检索结果-内蒙古大学图书馆

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Pant, Janmejay Pant, Hitesh Kumar Kotlia, Priyanshi Singh, Devendra Sharma, Vaibhav Kumar Bhatt, Jaishankar Graphic Era Hill University Department of Computer Science and Engineering Bhimtal Campus India Kumaun University Department of Management Studies Uttarakhand Nainital India Amrapali Group of Institutes Department of Computer Applications Uttarakhand Haldwani India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350379945

Time series analysis and forecasting play a crucial role due to their extensive application across various practical domains. Time series data represents a sequential order or collection of data points depicting the values of a variable at regular time intervals. The stock market is widely regarded as one of the most intricate financial systems, comprising numerous components or stocks, whose prices fluctuate significantly over time. Stock market forecasting aims to reveal the trends within the market as they evolve. All investors in the stock market strive to maximize returns on their investments while minimizing associated risks Due to the high sensitivity and rapid changes in stock markets, the primary objective of stock-trend prediction is to devise innovative approaches that can anticipate stocks leading to substantial profits. A statistical model capable of predicting Indian stock prices will be constructed using time series data from the Indian stock market. In our study, we utilize daily stock price data from a prominent company listed on the National Stock Exchange (NSE) of India. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Journal of Reliable Intelligent Environments 2023年第4期9卷 369-370页

作者： Augusto, Juan Carlos Coronato, Antonio Research Group on Development of Intelligent Environments Department of Computer Science Middlesex University London United Kingdom Università Giustino Fortunato Benevento Italy

来源：评论

学校读者我要写书评

暂无评论

Particle Swarm Optimizer Guided Active Contour Model for Lung Image Segmentation 1

Particle Swarm Optimizer Guided Active Contour Model for Lun...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Biradar, Ashwini Vishwanathrao Pancholi, Priti Vijaykumar Bhosale, Jyoti Dinkar Pawar, Bharat Madhavrao Suryawanshi, Ujwala V M.S.Bidve Engineering College Computer Engineering Department Maharashtra Latur India Vilasrao Deshmukh Foundations Group of Institutions Computer Engineering Department Maharashtra Latur India Rajarshi Shahu Junior Science College Computer Department Maharashtra Latur India

ISBN: (纸本)9798331518943

Snakes, also known as active contour models, are widely used in a variety of applications, including Detecting object boundaries, segmenting images, tracking objects, and classification based on energy minimization. While standard optimization techniques can be used to achieve energy minimization, more recently, techniques based on evolutionary algorithms inspired by nature have been created. Particle swarm optimization (PSO) is one such evolutionary method that has been widely applied in active contours. Conventional PSO provides accurate curve recognition in the object border because it converges quickly and is readily took in a local minimum. The suggested PSOGACM has each control point in the snake and also has a swarm to assign in it. Subsequently, the swarms exchange information with one another to jointly seek for their optimal spots. The active contour model considerably improves the PSO-based search process's performance. The outcomes of the experiments show that the suggested strategy is more effective than traditional methods. The proposed system has accuracy of 91.15%, sensitivity of 89.20%, and precision of 88.23% is more effective and more accurate. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Static Analysis Techniques for Fixing Software Defects in MPI-Based Parallel Programs

引用

computers, Materials & Continua 2024年第5期79卷 3139-3173页

作者： Norah Abdullah Al-Johany Sanaa Abdullah Sharaf Fathy Elbouraey Eassa Reem Abdulaziz Alnanih Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Software Engineering and Distributed System Research Group King Abdulaziz UniversityJeddah21589Saudi Arabia

The Message Passing Interface (MPI) is a widely accepted standard for parallel computing on distributed ***, MPI implementations can contain defects that impact the reliability and performance of parallelapplications. Detecting and correcting these defects is crucial, yet there is a lack of published models specificallydesigned for correctingMPI defects. To address this, we propose a model for detecting and correcting MPI defects(DC_MPI), which aims to detect and correct defects in various types of MPI communication, including blockingpoint-to-point (BPTP), nonblocking point-to-point (NBPTP), and collective communication (CC). The defectsaddressed by the DC_MPI model include illegal MPI calls, deadlocks (DL), race conditions (RC), and messagemismatches (MM). To assess the effectiveness of the DC_MPI model, we performed experiments on a datasetconsisting of 40 MPI codes. The results indicate that the model achieved a detection rate of 37 out of 40 codes,resulting in an overall detection accuracy of 92.5%. Additionally, the execution duration of the DC_MPI modelranged from 0.81 to 1.36 s. These findings show that the DC_MPI model is useful in detecting and correctingdefects in MPI implementations, thereby enhancing the reliability and performance of parallel applications. TheDC_MPImodel fills an important research gap and provides a valuable tool for improving the quality ofMPI-basedparallel computing systems.

关键词： High-performance computing parallel computing software engineering software defect message passing interface deadlock

来源：评论

学校读者我要写书评

暂无评论

Pre-trained SAM as data augmentation for image segmentation

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 268-282页

作者： Junjun Wu Yunbo Rao Shaoning Zeng Bob Zhang Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhouChina School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengduChina Pattern Analysis and Machine Intelligence Research Group Department of Computer and Information ScienceUniversity of MacaoMacaoChina

Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the ***,data augmentation mainly involved some simple transformations of ***,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative ***,these methods required a mass of computation of training or *** this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for *** the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved *** this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation *** comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and *** this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,***,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.

关键词： data augmentation image segmentation large model segment anything model

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Federated Relevance Framework for Spatial-Temporal Graph Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2227-2240页

作者： Zhang, Tiehua Liu, Yuze Shen, Zhishu Xu, Rui Chen, Xin Huang, Xiaowei Zheng, Xi Ant Group Shanghai200120 China Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430062 China Macquarie University Department of Computing SydneyNSW2109 Australia

Spatial-temporal data contains rich information and has been widely studied recently due to the rapid development of relevant applications. For instance, medical institutions often use electrodes attached to different parts of a patient to analyse the electroencephalogram data with rich spatial and temporal features for health assessment and disease diagnosis. Existing research has mainly used deep learning techniques such as convolutional neural network (CNN) or recurrent neural network (RNN) to extract spatial-temporal features. Yet, it is challenging to incorporate both inter-dependencies spatial information and dynamic temporal changes simultaneously. In reality, for a model that leverages these spatial-temporal features to fulfil complex prediction tasks, it often requires considerable training data to obtain satisfactory model performance. To address the challenges at hand, we propose an adaptive federated relevance framework called FedRel for spatial-temporal graph learning. After transforming the raw spatial-temporal data into high-quality features, the core Dynamic Inter-Intra Graph (DIIG) module in the framework leverages these features to generate the spatial-temporal graphs capable of capturing both the hidden topological and long-term temporal correlation information. To further enhance the model's generalization ability and performance, while still prioritizing local data privacy, we have incorporated a relevance-driven federated learning module into our framework. This module leverages the diverse data distributions from different participants and applies attentive aggregations of respective models. We then conducted extensive experiments on two real-world spatial-temporal datasets. The results demonstrate the framework's efficacy in spatial-temporal interpretation, collaborative model training, and handling divergent data distributions across various comparison settings. © 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

An effective algorithm for predicting load and dynamic task scheduling in cloud fog architecture for smart homes

引用

International Journal of Cloud Computing 2025年第1期14卷 54-85页

作者： Agrawal, Krishna Kant Kumar, Sujeet Seth, Jitendra Kumar Gupta, Abhishek Kumar Lamba, Sonia School of Computer Science and Engineering Galgotias University Uttar Pradesh Greater Noida India GL Bajaj Institute of Management Uttar Pradesh Greater Noida India Department of Information Technology KIET Group of Institutions Uttar Pradesh Ghaziabad India Department of Information Technology Jagannath International Management School New Delhi India Department of Computer Science ABES Engineering College Uttar Pradesh Ghaziabad India

The need for smart homes with many devices and services continues to rise quickly. With this surge, smart homes need task scheduling and load-prediction algorithms to provide the proper services for the residents. A deep learning-based dynamic job scheduling and load prediction technique for cloud-fog smart homes is proposed in this paper. This algorithm forecasts task arrival rates at each fog node and assigns them to available fog nodes. It dynamically schedules tasks based on fog node workload. Another option is to send non-real-time jobs to the cloud and real-time tasks to the fog layer. This optimises load distribution for performance. Using these task assignee models and features, the program optimises prioritised tasks, scores, network latency, and device resource characteristics. We simulate the algorithm’s performance in various workloads in this part. The proposed algorithms achieved in higher percentile for 93.79% latency, 95.00% throughput, 95.34% response time, 96.28% scalability, 94.20% fault-tolerance, 97.41% scheduling capacity, 91.41% load balancing capacity, and 95.22% priority management. The results indicate that such an algorithm significantly surpasses the conventional task scheduling methods in load balancing and shortens the average task response time. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

VGWO: Variant Grey Wolf Optimizer with High Accuracy and Low Time Complexity

引用

computers, Materials & Continua 2023年第11期77卷 1617-1644页

作者： Junqiang Jiang Zhifang Sun Xiong Jiang Shengjie Jin Yinli Jiang Bo Fan School of Information Science and Engineering Hunan Institute of Science and TechnologyYueyang414006China Department of Computer and Information Science Linköping UniversityLinköping58183Sweden Department of Safety and Quality Hunan Construction Investment GroupChangsha410004China

The grey wolf optimizer(GWO)is a swarm-based intelligence optimization algorithm by simulating the steps of searching,encircling,and attacking prey in the process of wolf *** with its advantages of simple principle and few parameters setting,GWO bears drawbacks such as low solution accuracy and slow convergence speed.A few recent advanced GWOs are proposed to try to overcome these ***,they are either difficult to apply to large-scale problems due to high time complexity or easily lead to early *** solve the abovementioned issues,a high-accuracy variable grey wolf optimizer(VGWO)with low time complexity is proposed in this *** first uses the symmetrical wolf strategy to generate an initial population of individuals to lay the foundation for the global seek of the algorithm,and then inspired by the simulated annealing algorithm and the differential evolution algorithm,a mutation operation for generating a new mutant individual is performed on three wolves which are randomly selected in the current wolf individuals while after each iteration.A vectorized Manhattan distance calculation method is specifically designed to evaluate the probability of selecting the mutant individual based on its status in the current wolf population for the purpose of dynamically balancing global search and fast convergence capability of VGWO.A series of experiments are conducted on 19 benchmark functions from CEC2014 and CEC2020 and three real-world engineering *** 19 benchmark functions,VGWO’s optimization results place first in 80%of comparisons to the state-of-art GWOs and the CEC2020 competition winner.A further evaluation based on the Friedman test,VGWO also outperforms all other algorithms statistically in terms of robustness with a better average ranking value.

关键词： Intelligence optimization algorithm grey wolf optimizer(GWO) manhattan distance symmetric coordinates

来源：评论

学校读者我要写书评

暂无评论

The Societal Implications of False Positives Using Machine Learning 6th

The Societal Implications of False Positives Using Machine L...

引用

6th International Conference on Recent Innovations in Computing, ICRIC 2023

作者： Dubey, Anurag Mishra, Aryan Tayal, Divyansh Yadav, Aarush Jamshed, Aatif Department of IT ABES Engineering College AKTU Lucknow India Department of Computer Science KIET Group of Institutions Delhi-NCR Ghaziabad India

ISBN: (纸本)9789819734412

The article aims to investigate the societal consequences of false positive detection through a systematic review leveraging ML (machine learning) techniques. It seeks to assess the impact of inaccurate detections on various aspects of society, such as healthcare, security, and privacy, to inform better decision-making and policy development. The study employs a comprehensive dataset encompassing diverse sources and topics to train and validate the model's efficacy. Results showcase promising outcomes, indicating that sentiment analysis can effectively contribute to the identification of misleading information. The proposed approach not only demonstrates robust performance in distinguishing between genuine and fake news but also provides insights into the emotional underpinnings of deceptive content. This research contributes to the evolving field of fake news detection, offering a nuanced perspective that aligns sentiment analysis with the imperative of fostering a more informed and resilient information landscape. The purpose of this work is to propose a notion and methods for identifying misinformation. The process of gathering news items and then utilizing SVM (SVM(Support Vector Machine)) to categorize them as either authentic or fake is accomplished through the utilization of ML (machine learning) and natural language-processing processes. Comparing the results of the proposed model with those of the existing models is the purpose of this comparison. With an accuracy rating of 93.6%, the model that was provided is performing efficiently and accurately identifying the outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Parameters of Fluidized Bed Dryer 9

Optimizing the Parameters of Fluidized Bed Dryer

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Soni, Binjal Padhiyar, Jay Ragupathy, A.G. Choudhury, Amitava Bharti, Santosh Pandit Deendayal Energy University Department of Computer Science And Engineering Gandhinagar India Zydus Group Department of Digitalization And Automation Ahmedabad India

ISBN: (纸本)9798350394474

The present study centres on the application of an all-encompassing methodology for optimizing the parameters of Fluidized Bed Dryer (FBD). First, a dataset with various FBD attributes are subjected to Principle Component Analysis (PCA). Subsequently, a variety of regression algorithms, including multiple linear regressors, support vector classifiers, decision trees, random forests, and gradient boosting regressors, are employed to analyze the identified key attributes. These attributes comprise the actual values of inlet air flow, inlet air temperature, exhaust air temperature, loss on drying, product temperature, and total drying time. When it comes to predicting the total drying time, the gradient boosting regressor performs better than others. A novel optimization technique called Bayesian optimization is used to find the optimized values of highly correlated features with the total drying time in order further maximize efficiency. This integrated approach uses both sophisticated machine learning algorithms for predictive modelling and optimization techniques to fine-tune specific parameters that are critical for the Fluidized Bed Dryer. The study's findings provide useful information about enhancing FBDs' overall performance and efficacy, which advances drying processes in a variety of industries. © 2024 IEEE.

关键词： Decision trees

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：