检索结果-内蒙古大学图书馆

7th IFIP TC 12 International Conference on Computational Intelligence in Data science, ICCIDS 2024

作者： Suchithra, M. Shashwat, Kumar Shoaib Khan, Mohammed Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9783031699856

Length of stay (LoS) in a hospital is an important metric in the healthcare management system, with profound implications for resource allocation, patient outcomes, and cost reduction. This paper reviews the literature on approaches for predicting hospital length of stay with a R2 score of 96.14 per cent using Light Gradient Boosting Machine regressor. We critically assess the merits and limitations of various methods and propose a unified framework for the generalized prediction of length of stay. Our framework includes investigating the types of routinely collected data and recommendations for robust knowledge modelling. © IFIP International Federation for Information Processing 2024.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

High Resolution Image Upsampler for Lung Adenocarcinoma diagnosis 3

High Resolution Image Upsampler for Lung Adenocarcinoma diag...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Sinha, Viraj Yadav, Richa Pretty Diana Cyril, C. Usha, G. Srm Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India

ISBN: (纸本)9798331528201

Lung Adenocarcinoma is a kind of NSCLC (non-small cell lung cancer) which is the most occurring form of lung cancer. It progresses in the epithelial cells that coat the Alveoli sacs of the lungs. Adenocarcinoma refers to cancer formed in mucus secreting cells, thus giving it its name. Patients suffering from this disease shows a combination of symptoms such as pneumonia, coughing up blood, fatigue and weight loss which covers a wide range of unrelated manifestation leading the disease to go unnoticed and often causing fatality. Just like any other cancer, Lung Adenocarcinoma desires early and accurate diagnosis. Current methods include various forms of imaging techniques such as PET scan, biopsy procedures and genetic testing. Diagnosis is followed by a plethora of treatment options such as Chemotherapy, Targeted therapy and Immunotherapy. Despite such efficacious treatment techniques, their effect entirely relies on the stage of diagnosis and its accuracy. Keeping such dearth in mind, we put forward a high resolution upsampled image generator which is packed with combinations of advanced neural network incorporating Machine learning model and techniques such as GANs (Generative Adversarial Network). This platform utilizes pathological data from several trusted sources to develop the AI model which as a result will increase the accuracy of biopsy diagnosis. Trained on the dataset that was carefully acquired and the initial 750 samples were augmented generating the final dataset of 4500+ image samples using the 'Augmentor' package in python, the model delivers superior results than current diagnosis methods while simultaneously improving biopsy performance. It guarantees model stability to variations which is achieved through minimizing loss function and parameter tuning while enhancing computational efficiency. This development may eventually result in filling the gap in current diagnosis methods by improving its results manifold. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A novel approach on heart disease prediction using optimized hybrid deep learning approach

引用

Multimedia Tools and Applications 2025年 1-26页

作者： C, Adline Sherifa Kanisha, B. Department of Computing Technologies Faculty of Engg and Technology SRM Institute of Science and Technology Kattankulathur Chennai603 203 India

The condition known as Cardio Vascular Disease can result in heart attacks, Angina, and brain assaults due to the restriction of blood flow to the myocardium. Among the most important causes of death and mortality worldwide, heart disease is also one of the main sources of disability for both young and old people. Moreover, it is one of the reasons behind weariness and mortality on Earth. Interruption can prompt benevolence, adjustments in lifestyle, and tailored therapy interventions, which ultimately lead to peaceful outcomes and reduced healthcare expenses. The data gathered in this question about work is processed beforehand using information cleaning and information standardization techniques. Measurable highlights, higher-order measurable highlights (for example, why measure weights are not measured), correlation-based IDM, weight standard deviation-related entropy, and the degree of relationship between the data and homogeneity, which in turn are removed. From the extricated features, the foremost ideal highlights are chosen via the relief-f demonstration. By selecting the most suitable features, one can prepare the crossover classifier that generates the heart illness prediction. The crossover classifier could be a combination of MLP and O-RBM. To advance the expectation exactness of the anticipated heart malady location show, the weight of Limited Boltzmann Machines is fine-tuned through the Self-Adaptive TLBO (SA- TLBO) demonstration. The result from the crossover classifier is the identified result. This SA-TLBO show is an extended version of the standard TLBO show. By analyzing the "Heart Malady Dataset" of the Kaggle store, it is established that the proposed show has 95% precision and 96% accuracy with an FNR of 0.05. This demonstration is then tested against the real models to show whether a model matches those of the proposed one. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional Task Offloading using Deep Learning for Vehicular Edge computing Networks: A Survey

引用

IEIE Transactions on Smart Processing and computing 2024年第1期13卷 1-11页

作者： Abuthahir, S. Syed Peter, J. Selvin Paul Department of Computing Technologies SRM Institute of Science & Technology KTR Campus Tamil Nadu Chennai India

Vehicular networks must support connection ubiquity and high levels of services for a large number of vehicles. In vehicular networks, mobile edge computing (MEC) is considered a viable technique, utilizing computing resources at the edge of wireless access networks. This survey examines effectual task offloading systems forvehicular edge computing (VEC) networks. Several deep learning methods have been suggested to enable task offloading schemes. Therefore, task offloading optimality is a main research topic in fog computing. The main aim of this work is to offer readers an overview of the journey from the task offloading concept to its mathematic problem formulation. This survey introduces fog computing and the process of task offloading that emulates numerous aspects of optimization. Subsequently, a number of machine learning and deep learning methodologies are employed in task offloading,and the challenge of fog computing is discussed. This paper provides a detailed statistical analysis from papers published between 2019 and 2022. Copyrights © 2024 The institute of Electronics and Information Engineers.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

AI-based Pneumonia Detection using a Deep Context Axial Reverse Capsule Neural Network with Sea-Horse Optimizer 3

AI-based Pneumonia Detection using a Deep Context Axial Reve...

引用

3rd International Conference on Intelligent Data Communication technologies and Internet of Things, IDCIoT 2025

作者： Mohideen AbdulKader, M. Tuteja, Ankush Joshi, Darsh Tholath, Joshua Bobby Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu India

ISBN: (纸本)9798331527549

Pneumonia detection with AI uses advanced deep learning algorithms for identifying the patterns in the chest X-ray images which makes diagnosis faster and efficient for physicians. AI-powered radiography improved the diagnostic approaches, even then existing methods face some limitations such as reduced accuracy and high computational costs. The Deep Context Axial Reverse Capsule Neural Network with Sea-Horse Optimizer (ADpCARCNNet+SHO) for pneumonia detection is proposed to overcome these challenges. This framework processes chest X-ray images from the Chest X-ray 14 dataset, beginning with Color Wiener Filtering (CWF) for noise reduction. Key features are then extracted using the Dynamic Range Quantized Discrete Haar Wavelet Transform (DRQDHWT), followed by classification using the ADpCARCNNet, optimized with the Sea-Horse Optimizer (SHO) to ensure high precision. Proposed method achieves a remarkable 99.9% accuracy on the Chest X-ray 14 dataset, outperforming existing techniques. The results demonstrate improved diagnostic accuracy, faster image analysis, enhanced reliability, and reduced computational cost, highlighting the potential of the ADpCARCNNet+SHO framework for efficient and reliable AI-driven pneumonia detection. © 2025 IEEE.

关键词： Diagnostic radiography

来源：评论

学校读者我要写书评

暂无评论

Hybrid Seagull and Whale Optimization Algorithm-Based Dynamic Clustering Protocol for Improving Network Longevity in Wireless Sensor Networks

引用

China Communications 2024年第10期21卷 113-131页

作者： P.Vinoth Kumar K.Venkatesh Department of Networking and Communications School of ComputingCollege of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur 603203India

Energy efficiency is the prime concern in Wireless Sensor Networks(WSNs) as maximized energy consumption without essentially limits the energy stability and network lifetime. Clustering is the significant approach essential for minimizing unnecessary transmission energy consumption with sustained network lifetime. This clustering process is identified as the Non-deterministic Polynomial(NP)-hard optimization problems which has the maximized probability of being solved through metaheuristic *** adoption of hybrid metaheuristic algorithm concentrates on the identification of the optimal or nearoptimal solutions which aids in better energy stability during Cluster Head(CH) selection. In this paper,Hybrid Seagull and Whale Optimization Algorithmbased Dynamic Clustering Protocol(HSWOA-DCP)is proposed with the exploitation benefits of WOA and exploration merits of SEOA to optimal CH selection for maintaining energy stability with prolonged network lifetime. This HSWOA-DCP adopted the modified version of SEagull Optimization Algorithm(SEOA) to handle the problem of premature convergence and computational accuracy which is maximally possible during CH selection. The inclusion of SEOA into WOA improved the global searching capability during the selection of CH and prevents worst fitness nodes from being selected as CH, since the spiral attacking behavior of SEOA is similar to the bubble-net characteristics of WOA. This CH selection integrates the spiral attacking principles of SEOA and contraction surrounding mechanism of WOA for improving computation accuracy to prevent frequent election process. It also included the strategy of levy flight strategy into SEOA for potentially avoiding premature convergence to attain better trade-off between the rate of exploration and exploitation in a more effective manner. The simulation results of the proposed HSWOADCP confirmed better network survivability rate, network residual energy and network overall throughput on par wi

关键词： clustering energy stability network lifetime seagull optimization algorithm(SEOA) whale optimization algorithm(WOA) wireless sensor networks(WSNs)

来源：评论

学校读者我要写书评

暂无评论

A new perspective exploration of machine learning algorithms for defending Side-Channel attacks

引用

Multimedia Tools and Applications 2025年第16期84卷 17021-17040页

作者： Ramakrishnan, Vedhavathy Thoguluva Seethapathy, Murugaanandam Sundar, Ramesh Dhandapani, Saveetha Munusamy, Sundarrajan Balasubrahmaniam, Lakshmi Dhevi Department of Networking and Communications School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur India

Machine learning algorithms are used in various real-time applications, where security is one of the major problems. Security is applied in various aspects of the application in cloud computing. One of the security issues is a side-channel attack, which is not a common problem that can be solved by a point solution. The emerging computing industries need a better solution for side-channel attack detection since the amount of data used in communication and sharing on the Internet is enormous. Several old research works have concluded that machine learning algorithms are highly suitable for data analytics. Hence, this paper has aimed to propose a better machine-learning model for side-channel attack detection. This paper explains some machine learning algorithms from a technical point of view. The explanation identifies that the Convolution Neural Network algorithm is selected as a better algorithm for side-channel attack detection. The proposed CNN model has experimented with Python software to verify the results. Since CNN is more efficient in data analytics, the analysis result produces more accurate predictions than earlier algorithms. The performance of the proposed CNN is compared with the earlier algorithms for evaluating it. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Improving Dog Breed Classification Performance through Stacked Deep Learning Models with Imbalanced Data 2

Improving Dog Breed Classification Performance through Stack...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Srinivasan, R. Iniyan, S. Santhanakrishnan, C. Subash, R. Sudhakaran, Pradeep School of Computing SRM Institute of Science and Technology Department of Computing Technologies 603 203 India

ISBN: (纸本)9798350368109

Image classification is a computer vision task that helps to classify the images based on various techniques with respect to feature extraction process. This research work is put together into two tasks. First, it aims to address the class imbalance issue inherent in the dataset through the utilization of data augmentation techniques. Secondly, the focus shifts towards employing deep learning (DL) methodologies for dog breed classification using stacked model. Stacked model is to combine the one or more DL techniques that helps to achieve good results. Evaluations are carried out using the following metrics such as accuracy, f1-score, precision, and recall. These metrics helps to analyse the performance of proposed stacked model in dog breed classification. Experimental result proves that the combined stack model with data augumentation techniques helps to achieves 88.7% result in the dog breed corpus. © 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

An Efficient Speech to Sign Language Conversion and Text Recognition through Live Gesture 1

An Efficient Speech to Sign Language Conversion and Text Rec...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Kowsigan, M. Dhawan, Rahul Kundu, Ankan School of Computing Srm Institute of Science and Technology Department of Computing Technologies Chengalpattu Kattankulathur India

ISBN: (纸本)9798350377002

Despite advancements in technology, a significant portion of the global population (over 5%) continues to face communication barriers due to deafness and speech impairments. Existing solutions often lack the comprehensiveness and inclusivity required to address the diverse needs of this community. Traditional methods, relying solely on speech-to-text or text-to-sign language conversion, fail to facilitate seamless two-way communication, limiting interpersonal connections and fostering a sense of isolation. Our research proposes a novel, multimodal approach integrating speech-to-sign language conversion and live gesture-to-text recognition, leveraging audio and visual inputs. By combining these modalities, our system aims to bridge the communication gap, enabling real-time, bidirectional interactions between individuals with and without hearing or speech impairments. Employing speech recognition, natural language processing techniques, and machine learning models developed using Python, our solution incorporates a custom dataset, encompassing personalized hand symbols and offering the flexibility to choose between American Sign Language (ASL) and Indian Sign Language (ISL), promoting inclusivity and catering to cultural preferences. The necessity of this research lies in its potential to revolutionize assistive technologies, fostering a more connected and empathetic society. By providing a comprehensive platform that facilitates effective communication and mutual understanding, our solution improves quality of life, educational opportunities, and social inclusion for individuals with impairments. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Solar Power Output Prediction with AI: Leveraging Meta Learner Ensemble Stacked Regressor

Solar Power Output Prediction with AI: Leveraging Meta Learn...

引用

2024 International Conference on Integration of Emerging technologies for the Digital World, ICIETDW 2024

作者： Shreeja, G. Kannan, Shruthi Sivakumar, Soubraylu SRM Institute of Science and Technology Computing Technologies School of Computing Chennai India

ISBN: (纸本)9798331541170

As the world shifts from fossil fuels to renewable energy, solar power has become essential in meeting global energy demands. The efficiency of solar energy depends on effectively capturing the environmental and physical factors that impact electricity production by solar panels. This study aims to leverage available data on power output and environmental conditions to build advanced machine learning models for predicting solar power. Models such as KNN, DNN, LGBM, RF, and a Meta Learner will be rigorously trained and fine-tuned using various data subsets and hyperparameter optimization. By employing the stacking regressor module from Scikit-learn, a Python machine-learning library, we successfully combined four distinct models, achieving an R-squared value of 0.68 in predicting solar power. This method not only improves the accuracy of solar power predictions but also enhances our ability to capture the complex data relationships critical for forecasting renewable energy. © 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

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：