between consecutive items within a session, with edge weights representing the time differences between interactions. This graph structure allows the model to capture the sequential nature of user interactions. The model generates recommendations by computing similarity scores from the learned embeddings and selecting the top N items with the highest scores. The experimental results on two real-world datasets showed the effectiveness of the proposed method in improving recommendation performance compared to the baseline approaches. The source code implementation is available on the GitHub repository at https://***/VrushaliM/SB-Recommendation-GNN. © 2024 CEUR-WS. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

AI Powered Chatbot For Mental Health Treatment 1

AI Powered Chatbot For Mental Health Treatment

引用

1st International Conference on Technological Innovations and Advance Computing, TIACOMP 2024

作者： Jayabhaduri, R. Vijayaraghavan, Aadesh Ajay Karthik, R. Ceralaathan, G. Sai Sailesh, S. Alliance University Computer Science and Engineering Bengaluru562106 India Sri Venkateswara College of Engineering Artificial Intelligence and Data Science Taluk Sriperumbudur602117 India

ISBN: (纸本)9798350392111

In the recent days, most people of all ages have their mental health affected by various factors like stress, anxiety, depression, fear, phobia and trauma. Hence it is mandatory for people to take care of their mental health. People may hesitate to approach therapists in real life due to societal stigmas. As many people are unable to access or afford mental health services, our research work aims at developing a SAAC Mental health chatbot to mimic a therapist to provide personalized support and guidance, learn about an individual's unique needs and preferences, and tailor their responses accordingly with 24/7 support by handling speech and text queries. SAAC chatbot also maintains chat history and notifies users by sending alerts to ensure follow-ups. © 2024 IEEE.

关键词： Anxiety Chatbot Depression Fear Mental Health Phobia Speech Therapist Trauma

来源：评论

学校读者我要写书评

暂无评论

Effect of Hyperparameter Tuning on Transfer Learning Models for Brain Tumor Detection and Classification 3

Effect of Hyperparameter Tuning on Transfer Learning Models ...

引用

3rd International Conference on Advanced Computing Technologies and Applications, ICACTA 2023

作者： Nazareth, Andre Isaac Pereira, Grace Prashant Nagarkatte, Trisha Nitin Save, Jagruti Artificial Intelligence and Data Science Fr.Conceicao Rodrigues College of Engineering Mumbai India

ISBN: (纸本)9798350348347

A mass of abnormal cell growth in the brain is known as a brain tumor, these are of two types benign and malignant. Currently, medical professionals use Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) scans to analyze and identify the presence of tumors. Finding brain tumors is an arduous but crucial endeavor. The emergence of artificial intelligence techniques has led to the detection of brain tumors using various Machine Learning algorithms and techniques, particularly Deep Learning. These algorithms are advantageous as there are fewer errors and greater precision which in turn which makes decision-making and selection of the patient's best course of action more accurate. In this paper, we have employed Magnetic Resonance Images (MRI) images that were applied to a variety of transfer learning models, including VGG19, InceptionV3, and DenseNet121. To determine the optimal values of the learning rate, batch size, optimizer, and the number of epochs we performed hyperparameter tuning for each model. The Wilcoxon-Mann-Whitney test was performed to assess whether the hyperparameters have made a significant impact on each metric used. After performing this test and determining the accuracy we discover that DenseNet121 gives us the highest accuracy of 96%, followed by InceptionV3 which displays an accuracy ranging from 89 to 91%, and VGG19 which provides an accuracy of 85% but with a rather high penalty on error. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Network Community Detection in Connectomics data using Graph Theory

Network Community Detection in Connectomics Data using Graph...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Gonzalez-Montesino, Leandro Grass-Boada, Darian H. Armannazas, Ruben Institute of Data Science and Artificial Intelligence Tecnun School of Engineering University of Navarra Pamplona Spain

ISBN: (纸本)9798350337488

This work presents a comprehensive descriptive analysis of a complex network derived from individual neuronal reconstructions from the vinegar fly (Drosophila melanogaster) using graph theory. The primary aim was to establish an informed criterion for selecting the most suitable community detection algorithm based on the network's topology. We implemented four state-of-the-art community detection algorithms, namely Louvain, Greedy Modularity, Label Propagation, and Infomap, and analyzed the intrinsic architecture and organization of the outcomes. In addition, to offer a more robust and consensual perspective on the results, we introduced a novel Rough Clustering method that allows a refined interpretation of communities within the overall network structure. © 2023 IEEE.

关键词： Community Detection Complex Networks Graph Theory Neuroscience Rough Clustering

来源：评论

学校读者我要写书评

暂无评论

Job Resumes Recommendation using Integration of Fuzzy Discernibility Matrix Feature Selection and Convolutional Neural Network Multi-label Text Classification

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第13期49卷 49-58页

作者： Hayami, Regiolina Yusoff, Nooraini Daud, Kauthar Mohd Fatma, Yulia Department of Informatics Engineering Faculty Computer Science Universitas Muhammadiyah Riau Indonesia Faculty of Data Science and Computing Universiti Malaysia Kelantan 16100 Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia 43600 Malaysia

The manual analysis of job resumes poses specific challenges, including the time-intensive process and the high likelihood of human error, emphasizing the need for automation in content-based recommendations. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNN) for Multi-label Text Classification (MLTC), offer a promising solution for addressing these challenges through artificial intelligence. While CNN is renowned for its robust feature extraction capabilities, it faces specific challenges such as managing high-dimensional data and poor data interpretability. To address these limitations, this study employs the Fuzzy Discernibility Matrix (FDM) feature selection technique to determine the relevance of skills for each job vacancy. FDM assigns weights to the features of each job category and ranks their relevance based on the highest scores, which are then utilized in the MLTC CNN model. The integration of FDM and MLTC CNN serves as the foundation for generating content-based recommendations derived from key features in job resumes. This study produces a content-based job recommendation system that displays the top three job categories, accompanied by explanations of the skills supporting each selected category. These recommendations also consider cosine similarity values between analyzed items and the integrated results of FDM and MLTC CNN. The application of FDM for feature weighting has been proven to enhance multi-label text classification outcomes by providing better insights during the feature selection process. With a recall of 97.26%, precision of 94.81%, and accuracy of 98.58%, the MLTC model integrating FDM feature selection and CNN demonstrates robust performance characteristics in content-based job recommendation tasks. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Identification of NPK Deficiency in Toor Dal Leaf Using CNN Technique

Identification of NPK Deficiency in Toor Dal Leaf Using CNN ...

引用

2023 International Conference on Integrated intelligence and Communication Systems, ICIICS 2023

作者： Hani, Syeda Umme Mallapur, Sujata V. Sharnbasva University Artificial Intelligence & Data Science Faculty of Engineering & Technology Karnataka Kalaburgi India

ISBN: (纸本)9798350315455

The main economic contributor to India is agriculture. The Nitrogen (N), phosphorus (P), and potassium (K), are the crucial parts of nutrients in plant growth. NPK deficiency levels affect plant development and crop productivity. By analyzing the leaf properties, we hope to build a model for an artificial neural network (Convolutional Neural Network Technique) that will be able to identify and categorize nutrient deficiencies in toor dal leaf. The two main characteristics used to determine NPK deficiencies in plants are the color and shape of a leaf. The dynamic capture of toor dal leaves by scanning was employed in this work to investigate how the regulation of leaf attributes changed in response to nutritional stress. In this work, the impact of various activation functions on the artificial neural network is also investigated. The findings demonstrate that the suggested technique was highly accurate in classifying and identifying NPK deficiencies in toor dal leaf. © 2023 IEEE.

关键词： artificial Neuron Network (ANN) Image Processing NPK deficiency

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Chatbot Architecture for Medical Diagnosis and Treatment Recommendation 3

Deep Learning based Chatbot Architecture for Medical Diagnos...

引用

3rd International Conference on Advanced Computing Technologies and Applications, ICACTA 2023

作者： Rajani, Girish Ruparel, Khushi Thadomal Shahani Engineering College Dept. of Artificial Intelligence and Data Science Mumbai India

ISBN: (纸本)9798350348347

With the exponential growth and rapid development in the fields of deep learning and neural networks, chatbots have gained a lot of popularity and have become a proven, and efficient tool to interact and provide service to users. Healthcare is one of the most promising fields where chatbots can be used more efficiently. This has become important, especially in the current medical landscape, where there is a shortage of doctors, and patients often have to wait long periods before getting any medical guidance. By using the power of transformer models and machine learning algorithms chatbots can help patients with personalized diagnoses and treatment recommendations, efficiently at ease and convenience. This helps the patients to access medical services anywhere, at any point in time. This paper proposes a well-planned systematic architecture for a medical chatbot that utilizes the potential of transformers, classification algorithms and machine-learning models. The architecture includes three main components: a Naïve Bayes Classifier, a Binary Tree classifier along with a Support Vector Classifier, and a sequence-to-sequence model. These algorithms are used to classify symptoms and determine the severity of a medical condition to provide patients with accurate medical diagnoses and treatment recommendations. Overall, the proposed architecture is built and designed to bridge the gap between doctors and patients by providing immediate access to medical advice, making it a promising tool for improving the quality and accessibility of healthcare services. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

引用

Chinese Journal of Electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

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：