检索结果-内蒙古大学图书馆

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Axcellin, T. Kamalakkannan, S. Department of Computer Science Vel’s Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India

ISBN: (纸本)9798331522667

Traffic flow prediction (TFP) for intelligent transportation system is essential for effective transportation planning and city development. Conventional models often have difficulty with the complex nature of traffic data, which includes nonlinear patterns, spatial dependencies, and external influences such as weather or road conditions. Prediction accuracy may be significantly increased by utilizing an ensembling strategy, which combines the capabilities of many models. The goal of the study is to improve TFP accuracy by integrating the results of different machine learning (ML) models. The study uses Random Forest(RF) Naïve Bayes(NB), K-Nearest Neighbor(KNN), Extreme Gradient Boosting(XGBoost) and Support vector machine(SVM) as prediction models and based on the prediction probabilities and the score level fusion is performed with RF and XGBoost ensembling. The new fusion procedure uses a weighted average technique in which weights are assigned dynamically depending on individual model performance criteria including accuracy, precision, recall, and F1-score. Higher-performing algorithms are given greater significance in the final forecast, resulting in a dynamic and data-driven assembly strategy. The findings show that the efficiency of the ensemble of RF-XGBoost is higher compared to the contrasted methods. The model also uses feature selection approaches like mutual information to find the most significant traffic-related characteristics, lowering computational cost and increasing forecast efficiency. © 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

Deep Learning Model with Optimization Strategies for DDoS Attack Detection in Cloud Computing 3

Deep Learning Model with Optimization Strategies for DDoS At...

引用

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

作者： Radhika, P. Kamalakkannan, S. Department of Computer Science Vel’s Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India

ISBN: (纸本)9798331527549

Cloud Computing (CC) remains as a chief research area for analysts because of its numerous applications and advantages. The dispersed nature of CC and its dependence on internet service poses several attacks and challenges. Mainly, the attacks like DDoS attempts to disrupt the online operations. Insider attacks cannot be detected using conventional detection techniques like firewalls. This study suggests a DDoS detection method for reducing the DDoS activity. The proposed work contributes under big data perspective by handling certain procedure for detection process. Data Generation phase is the initial step, and according to the work, DDoS dataset is considered under big data perspective. As the work is considered under the big data perspective, Map reduce (MR) framework is used, Mapper handles the data and process the feature extraction, which includes the extraction of raw features, Packet feature extractor, Improved Correlation and statistical Feature. Reducer provides the combined feature set. From the extracted feature set, appropriate features are selected via Weightage based Improved hybrid model combining the models like Long short term memory(LSTM) and Deep Maxout(DMO) networks is used. The weights of LSTM and DMO are optimally chosen using White Shark-Remora Optimization (WSROA) algorithm. Recursive Feature Elimination (RFE) process is used to precisely select the features for DDoS attack detection. The findings shows that the proposed hybrid bio-inspired algorithm outperforms with an accuracy of 94% compared to LSTM, Convolutional Neural Networks(CNN) and Deep Belief Networks(DBN). © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Models for Android Malware Detection–A Comparative Study 3

Machine Learning Models for Android Malware Detection–A Com...

引用

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

作者： Arun, N. Nisha Dayana, T.R. Department of Computer Science Vel’s Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India

ISBN: (纸本)9798331527549

In the mobile ecosystem, Android apps are expanding quickly, but malicious software for Android is also proliferating in ever-increasing quantities. The issue of identifying malware on Android has been examined by several researchers, who have proposed ideas and approaches from various angles. According to current research, machine learning (ML) is a promising and successful method of detecting Android malware. This study is performed to compare the various ML methods for Android malware detection, including Random Forest (RF), Decision Tree,(DT) Random Tree(RT), Support Vector Machine (SVM), and XGBoost. The study assessed these models using a Androzoo dataset of Android apps, taking into account the important performance parameters as detection latency, accuracy, precision, and false alarm rate (FAR). © 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

Emotional Contribution to Parkinson's Disease Diagnosis using Machine Learning for EEG Dataset Generation 6

Emotional Contribution to Parkinson's Disease Diagnosis usin...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Arockiya Selvi, S. Kamalakannan, T. Department of Computer science VEL’S Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India

ISBN: (纸本)9798331522667

Emotion is the root cause of nearly all harmful illnesses in humans. Emotion affects blood pressure, heart rate, kidney function, and a few disorders of the nervous system. Parkinson's disease, which causes impairment of movement, is one of the brain disorders. This issue is caused by a reduction in dopamine release in the cortex of the brain. Dopamine production deviations have been related to essential hypertension. Dopamine has a crucial role in anxiety modulation in multiple regions of the brain. Patients with Parkinson's disease frequently indicate that acute stress worsens their motor symptoms, especially gait freezing, dyskinesia, and tremors and the emotions play a substantial role in Parkinson's disease. This study focuses on the Classification Learner algorithms and the Electro Encephalogram (EEG) dataset, both of which covered the diagnostic range of PD development. The classifiers were evaluated using key performance indicators such as error rate, accuracy, sensitivity, specificity, and precision. The findings illustrate the convergence of emotional analysis, machine learning (ML), and neuroscience in improving diagnostic capabilities by demonstrating how a combination of EEG datasets with KNN algorithms offers a reliable and accurate approach for early Parkinson's disease identification. © 2025 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Detection System of Autism Spectrum Disorder Using Thermal Imaging and Deep Learning

引用

SN computer science 2025年第2期6卷 1-11页

作者： Jegan Amarnath, J. Meera, S. Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Tamil Nadu Chennai 600117 India

Autism Spectrum Disorder (ASD) is a brain-based condition characterized by social difficulties and repetitive behaviors. Traditional diagnostic methods can be subjective and time-consuming. Current diagnostic techniques for ASD often rely on behavioral assessments and clinical observations, which can be inconsistent and prone to subjectivity. Additionally, there is a need for more reliable and objective methods to differentiate between autistic and non-autistic individuals. Existing imaging techniques require further refinement to improve accuracy and efficiency in detecting ASD. The primary objective of this research is to develop and evaluate an enhanced detection system for ASD using thermal imaging and Improved Mask Faster Recurrent Convolutional Neural Network (IMFRCNN). This research focuses on enhancing the detection of ASD using Deep Learning (DL) methods and thermal imaging. Traditional diagnostic techniques for ASD often rely on subjective behavioral assessments, highlighting the need for more reliable methods. By examining cerebral imaging data from the thermal face image datasets collect facial thermal images using thermal cameras. Ensure the dataset is diverse, including varying expressions and environmental conditions. The study compares the effectiveness of IMFRCNN and the ResNet 50 system in classifying thermal images of 50 autistic and 50 non-autistic individuals. Emotions were evoked using audio-visual stimuli, and temperature variations in facial areas such as the nose, forehead, cheek, and eyes were measured. Anger showed the greatest temperature differences, with a 12.6% variation between autistic and non-autistic individuals. The IMFRCNN achieved a reliability of 96%, while the ResNet 50 achieved 90%. These findings indicate that computer-aided assessment techniques utilizing thermal imaging and DL can provide a consistent and objective method for identifying individuals with ASD. © The Author(s), under exclusive licence to Springer Nature Sing

关键词： Deep learning algorithms Diagnostic tool Improved mask faster recurrent convolutional neural network Performance measures

来源：评论

学校读者我要写书评

暂无评论

A Methodical Approach to Healthcare Cybersecurity: Handling Current Risks and Advancements 6

A Methodical Approach to Healthcare Cybersecurity: Handling ...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Husain Bathushaw, M. Nagasundaram, S. Department of Computer Applications VELS Institute of Science Technology and Advanced Studies Pallavaram Chennai600117 India

ISBN: (纸本)9798331522667

The methods were evaluated using machine learning-driven interruption detection, blockchain-enhanced access control for inconsistency localization, and structured threat insight data in a simulated healthcare environment. With an accuracy range of 0.88-0.94 and lift specified between 0.75 and 1, knowledge values ranging from.86 to.92, and F1 scores between and above, the test results demonstrated that all computations were possible. BACA strengthened access control with blockchain;ADA surpassed expectations in identifying discrepancies;TIAA succeeded in risk insights management;and ML-IDS achieved outstanding results in intrusion detection. A comparison with related research highlights the significance of these algorithms in tackling specific cybersecurity issues in the healthcare sector. Because the proposed algorithms provide a holistic approach to safeguard confidential health information, ensure the validity of assessment models, and strengthen organizations against a range of dynamic cyberthreats, they are pertinent to the expanding discussion about cybersecurity in the healthcare industry. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Human Chronic Disease Prediction Using CNN and Adaptive Dragon Fly Optimization (ADFO) Algorithm

引用

SN computer science 2025年第4期6卷 1-18页

作者： Ragu, B. Perumal, S. Department of Computer Science School of Computing Sciences Technology and Advanced Studies (VISTAS) Vels Institute of Science Tamil Nadu Chennai 600117 India

Chronic diseases in human beings are long-lasting health disorders that will progress slowly over months or a lifetime. The chronic diseases can affect various parts or systems of the body and are non-acute in nature. The chronic disease does not occur suddenly and shall not be resolved quickly. However, the spreading of the disease to other parts of the body and the effectiveness of the disease shall be suppressed by providing proper medical treatment from the earlier stages. The World Health Organization has expressed the significance of the treatment of chronic disease, stating that around 41 million deaths, representing 71% of all deaths occurring every year due to chronic diseases. This necessitates the earlier detection of human chronic diseases like cancer, cardiovascular disease and diabetes mellitus. The major challenge associated with chronic disease is that it does not express valid symptoms at the earlier stage and needs advanced technology for the earlier detection process with high accuracy. The existing system of chronic disease predictions falls short in diagnosis and detection at the earlier stages, whereas capable of detecting at stage 3 or stage 4, which were considered the advanced stage of the chronic disease. To overcome this challenge, this proposed work introduces a novel framework encompassing the Convolutional Neural Networks (CNN) and the Adaptive Dragon Fly Optimization algorithm for the earlier prediction process. The proposed work was trained with datasets of various chronic diseases individually to prove the system’s adaptability. In addition, the performance of the proposed work is analyzed in terms of accuracy, Precision, recall and F score, which were compared with the performance of the existing state-of-the-art methodologies. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adaptive dragon fly optimization algorithm Cancer Cardiovascular disease Convolutional neural networks Human chronic disease

来源：评论

学校读者我要写书评

暂无评论

Electrochemical sensor for dopamine detection based on multiwalled carbon nanotube/molybdenum disulfide quantum dots with machine learning integration and anti-interference capability

引用

Tungsten 2025年第1期7卷 137-151页

作者： Geethukrishnan Onkar Apte Kiran Kumar Tadi Energy Electrodics and Electrocatalysis (EEE) Lab Department of Chemistry School of Advanced Sciences Vellore Institute of Technology School of Computer Science and Engineering Vellore Institute of Technology

The precise detection and measurement of dopamine（DA）,a crucial neurotransmitter in the human body,plays a significant role in diagnosing,preventing,and treating neurological diseases associated with its levels.A highly sensitive DA electrochemical sensor was constructed by combining molybdenum disulfide quantum dots（MSQDs） with multiwalled carbon nanotubes（MWCNTs）.The MSQDs were synthesized using the shear exfoliation *** sensors consist of MSQDs with Mo-S edge catalytic centers for the DA redox reaction,and MWCNTs amplify the sensor *** linearity of the sensor for the detection of DA was tested in the presence of ascorbic acid(AA,50 μmol·L-1) and uric acid(UA,200 μmol·L-1),and exhibited linearity from 2 to 966 μmol·L-1of DA with 0.097 μA(mol·L-1)-1sensitivity and a low limit of detection of0.6 μmol·L-1（the ratio between signal and noise,S/N=3）.Moreover,the sensitivity and selectivity of the sensor were also studied using *** is no increase in amperometric current after adding the most potentially interfering *** sensor was successfully applied to recover DA in human blood sera ***,machine learning algorithms were operated to aid in the near-precise detection of DA in the heterogeneous mixture containing AA and *** algorithms facilitate the identification and quantification of DA amidst coexisting interferents,including AA,that are commonly present in biological matrices.

关键词： Dopamine MoS_2 Biosensor Multiwalled carbon nanotubes Machine learning Complex mixture

来源：评论

学校读者我要写书评

暂无评论

Investigating the Efficiency of a Federated Learning-Based Intrusion Detection System for Smart Grid

引用

SN computer science 2025年第3期6卷 1-14页

作者： Hamdi, Najet Department of Computer Science Higher Institute of Technological Studies Medenine 4100 Tunisia

With integration of IoT technologies, the power grid is getting more connected with external networks. This exposes its supervisory control and data acquisition (SCADA) system, the enabler component of smart grids, to severe cyberattacks. To secure smart grids, early identification of anomalies and threats is of utmost importance. Machine learning based intrusion detection systems (IDS) have shown reliable and efficient performance. Most of the proposed IDS are based on centralized learning where data is collected from remote smart devices and transferred to central server for training. Such centralized-based IDS brought up data security and user privacy concerns. To preserve user privacy, federated learning (FL)-based IDS have recently been suggested. FL keeps training data at the client’s side and distributes an aggregated global model which will be trained locally. However, distributed datasets are usually non Independently and Identically Distributed (non-IID) which can decrease the performance of machine learning models. In this paper, we investigate the efficiency and performance of federated-based IDS under non-IID data settings. We, in this study, investigate a different case of label skew where class distributions are significantly skewed within the same client (as when attacks are recently identified and hence only found in the test dataset). Experimental results show that the efficiency of federated-based IDS is reduced significantly when compared to regular scenarios where attacks in the training and testing datasets are the same. The findings also suggest that missing classes not only affect the performance of the related client but also propagate to other clients. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Centralized learning Class distributions Cyber attacks Federated learning IDS Smart grid

来源：评论

学校读者我要写书评

暂无评论

Faster and Stronger: Unleashing Data Processing Potential through Hardware Heterogeneity

引用

IEEE Internet of Things Journal 2025年第10期12卷 14559-14576页

作者： Wang, Cong Luo, Yang Du, Wenzhuo Wang, Ke Gu, Naijie Yu, Jun Huawei China University of Science and Technology of China Department of Computer Science and Technology Anhui China University of Science and Technology of China Institute of Advanced Technology Anhui China University of Science and Technology of China Department of Automation The Institute of Advanced Technology Anhui China

With the rapid advancement of AI technology, there has been a substantial surge in the need for computational resources. Particularly in deep learning, machine learning, and large-scale data analysis, the processing of extensive datasets necessitates exceptionally high levels of computational efficacy and speed. Conventional homogeneous computing platforms, predominantly reliant on Central Processing Units (CPU), have encountered challenges in meeting the escalating demands for high-performance computing. Consequently, this study advocates for heterogeneous hardware acceleration technology, strategically migrating data operations from CPU to varied hardware components (e.g. GPU, NPU) to enhance processing efficiency and computational performance during the data preprocessing phase. We conducted experiments to evaluate the impact of utilizing hardware heterogeneous acceleration technologies on data processing speed under various workloads and system hardware configurations. By adjusting parameters like batch size and CPU utilization rates, we compared the performance of frameworks that support hardware heterogeneity with popular deep learning frameworks (e.g. PyTorch and TensorFlow) across various hardware configurations and neural network models. Empirical findings demonstrate that the system framework optimized through heterogeneous hardware acceleration technology (the preprocessing speed is improved in all the given experimental environment tests) exhibits commendable universality and superiority in performance. Codes are available at https://***/mindspore-ai/mindspore. © 2014 IEEE.

关键词： Data processing Training Artificial intelligence Data preprocessing Computational modeling Hardware acceleration Data models Graphics processing units Central Processing Unit Tensors

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：