检索结果-内蒙古大学图书馆

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： D.S. Eunice Little Dani K. Rohini Department of Computer Science Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai Tamilnadu India School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai Tamilnadu India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

The growing need for geospatial data analysis highlight's location privacy issues. Although existing technologies such as differential privacy and location obfuscation can be relatively large, inaccurate, and difficult to handle in many applications like urban planning and disaster management, its privacy protection benefits make up for the defect. but in the research, a new privacy-preserving framework based on adaptive differential privacy model, k-anonymity and spatial cloaking is introduced. Based on geographic sensitivity, the system dynamically distributes privacy resources, thus ensuring accuracy in critical regions by choosing quality points from the data. It works to strike a balance between user privacy and system functionality by using genetic algorithm optimization and geographic analysis approaches like DBSCAN. As can be seen from the above comparisons with other systems, the experimental results show that it achieves higher levels of privacy protection than traditional methods with a lower differential privacy parameter (ε = 0.5) and larger k-anonymity k-values (k = 10). Also, the cluster quality improved phenomenally (silhouette coefficient = 0.75) and mean absolute error dropped significantly, both of which help with data utility improvement. The architecture offers a scalable, effective solution that ensures both high privacy protection and accurate representation of essential data.

关键词： Differential privacy Privacy Accuracy Adaptive systems Sensitivity Scalability Urban planning Geospatial analysis Protection Optimization

来源：评论

学校读者我要写书评

暂无评论

Novel Optimized Feature Selection Using Metaheuristics Applied to Physical Benchmark Datasets

引用

computers, Materials & Continua 2023年第2期74卷 4027-4041页

作者： Doaa Sami Khafaga El-Sayed M.El-kenawy Fadwa Alrowais Sunil Kumar Abdelhameed Ibrahim Abdelaziz A.Abdelhamid Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt School of Computer Science University of Petroleum and Energy StudiesDehradun248001India Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia

In data mining and machine learning,feature selection is a critical part of the process of selecting the optimal subset of features based on the target *** are 2n potential feature subsets for every n features in a dataset,making it difficult to pick the best set of features using standard ***,in this research,a new metaheuristics-based feature selection technique based on an adaptive squirrel search optimization algorithm(ASSOA)has been *** using metaheuristics to pick features,it is common for the selection of features to vary across runs,which can lead to *** of this,we used the adaptive squirrel search to balance exploration and exploitation duties more evenly in the optimization *** the selection of the best subset of features,we recommend using the binary ASSOA search strategy we developed *** to the suggested approach,the number of features picked is reduced while maximizing classification accuracy.A ten-feature dataset from the University of California,Irvine(UCI)repository was used to test the proposed method’s performance *** other state-of-the-art approaches,including binary grey wolf optimization(bGWO),binary hybrid grey wolf and particle swarm optimization(bGWO-PSO),bPSO,binary stochastic fractal search(bSFS),binary whale optimization algorithm(bWOA),binary modified grey wolf optimization(bMGWO),binary multiverse optimization(bMVO),binary bowerbird optimization(bSBO),binary hybrid GWO and genetic algorithm 4028 CMC,2023,vol.74,no.2(bGWO-GA),binary firefly algorithm(bFA),and *** results confirm the superiority and effectiveness of the proposed algorithm for solving the problem of feature selection.

关键词： Metaheuristics adaptive squirrel search algorithm optimization methods binary optimizer

来源：评论

学校读者我要写书评

暂无评论

Optimized Dense Neural Network Architecture for Bone Marrow Cancer Classification Using Custom Callbacks

Optimized Dense Neural Network Architecture for Bone Marrow ...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： G. Deepa Y. Kalpana Department of Computer Science VELS Institute of Science Technology and Advanced Studies (VISTAS) Chennai India Department of Computer Application and IT VELS Institute of Science Technology and Advanced Studies (VISTAS) Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Classification of bone marrow cancer is a crucial step in the analysis of several hematological cancers, such as multiple myeloma and leukemia. This study shows better dense neural network (DNN) architecture for significant the variation among the five main types of bone marrow cells includes lymphocytes, myelocytes, band neutrophils, and plasma cells. To find and diagnose bone marrow cancers like multiple myeloma, acute myeloid leukemia (AML), and acute lymphoblastic leukemia (ALL) early on, it is important to be able to accurately identify these cell types. The suggested DNN model uses unique callbacks to optimize training, avoid overfitting, and guarantee faster convergence. These callbacks include learning rate scheduling, early pausing, and dynamic weight modifications. The system preprocesses the high-resolution bone marrow image database to enhance contrast, adapt to fluctuations in illumination, and utilize dense layers for cell classification and convolutional layers for feature extraction. After extensive hyperparameter tuning, a model that classified these five categories of bone marrow cells obtained an overall accuracy rate of 95%. In terms of accuracy, recall, and F1 scores, the model performs better than conventional machine learning techniques while retaining computing economy. The model is able to increase training times without sacrificing classification performance by incorporating custom callbacks. With its enormous clinical application potential, our improved DNN architecture offers pathologists a dependable and effective tool for accurately classifying bone marrow cells. By improving bone marrow cancer diagnosis accuracy, this approach can improve patient care and treatment results.

关键词： Training Adaptation models Accuracy Computational modeling Neural networks Leukemia Cells (biology) computer architecture Bones Overfitting

来源：评论

学校读者我要写书评

暂无评论

A Novel Preprocessing Technique to Aid the Detection of Infected Areas of CT Images in COVID-19 Patients Artificial Intelligence (AI) for Communication Systems

A Novel Preprocessing Technique to Aid the Detection of Infe...

引用

Trends in Quantum computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： J. Kalaivani A. S. Arunachalam R. Gobinath Department of Computer Science School of Computing Sciences Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai India Department of Computer Science Christ University Bengaluru India

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

An innovative preprocessing method for discerning infected areas in CT images of COVID-19 is described in this abstract. The methodology being suggested exploits the capabilities of artificial intelligence (AI) to improve disease detection communication systems. By employing sophisticated AI algorithms to preprocess CT images, the method seeks to increase the precision and effectiveness of COVID-19-associated area detection. The incorporation of artificial intelligence (AI) into communication systems facilitates enhanced image analysis, resulting in improved diagnostic capabilities and treatment strategizing. The study's findings demonstrate the potential of preprocessing techniques powered by artificial intelligence in augmenting communication systems with the aim of enhancing healthcare outcomes.

关键词： COVID-19 Quantum computing Communication systems Computed tomography Perturbation methods Noise Refining

来源：评论

学校读者我要写书评

暂无评论

Product Reviews Based Sentimental Analysis by Feature Extraction and Classification Using Machine Learning Algorithm

Product Reviews Based Sentimental Analysis by Feature Extrac...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： A.S. Sridhar S. Nagasundaram Department of Computer Science School of Computing Sciences Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai Tamil Nadu India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Sentiment analysis and opinion mining are two of the most popular domains for evaluating and extracting insights from text data from various sources, like Facebook, Twitter, Amazon, and so on. It is essential for giving companies the ability to actively work on refining their company plans and thoroughly understand what customers have to say about their offerings. This research proposes novel technique in product review based sentimental analysis by online reviews data feature extraction with classification using machine learning model. here the input has been collected as online review data and processed for noise removal and normalization. Then, this data features are extracted and classified using graph recurrent component analysis with support Bayesian fuzzy neural network (GRCA-SBFNN) for detection of the user sentiment for the reviewed product. the experimental analysis has been carried out for various online product review dataset in terms of training accuracy, average precision, area under the curve (AUC), F-1 score and recall. The proposed technique Training accuracy 98%, Average precision 97%, AUC 91%,Recall 96%, F-1 SCORE 92%.

关键词： Training Sentiment analysis Analytical models Reviews Social networking (online) Machine learning Companies Feature extraction Fuzzy neural networks Data mining

来源：评论

学校读者我要写书评

暂无评论

Analysing the Quality and Management of Data in Big Data

Analysing the Quality and Management of Data in Big Data

引用

Distributed computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Pratheesh R V. Divya School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

Big data analytics delves into these immense datasets to reveal hidden patterns and correlations, yet its pervasive use raises substantial security and privacy concerns. This article centers on the specific issues concerning privacy and security within the realm of big data, distinguishing between these concerns and outlining their distinct requirements. The focus is on various privacy strategies, including L-diversity, k-anonymity, HyBrEx, and T-closeness, examining their practical applications in diverse business contexts. Privacy protection methods have surfaced throughout various stages of the big data life cycle, aiming to ensure privacy during data creation, retention, and handling. This paper provides an extensive review of these privacy mechanisms while addressing the challenges encountered by current approaches. As the extended comprehensive study is experimented with features extraction techniques such as Principle component analysis (PCA), Independent component analysis (ICA), Linear discriminant analysis(LDA) the evaluated performance in terms of accuracy achieved with 98%, 99% and 95% respectively.

关键词： Privacy Differential privacy Technological innovation Shape Reviews Big Data Security

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of RPL Protocol Under Decreased and Increased Rank Attacks: A Focus on Smart Home Use-Case

引用

SN computer science 2023年第4期4卷 329页

作者： Bang, Ankur Rao, Udai Pratap Knowledge Associate Centre for Development of Advanced Computing (C-DAC) Maharashtra Mumbai 400049 India Computer Science and Engineering Department National Institute of Technology Bihar Patna 800005 India

The rank value of a node in Routing Protocol for Low Power and Lossy Networks (RPL) plays a significant role in preventing loops and route optimization. Advertising a fake rank value creates a false topology and can degrade network performance to a great extent. This manuscript aims to study the effects of increased and decreased variants of the rank attack on the RPL performance. We consider a smart home network topology to evaluate the RPL performance, and the simulation experiments are performed using the Cooja simulator. Through this study, we portray a rational analysis and discuss how the network performance can be degraded by each variant of the rank attack and the position of the attacker node in the network topology. The simulation results obtained in our work demonstrate how each variant of the rank attack can disrupt the default RPL working. We notice significant effects of both the studied rank attacks on the crucial parameters like packet overhead, average inter-packet time, packet delivery ratio and average power consumption. Researchers working in this field can take advantage of our research findings and extend their study to develop new defence mechanisms against these attacks. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： IoT Performance evaluation Rank attack RPL Smart home

来源：评论

学校读者我要写书评

暂无评论

An Integrated Algorithm for Load Balancing Discrepancies in Cloud computing Using Weighted Least Connection

An Integrated Algorithm for Load Balancing Discrepancies in ...

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： D. Sathiya Priya S. Perumal Department of Computer Science School of Computing Sciences Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai Tamil Nadu India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Cloud computing is expanding faster than anticipated; hence, load balancing must be done effectively. Conventional methods like Round Robin and static prioritization tend to struggle under dynamic demand, resulting in resource hoarding and headaches from bottlenecking. To avoid these limitations, the proposed Weighted Least Connection (WLC), which introduces manipulation of server weights dynamically, where server weight is recorrected based on live load metrics. It comprises adaptive weight adjustments, load checking in real time and task allocation based on server capacity to improve resilience and scalability together. The comparative analysis shows that WLC system reduces latency up to 25% and improved resource utilization across the servers by (41.67%). Medium and large task times also show an improvement of 33.33%-time savings for completion of a task. These highlights the ability of WLC in balancing cloud environments, and dynamic load balancing techniques as an alternative to static load balancing methods.

关键词： Cloud computing Machine learning algorithms Heuristic algorithms Load management Prediction algorithms Dynamic scheduling Real-time systems Servers Resource management Weighted sum model

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

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

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

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

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

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.

关键词： Support vector machines Osteoporosis Accuracy Statistical analysis Computational modeling Predictive models Nearest neighbor methods Data models Risk management Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT 30

Benchmarking Large Language Models for Persian: A Preliminar...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Abaskohi, Amirhossein Baruni, Sara Masoudi, Mostafa Abbasi, Nesa Babalou, Mohammad Hadi Edalat, Ali Kamahi, Sepehr Sani, Samin Mahdizadeh Naghavian, Nikoo Namazifard, Danial Sadeghi, Pouya Yaghoobzadeh, Yadollah Computer Science Department University of British Columbia Vancouver Canada School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Tehran Institute for Advanced Studies Khatam University Tehran Iran

ISBN: (纸本)9782493814104

This paper explores the efficacy of large language models (LLMs) for Persian. While ChatGPT and consequent LLMs have shown remarkable performance in English, their efficiency for more low-resource languages remains an open question. We present the first comprehensive benchmarking study of LLMs across diverse Persian language tasks. Our primary focus is on GPT-3.5-turbo, but we also include GPT-4 and OpenChat-3.5 to provide a more holistic evaluation. Our assessment encompasses a diverse set of tasks categorized into classic, reasoning, and knowledge-based domains. To enable a thorough comparison, we evaluate LLMs against existing task-specific fine-tuned models. Given the limited availability of Persian datasets for reasoning tasks, we introduce two new benchmarks: one based on elementary school math questions and another derived from the entrance exams for 7th and 10th grades. Our findings reveal that while LLMs, especially GPT-4, excel in tasks requiring reasoning abilities and a broad understanding of general knowledge, they often lag behind smaller pretrained models fine-tuned specifically for particular tasks. Additionally, we observe improved performance when test sets are translated to English before inputting them into GPT-3.5. These results highlight the significant potential for enhancing LLM performance in the Persian language. This is particularly noteworthy due to the unique attributes of Persian, including its distinct alphabet and writing styles. We have made our codes, prompts, and data available here: https://***/Ipouyall/Benchmarking_ChatGPT_for_Persian. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Benchmarking

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：