检索结果-内蒙古大学图书馆

1st International Conference on Innovative engineering sciences and Technological Research, ICIESTR 2024

作者： Alam, Shahid Altiparmak, Zeynep Adana Alparslan Turkes Science and Technology University Department of Computer Engineering Adana Turkey

ISBN: (纸本)9798350348637

In cyber forensics, one of the main challenges of file fragment classification is the proliferation of file formats. This leads to a multinomial classification problem that aggravates the class imbalance problem in classifying file fragments. In real life, most of the data across the classes is always imbalanced. For a successful classification of file fragments, we need to solve both of these problems. In this paper, we take a step towards optimizing file fragment classification by mitigating the class imbalance problem. This also helps solve the multinomial classification problem. Oversampling and Undersampling are two popular techniques to improve the performance of a classifier in the presence of imbalanced data. They both have their advantages and disadvantages. We combine these two techniques and propose a hybrid model to mitigate the class imbalance problem and optimize the classification of imbalanced file fragment data. This hybrid model develops a better class separation by having a clear and concise lower and upper boundary using class clusters of the nearest neighbors and hence also improves the overfitting of the classes. For evaluating our model, we extracted 47,482 samples (fragments) belonging to twenty file types (classes) from a publicly available standardized dataset for cyber forensics research. When compared with state-of-the-art research works, the proposed model produces better results. © 2024 IEEE.

关键词： computer forensics

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Strategic Sales Forecasting in Retail Chains

Machine Learning for Strategic Sales Forecasting in Retail C...

引用

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Rajaram, Tharanimathi Udhayamoorthi, M. Department of Computer Science and Engineering Sri Krishna College of Technology Coimbatore641042 India

ISBN: (纸本)9798331510299

Sales of an individual item record maintained by supermarket chains/big retailers like Big Mart help in estimating consumer demand and thereby enable them to do effective inventory management. Through the analysis of data stored in the data warehouses, they access the anomalies and trends informing decision-making processes. This will be invaluable information to the retailers, in this case Big Mart, in predicting the future sales volume using machine learning techniques. A predictive model was developed utilizing XGBoost, Linear Regression, Logistic Regression, and SVM techniques to forecast sales for businesses like Big Mart. It was found that this model outperforms existing ones, providing more accurate sales predictions and enabling better inventory management decisions. © 2024 IEEE.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Potential: A Review of Digital Twins and Integration with Emerging Technologies 1

Unlocking the Potential: A Review of Digital Twins and Integ...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Dinesh Babu, V. Geetha, S.K. Aneeshkumar, M. Revathi, S. Arulprakash Arulprakash, P. Karpagam Institute of Technology Department of Information Technology Coimbatore India Department of Computer Science and Engineering Coimbatore India Arjun Collge of Technology Department of Artificial Intelligence and Data Science Thamaraikulam India Erode Sengunthar Engineering College Department of Computer Science and Engineering Erode India Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350359756

The Digital Twin (DT) is primarily used to digitally represent a physical object, process, or service. Simply put, DT is a clone representation of a physical object in the real world, such as wind farms, objects like a building or even an entire city. The key uses of technology are to collaborate, train, and simulate processes or products. The results of DT vary greatly depending on the sector and application, but a few key advantages include reducing costs and risks before investing in real-world resources and helping to enhance products or processes over their entire life cycles. The integration of the digital Twin with so many various industries, including manufacturing, healthcare, and the growth of urban and rural areas, has enhanced the prominence of this emerging technology. This paper's major goal is to identify ongoing initiatives by numerous engineering fields to apply digital twin technology for sustainable development. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Sensor Automation for Industrial Applications and Prediction of Energy Level for Home Appliances Using Machine Learning Algorithm 9

Sensor Automation for Industrial Applications and Prediction...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Duraisamy, Premkumar Natarajan, Yuvaraj Selvakumari Jeya, I Jasmine Niranjani, V. KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Hindusthan College of Engineering and Technology Department of Information Technology Coimbatore India Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350397376

In recent years wireless sensor networks have helped with automation in many industry domains. Wireless technology cuts cable costs, deployment time and information to transfer and process from source to destination. To make good intelligent and highly automated systems, sensors are crucial. They make it possible to detect, analyze, measure, and process a variety of alterations that occur in industrial equipment's location, length, height, appearance, displacement, etc. This paper described the industrial standardization of different WSN protocols like Zig-Bee, Wireless HART, UWB, IETF 6LowPAN, ISA100, Bluetooth and Wi-Fi. The work represented a few applications of WSNs in industry and its implementation challenges like safety, security, and availability. The work collected the energy consumption data of different home appliances. We applied the LightGBM machine learning algorithm to find a better energy consumption and prediction result. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Microstrip Patch Antenna with an Inverted T-Type Notch in the Partial Ground for Breast Cancer Detections

引用

computer Modeling in engineering & sciences 2024年第2期138卷 1301-1322页

作者： Nure Alam Chowdhury Lulu Wang Md Shazzadul Islam Linxia Gu Mehmet Kaya Department of Biomedical Engineering and Science Florida Institute of TechnologyMelbourneFL 32901USA Biomedical Device Innovation Center Shenzhen Technology UniversityShenzhen518118China Department of Electrical and Computer Engineering International Islamic University MalaysiaJalan GombakSelangor53100Malaysia

This study designs a microstrip patch antenna with an inverted T-type notch in the partial ground to detect tumorcells inside the human *** size of the current antenna is small enough(18mm×21mm×1.6mm)todistribute around the breast *** operating frequency has been observed from6–14GHzwith a minimumreturn loss of−61.18 dB and themaximumgain of current proposed antenna is 5.8 dBiwhich is flexiblewith respectto the size of *** the distribution of eight antennas around the breast phantom,the return loss curveswere observed in the presence and absence of tumor cells inside the breast phantom,and these observations showa sharp difference between the presence and absence of tumor *** simulated results show that this proposedantenna is suitable for early detection of cancerous cells inside the breast.

关键词： Antenna microwave wideband cancer breast phantom tumor detection

来源：评论

学校读者我要写书评

暂无评论

TROI: Cross-Subject Pretraining with Sparse Voxel Selection for Enhanced fMRI Visual Decoding

TROI: Cross-Subject Pretraining with Sparse Voxel Selection ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Ziyu Pan, Tengyu Li, Zhenyu Wu, Ji Li, Xiuxing Wang, Jianyong Department of Computer Science and Technology Tsinghua University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9798350368741

fMRI (functional Magnetic Resonance Imaging) visual decoding involves decoding the original image from brain signals elicited by visual stimuli. This often relies on manually labeled ROIs (Regions of Interest) to select brain voxels. However, these ROIs can contain redundant information and noise, reducing decoding performance. Additionally, the lack of automated ROI labeling methods hinders the practical application of fMRI visual decoding technology, especially for new subjects. This work presents TROI (Trainable Region of Interest), a novel two-stage, data-driven ROI labeling method for cross-subject fMRI decoding tasks, particularly when subject samples are limited. TROI leverages labeled ROIs in the dataset to pretrain an image decoding backbone on a cross-subject dataset, enabling efficient optimization of the input layer for new subjects without retraining the entire model from scratch. In the first stage, we introduce a voxel selection method that combines sparse mask training and low-pass filtering to quickly generate the voxel mask and determine input layer dimensions. In the second stage, we apply a learning rate rewinding strategy to fine-tune the input layer for downstream tasks. Experimental results on the same small sample dataset as the baseline method for brain visual retrieval and reconstruction tasks show that our voxel selection method surpasses the state-of-the-art method MindEye2 with an annotated ROI mask. © 2025 IEEE.

关键词： Computational neuroscience multi-modal learning region of interest analysis small sample learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced QoS Optimization of Opportunistic Networks using Decision Tree

Enhanced QoS Optimization of Opportunistic Networks using De...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Mathur, Mansi Sawanni, Ritu Kumar, Anuj Jain, Ayushi Pal, Atul Kumar Manwal, Manika Department Of Information Technology New Delhi India Graphic Era Hill University Department Of Computer Science And Engineering Uttarakhand Dehradun India Department Of Computer Science And Engineering Lucknow Kannauj India Graphic Era Deemed To Be University Department Of Computer Science And Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350366846

Opportunistic networks are a type of dynamic wireless network that lack a fixed infrastructure and rely on intermittent connections between nodes to facilitate communication. Quality of Service (QoS) is an essential factor for the efficient operation of opportunistic networks, as it ensures that data is delivered in a timely and reliable manner. This paper proposes an enhanced QoS optimization approach for opportunistic networks using a Decision Tree algorithm. The algorithm considers various network parameters such as node mobility, data transmission rate, and available storage capacity to predict the optimal routing path for data transmission. The Decision Tree algorithm uses a classification technique to build a model based on historical data to identify the most suitable routing path for each data transmission. This approach allows for dynamic adaptation to changing network conditions, improving the overall performance and QoS of the opportunistic network. By incorporating the Decision Tree algorithm into the routing decisions of the opportunistic network, we can achieve better QoS optimization than traditional routing protocols. Our experimental results show that the proposed approach outperforms existing routing protocols regarding data delivery ratio, end-to-end delay, and energy consumption, making it a promising solution for enhancing QoS in opportunistic networks. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A nonlinear recurrent encoders for early detection of strep throat infection to prevent acute rheumatic fever

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第4期15卷 2201-2213页

作者： Kumar, K. Antony Belinda, M. J. Carmel Mary Kumar, V. Dhilip Rajan, Jerlin Francy Arif, Muhammad Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Medical Surgical Nursing Dr. Jeyashekaran Medical Trust Nagercoil India Superior University Lahore Pakistan

Rheumatic Fever or Acute Rheumatic Fever (RF) and Rheumatic Heart Disease (RHD) are commonly suffered by people of all ages around the world. RF usually begins with strep throat infections, skin problems, joint pain etc. Clinical tests and medical informatics are useful to save patients from Streptococcus Group-A bacteria using medical treatments and detection mechanism. Clinical data based statistical analysis approaches assist medical diagnosis model in detecting diseases based on standard decision. Standard decision making frameworks are effective when using these approaches. Nevertheless, existing mechanisms cannot detect or predict the incidence of strep throat infection at an earlier stage based on unclear datasets or complex datasets. The recent computational healthcare informatics systems use Machine Learning (ML) and Deep Learning (DL) techniques, but they are not sufficient in terms of their field integration. The proposed work implements a nonlinear recurrent auto encoder using complex data evaluation procedures to accurately detect and predict the strep throat infections accurately. In this regard, the proposed model builds on the technical features of Denoised Variational Stacked Auto Encoders (DVSE), nonlinear regression computations and Long Shot Term Memory (LSTM) to perform recurrent data analysis practices. Compared with the existing techniques such as Blood Serum Content Analysis model (BSCA), Smartphone based Strep Throat Detection (SSTD) approach and Logistic Regression Based RF Detection approach (LRRF), the multi-level medical data evaluation (throat images and blood samples) provides 10–15% more accuracy for strep throat detection. As shown in the implementation section, the proposed nonlinear recurrent system has the potential to detect strep throat infections early. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Generative Adversarial Network for Inverse Kinematics of Self-Assembly Robotic Arm Based on the Depth Sensor

引用

IEEE Sensors Journal 2023年第1期23卷 758-765页

作者： Hsieh, Yi-Zeng Xu, Fu-Xiong Lin, Shih-Syun National Taiwan University of Science and Technology Department of Electrical Engineering Taipei City106335 Taiwan National Taiwan Ocean University Department of Computer Science and Engineering Keelung City202301 Taiwan

In this study, we propose a new deep convolutional generative adversarial kinematics network (DCGAKN) to establish inverse kinematics of self-assembly robotic arm. We design that the robot system uses a depth sensor detecting an object by you only look once v4 (YOLOv4) algorithm, and then, our proposed DCGAKN is with generator and discriminator of adversarial evolution training inverse kinematics model for controlling self-assembly robotic arm to solve the limited solution space to be more adaptive in the dynamic environment. The following are advancements of our proposed method: 1) generator neural network is trained by few-shot training data to control the self-assembly robotic arm to achieve high-accuracy position;2) generator is evaluated with discriminator not only depending on training data but also on adaptive evolutionary;3) the self-assembly robotic arm is like humanoid arm not traditional robotic arm structure and it is easy for self-assembly model to build inverse kinematics without computing inverse kinematics matrix;4) the object is detected by the depth information based on YOLOv4;and 5) through generator evolutionary, the activity range of robotic arm is not limited with training data range. The proposed DCGAKN is compared with convolutional neural network (CNN) and deep neural network (DNN) that the accuracy rate and distance error achieve 87% and 1.26 cm, respectively. The source code of this work is at: https://***/YiZengHsieh/DCGAKN. © 2001-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A High-Quality Adaptive Video Reconstruction Optimization Method Based on Compressed Sensing

引用

computer Modeling in engineering & sciences 2023年第10期137卷 363-383页

作者： Yanjun Zhang Yongqiang He Jingbo Zhang Yaru Zhao Zhihua Cui Wensheng Zhang School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan030024China Department of Big Data and Intelligent Engineering Shanxi Institute of TechnologyYangquan045000China School of Computer Science Beijing University of TechnologyBeijing100124China The Institute of Automation Chinese Academy of Sciences(CAS)Beijing100049China

The video compression sensing method based onmulti hypothesis has attracted extensive attention in the research of video codec with limited ***,the formation of high-quality prediction blocks in the multi hypothesis prediction stage is a challenging *** resolve this problem,this paper constructs a novel compressed sensing-based high-quality adaptive video reconstruction *** includes the optimization of prediction blocks(OPBS),the selection of searchwindows and the use of neighborhood ***,the OPBS consists of two parts:the selection of blocks and the optimization of prediction *** combine the high-quality optimization reconstruction of foreground block with the residual reconstruction of the background block to improve the overall reconstruction effect of the video *** addition,most of the existing methods based on predictive residual reconstruction ignore the impact of search windows and reference frames on ***,Block-level search window(BSW)is constructed to cover the position of the optimal hypothesis block as much as *** maximize the availability of reference frames,Nearby reference frame information(NRFI)is designed to reconstruct the current *** proposed method effectively suppresses the influence of the fluctuation of the prediction block on reconstruction and improves the reconstruction *** results showthat the proposed compressed sensing-based high-quality adaptive video reconstruction optimization method significantly improves the reconstruction performance in both objective and supervisor quality.

关键词： Compressed sensing OPBS block-level search window nearby reference frame information evolutionary algorithm

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：