检索结果-内蒙古大学图书馆

Computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Ying Yang Jielin Chen Zehua Xu Jundong Li Zeye Lin Guangdong Communication Polytechnic Guangzhou China Wuyi University Jiangmen China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

To address the limitations of traditional garbage sorting methods that rely on manual intervention, this paper presents an innovative intelligent waste classification system that combines deep learning-based image recognition technology with automated robotic arm control for the efficient identification and classification of four typical types of household waste. The core innovation of the system lies in the use of an improved YOLOv5 model, employing a lightweight MobileNet as the backbone network to achieve efficient feature extraction and incorporating an attention mechanism to enhance classification accuracy. By assigning greater weight to important features, the model significantly improves its ability to capture key waste characteristics, thereby increasing recognition accuracy. In terms of hardware selection, after evaluating various modules, the K210 module was ultimately chosen due to its outstanding advantages in power consumption, control capabilities, and intelligence performance. The control system is centered around the STM32F103C8T6 microcontroller, which centrally manages the waste recognition module, robotic arm, power supply, and communication modules, enabling real-time waste recognition and classification while coordinating the robotic arm and vehicles for efficient waste processing. The The system also developed the mobile terminal software enhancing the user interaction experience. Testing results indicate that this intelligent waste classification system demonstrates high intelligence, accurate waste classification capabilities, and good real-time operational performance along with modular expandability. Overall, this paper provides a new solution for intelligent waste classification by combining deep learning and automation technologies, promoting development in related fields, and showcasing the broad potential of deep learning in practical applications.

关键词： YOLO deep learning Technological innovation Attention mechanisms Accuracy Robot kinematics Manipulators real-time systems Sorting Testing

来源：评论

学校读者我要写书评

暂无评论

Automated Sex Assessment of Individual Adult Tooth X-Ray images 12

Automated Sex Assessment of Individual Adult Tooth X-Ray Ima...

引用

12th International Symposium on image and Signal processing and Analysis (ISPA)

作者： Milosevic, Denis Vodanovic, Marin Galic, Ivan Subasic, Marko Univ Zagreb Fac Elect Engn & Comp Zagreb Croatia Univ Zagreb Sch Dent Med Zagreb Croatia Univ Hosp Ctr Split Split Croatia

ISBN: (纸本)9781665426398

Sex assessment is an important step of the forensic process. Dental remains are often the only remains left to examine due to their resistance to decay and external factors. Contemporary forensic odontology literature describes multiple methods for sex assessment from mandibular parameters, all of which require manual measurements and expert training. This study aims to explore the applicability of deep learning and image analysis methods to automate this task, thus allowing for easier reproducibility of assessments, reduction of the time experts lose on repetitive tasks, and potentially better performance. We have evaluated state-of-the-art deep learning models and components on the largest dataset of individual adult tooth x-ray images, consisting of 76293 samples. This study also explores the usage of decayed or structurally altered teeth, with which contemporary methods struggle. Two types of models are constructed, a family of models specialized for specific tooth types, and a general model that can assess the sex from any tooth type. We examine the performance of those models per tooth type and age group, as well as the impact of decayed and structurally altered teeth. The specialized models achieve an overall accuracy of 72.40%, and the general model reaches an overall accuracy of 72.68%.

关键词： forensic odontology x-ray image analysis convolutional neural network deep learning machine learning image processing

来源：评论

学校读者我要写书评

暂无评论

On-Device Lumbar-Pelvic Movement Detection Using Dual-IMU: A DNN-Based Approach

引用

IEEE ACCESS 2021年 9卷 62241-62254页

作者： Zhang, Yuxin Haghighi, Pari Delir Burstein, Frada Yao, Lina Cicuttini, Flavia Monash Univ Fac Informat Technol Caulfield Vic 3145 Australia UNSW Sydney Sch Comp Sci & Engn Sydney NSW 2052 Australia Monash Univ Sch Publ Hlth & Prevent Med Melbourne Vic 3004 Australia

Lumbar-pelvic movements (LPMs) are generally performed in the clinical setting to identify limitations in a range of movements. Continuous monitoring of these movements can provide real-time feedback to both patients and medical experts with the potential of identifying activities that may precipitate symptoms of low back pain (LBP) as well as improving therapy by providing a personalised approach. Recent advances in mobile computing technology and wearable sensors have paved the way for developing mobile physical activity monitoring applications with more advanced and complex algorithms, such as deep neural network (DNN) based models. However, there is a lack of prior studies that focus on real-time LPMs detection with multimodal sensory data. Meanwhile, most research in the area of body movement detection do not consider the potential transition logic of the constituent low-level body movements (e.g., LPMs) within their corresponding high-level physical activity. This information could significantly increase accuracy of detection results. Further, current studies mainly perform deep learning-based movement detection in the cloud (or a backend server) that could increase network bandwidth and response time. To address these limitations, this paper proposes a novel LPMs detection approach using an enhanced and adapted hybrid DNN model, which includes a convolutional neural network followed by a long-short term memory recurrent network (CNN-LSTM), and performs detection locally on the mobile device. The results of a comparative evaluation of the proposed model and baseline models are described. We also introduce a set of domain-specific pre-defined rules, based on the transition logic information, to reconstruct the detection outputs to further improve the detection accuracy.

关键词： Sensors Monitoring Adaptation models Mobile handsets real-time systems Performance evaluation Computational modeling deep neural networks domain adaptation lumbar-pelvic movement detection mobile platform on-device processing temporal-wise attention

来源：评论

学校读者我要写书评

暂无评论

Automated end-to-end deep learning framework for classification and tumor localization from native non-stained pathology images

Automated end-to-end deep learning framework for classificat...

引用

Conference on Medical Imaging - image processing

作者： Bayat, Akram Anderson, Connor Shah, Pratik MIT Program Media Arts & Sci Media Lab 77 Mass Ave Cambridge MA 02139 USA

ISBN: (纸本)9781510640221

deep learning based quantitative assessment of digital pathology images and understanding the underlying reasons for a specific clinical decision is challenging, and automatic histology pattern classification and tumor localization in whole-slide pathology images am critical for interpretable learning systems. In this study, we propose an end-to-end deep learning framework for automatic detection and localization of tumors directly from non-stained whole slide prostate core biopsy images (WSI). We use a previously described Generative Adversarial Network (GAN)-based model from our laboratory for computational Hematoxylin and Eosin (H&E) staining of native non-stained pathology images. A convolutional neural network to detect and classify tumor regions in 1024x1024 virtually stained H&E pixel patches, and a concurrent deep weakly supervised (WSL) model that provides localization of predominant histologic patterns used for tumor classification without the need for pixel-level annotations are reported in this study for the first time. The end-to-end system was evaluated on a 17K hold out set of 1024x1024 non-stained patches extracted from 13 whole slide prostate biopsy images. Experimental results yielded 86.37% patch-level classification accuracy with 85.05% precision, and achieved a Dice index of 65.07 +/- 1.99 (compared to 70.24 +/- 1.86 Dice index in the U-Net reference model for pixel-level segmentation). The end-to-end deep learning framework thus automates digital pathology image workflow from tissue staining to interpretable prostate tumor classification and can be valuable for accurate grading of prostate cancer and generalized to other whole-slide image classification tasks.

关键词： Pathology image analysis prostate cancer automated classification tumor localization deep learning

来源：评论

学校读者我要写书评

暂无评论

deep learning Techniques for image Recognition in IoT-Enabled Surveillance Systems

Deep Learning Techniques for Image Recognition in IoT-Enable...

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： V Dankan Gowda Y. Vishnu Tej Vidya Sagar Potharaju Premkumar Reddy Jakkidi Aanchal Sharma N Sudhakar Reddy Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka Department of Computer Science and Systems Engineering Andhra University Visakhapatnam India Department of ECE Vignana Bharati Institute of Technology Ghatkesar Hyderabad India 15950 paramount way Frisco Texas DCSA Panjab University Chandigarh India Department of ECE School of Engineering Mohan Babu University Tirupati India

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

This paper proposed an improved method that can be used in the identification of images within IoT based surveillance systems through the use of deep learning techniques especially the CNNs. The growth of concern and complexity therefore entails massive feeding from bursts of data from surveillance cameras, hence the need for reliable algorithms for processing the data in real-time with reasonable accuracy. The described system can be described as inclusive of IoT devices communicating with edge computing and cloud services for the purpose of scalability and performance enhancement. In this study, a very sophisticated experimental setup was employed; the authors used a number of datasets for surveillance purposes to evaluate the model. The results revealed that the segments of the method achieve a high accuracy and are continuously running through data in diverse surveillance scenarios while also being scalable. In the results section, we realized that CNN model was able to handle various environmental conditions such as; extreme lightening and occlusion. On the basis of the above mentioned data, it will be possible to suggest that this approach is rather superior compared to the other conventional approaches and therefore can be suggested as the possible solution of the modern conditions of surveillance. It thus provides platform for the advancement of intelligent surveillance system for use in smart city, security and safety application.

关键词： deep learning Accuracy image recognition Smart cities Surveillance Computational modeling real-time systems Internet of Things Security Edge computing

来源：评论

学校读者我要写书评

暂无评论

Design of an Intelligent System for Sports Motion Recognition Based on Data Analysis Algorithms

Design of an Intelligent System for Sports Motion Recognitio...

引用

image processing and Computer Applications (ICIPCA), IEEE International Conference on

作者： Qiuling Wu Department of Physical Education Guangdong University of Science and Technology Dongguan Guangdong China Physical Education Research Center Guangdong University of Science and Technology Dongguan Guangdong China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

This study is dedicated to the design and implementation of an intelligent sports motion recognition system based on data analysis algorithms, aiming to enhance the efficiency and safety of sports training and competitions. By collecting and analyzing athletes' motion data, the system is capable of recognizing and classifying various sports movements in real-time, providing coaches and athletes with immediate feedback and suggestions for improvement. The paper begins by reviewing related research in the field of sports motion recognition, particularly the application of machine learning and deep learning methods in motion recognition. Subsequently, we introduce the methodology of the system, including the detailed process of data collection, preprocessing, and algorithm selection. The system design section elaborately describes the architecture of the intelligent system, comprising hardware components and software implementation, as well as user interface design. A series of experiments were conducted to validate the effectiveness of the proposed system, indicating its high accuracy in recognizing a variety of sports movements. Moreover, we discuss the challenges and limitations encountered during the system implementation and propose potential directions for improvement. The results of this research are anticipated to significantly contribute to the scientific level of sports training and the performance of athletes.

关键词： Training deep learning Data privacy Accuracy Recurrent neural networks image recognition Convolutional neural networks Intelligent systems Long short term memory Sports

来源：评论

学校读者我要写书评

暂无评论

An Enhanced deep learning Approach for Smartphone-Based Human Activity Recognition in IoHT 3rd

An Enhanced Deep Learning Approach for Smartphone-Based Hum...

引用

3rd International Conference on Machine learning, image processing, Network Security and Data Sciences, MIND 2021

作者： Soni, Vaibhav Jaiswal, Shashank Semwal, Vijay Bhaskar Roy, Bholanath Choubey, Dilip Kumar Mallick, Dheeresh K. Department of Computer Science and Engineering Maulana Azad National Institute of Technology Bhopal Madhya Pradesh Bhopal India Department of Computer Science and Engineering Indian Institute of Information Technology Bhagalpur Bihar Bhagalpur India Department of Computer Science and Engineering Birla Institute of Technology Mesra Jharkhand Ranchi India

ISBN: (纸本)9789811958670

Human activity recognition (HAR) uses sensor-based technology to predict human activity using sensor-generated time-series data. According to recent studies, researchers have been drawn to the area of HAR as the use of mobile devices with various sensors has increased in several research areas in health care that includes the identification of gait abnormality in brain or neurological disorder subjects, designing techniques for clinical gait analyses of a disabled and elderly person, etc. HAR is especially essential on the Internet of healthcare things (IoHT) because of the increasing growth of the Internet of Things (IoT) technology incorporated in numerous smart products and wearable technology (such as smartwatches and smartphones) that have a significant impact on the life of human. A deep neural network (DNN) comprising a bidirectional gated recurrent unit (BiGRU) and two convolutional layers is proposed in this research. The model used could automatically extract and identify activity features using a few of the architecture parameters. The raw data obtained using smartphone sensors is sent into a two layer BiGRU followed by two CNN layers in the proposed architecture. The model’s performance is assessed using two publicly available datasets (UCI-HAR and WISDM). The observations indicate that the reliability and activity identification capability of the proposed model is better than earlier findings. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Disease in Rice Paddy: A deep learning based Convolution Neural Networks Approach 12

Early Detection of Disease in Rice Paddy: A Deep Learning ba...

引用

12th International Conference on Computing Communication and Networking Technologies, ICCCNT 2021

作者： Chakraborty, Anghsuman Layek, Soumik Sankar, Ravi Saha, Sangit Ghosh, Alokesh Ray, Hena Centre for Development of Advanced Computing Kolkata India

ISBN: (纸本)9781728185958

The agriculture industry faces huge economic losses due to bacterial, viral or fungal infections in the crops due to which farmers lose 15 to 20% of their total profit every year. India is the second largest producer of rice and a leading exporter of the same in the global market. Thus, early detection of diseases in essential crops is a significant area of research in order to prevent further damage to them. The widespread development of deep learning makes it possible to achieve the goal of disease detection in crops. The novelty of this work is early detection of Brown spot disease in rice paddy using Convolution Neural Networks. The area of the disease affected was also found to optimize the usage of fertilizers. This work makes use of image recognition and pre-processing algorithm based on real time data. Data pre-processing and feature extraction has been done using a self-designed image-processing tool. Tensor flow and Keras framework has been implemented on both training and testing data which was collected manually from rice fields. The proposed model achieved an accuracy of 97.32%. © 2021 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Low SWaP real-time edge processing for cognitive sensing and autonomous control applications 2

Low SWaP real-time edge processing for cognitive sensing and...

引用

AI and Optical Data Sciences II 2021

作者： Adl, Sanaz Kabakian, Adour V. Petre, Peter Garrido, Austin HRL Laboratories LLC 3011 Malibu Canyon Dr. MalibuCA90265 United States

ISBN: (数字)9781510642423

ISBN: (纸本)9781510642416

Many real-time cognitive sensing signal processing and control applications require low SWAP edge processors with ultra-low latency adaptation and learning capabilities along with strict throughput, accuracy and power requirements. Achieving 3rd generation AI capabilities, i.e., real-time contextual adaptation, requires fast adaptive inference operations at low power beyond what is achievable with currently available neural networks and deep learning systems. While there has been tremendous progress in the form of edge accelerators, today's processors lack capabilities for real-time processing, adaptation to novel situations, and low latency decision making. This paper addresses currently unsolved critical challenges in real-time cognitive sensing and autonomous system control applications, such as ultra-wide bandwidth and real-time signal denoising, anomaly detection, blind signal separation, and adaptive system equalization and control. We also present experimental results for low Cost-Size Weight and Power (C-SWAP) hardware implementation of an edge processor prototype implemented on a commercially available FPGA board. © 2021 SPIE.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Perturbation of image-based Malware Detection with Smali level morphing techniques 19

Perturbation of Image-based Malware Detection with Smali lev...

引用

19th IEEE International Symposium on Parallel and Distributed processing with Applications (IEEE ISPA)

作者： Gerardi, Federico Iadarola, Giacomo Martinelli, Fabio Santone, Antonella Mercaldo, Francesco Geckosoft Pisa Italy Natl Res Council Italy CNR Inst Informat & Telemat Pisa Italy Univ Molise Dept Med & Hlth Sci Vincenzo Tiberio Campobasso Italy

ISBN: (纸本)9781665435741

Considering the weaknesses of signature-based approaches adopted by current antimalware, from both academic and industrial side there is a boost in the development of techniques exploiting artificial intelligence, where one of the most promising are based on the representation of application under analysis as image. In order to understand whether these approaches can be effectively adopted in the real-world, starting from a detector based on deep learning, in this paper we evaluate the resilience of these approaches when morphed samples are considered. We present DexWave, a tool aimed to automatically inject perturbations techniques targeting the smali code representation of Android applications. The experimental analysis demonstrate that image-based malware classifier are vulnerable to simple perturbations attack.

关键词： malware obfuscation deep learning artificial intelligence security Android

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：