检索结果-内蒙古大学图书馆

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Thara, Machakanti Navya Chatterjee, Kalyan Raju, Muntha Rout, Sandip Priyadharshini, M. Prasad, Kokkula Shiva Suraj Kumar, Samala Reddy, Mandadi Sriya Nalla Malla Reddy Engineering College Artificial Intelligence & Machine Learning Hyderabad India Nalla Malla Reddy Engineering College Computer Science & Engineering Hyderabad India Government of Odisha Mathematics Government Autonomous College Dept. of Higher Education Odisha Angul India

ISBN: (纸本)9798350361537

Cancer instills fear in people worldwide, with millions succumbing to its grasp each year. Among the various types, lung cancer stands as a prominent contributor to this alarming statistic. Therefore, this novel research Lung Cancer Classification and Detection using Convolutional Neural Network-based Gated Recurrent Unit Neural Network Model (LaCK) has focused on classifying lung cancer, notably Non-Small Cell Lung Cancer, which constitutes the majority of cases. We employed five units of gated recurrent unit neural network (GRU-NN) together to achieve this classification, utilizing logistic regression (LR) and support vector classifier (SVC) models for comparisons. Among all models, the LaCK model demonstrated remarkable accuracy, achieving approximately 98% success rate, outperforming its counterparts. Implementing this model in clinical settings enables medical professionals to establish a precise and automated approach to diagnosing lung cancer. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Predicting Stock Market Trends Using Deep learning: A Case Study of Pakistan Stock Exchange 18

Predicting Stock Market Trends Using Deep Learning: A Case S...

引用

18th International Conference on Open Source Systems and Technologies, ICOSST 2024

作者： Balouch, Maaz Hamayat, Faizan Abbasi, Humza Fazal Javed, Muhammad Qasim Mehrban, Ali Ahmad, Rana Fayyaz Department of Business Studies Namal University Mianwali Pakistan National Center for Physics Machine Learning and Deep Learning Lab Artificial Intelligence Technology Center Islamabad Pakistan Department of Computer Science Bahria University Islamabad Pakistan School of Electrical and Electronics Engineering Newcastle University Newcastle United Kingdom

ISBN: (纸本)9798331508692

This research investigates the short-term stock price prediction in the Pakistan Stock Exchange (PSX) using Deep learning (DL) techniques. By integrating historical stock data, economic indicators, and market news, the research aims to address the limitations of traditional stock analysis methods. Data was collected and pre-processed from various sources, including the PSX, economic indicators, and market news. Four techniques were implemented: ARIMA, LSTM, BI-LSTM, and a hybrid CNN-BI-LSTM. Their performance was evaluated using RMSE, MAE, and MAPE metrics. Comparative analysis revealed that BILSTM outperformed the other techniques, with RMSE, MAE, and MAPE scores of 0.9298, 0.6099, and 13.9443, respectively. Despite ARIMA's lower accuracy, it had the fastest inference time, followed by LSTM, CNN-BI-LSTM, and BI-LSTM. Results indicate that using comprehensive data with DL models significantly improves stock price forecast accuracy, highlighting the potential of technological innovation in enhancing financial market decision-making. These DL algorithms can provide valuable insights for investors and analysts in the PSX, leading to better decision-making and more accurate economic predictions. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Optimal Scheduling of Energy Storage Units in Renewable Energy Systems Using Strength-Pareto Evolutionary Algorithm

An Optimal Scheduling of Energy Storage Units in Renewable E...

引用

2024 International Conference on Intelligent Algorithms for Computational intelligence Systems, IACIS 2024

作者： Kumari, Nalli Vinaya Kumar, Komuravelly Sudheer Alsalami, Zaid Harshitha, P. Ramadan, Ghazi Mohamad Jntuh Malla Reddy Engineering College for Women Department of Computer Science and Engineering Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ahl Al Bayt University College of Mlt Karbala Iraq

ISBN: (纸本)9798350360660

Dual-stage optimization scheduling model by hybrid energy storage for grid-connected renewable energy systems, is proposed in this paper which focuses on both intra-day and day-ahead phases. In day-ahead phase, model improves economic efficiency by considering of price values at its peak value difference. In intra-day phase, its motive is to decrease renewable energy usage and it's related with the day-ahead schedules using accurate, short-term predictions. Strength-pareto evolutionary algorithm 2 (SPEA2) algorithm for optimization is for multiple objective optimizations, achieving optimal and balanced solutions across multiple objectives. This SPEA2 optimization algorithm efficient handles and it enables system to cost-effectively and firmly operate and optimizing scheduling of grid-connected systems by addressing both the aspects of economic and operational. Overall, the model improves economic efficiency, reduces 6.3% the usage of renewable energy, and improves the sustainability power grid through effective integration and utilization of renewable energy sources. © 2024 IEEE.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Utilising SkyScript for Open-Vocabulary Categorization, Extraction, and Captioning to Enhance Multi-Modal Tasks in Remote Sensing

引用

Remote Sensing in Earth Systems sciences 2024年第3期7卷 149-158页

作者： Nagaraj, Saranya Sivakumar, Shanmuga Priya Annabel, Lawrence Sherly Puspha Joshi, Vilas Ramrao Patil, Mithun Baswaraj Patil, Vishal Ratansing SRM Institute of Science and Technology School of Computing SRM Institute of Science and Technology Department of Artificial Intelligence and Machine Learning St. Joseph’s College of Engineering Department of Computer Engineering ISBM College of Engineering Department of Computer Science and Engg N K Orchid College of Engg and Technology Solapur Department of CSE (AIML) Pimpri Chinchwad College of Engineering Nigdi

The SkyScript dataset was developed by integrating large-scale remote sensing images from Google Earth Engine with geo-tagged semantic data from OpenStreetMap. This open-access dataset, consisting of 2.6 million image-text pairs covering 29,000 unique tags, facilitates various remote sensing tasks such as cross-modal retrieval, image captioning, and classification. The dataset ensures global representation and semantic diversity, although it exhibits a higher concentration of high-resolution images from the USA and Europe due to licencing constraints. The images, sourced from multiple collections with varying ground sampling distances, are paired with captions generated using a combination of rule-based methods and logistic regression models for tag classification. Experiments demonstrate that models pre-trained on SkyScript outperform those trained on other datasets in zero-shot classification and fine-grained attribute recognition, highlighting its potential for advancing vision-language models in remote sensing applications. Future improvements could involve enhancing geographic coverage and refining caption quality using advanced language models. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Image captioning Remote sensing Sampling distance Vision language

来源：评论

学校读者我要写书评

暂无评论

A Classification of Face Recognition System Using Faster Region-Based Convolutional Neural Network 2

A Classification of Face Recognition System Using Faster Reg...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Maheswari, M. Alabdeli, Haider Aruna, T.M. Reddy, R. Archana Revathi, R. School of Computing Srm Institue of Science and Technology Department of Computational Intelligence Kattankulathur India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Artificial Intelligence and Machine Learning Bengaluru India School of Computer Science and Engineering Sr University Warangal India Karpagam Academy of Higher Education Department of Computer Science Echanari Coimbatore India

ISBN: (纸本)9798350373110

In recent times, face recognition is a kind of biometric authentication which is widely used for security purpose in many areas like image processing, pattern recognition. However, recognizing the human face was very difficult as the poses in the input images vary, various conditions of light, brightness, expressions, ages. To overcome from it, a proposed method was introduced in this paper known as Faster Region-based Convolutional Neural Network (RCNN). The main advantage of using the proposed method is it will minimize the training process time as it consisting of two fully connected layers namely classifier and regression layer. Initially, the proposed method was implemented on ORL database consisting of 40 classes, then the images in the database undergoes image resizing and enhancing in the preprocessing stage. Where, Image resizing id done to reduce images size so that every image is same in size that will minimize the processing time and image enhancing was done to adjust the brightness of the image. In further, for extracting the features from preprocessed images, CNN is used, so that extracted features are given to the classification stage to detect the face of human or not. In detecting the faces, proposed Faster RCNN achieved high accuracy of 98.64% when compared with other existing methods like IFC, EFRA and VGG16. © 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

An Effective Expectation of Diabetes Mellitus via Improved Support Vector machine through Cloud Security

An Effective Expectation of Diabetes Mellitus via Improved S...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Lal N, Dayanand Hema, K. Spoorthi, T. Chegoni, Ramesh Madhura, K.G. Gitam School of Technology Gitam University Department of Computer Science & Engineering India Cmr Technical Campus Department of It Kandlakoya India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350398465

Nerve pain, eye difficulties, skin issues, renal problems, heart disease, depression, and a host of other illnesses are all linked to diabetes if left untreated. In an effort to lengthen the human lifespan, scientists all around the world have applied a variety of methods for early disease prediction. Diseases of the eyes, heart, and kidneys are prioritised because they can cause serious consequences and even death if left untreated. After conducting an in-depth analysis of the strategies used by several researchers, the following models were constructed and tested using the datasets most frequently favoured by leading scientists throughout the world. Diabetic retinopathy (DR) is an eye condition, and this research seeks to construct a hybrid learning model for early prediction of DR. The proposed approach combines elements of both machine learning and Deep learning. Score Level Fusion is the last arbiter of the model's precision. Images from the first dataset of its sort reflecting the Indian population, the Indian Diabetic Retinopathy Imaging Dataset, were used to make the prediction. Predicting the DR and recommending the necessary treatment to patients is possible based on severity levels, which ultimately leads to the elimination of blindness. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Hybrid Fuzzy Assisted RNN Algorithm for Diabetic Retinopathy Identification

Hybrid Fuzzy Assisted RNN Algorithm for Diabetic Retinopathy...

引用

2023 International Conference on Energy, Materials and Communication Engineering, ICEMCE 2023

作者： Sivaprakash, P. Gifta Jerith, G. Packiaraj, H. Manikandan, R.A. Thanish Kumar, T. Ashok, S. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu India Malla Reddy University School of Engineering Department of Artificial Intelligence & Machine Learning Hyderabad India

ISBN: (纸本)9798350393378

The most common cause of blindness in diabetics is diabetes retinopathy. The importance of early detection in preventing the DR cannot be overstated. However, because eye checkups are so expensive, many people let DR worsen and eventually lead to blindness. To identify persons with DR, the current study employs a color fundus image and a Fuzzy RNN algorithm. Although the purpose of this study is to save money, it could be a game changer for people with DR who cannot afford a medical diagnosis. Prior processing methods include green band extraction, histogram equalization, filtration, optic disc removal with organizational components on architecturally procedures, and illumination changes. The data acquired by GLCM contains contrast, correlation, energy, and homogeneity, and it is utilised to extract characteristics from the preprocessing results. This paper describes a threshold segmentation-based DR detection system. As a result of this study, a fuzzy-RNN methodology for identifying diabetic retinopathy has been developed. Threshold-based categorization is used to determine the diabetic zone. GLCM (Grey Level Co-occurrence Matrix) is the feature extraction technique applied in this case. These characteristics are utilised for categorization. For classification, an RNN classifier is utilised. To simulate the image processing using Phython in diabetic retinopathy is used to validate the final outcome. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Prediction Of Rheumatoid Arthritis Flares Through Ensemble learning Methods 2

Enhanced Prediction Of Rheumatoid Arthritis Flares Through E...

引用

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

作者： Priyadharshini, K. Vinitha, S. Sivaprakash, S. Kayalvili, S. Thilakavathy, P. Vasavi, M. Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chennai India Department of Artificial Intelligence and Machine Learning Jerusalem College of Engineering Chennai India School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Artificial Intelligence Kongu Engineering College Erode India Vels Institute of Science Technology and Advanced Studies Chennai India ET Department CVR College of Engineering Hyderabad India

ISBN: (纸本)9798350383867

RA is an inflammatory, autoimmune disease with an unpredictable course, during which patients experience exacerbations (increases in symptoms) and its associated complications, such as deterioration of the joint and decreased quality of life. Tipping the exact point when remission is reached or RA flares is most essential for devising optimal treatment and enhancing patient's well-being. In this study, we put forward the usage of various types of ensemble learning algorithms aimed at improved the predictive power of RA flares. We use diverse data sources, including clinical data, medical imagery, genetic profiles and patient-reported data, and ensemble methods like Random Forest, Gradient Boosting, AdaBoost and Stacking processors to help us identify the patterns automatically. Thus ensembles of models are shown to be leading in performance, reaching superior accuracy, accuracy precision, recall rate, F1-score and area under the receiver operating characteristic curve (AUC-ROC). Feature importance analysis highlights the significant impact of clinical features which include the levels of CRP, ESR, age of the patient, duration of the disease on the likelihood of RA flares among the individual variants. The sensitivity analysis shows how well the ensemble model behaves under the generation of different model parameters and input data. The presented study emphasizes the immense facilitative ability of the ensemble methods of learning as predicting RA flares and this can also provide great information about the disease process and personalized medical decision-making. The areas for future research could be improved ensembles models, identification of novel feature selection approaches and validation of model performance in a variety of clinical settings. This will give the researchers an opportunity to implement the models in practice and make clinics more effective. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Pose Estimation and machine learning Classifiers for Precise Yoga Pose Detection and Classification 3

Comprehensive Analysis of Pose Estimation and Machine Learni...

引用

3rd International Conference on machine learning and Data Engineering, ICMLDE 2024

作者： Meghana, J.H. Chethan, H.K. Santhosh Kumar, K.S. Prakash, S.P. Shiva Department of Studies in Computer Science University of Mysore Mysuru Karnataka570006 India Department of Computer Science and Engineering Maharaja Institute of Technology Thandavapura Mysuru571302 India Department of Artificial Intelligence and Machine Learning Mysore University School of Engineering University of Mysore Mysuru Karnataka570006 India Department of Information Science and Engineering & Computer Science and Business Systems JSS Science and Technology University Mysuru Karnataka570006 India

Yoga contributes to mental and physical well-being by improving flexibility, strength, balance, and emotional stability when integrated into daily routines. This ancient practice can become more accessible and adaptable to a wider audience when combined with modern artificial intelligence (AI). This study introduces a comprehensive system for detecting and classifying yoga poses using computer vision and machine learning techniques. Central to this work is the application of posture estimation algorithms, such as MediaPipe, PoseNet, and OpenPose, to identify key points on the human body within a single image or video frame. These key points are analyzed in both two-dimensional (2D) and three-dimensional (3D) spaces to construct a skeletal representation of the body, enabling accurate classification of yoga poses. The study focuses on five distinct yoga poses: Downdog, Goddess, Plank, Tree, and Warrior II. To categorize these poses, machine learning classifiers including Support Vector machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and Naive Bayes utilize the key points extracted from the pose estimation models. This research is distinctive in its thorough evaluation of various conventional classifiers across multiple yoga positions. A comprehensive comparative analysis is essential for identifying the most effective classifiers for posture detection and classification. The dataset used in this study has been carefully curated to encompass a wide array of yoga poses and is divided into training and testing sets at various ratios (90:10, 80:20, 70:30, and 60:40) to ensure robust validation. Results indicate the system's effectiveness, with SVM and KNN consistently achieving high values for AccuracyPE, PrecisionPE, RecallPE, and F1-S corePE across all yoga poses. Notably, Random Forest attains up to 100% AccuracyPE in detecting and classifying certain poses, demonstrating its robustness and reliability. This research highlights the potential of integrating p

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

IDENTIFIABLE LATENT POLYNOMIAL CAUSAL MODELS THROUGH THE LENS OF CHANGE 12

IDENTIFIABLE LATENT POLYNOMIAL CAUSAL MODELS THROUGH THE LEN...

引用

12th International Conference on learning Representations, ICLR 2024

作者： Liu, Yuhang Zhang, Zhen Gong, Dong Gong, Mingming Huang, Biwei van den Hengel, Anton Zhang, Kun Shi, Javen Qinfeng Australian Institute for Machine Learning The University of Adelaide Australia School of Computer Science and Engineering The University of New South Wales Australia School of Mathematics and Statistics The University of Melbourne Australia University of California San Diego United States Department of Philosophy Carnegie Mellon University United States Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability. A recent breakthrough explores identifiability by leveraging the change of causal influences among latent causal variables across multiple environments (Liu et al., 2022). However, this progress rests on the assumption that the causal relationships among latent causal variables adhere strictly to linear Gaussian models. In this paper, we extend the scope of latent causal models to involve nonlinear causal relationships, represented by polynomial models, and general noise distributions conforming to the exponential family. Additionally, we investigate the necessity of imposing changes on all causal parameters and present partial identifiability results when part of them remains unchanged. Further, we propose a novel empirical estimation method, grounded in our theoretical finding, that enables learning consistent latent causal representations. Our experimental results, obtained from both synthetic and real-world data, validate our theoretical contributions concerning identifiability and consistency. © 2024 12th International Conference on learning Representations, ICLR 2024. All rights reserved.

关键词：

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：