检索结果-内蒙古大学图书馆

AI-driven drowned-detection system for rapid coastal rescue operations

SPATIAL INFORMATION RESEARCH 2024年第2期32卷 143-150页

作者： Dileep, P. Durairaj, M. Subudhi, Sharmila Rao, V. V. R. Maheswara Jayanthi, J. Suganthi, D. Malla Reddy Coll Engn & Technol Dept Comp Sci & Engn Hyderabad 500100 Telangana India Peri Inst Technol Dept ECE Tambaram Tamil Nadu India Maharaja Sriram Chandra Bhanja Deo Univ Dept Comp Sci Baripada 757001 Odisha India Shri Vishnu Engn Coll Women A Dept Comp Sci & Engn Bhimavaram India Sona Coll Technol Dept Comp Sci & Engn Salem 636005 India SIMATS Saveetha Coll Liberal Arts & Sci Dept Comp Sci Saveetha Nagar Chennai 602105 India

Recent observations indicate that nearly 50% of the public frequently visit coastal areas during weekends, seeking the health benefits of natural sunlight and fostering familial bonds. Notably, a significant portion of these visitors are unaware of swimming techniques or face other physical challenges, rendering them vulnerable to drowning, especially in areas lacking adequate lifeguard support or immediate medical emergency services. This study introduces an advanced drowned-detection device that employs a deep learning algorithm, grounded in artificial intelligence architecture, to swiftly detect and address potential drowning incidents. The system is particularly vigilant towards high-risk groups, such as children and the elderly. Upon detecting a threat, it autonomously deploys drones equipped with inflatable rescue tubes and notifies local authorities. Preliminary results suggest that our proposed model can effectively rescue a drowning individual in under 7 min, highlighting its prospective utility in curtailing swimming-related fatalities worldwide. This research underscores the need for technological intervention to enhance safety measures at coastal destinations and seeks to raise awareness about the importance of well-established lifeguard support.

关键词： Drowned-detection deep learning algorithm Coastal safety Autonomous drones Swimming-related fatalities

来源：评论

学校读者我要写书评

暂无评论

An Overview of Advancements in Lie Detection Technology in Speech

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGIES AND SYSTEMS APPROACH 2023年第2期16卷 1-24页

作者： Zhou, Yan Bu, Feng Suzhou Vocat Univ Suzhou Peoples R China

Lie detection technology in speech is a process of lying psychological state recognition according speech signal analysis. Normally, the emotion of tension if felt when people lie. As a result, this tension leads to some subtle changes of the sound channel structure;for example, the semantic characteristics, prosodic characteristics, resonance peak, and the psychoacoustics parameters all can be different from before. In this paper, the development situation of current lie detection technology is presented. Several public speech databases for lie detection are also introduced. Then, the research situation of feature expression, selection, and extraction for lie detection is described. In addition, the research progress of lie detection algorithm is highlighted. Finally, the future direction and the existing problems of lie detection technology in speech are summarized.

关键词： deep learning algorithm Speech Signal Processing Detection Model Feature Extraction Lie Detection Technology

来源：评论

学校读者我要写书评

暂无评论

Traffic State Estimation of Signalized Intersections Based on Stacked Denoising Auto-Encoder Model

引用

WIRELESS PERSONAL COMMUNICATIONS 2018年第1期103卷 625-638页

作者： Xiang, Junping Chen, Zonghai Univ Sci & Technol China Dept Automat Hefei Anhui Peoples R China Lianyungang JARI Elect Co Ltd CSIC Dept ITS Lianyungang Peoples R China

To solve the problem of fuzziness and uncertainty of traffic states in signalized intersection, a method was proposed for estimating traffic condition based on stacked de-noising auto-encoder model. The simulation data and empirical data were used to train the model, and the K-means clustering method was used to determine the traffic state thresholds and the data were divided into three categories based on the threshold values. Relevant features based on the reconstruction theory of de-noising auto-encoder were automatically extracted, and unsupervised greedy layer-wise pre-training and supervised fine-tuning were utilized to train the deep auto-encoder network, so that it had good robust performance on obtaining the traffic state characters with low quality in the complex environment. From the experimental results, the proposed method obtains an accuracy of 91.5% in simulation data and 88% in empirical data, which is better by 7.1% than using decision tree model.

关键词： Traffic state estimation deep learning algorithm Signalized intersections Decision tree model

来源：评论

学校读者我要写书评

暂无评论

EEG Brain Signal Processing for Epilepsy Detection

引用

RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING 2023年第7期16卷 709-716页

作者： Jain, Shruti Paul, Sudip Sharma, Kshitij Jaypee Univ Informat Technol Dept ECE Solan 173234 Himachal Prades India North Eastern Hill Univ Dept Biomed Engn Shillong 793022 India

Background: Millions of neurons make up the human brain, and they play an important role in controlling the body's response to internal and external motor and sensory stimuli. These neurons can function as contact conduits between the human body and the brain. Analyzing brain signals or photographs will help one better understand cognitive function. These states are linked to a particular signal frequency that aids in the comprehension of how a complex brain system ***: Electroencephalography (EEG) is a useful method for locating brain waves associated with different countries on the scalp. Epilepsy is a condition where the brain or some part of it is overactive and sends too many signals. This results in seizures causing muscles to twitch or whole-body ***: In this paper, the author has designed a model to predict epilepsy using machine learning algorithms and deep learning models. For the machine learning algorithm, different features were extracted and a particle swarm optimization algorithm was used to select the best feature which was classified using wavelet ***16, Vgg19, and Inception V3 models are used for the detection of ***: The inception V3 model results in 97.87% accuracy which is better than all other techniques. 5.1% accuracy improvement has been observed using a machine learning algorithm. The model is compared using existing work and it has been observed that the proposed model results ***: The technique for modeling EEG signals and insight brain signals recorded during surgical procedures has been identified in detail. 0.7% and 0.13% accuracy improvement were achieved when the model is validated on Kaggle and CHB-MIT datasets respectively.

关键词： Electroencephalography epilepsy machine learning algorithm particle swarm optimization deep learning algorithm auto-regression

来源：评论

学校读者我要写书评

暂无评论

Unified framework for early stage status prediction of autism based on infant structural magnetic resonance imaging

引用

AUTISM RESEARCH 2021年第12期14卷 2512-2523页

作者： Gao, Kun Sun, Yue Niu, Sijie Wang, Li Univ N Carolina Dept Radiol Developing Brain Comp Lab 130 Mason Farm Rd Chapel Hill NC 27599 USA Univ N Carolina Biomed Res Imaging Ctr 130 Mason Farm Rd Chapel Hill NC 27599 USA Univ Jinan Sch Informat Sci & Engn 336 West Rd Nan Xinzhuang Jinan Peoples R China

Autism, or autism spectrum disorder (ASD), is a developmental disability that is diagnosed at about 2 years of age based on abnormal behaviors. Existing neuroimaging-based methods for the prediction of ASD typically focus on functional magnetic resonance imaging (fMRI);however, most of these fMRI-based studies include subjects older than 5 years of age. Due to challenges in the application of fMRI for infants, structural magnetic resonance imaging (sMRI) has increasingly received attention in the field for early status prediction of ASD. In this study, we propose an automated prediction framework based on infant sMRI at about 24 months of age. Specifically, by leveraging an infant-dedicated pipeline, iBEAT V2.0 Cloud, we derived segmentation and parcellation maps from infant sMRI. We employed a convolutional neural network to extract features from pairwise maps and a Siamese network to distinguish whether paired subjects were from the same or different classes. As compared to T1w imaging without segmentation and parcellation maps, our proposed approach with segmentation and parcellation maps yielded greater sensitivity, specificity, and accuracy of ASD prediction, which was validated using two datasets with different imaging protocols/scanners and was confirmed by receiver operating characteristic analysis. Furthermore, comparison with state-of-the-art methods demonstrated the superior effectiveness and robustness of the proposed method. Finally, attention maps were generated to identify subject-specific autism effects, supporting the reasonability of the predictive results. Collectively, these findings demonstrate the utility of our unified framework for the early-stage status prediction of ASD by sMRI. Lay Summary The status prediction of autism spectrum disorder (ASD) at an early age is highly desirable, as early intervention may significantly reduce autism symptoms. However, current methods for diagnosing young children are limited to behavioral assays. In this

关键词： autism Spectrum disorder (ASD) deep learning algorithm early-stage status prediction infant structural MRI subject-specific autism attention

来源：评论

学校读者我要写书评

暂无评论

A hybrid of RainNet and genetic algorithm in nowcasting prediction

引用

EARTH SCIENCE INFORMATICS 2023年第4期16卷 3885-3894页

作者： Ngan, Tran Thi Son, Ha Gia Omar, Michael Thang, Nguyen Truong Giang, Nguyen Long Tuan, Tran Manh Tho, Nguyen Anh Vietnam Natl Univ Int Sch Hanoi 100000 Vietnam Vietnam Acad Sci & Technol Grad Univ Sci & Technol Hanoi 100000 Vietnam Vietnam Hungary Ind Univ Hanoi 100000 Vietnam Vietnam Natl Univ VNU Informat Technol Inst Artificial Intelligence Res Ctr Hanoi Vietnam FPT Greenwich Dept Informat Technol Hanoi 100000 Vietnam Vietnam Acad Sci & Technol Inst Informat Technol Hanoi 100000 Vietnam Thuyloi Univ Fac Comp Sci & Engn Hanoi 100000 Vietnam

Quantitative precipitation nowcasting QPN is a powerful tool with many applications, such as rainfall prediction, urban sewage control, etc. Recently, researchers have focused on using machine learning and deep learning models for nowcasting raindrops. A few famous frameworks for nowcasting raindrops in a short leading time are Rainymotion, Segnet, Unet and RainNet. Rainymotion was developed using machine learning models and extracting areas of interest. Segnet is a deep, fully convolutional neural network architecture for semantic pixel-wise segmentation with a core trainable segmentation engine consisting of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer while the U-net is a radar data-based model for precipitation nowcasting. The U-Net architecture is based on convolutional neural networks CNNs. The three models, RainyMotion, U-Net, and Segnet, are used to compare the experiment results. In this manuscript, we combined the genetic algorithm GA with the RainNet model to improve the nowcasting performance of the model RainNet. The GA is used to tune hyperparameters such as filter size, activation function, and the number of epochs for the model. To enhance the performance of the baseline models for nowcasting, an objective function is defined to decrease the mean absolute error MAE below 0.3 for the next 5 minutes. The proposed algorithm was evaluated on radar images taken by the German Weather Service DWD, a German Meteorological Service based in Offenbach am Main, a city in Hesse, Germany, which monitors weather and meteorological conditions over Germany. The result from our experiments obtained indicated that the RainNet+GA model is more accurate in predicting short-term raindrops but requires an expensive implementation of a powerful computer to run on Graphical processor Unit GPU. Our hybrid model RainNet +GA did not overcome the computational power of using GPU. However, the experimental results with a loss o

关键词： deep learning algorithm Genetic algorithm (GA) Hyper-parameter optimization Convolutional neural network -(CNN) Prediction

来源：评论

学校读者我要写书评

暂无评论

Detecting Heart Valve Regurgitation in Medical Images-Using YOLOv7 24

Detecting Heart Valve Regurgitation in Medical Images-Using ...

引用

5th Asia Service Sciences and Software Engineering Conference

作者： Chen, Shih-Hsin Kao, Ting-Yi Chen, Yi-Hui Tamkang Univ Dept Comp Sci & Informat Engn Taipei Taiwan Chang Gung Univ Dept Informat Management Taoyuan Taiwan

ISBN: (纸本)9798400717543

This study aims to investigate the effectiveness of the YOLOv7 computer vision algorithm in analyzing medical images to predict the four main types of heart valve regurgitation. Additionally, the overall performance of the YOLOv7 baseline model in accurately detecting and characterizing regurgitation-related lesions is compared. Through comprehensive evaluations on various datasets of heart regurgitation, the aim is to deepen understanding of the capabilities and limitations of these models, comparing, and analyzing which model offers superior accuracy and computational efficiency. The results obtained from this study are expected to guide the selection of the most suitable model to develop automated and precise diagnostic tools for heart valve regurgitation, assisting healthcare professionals in diagnosing heart valve regurgitation and improving patient outcomes.

关键词： YOLOv7 Cardiac Regurgitation Medical Images Computer Vision algorithm deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

deep prediction on financial market sequence for enhancing economic policies

引用

DECISIONS IN ECONOMICS AND FINANCE 2024年 1-20页

作者： Salahshour, Soheil Salimi, Mehdi Tehranian, Kian Erfanibehrouz, Niloufar Ferrara, Massimiliano Ahmadian, Ali Istanbul Okan Univ Fac Engn & Nat Sci Istanbul Turkiye Bhacesehir Univ Fac Engn & Nat Sci Istanbul Turkiye Mediterranea Univ Reggio Calabria Decis Lab Calabria Italy Univ Calif Angeles UCLA Dept Econ Los Angeles CA USA Syracuse Univ Dept Econ Syracuse NY 13244 USA Univ Mediterranea Reggio Calabria Dept Law Econ & Human Sci Via Univ 25 I-89124 Reggio Di Calabria Italy

Numerous sectors are significantly impacted by the quick advancement of image and video processing technologies. Investors can kind knowledgeable savings choices based on the examination and projection of financial bazaar income, and the government can create accurate policies for various forms of economic control. This study uses an artificial rabbits optimization algorithm in image processing technology to examine and forecast the returns on financial markets and multiple indexes using a deep-learning LSTM network. This research uses the time series technique to record the regional correlation properties of financial market data. Convolution pooling in LSTM is then used to gather significant details concealed in the time sequence information, generate the data's tendency bend, and incorporate the structures using technology for image processing to ultimately arrive at the forecast of the economic sector's moment series earnings index. A popular artificial neural network used in time series examination is the long short-term memory (LSTM) network. It can accurately forecast financial marketplace values by processing information with numerous input and output timesteps. The correctness of financial market predictions can be increased by optimizing the hyperparameters of an LSTM model using metaheuristic procedures like the Artificial Rabbits Optimization algorithm (ARO). This research presents the development of an enhanced deep LSTM network with the ARO method (LSTM-ARO) for stock price prediction. According to the findings, the research's deep learning system for financial market series prediction is efficient and precise. Data analysis and image processing technologies offer practical approaches and significantly advance finance studies.

关键词： Image processing Financial market Time series prediction deep learning algorithm Artificial rabbits optimization algorithm Prediction G17 G11 C45 C23

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised False Data Detection Using Gated Recurrent Units and Threshold Scoring algorithm

Semi-Supervised False Data Detection Using Gated Recurrent U...

引用

IEEE-Power-and-Energy-Society General Meeting (PESGM)

作者： Parizad, Ali Hatziadoniu, Constantine Southern Illinois Univ Dept Elect & Comp Engn Carbondale IL 62901 USA

ISBN: (纸本)9781665405072

In recent years, cyber attackers are targeting the power system and imposing different damages to the national economy and public safety. False Data Injection Attack (FDIA) is one of the main types of Cyber-Physical attacks that adversaries can manipulate power system measurements and modify system data. Consequently, it may result in incorrect decision-making and control operations and lead to devastating effects. In this paper, we propose a two-stage detection method. In the first step, Gated Recurrent Unit (GRU), as a deep learning algorithm, is employed to forecast the data for the future horizon. Meanwhile, hyperparameter optimization is implemented to find the optimum parameters (i.e., number of layers, epoch, batch size, beta(1), beta(2), etc.) in the supervised learning process. In the second step, an unsupervised scoring algorithm is employed to find the sequences of false data. Furthermore, two penalty factors are defined to prevent the objective function from greedy behavior. We assess the capability of the proposed false data detection method through simulation studies on a real-world data set (ComEd. dataset, Northern Illinois, USA). The results demonstrate that the proposed method can detect different types of attacks, i.e., scaling, simple ramp, professional ramp, and random attacks, with good performance metrics (i.e., recall, precision, F1 Score). Furthermore, the proposed deep learning method can mitigate false data with the estimated true values.

关键词： Cyber Security Attack Templates False Data Injection Attack deep learning algorithm Gated Recurrent Unit (GRU) Supervised/Unsupervised learning Detection Method

来源：评论

学校读者我要写书评

暂无评论

Identify IoT Devices from Backbone Networks Using Lightweight Neural Networks 47

Identify IoT Devices from Backbone Networks Using Lightweigh...

引用

47th IEEE Conference on Local Computer Networks (LCN)

作者： Wu, Hua Fan, Xingmeng Cheng, Guang Hu, Xiaoyan Southeast Univ Sch Cyber Sci & Engn Nanjing Peoples R China Purple Mt Labs Network & Commun Secur Nanjing Peoples R China Southeast Univ Key Lab Comp Network & Informat Integrat Nanjing Peoples R China Jiangsu Prov Engn Res Ctr Secur Ubiquitous Networ Nanjing Peoples R China

ISBN: (数字)9781665480017

ISBN: (纸本)9781665480017

Due to the heterogeneity, fragmentation, and lack of visibility, Internet of Things has become the new target for attacks. Therefore, it is necessary for Internet Service Providers to identify IoT devices to prevent attacks and protect the entire network in time. In this paper, we propose an IoT device identification approach based on lightweight deep learning models using a single feature. Specifically, we analyze the traffic pattern specific to IoT devices and use one feature to characterize this pattern, reducing the time consumption. Moreover, we select multiple time scales to extract this feature for different IoT devices, achieving an accurate characterization and improving the accuracy. Furthermore, we use unidirectional flows as analysis objects, suitable for backbone networks. The evaluation results on real-world datasets show that our approach achieves an accuracy of over 99%, with one-seventeenth of the time consumption of the state-of-the-art approach, realizing the lightweight and real-time requirements.

关键词： Internet of Things devices identification specific traffic pattern deep learning 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：