检索结果-内蒙古大学图书馆

7th International Conference on Soft computing: Theories and Applications, SoCTA 2023

作者： Kayathri, V. Prabakaran, P. Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai600 117 India

ISBN: (纸本)9789819720309

Successful stock market investors should consider these trends. This article defines price effect, optimal execution, and placement through the lens of algorithmic trading and strategies based on news and events. By using feedbacks controlled to include consideration of a stop-loss order, algorithmic trading allows traders and investors at large to liquidate or construct big securities positions in a fully automated manner, thus generalising the existing stock trading results. Trading decisions made by the AI agent could affect the asset price. We see this as a marketplace where people are bartering and swapping goods. Creating a new market is the driving force behind our research into generative models. This news sentiment does a good job of describing stocks, and AI systems that read the news and quantify them react to factors that affect prices far more quickly than humans do. All three of the stock market's underpinnings—price, volume, and volatility—respond strongly to news events. Sentiment analysis is a method for gauging the overall tone of a news piece and classifying it as optimistic, pessimistic, or neutral. The simulation is conducted in python to test the effectiveness of the model in trading in an automated manner for stocks. The results show that the proposed sentimental analysis for stock trading achieves higher rate of accuracy and precision than the other methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization-Load Balancing in Cloud computing 3

Ant Colony Optimization-Load Balancing in Cloud Computing

引用

3rd IEEE International Conference on Distributed computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Sivasankari, S. Aneetha, A.S. Vels Institute Of Science Technology & Advanced Studies Department Of Computer Science Chennai India

ISBN: (纸本)9798350318609

The cloud computing is a novel approach to online computing. It offers numerous benefits, but several important problems need to be fixed if the cloud environment is to become more reliable. These are the problems associated with fault tolerance, load management, and other security concerns in cloud environments. The main focus is to solve the issue in the pressure of network and improve the cloud computing efficiently and this paper runs with ant colony algorithm. The real time network loads the situation that provides and calculates the link to smallest load ad provides the dynamic stream of data forwarding strategy. The results showed the technique of load balanced ACO that can improve the response computationally. The Ant Colony Optimization Algorithm got the average response 30% lower compare to other algorithms. The ant colony optimization shows the uses and good result in optimization analysis. © 2024 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Analysis of deep actor-critic methods for classifying cancer subtypes through gene expression

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2024年第4期8卷 46-66页

作者： Jayakrishnan, R. Meera, S. Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India

The word “cancer” denotes a syndromes that can spread to various bodily areas and are brought on by abnormal cell proliferation. After cardiovascular illnesses, according to the World Health Organisation (WHO), cancer is the second largest cause of death in the world. To better understand molecular processes behind various cancer subdivisions, cancer categorization depends on gene expression information is essential. Conventional machine learning methods have proven helpful in this situation, but new approaches are needed for accurate and understandable categorisation due to the difficulty and dimensionality of gene expression datasets. In this article, we analyse various methods for multiclass categorising cancer subtypes using deep structured reinforcement learning (DSRL). Our methodology addresses several significant issues in cancer subtype classification by combining the strength of deep neural networks with reinforcement learning. In this research, seven different gene expression datasets are utilised to classify the cancer subtype. We also used different classification approaches in Python for the same dataset to perform a comparative study. Deep reinforcement learning for cancer subtype classification improves the accuracy of gene expression data by integrating intricate data patterns, enabling customised therapies, and expanding the field of precision medicine research. The analysis reveals that the newly suggested model exceeds the contemporary state-of-the-art classifiers, achieving the highest accuracy across all seven datasets, ranging from 55% to 100%, while attaining the lowest loss, which varies between 0.02 and 0.11. This work offers a viable method for classifying cancer subtypes into many categories using gene expression data. © (2024), (Society of Sytematic Innovation). All rights reserved.

关键词： Cancer subtypes Deep neural networks Deep-learning Gene expression Machine-learning Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An AI-integrated Enhanced Anatomical Brain Tumor Segmentation in Substantia Nigra for Early Disease Identification using Deep Resnet50-CNN

An AI-integrated Enhanced Anatomical Brain Tumor Segmentatio...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Ganeshkumar, P.V. Prasanna, S. Vels Institute of Science Technology and Advanced Studies Chennai India Vels Institute of Science Technology and Advanced Studies Department of Computer Application Chennai India

ISBN: (纸本)9798350375442

The early identification of brain tumours is crucial for improving patient prognosis and treatment planning. Recent advancements in neuroimaging techniques have paved the way for the enhanced detection and characterization of these lesions through CT or MRI image scans. During medical image analysis, the feature analysis is important factor to know the object relations, entity resolution information and disease relational properties, from the prior analysis, machine learning models are mostly covered to segment the disease region by retaining non scaling factors. Due to lower precision class, poor segmentation leads low accuracy to identifying the disease regions to produce higher false rates. In this research explores a novel approach to brain tumour identification utilizing Neuromelanin-Sensitive Magnetic Resonance Imaging (NMS-MRI). We propose a novel preprocessing methodology leveraging the Weigner filter to enhance image normalization and overall quality, facilitating more accurate subsequent analyses. Following preprocessing, we employ Cascading Slice Window Volumetry Segmentation (CSWVM) to achieve refined tumor delineation in three-dimensional MRI scans. The segmentation results are further refined through Cross Modality Particle Swarm Optimization (CMPSO)-based feature selection, which effectively identifies the most relevant features across various imaging modalities to optimize the classification process. To classify the detected tumors, further to integrate a ResNet 50-Convolutional Neural Network (ResNet50-CNN), leveraging its deep learning capabilities for robust pattern recognition in neuroimaging data. The proposed system proves higher performance in precision, recall, f1 score by attaining feature selection, and deep learning algorithms, ultimately contributing to enhanced accuracy and effectiveness in brain tumor identification. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Efficient Education Community Detection Using Deep Learning Algorithm for Similarity Identification in Online Social Networks

Efficient Education Community Detection Using Deep Learning ...

引用

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

作者： Tharani, A.P. Sumalatha, V. Meenakshi, S. Vels Institute of Science Technology and Advanced Studies Department of Computer Applications Chennai India Vels Institute of Science Technology and Advanced Studies Department of Mathematics Chennai India

ISBN: (纸本)9798350360660

Education development is tremendous in online social network through information communication technology by group of various communities depends on the education types. Increasing online learners through distance education carry the search groups to find the suitable courses in the online community forms. So, community detection is important aspect for identifying the resource dependencies properties to make community groups on relevant education groups. The network of communities in the online are so huge and the information sharing among the field of entities in the groups contains various features. By identifying the communication relation feature e properties is big problem in community detection. Most of the prior Machine Learning (ML) models failed to analysis the feature relation properties lead poor accuracy because of non-relation community feature margins are grouped. To addressing the problem, to implement a Hyper spectral feature selection with deep Recurrent convolution Neural network (DRCNN). First, to normalize academic community data records collected from online community forums, Box-cox normalization is preprocessed. The community pattern interest rate (CPIR) is estimated based on the learner interest specific terms of subjectivity relation. By selecting the properties of the feature in hyper level by creating patterns and entity relation using spider ant colony Correlation Exhaustive Feature Selection (CEFS) to identify the feature relation related specific community group. Then deep Recurrent convolution Neural network (DRCNN) is attained to identify the community groups effectively. Then proposed system produce high performance compared to the system as well to find the communities properties effectively in high true positive rates to improve the performance with redundant time complexity. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Advancements in Speech Recognition: Exploring Feature Extraction Techniques for Enhanced Accuracy and Human-Machine Communication 4

Advancements in Speech Recognition: Exploring Feature Extrac...

引用

4th International Conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Bhavani, R. Kathirvelu, Kalaivani Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350343670

Speech Recognition (SR), for all diverse languages, is still a big challenge. SR is predominantly used in telecommunication, medical documentation, car control, aviation, etc. SR involves breaking down an audio signal of spoken words into discrete units and then matching those units to words in a language model. The main target of SR is to attain healthier verbal communication amid humans and machines. Therefore, it is a good technology of the human-machine crossing point. The SR uses the Feature Extraction (FE) techniques for better accuracy. In this paper, various techniques for FE are discussed, and an overview is provided to assist in selecting the most suitable technique for achieving higher accuracy. The review highlights the importance of developing more accurate and robust SR systems to improve the user experience in various domains. Overall, it provides the manuscript deals with five different techniques, and among them, the Mel-Frequency Cepstral Coefficients (MFCC) technique was found to exhibit a high level of accuracy. © 2024 IEEE.

关键词： feature extraction Signal processing Signals Sound Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Performance Juxtapose of Plant Leaf Disease Detection using Adaptive Deep Convolutional Recurrent Neural Network (ADCRNN) in MATLAB Versus Python

Performance Juxtapose of Plant Leaf Disease Detection using ...

引用

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

作者： Jayashree, S. Sumalatha, V. Vels Institute of Science Technology & Advanced Studies Department of Information Technology Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Application Chennai India

ISBN: (纸本)9798350360660

Leaf diseases can cause several detriments in crops' overall yield and fertility. While analyzing the various diseases that affect plants is imperative, identifying the diseases using algorithmic techniques that render optimal performance is crucial. In agriculture, detecting multiple diseases in plants is difficult. However, the provision to automate disease identification through machine learning approaches through the various phases of preprocessing and segmentation is implemented in this study. This indagation delineates the leaf disease identification using the proposed hybrid algorithmic Adaptive Deep Convolutional Recurrent Neural Network (ADCRNN) in bifurcated platforms such as MATLAB and Python. The Radial basis function is incorporated to optimize the throughput in MATLAB before observing the juxtaposed results in both platforms. The purpose of utilizing ADCRNN is to effectively combine the advantages and parallelly overcome the challenges of Deep Convolutional Neural Network (DCNN), RNN, and adaptive techniques that unsheathe the pivotal features from the provided input. The ADCRNN simulation is carried out in MATLAB and Python, and the results are successfully obtained. In addition, after optimization, the proposed ADCRNN technique's accuracy increased to 94.5% in performance evaluation in MATLAB. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

science China(Information sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

来源：评论

学校读者我要写书评

暂无评论

Security on mobile cloud computing using cipher text policy and attribute based encryption scheme

引用

Materials Today: Proceedings 2023年 80卷 3059-3063页

作者： Swetha, Madireddy Latha, M. Department Of Computer Science & Engineering Vels Institute of Science Technology and Advanced Studies Tamil Nadu India Vels Institute of Science Technology & Advance Studies Tamil Nadu India

Mobile Cloud computing (MCC) is a new paradigm that has been emerged by the advances in the Cloud computing for Mobile devices to access Cloud services. The data security challenges against the data thefting, deleting, corrupting, or exploiting are existed as the data storage and access to/from the cloud has been most popular. In order to handle these data security issues in the cloud and to provide protection for the data, some innovative encryption methods have been developed. One of such encryption methods is Attribute-Based Encryption (ABE) that has a more control on the data in cloud as which is accessed by whom. Since from the recent years, many of academic researchers have paying a widespread of attention on using advanced cryptographic techniques to securely store, process, also share data over the untrusted cloud environment. One of the promising cryptographic techniques which can solve the open challenge of regulating the fine-grained access control of important data over the distributed cloud is the Cipher text Policy – Attribute Based Encryption (CP-ABE). Therefore, a survey of work is presented in this paper on different CP-ABE methods for the secure mobile cloud computing architecture. This paper presents some works that are focused on secure data storing, accessing and sharing using CP-ABE methods over the untrusted cloud environments. All the works that are studied are analyzed and compared with each other in the results to find the best out of it. © 2021

关键词： Mobile cloud computing

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Machine Learning Model for Osteoporosis Risk Prediction from Medical Data 2

An Ensemble Machine Learning Model for Osteoporosis Risk Pre...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Thulasi, M. Thailambal, G. Vels Institute of Science Technology & Advanced Studies Department of Advanced Computing and Analytics Tamil Nadu Chennai India

ISBN: (纸本)9798331505745

The metabolic condition osteoporosis afflicted a large number of people worldwide. Osteoporosis causes major health and its financial implications worldwide. However, the advancement of osteoporosis-related methods for forecasting is inadequate. Machine Learning (ML), a subfield of Artificial Intelligence (AI)I allows computers to 'learn' using programs. In comparison to classic statistical methods, ML places a greater focus on prediction accuracy and can find patterns in multidimensional data sets. This study propose an ensemble model employing Random Forest(RF), XGBoost(XGB) and Light Gradient Boosting(LGBM) techniques for the prediction of osteoporosis from the medical data of an individual. The accuracy, precision, recall, and f1-score were computed to compare the model with four alternative machine learning models: Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN). The findings show that the ensemble model outperforms with an accuracy, precision, recall and F1-score of 93.5%, 92.8%, 94.2% and 93.5% respectively. © 2025 IEEE.

关键词： Support vector machines

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：