检索结果-内蒙古大学图书馆

Design of ensemble classifier using Statistical Gradient and Dynamic Weight LogitBoost for malicious tumor detection

引用

Journal of Ambient Intelligence and Humanized Computing 2020年第6期12卷 6713-6723页

作者： Subash Chandra Bose, S. Sivanandam, Natarajan Praveen Sundar, P. V. Department of Computer Applications Karpagam Academy of Higher Education Coimbatore India Department of Computer Science School of Informatics Wolaita Soda University Wolaita Soda Addis Ababa Ethiopia Department of Computer Science Adhiparasakthi College of Arts and Science Ranipet India

In medical field, the detection of abnormalities in breast is essential to find earlier stage of breast tumor. Conventional semi-supervised ensemble framework based on the normalized cut algorithm developed and it strongly improves the detection accuracy of the resulting images. However, further development of classification algorithm with minimum computational time and cost, several conventional methods limits the classification of tumor. In this paper, Statistical Gradient and Dynamic Weight based LogitBoost (SG-DWL) Ensemble approach is presented to improve the detection rate of malicious tumor. The key objective of SG-DWL Ensemble approach is to increase the malicious tumor performance with higher accuracy and lesser time consumption. The Statistical Gradient Boosting model is introduced as a numerical technique to improve feature set identification in test images. The proposed feature ensemble is formed by concatenating the probability density function, gradient vector and powerful algorithmic framework for feature selection with the best fit feature set is selected. Dynamic Weight based LogitBoost classifier (DW-LC) is applied for malicious tumor detection. This Dynamic Weight based LogitBoost classifier uses Hoeffding tree to achieve high malicious tumor detection rate by reducing the computational complexity involved in the classification of benign and malignant tumor. The performance of the proposed approach is evaluated by comparing it with the existing approaches, and the results improve the classification accuracy with minimum time period for malicious tumor detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Time-varying Graph Signals via Sobolev Smoothness

arXiv

引用

arXiv 2022年

作者： Giraldo Zuluaga, Jhony Heriberto Mahmood, Arif Garcia-Garcia, Belmar Thanou, Dorina Bouwmans, Thierry The laboratoire MIA Mathématiques Image et Applications La Rochelle Université La Rochelle17000 France The Department of Computer Science Information Technology University Lahore48730 Pakistan The Center for Intelligent Systems EPFL Lausanne1015 Switzerland

Graph Signal Processing (GSP) is an emerging research field that extends the concepts of digital signal processing to graphs. GSP has numerous applications in different areas such as sensor networks, machine learning, and image processing. The sampling and reconstruction of static graph signals have played a central role in GSP. However, many real-world graph signals are inherently time-varying and the smoothness of the temporal differences of such graph signals may be used as a prior assumption. In the current work, we assume that the temporal differences of graph signals are smooth, and we introduce a novel algorithm based on the extension of a Sobolev smoothness function for the reconstruction of time-varying graph signals from discrete samples. We explore some theoretical aspects of the convergence rate of our Time-varying Graph signal Reconstruction via Sobolev Smoothness (GraphTRSS) algorithm by studying the condition number of the Hessian associated with our optimization problem. Our algorithm has the advantage of converging faster than other methods that are based on Laplacian operators without requiring expensive eigenvalue decomposition or matrix inversions. The proposed GraphTRSS is evaluated on several datasets including two COVID-19 datasets and it has outperformed many existing state-of-the-art methods for time-varying graph signal reconstruction. GraphTRSS has also shown excellent performance on two environmental datasets for the recovery of particulate matter and sea surface temperature signals. Copyright © 2022, The Authors. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A scalable time-division-based emergency messages broadcast scheme for connected and autonomous vehicles in urban environment

引用

Vehicular Communications 2022年 38卷

作者： Guesmia, Salah Semchedine, Fouzi Djahel, Soufiene Laboratory of Informatics and its Applications of M'sila (LIAM) Faculty of Mathematics and Computer Science University of M'sila M'sila 28000 Algeria Mechatronics Laboratory - E1764200 Optics and Precision Mechanics Institute University of Setif 1 Setif 19000 Algeria Department of Computer Science University of Huddersfield Huddersfield United Kingdom

Connected and Autonomous Vehicles (CAVs) technology promises to revolutionize the transportation sector by solving many safety and traffic efficiency challenges while significantly enhancing passengers' and drivers' comfort. Most of these applications are built upon multi-hop broadcast of information among vehicles, leading to an increased contention and thus higher collision probability due to the limited bandwidth available for vehicular communications. In this paper, we propose a novel Time-Division-based Broadcast (TDB) scheme to mitigate interferences originating from hidden nodes (i.e., vehicles) to meet the stringent safety applications requirements. Then, we use this broadcast scheme as a basis for designing a new efficient and scalable protocol for emergency messages dissemination in urban vehicular networks (UV-TDB: an Urban, Vehicular and Time-Division-based Broadcast protocol). The simulation experiments show that UV-TDB significantly improves the performance of multi-hop broadcast and outperforms two state of the art protocols in terms of the achieved reduction in broadcast overhead (up to 77.9%), packet collisions ratio (up to 93.5%), interference rate (up to 43.5%) and increase in message reception rate (up to 337.7%). The results highlight also that UV-TDB adapts better to varying levels of vehicle density, making it more scalable. © 2022

关键词： Connected and autonomous vehicles (CAVs) Intelligent transportation systems (ITS) Multi-hop broadcasting Safety applications Smart cities Urban areas

来源：评论

学校读者我要写书评

暂无评论

Special issue on the 100^(th) anniversary of Xiamen University

引用

Light(science & applications) 2021年第10期10卷 1812-1813页

作者： Junyong Kang Minghui Hong Zhongqun Tian Engineering Research Center of Micro-nano Optoelectronic Materials and Devices Ministry of EducationFujian Key Laboratory of Semiconductor Materials and ApplicationsCI center for OSEDCollege of Physical Science and Technology361005 XiamenChina Department of Electrical and Computer Engineering National University of Singapore4 Engineering Drive 3117576 SingaporeSingapore State Key Laboratory of Physical Chemistry of Solid Surfaces Collaborative Innovation Center of Chemistry for Energy MaterialsCollege of Chemistry and Chemical EngineeringXiamen University361005 XiamenChina

This special issue is devoted to the celebration of the century anniversary of Xiamen University(XMU)(6 April 2021)and the establishment of the LSA Editorial Office in Xiamen(3 July 2021),a collection to highlight the recent exciting research works performed in XMU or by XMU alumni,from all aspects of optics and photonics,including basic,applied and engineering research and *** guest editors are three XMU alumni who are active researchers in these areas:Professor Minghui Hong from National University of Singapore,Professor Zhongqun Tian and Professor Junyong Kang from XMU.

关键词： Xiamen anniversary devoted

来源：评论

学校读者我要写书评

暂无评论

Thoughts on Non-IID Data Impact in Healthcare with Federated Learning Medical Blockchain

Thoughts on Non-IID Data Impact in Healthcare with Federated...

引用

IEEE International Conference on Cognitive Machine Intelligence (CogMI)

作者： Zon-Yin Shae Kun-Yi Chen Chi-Yu Chang Yuan-Yu Tsai Che-Yi Chou William I. Baskett Chi-Ren Shyu Jeffrey J.P. Tsai Department of Computer Science and Information Engineering Asia University Taichung Taiwan Department of M-Commerce and Multimedia Applications Asia University Taichung Taiwan Division of Nephrology Asia University Hospital Taichung Taiwan Institute for Data Science and Informatics University of Missouri Columbia USA Department of Bioinformatics and Medical Engineering Asia University Taichung Taiwan

We share the common hypothesis/belief that the more aggregated good quality training data, the better the performance that can be attained by the resulting Artificial Intelligence (AI) model. However, this common belief, in general, is not true in the medical area, since healthcare data sets sourced from different hospitals are often not identically distributed (Non-IID). This imposes severe technical challenges for effectively aggregating the individual hospital data sets together. In this vision paper, instead of offering complete solutions, we will discuss some questions and food for thought with the goal of aiding effective data aggregation and improving federated learning (FL) AI model performance: (1) benchmark and measure the Non-IID degree of medical data sets. (2) include the Non-IID degree metrics in the FL data aggregation mechanism. (3) search for the optimal global model creation strategy among a group of many medical data sets. (4) investigate FL performance better than the centralized learning. This paper will discuss these questions by outlining a visionary approach for exploring a medical blockchain FL mechanism to effectively aggregate medical data across multiple healthcare systems to serve large populations with broad demographics.

关键词： Measurement Federated learning Hospitals Sociology Training data Data aggregation Data models

来源：评论

学校读者我要写书评

暂无评论

Exploring structural and optical properties of iodine-doped TiO2 nanoparticles in Rhodamine-B dye degradation: Experimental and theoretical investigation

引用

Chemosphere 2024年 364卷 143183页

作者： Raguram, T. Rajni, K.S. Kanchana, D. José, Solar-Encinas Granados-Tavera, Kevin Cárdenas-Jirón, Gloria Shobana, M. Meher, S.R. Centre for Applied Nanomaterials Chennai Institute of Technology Tamil Nadu Chennai600 069 India Department of Sciences Amrita School of Physical Sciences Amrita Vishwa Vidyapeetham Coimbatore India Functional Materials Laboratory Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India Department of Computer Science and Applications SRM Institute of Science and Technology Ramapuram Campus Tamil Nadu Chennai India Santiago Chile Facultad de Ciencias Básicas Universidad de la Amazonia Florencia Colombia Department of Physics School of Advanced Sciences Vellore Institute of Technology Vellore632 014 India

Energy conversion and pollutant degradation are critical for advancing sustainable technologies, yet they often encounter challenges related to charge recombination and efficiency limitations. This study explores iodine-doped TiO2 nanoparticles as a potential solution for enhancing both energy conversion and pollutant degradation. The nanoparticles were synthesized via the sol-gel method with varying iodine precursor concentrations (0.025–0.1 M) and were characterized for their structural, compositional, and optical properties, particularly in relation to their photocatalytic performance in Rhodamine-B dye degradation. X-ray diffraction confirmed a tetragonal anatase crystal structure, with the average crystallite size decreasing from 10.06 nm to 8.82 nm with increase in iodine concentration. Selected area electron diffraction patterns verified the polycrystalline nature of the nanoparticles. Dynamic light scattering analysis showed hydrodynamic radii ranging from 95 to 125 nm. Fourier-transform infrared spectroscopy identified metal-oxygen vibrations at 441 cm⁻1, and electron microscopy confirmed the spherical morphology of the nanoparticles. Elemental analysis detected the presence of Ti, O, and I in the samples. Diffuse reflectance spectroscopy indicated the optical absorption edges for the doped samples in the visible region from which the corresponding band gap values were deduced. Photoluminescence spectroscopy revealed that the sample with 0.1 M iodine exhibit the lowest emission intensity, suggesting reduced charge recombination. Notably, 0.1 M iodine doped TiO2 samples demonstrated the highest photocatalytic efficiency, achieving 82.36% degradation of Rhodamine-B dye within 140 min under visible light. Additionally, ab-initio density functional theory calculations were performed to investigate the structural, optical, and adsorption properties of TiO2, iodine-doped TiO2, Rhodamine-B, and their composites, providing further insight into the enhanced photocat

关键词： Sol-gel process

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model

arXiv

引用

arXiv 2022年

作者： Qi, Zhenting Zhu, Ruike Fu, Zheyu Chai, Wenhao Kindratenko, Volodymyr ZJU-UIUC Institute Zhejiang University Haining China Department of Computer Science University of Illinois at Urbana-Champaign UrbanaIL United States National Center for Supercomputing Applications University of Illinois at Urbana-Champaign UrbanaIL United States

Fight detection in videos is an emerging deep learning application with today’s prevalence of surveillance systems and streaming media. Previous work has largely relied on action recognition techniques to tackle this problem. In this paper, we propose a simple but effective method that solves the task from a new perspective: we design the fight detection model as a composition of an action-aware feature extractor and an anomaly score generator. Also, considering that collecting frame-level labels for videos is too laborious, we design a weakly supervised two-stage training scheme, where we utilize multiple-instance-learning loss calculated on video-level labels to train the score generator, and adopt the self-training technique to further improve its performance. Extensive experiments on a publicly available large-scale dataset, UBI-Fights, demonstrate the effectiveness of our method, and the performance on the dataset exceeds several previous state-of-the-art approaches. Furthermore, we collect a new dataset, VFD-2000, that specializes in video fight detection, with a larger scale and more scenarios than existing datasets. The implementation of our method and the proposed dataset will be publicly available at https://***/HeptaCol/VideoFightDetection. Copyright © 2022, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

An Efficient License Plate Text Extraction Technique

An Efficient License Plate Text Extraction Technique

引用

International Conference on Recent Advancement in computer, Communication and Computational sciences, RACCCS 2018

作者： Kumar, Anuj Sharma, Anuj Singla, R.K. Department of Computer Science and Applications Panjab University Chandigarh India

ISBN: (纸本)9789811359330

In vehicle recognition, a machine-based system is required to recognize vehicles. To accomplish this, extraction of character regions are required to perform with high degree of accuracy in real-life images datasets. In this letter, we present an innovative framework for character regions extraction from the license plate of vehicles. Our framework includes needful preprocessing steps to remove noise in images. The necessary checks are applied to structural properties of regions to result in character regions as an outcome. The proposed algorithms of character region extraction work with intra-regions and inter regions-dependent structural properties of characters. Our developed framework achieves results at par with respect to results reported in the literature. The character regions extraction and recognition results are 97 and 95%, respectively. These results are for images where all the regions are correctly extracted and recognized. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Structural properties

来源：评论

学校读者我要写书评

暂无评论

Next web page prediction using genetic algorithm and feed forward association rule based on web-log features

引用

International Journal of Performability Engineering 2020年第1期16卷 10-18页

作者： Gangurde, Roshan A. Kumar, Binod Department of Computer Science Savitribai Phule Pune University Maharashtra India Jayawant Institute of Computer Applications Pune Maharashtra India

The frequent utilization of websites has captivated numerous researchers, who have sought to upgrade the performance of websites through behavior analysis. Weblog feature concerning web mining is employed in this paper to construct a web page recommendation model. The feed forward counter model (FFC) is presented to effectively determine association rules with a single data iteration technique. Hence, when the recommended model is executed, the time of execution is diminished. The particle swarm optimization (PSO) algorithm is introduced in the work to pick relevant pages from a given user path as the recommended pages. The association rule AIDS in the work as the fitness value (FV). The actual dataset is acquired from the project tunnel website. The improvement of numerous evaluation parameters, like the precision, coverage, and m-metric, is achieved using the feed forward association rule with PSO for the next page recommendation system. © 2020 Totem Publisher, Inc.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Descriptors Enhancement using Sparse Autoencoder for biometric system based Minor, Major Finger Knuckle pattern 4

Descriptors Enhancement using Sparse Autoencoder for biometr...

引用

4th International Symposium on Informatics and its applications, ISIA 2020

作者： Hammouche, Rabah Attia, Abdelouahab Akhrouf, Samir Computer Science and Its Applications Laboratory Mohamed Boudiaf University M'Sila28000 Algeria LMSE Laboratory Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj34000 Algeria Mohamed Boudiaf University Computer Science Department M'Sila28000 Algeria

ISBN: (纸本)9781728196527

The outer finger knuckle print (FKP) surface has been widely used for personal authentication systems, where the traditional methods for feature extraction used in these systems not be able to achieve interesting results. Thus, we have proposed in this paper to employ a deep learning method named Sparse Auto Encoder (SAE) to enhance the features extracted from several descriptors including Gabor filter, Binarized Statistical Image Features (BSIF), Histograms of Oriented Gradients (HOG), and GIST. The main purpose is to extract features by each descriptor from the input images, then these features are enhanced using the SAE method. Next, these features are reduced by Principal Component Analysis, Linear Discriminant Analysis (PCA+LDA) technique. Then, the Nearest Neighbor (NN) Classifier based on cosine Mahalanobis distance has been applied in the matching stage. The system has been tested on the Contactless Finger Knuckle Images Database (Version 1.0) which are publicly available, the achieved results are good compared to the previous methods given in the state of the art. © 2020 IEEE.

关键词： Gabor filters

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：