检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Devi, M. Shyamala Hepzhibha Rachel, S. Janani, G. Irene, B. Joy Praisy, E. Humaira, S. Department of Computer Science and Engineering Panimalar Engineering College Tamilnadu Chennai India Department of Artificial Intelligence and Data Science Panimalar Engineering College Tamilnadu Chennai India

ISBN: (纸本)9798350383867

Assessments have demonstrated that the human lip and its motions provide a wealth of knowledge about the identity and substance of communication. However, due to large differences in illumination condition, head perspective, and background, obtaining strong and precise lip image segmentation in natural settings remains difficult. This paper recommends Deep Masked Input UNet that categorizes the Gender based on the lip segmentation with high precision. For implementation, 10,132 face images from the KAGGLE Lip Segmentation dataset were used. The dataset includes 5066 images of the face and 5066 segmented lip images. The proposed Deep Masked Input UNet starts by masking the original picture with a segmented lip image to create masked face images with lips segments. Utilizing the Relu Activation function, Deep Masked Input UNet with contracting and expansion was enabled. The masked lip images are fitted to the proposed Deep Masked Input UNet and traditional CNN models. The results show that the suggested Deep Masked Input UNet model performs better in lip segmentation and gender classification, with a high accuracy of 98.95%. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deformable Dual Graph Aggregation Transformer Convolutional Networks with Spider Wasp Optimizer for Ovarian Tumor Classification Using Magnetic Resonance Imaging

引用

Biomedical Materials and Devices 2025年 1-19页

作者： Shanmugaveni, V. Jotheeswari, M. Abarnaswara, R. VijayaKumar, M. Manojanani, A. Department of Computer Science and Engineering (Cyber Security) Dr. Mahalingam College of Engineering and Technology Tamil Nadu Pollachi India Department of Computer Science and Engineering PSNA College of Engineering and Technology Tamil Nadu Dindigul India Department of Artificial Intelligence & Data Science Dr. Mahalingam College of Engineering and Technology Tamil Nadu Pollachi India Department of Computer Science and Engineering RVS Technical Campus Tamil Nadu Coimbatore India

The diagnosis of Ovarian Tumor (OT) remains a significant challenge as there is presently no practical non-invasive technique to determine true benign or malignant lesions before treatment. This study proposes a unique Deformable Dual Graph Aggregation Transformer Convolutional Network (DeDGATCNet) with Spider Wasp Optimizer (SWO) for the classification of ovarian tumors acquired from magnetic resonance imaging (MRI). In contrast to traditional deep learning models, DeDGATCNet + SWO directly integrates bending graph-based forming transformer convolutional learning and improves representation for better classification. The SWO is combined to optimize the parameters of the network, thereby improving its performance. The procedures include pre-processing the MRI data from the study of ovarian tumor TCGA-OV datasets with an Adaptive Bilateral Texture Filter (ABTF) for removing artifacts and normalization of intensity, accompanied by a segment using a Masked-Attention Mask Transformer (MAMT). Feature extraction is achieved through a One-Dimensional Quaternion Discrete Fourier Transform (1D-QDFT), which captures features from both the spatial and frequency domains. DeDGATCNet + SWO performance is way ahead and sets a new accuracy record of 99.9% for state-of-the-art models. This research introduces a new type of hybridization between deformable graph transformers, quaternion-based spectral analysis, and nature-inspired optimization techniques, setting non-invasive OT at a new height for classification and improving early diagnosis. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Adaptive bilateral texture filter Deformable dual graph aggregation transformer convolutional networks Masked-attention mask transformer One-dimensional quaternion discrete fourier transform

来源：评论

学校读者我要写书评

暂无评论

Prediction of Alzheimer’s Disease Using Adaptive Fine-Tuned Deep Resnet-50 with Attention Mechanism

引用

SN computer science 2024年第4期5卷 392页

作者： Venkatesh, R. Anantharajan, Shenbagarajan Gunasekaran, Shenbagalakshmi Yogaraja, C.A. Gethzi Ahila Poornima, I. Computer Science and Engineering Ramco Institute of Technology Rajapalayam Tamil Nadu Virudhunagar 626117 India Artificial Intelligence and Data Science Mepco Schlenk Engineering College Sivakasi Tamilnadu Virudhunagar 626005 India Computer Science and Engineering Mepco Schlenk Engineering College Sivakasi Tamilnadu Virudhunagar 626005 India

Alzheimer’s disease (AD) sufferers can benefit from early detection and diagnosis so that protective treatments can be taken before permanent brain impairment develops. Magnetic resonance imaging (MRI)-detected lesion sites in AD patients exhibit significant heterogeneity and these characteristics are spread throughout the imaging space, according to cross-sectional imaging studies of Alzheimer's disease. Because conventional Deep Learning (DL) methods can’t generate enough long-distance correlations in the characteristic space, adaptive fine-tuned deep resnet-50 with attention mechanism (AFDR-AM) is introduced in this research for the early identification of AD. The input MRI data is de-noised using a wavelet thresholding approach, and the contrast is enhanced using Improved Color Histogram Equalization (ICHE). Image recognition and classification characteristics are extracted at the feature extraction phase using a Gabor Filter Bank (GFB). To narrow down a big list of traits, the Artificial Bee Colony Optimization (ABCO) technique can be used to pick the most useful ones and get rid of the rest. Measures of accuracy, precision, recall, f1-score, specificity, and MSE are used to evaluate the effectiveness of the suggested strategy. Comprehensive experiments reveal that our approach achieved the best performance compared to other approaches. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： AFDR-AM Alzheimer’s disease (AD) Artificial Bee colony optimization (ABCO) Deep learning (DL) Gabor filter bank (GFB) Improved color histogram equalization (ICHE) Magnetic resonance imaging (MRI)

来源：评论

学校读者我要写书评

暂无评论

Market resilience in turbulent times: a proactive approach to predicting stock market responses during geopolitical tensions

引用

Journal of Capital Markets Studies 2024年第2期8卷 173-194页

作者： Maddodi, Srivatsa Kunte, Srinivasa Rao Department of Computer Science Srinivas University Mangaluru India Department of Data Engineering United Airlines Inc Bengaluru India

Purpose: The Indian stock market can be tricky when there's trouble in the world, like wars or big conflicts. It's like trying to read a secret message. We want to figure out what makes investors nervous or happy, because their feelings often affect how they buy and sell stocks. We're building a tool to make prediction that uses both numbers and people's opinions. Design/methodology/approach: Hybrid approach leverages Twitter sentiment, market data, volatility index (VIX) and momentum indicators like moving average convergence divergence (MACD) and relative strength index (RSI) to deliver accurate market insights for informed investment decisions during uncertainty. Findings: Our study reveals that geopolitical tensions' impact on stock markets is fleeting and confined to the short term. Capitalizing on this insight, we built a ground-breaking predictive model with an impressive 98.47% accuracy in forecasting stock market values during such events. Originality/value: To the best of the authors' knowledge, this model's originality lies in its focus on short-term impact, novel data fusion and high accuracy. Focus on short-term impact: Our model uniquely identifies and quantifies the fleeting effects of geopolitical tensions on market behavior, a previously under-researched area. Novel data fusion: Combining sentiment analysis with established market indicators like VIX and momentum offers a comprehensive and dynamic approach to predicting market movements during volatile periods. Advanced predictive accuracy: Achieving the prediction accuracy (98.47%) sets this model apart from existing solutions, making it a valuable tool for informed decision-making. © 2024, Srivatsa Maddodi and Srinivasa Rao Kunte.

关键词： Geopolitical tension LSTM Momentum indicator Sentiment analysis Stock market prediction

来源：评论

学校读者我要写书评

暂无评论

Digitalizing the Dress-up Experience: An Exploration of Virtual Try-On for Traditional Chinese Costume 18

Digitalizing the Dress-up Experience: An Exploration of Virt...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Lu, Yifan Zhang, Maochun Huang, Wenxuan Guan, Shouqin Ningbotech University College of Computer Science and Data Engineering Ningbo China

ISBN: (纸本)9798350312201

With the recent rapid developments in artificial intelligence (AI) technology, virtual try-on technology empowered by generative approaches has reached a level of maturity that is ripe for commercialization. However, the application of virtual try-on technology to traditional cultural costumes has not received adequate attention from research institutions and enterprises. To address this research gap, we present a novel virtual try-on system for traditional Chinese costume that incorporates diverse AI technologies, including generative models, pose estimation, human parsing, and image processing algorithms, to provide an accurate and immersive virtual try-on experience. In particular, we leverage five distinct techniques Human Keypoint Detection, Human Parsing, Densepose Parts Segmentation, Cloth Mask Extraction, and Clothing-Agnostic Representation - to realize a web service that can effectively handle the specific challenges of traditional Chinese costume, such as the need to preserve cultural authenticity and ensure accurate fit and drape. Finally, we conduct various experiments to evaluate the system's performance and have received positive feedback from users, indicating that it provides a realistic and engaging virtual try-on experience. Our work contributes to the growing body of research on virtual try-on technology and has the potential to impact the way traditional cultural costumes are designed, marketed, and worn. © 2023 IEEE.

关键词： Web services

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

Calligraphy Alphabet Perception Using Artificial Intelligence 9

Calligraphy Alphabet Perception Using Artificial Intelligenc...

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Venkatesh, S. Jeevitha, D. Gnanaselvi, J. Anitha Srm Institute of Science And Technology Department of Data Science And Business Systems School of Computing Chennai Kattankulathur India Jeppiaar Engineering College Department of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350365092

The human brain has a simple time analyzing and processing images. The brain is able to rapidly deconstruct and distinguish an image's various components when the eye perceives it. With the Convolutional Neural Network (CNN) as its foundation, this research suggests deep learning conceptual models. When the algorithms are compared, it becomes clear that CNN-based classification of handwritten alphabets performs better than other algorithms in terms of accuracy. The Manual Net, Alex Net, and LeNet Architectures are among the CNN algorithms employed in this research. The convulational layer, max pooling, flattening, feature assortment, rectifier lined unit, and completely linked softmaxx layers are each components of the aforementioned designs. The proposed network is tested using an image dataset comprising 530 training photos and 2756 testing images. The top precision and cost-efficient model will be used in the Django context to build a handler line for supplying the appeal to be recognized and obtaining the productivity outcome of recognized appeal. © 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

Corner Key Point Extracted Deep Learning Framework Based Birds Species Classification 8

Corner Key Point Extracted Deep Learning Framework Based Bir...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Devi, M. Shyamala Jamal Mohammed, R. Hemanth, S. Harish Raj, B. Gajapathy, R. Kamalesh, P. 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)9798331505462

Climate change and habitat destruction have caused the extinction of many bird species. Classifying bird species is a crucial aspect of ornithology, as it aids in the comprehension of species distribution, habitat needs, and environmental changes that impact bird populations. Ornithologists can use variations in bird species distributions to measure the health of a particular environment. Expert ornithologists have relied heavily on visual inspection, which can be tedious, time-consuming, and unreliable when classifying bird species. The development of technology can be used to categorize the bird species. This paper proposes Corner Key Filtered VGG16 (CKP-VGG16) that categorizes eight bird species with high accuracy. The execution was carried out using the 4000 bird images from the KAGGLE Birds species dataset. First, the CKP-VGG16 model separates the images of birds, and then it labels each image. After data augmentation on the labeled images, 84,000 bird images are produced. The augmented images are transformed into grayscale versions, which are then used in filtering techniques to produce Corner Key Point Filtered (CKP) bird image. The performance is analyzed by applying the CKP filtered bird images to the current CNN models. The application demonstrates that the suggested CKP-VGG16 model performs significantly well in classifying bird species, with a high accuracy of 99.7%. © 2024 IEEE.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

An Efficient Image to Speech Generation System for Visually Impaired Individuals Using Deep Learning Techniques 10

An Efficient Image to Speech Generation System for Visually ...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Priyanka, G. Nivaashini, M. Shree Akshaya, B. Subashini, M. Ritish, G. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Sri Eshwar College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

As the world is becoming more visually oriented, visually impaired people are struggling to access and understand visual content. This paper aims to represent the model created to assist blind and visually impaired people. This method leverages deep learning techniques to convert images into meaningful audio outputs. It involves capturing input images and processing them using advanced deep-learning algorithms. The extracted features are translated into speech. The resulting auditory output provides an alternative sensory experience for individuals with visual impairments, enabling them to perceive and interpret visual information through sound. This study implements four deep learning models namely CNN-LSTM, Resnet34, YOLOv5 and Vision Transformer to process sequential visual data capturing intricate patterns and dependencies within images. By integrating these models in this work, the Image to audio converter not only achieves superior accuracy in image recognition but also enhances the richness and depth of the auditory output, creating a nuanced and immersive sensory experience for users. The performance of the proposed models was evaluated using several metrics and it was noted that vision transformer outperformed the remaining models. This seamless integration of deep learning models amplifies the study's effectiveness in translating diverse visual inputs into detailed and coherent auditory output, thereby enhancing accessibility and inclusivity for individuals with visual impairments. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Watch Product Categorization through Conv2D Sequential Covolutional Neural Network with Truncated Normal Kernel Initializer 2

Watch Product Categorization through Conv2D Sequential Covol...

引用

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

作者： Shyamala Devi, M. Harivishnu, K.C. Jamal Mohammed, R. Jagan, S. Gurucharan, G. Mohamed Arshad, M. 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)9798350371314

For the sake of customer satisfaction and high profitable revenue, the products are designed in the Ecommerce application along with the product category. Based on the product category, prices may differ in a broad range. So, the application must be able to categorize the products before releasing the price voucher to the customers. The absence of effective product categorization, made it challenging to provide deep learning algorithm that results in the usage of modern tools towards product classification. This paper proposes Truncated Normal Kernel Initializer Conv2D (TNKIC) Sequential model for categorizing the watch product. The suggested TNKIC model includes the Watche Image dataset from KAGGLE which consists of 2000 pictures divided into 10 groups. To classify watch goods, pictures are preprocessed and fitted using the TNKIC model. Three convolutional layers, a max pooling layer, and three dense layers that are weight initialized using a Truncated Normal Kernel initializer are preprocessed on the watch pictures in order to classify the watch products. The watch images are splitted into training and testing images. The TNKIC model is examined to determine how well the suggested model works in the watch product categorization than the current conV2D models after being trained with watch images. When compared to current conV2D models, implementation observations using Python on a Gtx Geforce Tesla V100 Nvidia GPU workstation utilizing 64 and 250 training intervals show that the suggested TNKIC model classifies the watch product category with the accuracy of 97.88%. © 2024 IEEE.

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：