检索结果-内蒙古大学图书馆

Joint Detection, Tracking, and classification of Multiple Maneuvering Star-Convex Extended Targets

IEEE SENSORS JOURNAL 2024年第4期24卷 5004-5024页

作者： Wang, Liping Zhan, Ronghui Peoples Publ Secur Univ China Sch Criminal Invest Beijing 100038 Peoples R China Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410073 Peoples R China

The extended target (ET) joint detection, tracking, and classification (JDTC) algorithms based on elliptical shape utilize rough target size information for classification, which makes it difficult to effectively solve the problem of accurate classification of similarly sized targets. Therefore, this article proposes a multiple maneuvering star-convex ET JDTC algorithm called JDTC-MM-CBMeMBer filter. First, the target extent state is modeled as a star-convex shape via the star-convex random hypersurface model (RHM). By modeling the target class-related prior information with vector form, we construct its relationship with the simultaneous extent state and integrate it into the Bayesian filter framework for joint processing. Second, to solve the implementation difficulty due to the high-dimensional target state and strong nonlinear observation model in the star-convex RHM, we model the target kinematic by two separate vectors and use the particle filter (PF) to update target class probability. Next, we use the multiple model (MM) cardinality balanced multitarget multi-Bernoulli (CBMeMBer) filter to derive the JDTC recursion process of the multiple maneuvering star-convex ETs. At last, the Gamma-Gaussian-Gaussian mixture implementation is present. The simulation results show that: 1) compared with the ET JDTC algorithm based on an elliptical shape, the proposed filter can accurately classify targets with similar sizes but different shapes and 2) compared with the multiple ET tracking algorithm based on star-convex RHM, the proposed filter can significantly improve the target state estimation results without significantly increasing the running time.

关键词： Filtering algorithms Filtering theory Target tracking classification algorithms Shape Information filters Kinematics Cardinality balanced multitarget multi-Bernoulli (CBMeMBer) extended targets (ETs) ioint tracking and classification star-convex random hypersurface model (RHM)

来源：评论

学校读者我要写书评

暂无评论

Animal species detection and classification framework based on modified multi-scale attention mechanism and feature pyramid network

引用

SCIENTIFIC AFRICAN 2022年 16卷

作者： Ukwuoma, Chiagoziem C. Qin, Zhiguang Yussif, Sophyani B. Happy, Monday N. Nneji, Grace U. Urama, Gilbert C. Ukwuoma, Chibueze D. Darkwa, Nimo B. Agobah, Harriet Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu Sichuan Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Sichuan Peoples R China Fed Univ Technol Owerri Departmemt Phys Elect Owerri Nigeria

Detecting and classifying animal species is the first step in determining their long-term viability and the influence we may be having on them. Second, it aids people in recognizing predators and non-predatory animals, both of which pose a significant threat to humans and the environment. Third, it lowers the rate of traffic accidents in various regions since it has been a regular sighting on roadways, resulting in several collisions with automobiles. However, animal species' detection and classification of animal species face many challenges such as the size and inconsistent behaviors various among the species. This paper proposes using a novel two-stage network with a modified multi-scale attention mechanism to create a more integrated recognition and classification system to attend to the challenges. At the regional proposal stage, a deeply characterized pyramid design with lateral connections was adopted, making the semantic characteristic of a small item more sensitive. Secondly, by reason of a densely connected convolutional network, the functional transmission is enhanced and multiplexed throughout the classification stage, resulting in a more precise classification with fewer parameters. The Proposed model was evaluated using the AP and mAP evaluation metrics on the Animal wildlife and the challenging Animal-80 dataset. An mAP of + 0.1% and an AP of 5% to 20% increase in each class was achieved by the attention-based proposed model compared to the non-attention-based model. Further comparison with other related works shows the proposed techniques' effectiveness for detecting and classifying animal species.(c) 2022 The Author(s). Published by Elsevier B.V. on behalf of African Institute of Mathematical Sciences / Next Einstein Initiative. This is an open access article under the CC BY license ( http://***/licenses/by/4.0/ )

关键词： Deep Learning Multiscale Attention Mechanism Feature pyramid Animal Detection and classification Deep Learning Multiscale Attention Mechanism Feature pyramid Animal Detection and classification

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Model Assisted Data Compression and classification for Efficient Data Delivery in Mobile Health Applications

引用

IEEE ACCESS 2020年 8卷 94757-94766页

作者： Cao, Youshen Zhang, Hanzhi Choi, Yong-Bae Wang, Hao Xiao, Sicheng Dong A Univ Coll Arts & Sports Busan 49315 South Korea Dong A Univ Coll Humanities Busan 49315 South Korea Beijing Sport Univ China Swimming Sports Coll Beijing 100084 Peoples R China Shangqiu Normal Univ Coll Sports Shangqiu 476000 Peoples R China

With the growing amount of chronic patients, consistent monitoring for health care professionals has been a major concern and a direct incentive to develop mobile health systems that are adaptive and energy-efficient. The data collected from these devices is extremely important and may be affected by wireless communication environments encouraging a preliminary stage that adapts transmission of data to network dynamics. The paper provides compression and classification schemes for data based on a Hybrid Deep Learning Model (HDLM) that represents data characteristics, acquired data, and energy efficiency data delivery dynamics. Further, the EEG and EMG signals are compressed and classified based on Hybrid Deep Learning Model (HDLM) has been mathematically analyzed. Hence, The system is specifically based on the Stacked Auto-Encoder (SAE) architecture which extracts discrimination in the multimodal representation of data;it reconstructs data from the latent description with the help of encoder-decoder layers for data analysis. Furthermore, Multi-Modality Adaptive Compression shows its performance, computational complexity and response to different network states has been experimentally analyzed at lab scale numerical analysis. This method is therefore appropriate for mHealth applications, which can improve energy efficiency, minimize capacity, and minimize transmission latency in the mHealth cloud with intelligent preprocessing.

关键词： Data compression Machine learning Energy efficiency Brain modeling Data models Medical services Wireless sensor networks Deep learning model wireless network auto-encoder data compression and classification

来源：评论

学校读者我要写书评

暂无评论

Hair Follicle classification and Hair Loss Severity Estimation Using Mask R-CNN

引用

JOURNAL OF IMAGING 2022年第10期8卷 283-283页

作者： Kim, Jong-Hwan Kwon, Segi Fu, Jirui Park, Joon-Hyuk Korea Mil Acad Mech & Syst Engn Seoul 01805 South Korea J Solut Daegu 41566 South Korea Univ Cent Florida Mech & Aerosp Engn Orlando FL 32816 USA

Early and accurate detection of scalp hair loss is imperative to provide timely and effective treatment plans to halt further progression and save medical costs. Many techniques have been developed leveraging deep learning to automate the hair loss detection process. However, the accuracy and robustness of assessing hair loss severity still remain a challenge and barrier for transitioning such a technique into practice. The presented work proposes an efficient and accurate algorithm to classify hair follicles and estimate hair loss severity, which was implemented and validated using a multitask deep learning method via a Mask R-CNN framework. A microscopic image of the scalp was resized, augmented, then processed through pre-trained ResNet models for feature extraction. The key features considered in this study concerning hair loss severity include the number of hair follicles, the thickness of the hair, and the number of hairs in each hair follicle. Based on these key features, labeling of hair follicles (healthy, normal, and severe) were performed on the images collected from 10 men in varying stages of hair loss. More specifically, Mask R-CNN was applied for instance segmentation of the hair follicle region and to classify the hair follicle state into three categories, following the labeling convention (healthy, normal and severe). Based on the state of each hair follicle captured from a single image, an estimation of hair loss severity was determined for that particular region of the scalp, namely local hair loss severity index (P), and by combining P of multiple images taken and processed from different parts of the scalp, we constructed the hair loss severity estimation (P-avg) and visualized in a heatmap to illustrate the overall hair loss type and condition. The proposed hair follicle classification and hair loss severity estimation using Mask R-CNN demonstrated a more efficient and accurate algorithm compared to other methods previously used, enhancing the

关键词： Mask R-CNN hair loss hair follicle detection image segmentation and classification hair severity estimation

来源：评论

学校读者我要写书评

暂无评论

Drug resistant tuberculosis classification using logistic regression

引用

International Journal of Information Technology (Singapore) 2021年第2期13卷 741-749页

作者： Bridget, Odu Nkiruka Prasad, Rajesh Onime, Clement Ali, Adamu Abubakar African University of Science and Technology Abuja Nigeria Abdu-Salam International Centre for Theoretical Physics Trieste Italy American University of Nigeria Yola Nigeria

Tuberculosis (TB) is a communicable disease that poses a serious threat to the lives of people in the world. TB may be classified as drug-sensitive (DS-TB) or drug resistant (DR-TB). Clinical methods for diagnosing DR-TB require costly infrastructure as well as highly skilled expertise and also have major limitations due to the large amount of time taken to provide results. Researchers in the past have applied some machine learning methods in diagnosing TB, but not many studies have considered DR-TB and proved much satisfactory results. This paper examines the classification of DR-TB, based on existing symptoms, using logistic regression (LR) which is well known for its application in predictive diagnosis of diseases, and such approach is advantageous because they allow a quick evaluation and classification of disease outcomes in the presence of multiple and complex symptoms. To ensure that the symptoms selected have a direct relationship with DR-TB, a statistical test of hypothesis was established to prove the degree of association between the symptoms and DR-TB. In comparison to other techniques, the key advantages of the proposed LR classifier are its ability to show the degree to which a predictor variable affects the target variable and it works well with fewer feature variables. The comparative results with other machine learning techniques shows that LR classifier resulted in more accuracy score than others. © 2021, Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： and classification Data mining Drug resistance Drug sensitive Logistic regression Tuberculosis

来源：评论

学校读者我要写书评

暂无评论

A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities

引用

IEEE ACCESS 2024年 12卷 142606-142639页

作者： Shin, Jungpil Miah, Abu Saleh Musa Kabir, Md. Humaun Rahim, Md. Abdur Al Shiam, Abdullah Univ Aizu Sch Comp Sci & Engn Aizu Wakamatsu 9658580 Japan Bangamata Sheikh Fojilatunnesa Mujib Sci & Technol Dept Comp Sci & Engn Jamalpur 2012 Bangladesh Pabna Univ Sci & Technol Dept Comp Sci & Engn Pabna 6600 Bangladesh Sheikh Hasina Univ Dept Comp Sci & Engn Netrokona 2400 Bangladesh

Researchers have been developing Hand Gesture Recognition (HGR) systems to enhance natural, efficient, and authentic human-computer interaction, especially benefiting those who rely solely on hand gestures for communication. Despite significant progress, automatic and precise identification of hand gestures remains a considerable challenge in computer vision. Recent studies have focused on specific modalities like RGB images, skeleton data, and spatiotemporal interest points. This paper comprehensively reviews HGR techniques and data modalities from 2014 to 2024, exploring advancements in sensor technology and computer vision. We highlight accomplishments using various modalities, including RGB, Skeleton, Depth, Audio, Electromyography (EMG), Electroencephalography (EEG), and Multimodal approaches and identify areas needing further research. We reviewed over 250 articles from prominent databases, focusing on data collection, data settings, and gesture representation. Our review assesses the efficacy of HGR systems through their recognition accuracy and identifies a gap in research on continuous gesture recognition, indicating the need for improved vision-based gesture systems. The field has experienced steady research progress, including advancements in hand-crafted features and deep learning (DL) techniques. Additionally, we report on the promising developments in HGR methods and the area of multimodal approaches. We hope this survey will serve as a potential guideline for diverse data modality-based HGR research.

关键词： Sign language Feature extraction Surveys Focusing Electroencephalography Cameras Skeleton Sign language recognition (SLR) vision-based hand gesture hand gesture recognition (HGR) recognition accuracy feature extraction and classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing lung cancer detection through integrated deep learning and transformer models

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-28页

作者： Durgam, Revathi Panduri, Bharathi Balaji, V. Khadidos, Adil O. Khadidos, Alaa O. Selvarajan, Shitharth AVN Inst Engn & Technol Dept Data Sci Hyderabad India Gokaraju Rangaraju Inst Engn & Technol Dept Informat Technol Hyderabad India Vardhaman Coll Engn Dept CSE AIML Hyderabad India King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Technol Jeddah Saudi Arabia King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Syst Jeddah 21589 Saudi Arabia Kebri Dehar Univ Dept Comp Sci & Engn Kebri Dehar Ethiopia Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura 140401 Punjab India Chennai Inst Technol Dept Comp Sci & Engn Chennai India King Abdulaziz Univ Ctr Res Excellence Artificial Intelligence & Data Jeddah Saudi Arabia

Lung cancer has been stated as one of the prevalent killers of cancer up to this present time and this clearly underlines the rationale for early diagnosis to enhance life expectancy of patients afflicted with the condition. The reasons behind the usage of the transformer and deep learning classifiers for the detection of lung cancer include accuracy, robustness along with the capability to handle and evaluate large data sets and much more. Such models can be more complex and can help to utilize multiple modalities of data to give extensive information that will be critical in ascertaining the right diagnosis at the right time. However, the existing works encounter several limitations including reliance on large annotated data, overfitting, high computation complexity, and interpretability. Third, the issue of the stability of these models' performance when applied to actual clinical datasets is still an open question;this is an even bigger issue that will greatly reduce the actual utilization of these models in clinical practice. To tackle these, we develop a novel Cancer Nexus Synergy (CanNS), which applies of A. Swin-Transformer UNet (SwiNet) Model for segmentation, Xception-LSTM GAN (XLG) CancerNet for classification, and Devilish Levy Optimization (DevLO) for fine-tuning parameters. This paper breaks new ground in that the presented elements are incorporated in a manner that co-operatively elevates the diagnostic capabilities while at the same time being computationally light and resilient. These are SwiNet for segmented analysis, XLG CancerNet for precise classification of the cases, and DevLO that optimizes the parameters of the lung cancer detection system, making the system more sensible and efficient. The performance outcomes indicate that the CanNS framework enhances the detection's accuracy, sensitivity, and specificity compared to the previous approaches.

关键词： Lung Cancer Disease detection Transformer models Deep learning Optimization Segmentation and classification

来源：评论

学校读者我要写书评

暂无评论

An ideal deeply contextual prediction model for an effective prediction and mitigation of cyberbullying in social networks

引用

International Journal of Information Technology (Singapore) 2025年第3期17卷 1561-1579页

作者： Prathaban, Banu Priya Vaishnavi, T. Ramesh, Addanki Purna Sujaritha, M. Rama, R. Senthil Gracewell, J. Jeffin Department of Networking and Communications School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Chennai 603203 India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Avadi Tamil Nadu Chennai 600062 India Department of Electronics and Communication Engineering DNR College of Engineering and Technology West Godavari Andhra Pradesh Bhimavaram India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Tamil Nadu Kuniyamuthur 641008 India Department of Electrical and Electronics Engineering DMI College of Engineering Tamil Nadu 600123 Chennai India Department of Electronics and Communication Engineering Saveetha Engineering College Chennai 602105 India

Social media have evoked a host of problems, especially Twitter and Instagram, considering misconceived notions of free speech. Among the concerns that have been seen as crucial is the impact of cyberbullying;it is a global issue affecting an individual and society in general. Though various methods have been suggested for deterring cyberbullying, most of these depend on victim interaction and are hence ineffective in the task of independently identifying and preventing cyberbullying. Within this context, the research introduces a new, innovative framework that is ideal and deeply contextual in terms of prediction, thus creating an approach to detecting cyberbullying on social networks without directly engaging with any victim. Consequently, the key contribution of this work is developing the Embedded Residual Recurrent Convolution Network, a hybrid deep learning architecture for the detection of cyberbullying data with more precision and accuracy. Further, this is optimized by a Tenacious Projectile Optimizer for minimizing computational time and improving classifier performance. In this regard, the novelty of the proposed I-DCP framework is established in its superior performances on different social media datasets, with an average accuracy of over 99% and an execution time as low as 13 s, hence highly efficient for real-time detection of cyberbullying. These represent important advances compared to previous methodologies and constitute a strong and scalable response in the fight against cyberbullying. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： and classification Artificial intelligence (AI) Cyberbullying detection Deep learning Instagram Optimization Social network Twitter

来源：评论

学校读者我要写书评

暂无评论

Implementation of multikernel sparse representation on remote sensing image classification 1

Implementation of multikernel sparse representation on remot...

引用

International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT)

作者： Shivakumar, G. S. Natarajan, S. Murthy, K. Srikanta Srinivas Inst Technol Dept Comp Sci & Engn Mangalore India PESIT Dept ISE Bangalore Karnataka India PESSE Dept CSE Bangalore Karnataka India

ISBN: (纸本)9781467392235

This paper presents a novel multikernel based Sparse representation for the classification of Remotely sensed images. The sparse representation based feature extraction are in a run which is a signal dependent feature extraction and thus more accurate. Multikernel Sparse representation was also had proved to be more accurate and less computationally complex while implemented in other applications like the video object tracking. Affine transform based templates are extracted from the image which has to be trained and the kernel matrix is generated which is used for comparison with the templates extracted from the test images. Kernel Coordinate Descent (KCD) algorithm. The weight values updated using the observation likelihood calculation from the proposed algorithm is used to train the SVM for the image classification in remote sensing images. The template with the highest weight values would be taken as the classified portion of the query image. Matlab based implementation is carried out on the image classification using the Multikernel Sparse Represenation (MKSR) and the results are observed and tabulated.

关键词： Active Learning Sparse Representation Remote Sensing and classification

来源：评论

学校读者我要写书评

暂无评论

Joint Camera Spectral Response Selection and Hyperspectral Image Recovery

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第1期44卷 256-272页

作者： Fu, Ying Zhang, Tao Zheng, Yinqiang Zhang, Debing Huang, Hua Beijing Inst Technol Sch Comp Sci & Technol Beijing Lab Intelligent Informat Technol Beijing 100081 Peoples R China Natl Inst Informat Tokyo 1018430 Japan DeepGlint Beijing 100091 Peoples R China

Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral response (CSR). In this paper, we present an efficient convolutional neural network (CNN) based method, which can jointly select the optimal CSR from a candidate dataset and learn a mapping to recover HSI from a single RGB image captured with this algorithmically selected camera under multi-chip or single-chip setups. Given a specific CSR, we first present a HSI recovery network, which accounts for the underlying characteristics of the HSI, including spectral nonlinear mapping and spatial similarity. Later, we append a CSR selection layer onto the recovery network, and the optimal CSR under both multi-chip and single-chip setups can thus be automatically determined from the network weights under the nonnegative sparse constraint. Experimental results on three hyperspectral datasets and two camera spectral response datasets demonstrate that our HSI recovery network outperforms state-of-the-art methods in terms of both quantitative metrics and perceptive quality, and the selection layer always returns a CSR consistent to the best one determined by exhaustive search. Finally, we show that our method can also perform well in the real capture system, and collect a hyperspectral flower dataset to evaluate the effect from HSI recovery on classification problem.

关键词： Camera spectral response selection hyperspectral image recovery spectral nonlinear mapping spatial similarity and classification

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：