检索结果-内蒙古大学图书馆

IEEE 27th International Conference on Advanced Information Networking and Applications Workshops (WAINA)

作者： Imai, Shintaro Miyamoto, Mariko Arai, Yoshikazu Inomata, Toshimitsu Iwate Prefectural Univ Grad Sch Software & Informat Sci Takizawa Iwate 0200193 Japan

ISBN: (纸本)9780769549521;9781467362399

Some systems use machine learning techniques such as support vector machines to estimate human motions using acceleration sensors. These systems must acquire acceleration data to build a model. Therefore, it is difficult to estimate a newly observed person's motions promptly. Moreover, a newly observed person must carry out sufficiently diverse and numerous motions to build a model. These are heavy burdens that must be borne to observe people. As described in this paper, we propose a method for sensor data processing using similarity in feature of motions between observed persons. This method is designed to achieve a balance between providing motion estimation for a newly observed person promptly and for maintaining precision of motion estimation. In this method, the system can estimate a newly observed person's motions initially because the system uses a similar observed persons' standard. We implement a prototype system to evaluate this method. The system estimates human motions using the acceleration sensor. We perform some initial experiments using this prototype system.

关键词： sensor data processing Human motion estimation Support vector machine Ubiquitous system

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-Stage Training Approach for Human Activity Recognition From Multimodal Wearable sensor data Using Deep Neural Network

引用

IEEE sensorS JOURNAL 2021年第2期21卷 1715-1726页

作者： Mahmud, Tanvir Sazzad Sayyed, A. Q. M. Fattah, Shaikh Anowarul Kung, Sun-Yuan Bangladesh Univ Engn & Technol Dept Elect & Elect Engn Dhaka 1000 Bangladesh Princeton Univ Dept Elect Engn Princeton NJ 08544 USA

Deep neural network is an effective choice to automatically recognize human actions utilizing data from various wearable sensors. These networks automate the process of feature extraction relying completely on data. However, various noises in time series data with complex inter-modal relationships among sensors make this process more complicated. In this article, we have proposed a novel multi-stage training approach that increases diversity in this feature extraction process to make accurate recognition of actions by combining varieties of features extracted from diverse perspectives. Initially, instead of using single type of transformation, numerous transformations are employed on time series data to obtain variegated representations of the features encoded in raw data. An efficient deep CNN architecture is proposed that can be individually trained to extract features from different transformed spaces. Later, these CNN feature extractors are merged into an optimal architecture finely tuned for optimizing diversified extracted features through a combined training stage or multiple sequential training stages. This approach offers the opportunity to explore the encoded features in raw sensor data utilizing multifarious observation windows with immense scope for efficient selection of features for final convergence. Extensive experimentations have been carried out in three publicly available datasets that provide outstanding performance consistently with average five-fold cross-validation accuracy of 99.29% on UCI HAR database, 99.02% on USC HAR database, and 97.21% on SKODA database outperforming other state-of-the-art approaches.

关键词： Feature extraction Training Time series analysis data mining Neural networks sensor phenomena and characterization sensor data processing feature learning CNN activity recognition multi-stage training

来源：评论

学校读者我要写书评

暂无评论

Auto-Fusing Covariance and Phase Locking Value With Brain-Inspired Spiking Neural Networks for EEG-Based Driver Reaction Time Prediction

IEEE SENSORS LETTERS

引用

IEEE sensorS LETTERS 2025年第2期9卷

作者： Parekkattil, Adarsh, V Singh, Vivek Bollu, Tharun Kumar Reddy Indian Inst Technol Roorkee Dept Elect & Commun Engn Roorkee 247667 India

Drowsy driving stands out as one of the major contributors to road collisions. Drowsiness is characterized by a sense of fatigue and a compelling desire to sleep. It manifests through a gradual decrease in reaction time. The electroencephalogram (EEG), which records the patterns of electrical waves in the brain, exhibits a significant correlation with the gradual decline in reaction time induced by drowsiness. This research proposes a superior novel approach that combines phase locking value (PLV) and covariance representations by feature-level fusion by using an autoencoder on brain-inspired reservoir-based spiking neural networks (BI-SNNs) to estimate drivers' reaction times by examining the EEG data. By fusing PLV and covariance features into the reservoir-based BI-SNN method, the network can efficiently capture the spatio-temporal dynamics in the data. The superiority of the proposed methodology is assessed by evaluating the root-mean-squared error (RMSE) and mean absolute error (MAE) on the publicly available lane keeping task (LKT) dataset.

关键词： Neurons Electroencephalography Synchronization Spiking neural networks Covariance matrices Encoding Autoencoders Tensors Standards sensor phenomena and characterization sensor applications brain-inspired spiking neural network (BI-SNN) drowsiness electroencephalogram (EEG) regression task mean absolute error (MAE) phase locking value (PLV) reaction time (RT) root-mean-squared error (RMSE) sensor data processing sensor signal processing

来源：评论

学校读者我要写书评

暂无评论

A critical note on meal criteria in pigs: Which behaviours do they perform during feeder visit intervals?

引用

APPLIED ANIMAL BEHAVIOUR SCIENCE 2024年 273卷

作者： Bus, Jacinta D. Boumans, Iris J. M. M. Webb, Laura E. Bokkers, Eddie A. M. Wageningen Univ & Res Anim Prod Syst Grp POB 338 NL-6700 AH Wageningen Netherlands

The feeding behaviour of pigs can be continuously recorded using sensors, providing promising avenues for automatic monitoring of pig performance and welfare. To utilise this potential, however, the data must be cleaned and aggregated meaningfully. A common aggregation is from visits into meals, in which visits separated by intervals shorter than a meal criterion (s or min) are merged. Methods to determine the criterion and the criteria themselves vary widely between studies, and have been applied indiscriminately or only when no pen mates visited the feeder during the interval. Aggregation choices should be biologically relevant, but there is no empirical knowledge on how pigs behave during these intervals or how the intervals are influenced by feeder competition. This study had three aims: 1) test the method that classifies intervals using a three-part probability density function (short, intermediate and long intervals);2) determine whether feeder competition differed between interval types and application methods;and 3) describe and compare the behaviours of pigs between intervals. Visit intervals were obtained from 110 barrows in ten pens with one IVOG (R) electronic feeding station each. A three-part probability density function was fitted to the log-transformed intervals, and its fit was assessed visually. For each pig, a short and an intermediate interval were selected for behavioural observations from camera. We found that pigs had relatively more intermediate intervals (1-28 min) than cows and that the fit of the three-part function was suboptimal. Nevertheless, identified meal criteria were in similar ranges as for other species. Intermediate intervals were more often initiated by displacements than short intervals (<= 1 min), and there was more aggression and less pen exploration if pen mates visited the feeder during these intervals. Short intervals reflected interruptions in feeding behaviour, shown by standing (e.g. vigilance/chewing outside the feede

关键词： Fattening pigs Feeding patterns Feeding behaviour Feeder competition Precision livestock farming (PLF) sensor data processing

来源：评论

学校读者我要写书评

暂无评论

A Safe Driving Decision-Making Methodology Based on Cascade Imitation Learning Network for Automated Commercial Vehicles

引用

IEEE sensorS JOURNAL 2023年第11期23卷 11285-11295页

作者： Hu, Weiming Li, Xu Hu, Jinchao Kong, Dong Hu, Yue Xu, Qimin Liu, Yan Song, Xiang Dong, Xuan Southeast Univ Sch Instrument Sci & Engn Nanjing 210096 Peoples R China China Automot Engn Res Inst Co Ltd Chongqing 401122 Peoples R China Nanjing Xiaozhuang Univ Sch Elect Engn Nanjing 211171 Peoples R China Res Inst Highway Minist Transport Beijing 100088 Peoples R China

Safe driving decision-making is particularly important for automated commercial vehicles (ACVs). Small passenger vehicles pay more attention to collision prevention, while commercial vehicles with a longer brake distance and worse roll stability need to consider both anti-collision and anti-rollover. The widely studied driving decision-making methods for small passenger vehicles cannot be simply and directly applied to commercial vehicles. This article proposes a safe driving decision-making methodology based on a cascade imitation learning network (CILN). The CILN integrates two parts, namely, the supervised learning part and the imitation learning part. The first part learns safe driving maneuvers extracted from naturalistic vehicle sensor data. Through sensor data processing, it develops decision-making at a humanoid level, such as avoiding jerky driving actions. In the second part, generative adversarial imitation learning (GAIL) is introduced to further learn safe driving decisions under conditions prone to collision and rollover. Finally, both highD dataset and simulation of urban mobility (SUMO) are used to train and verify the performance of the CILN. By comparing the evaluation indicators of time to collision (TTC), reverse TTC (RTTC), deceleration rate to avoid the crash (DRAC), distance headway, and lateral acceleration, the CILN outperforms the other decision-making algorithms. Experimental results show that the CILN can provide safe driving decision-making and ensure the driving safety of ACVs in dense traffic flow.

关键词： Decision making sensors Safety Rollover Accidents Task analysis Supervised learning Anti-collision and anti-rollover automated commercial vehicle (ACV) driving decision-making imitation learning sensor data processing

来源：评论

学校读者我要写书评

暂无评论

Automatic Classification of Liquid Crystal Images Based on Topological Analysis

引用

IEEE sensorS JOURNAL 2023年第2期23卷 1377-1388页

作者： Romanov, Alexey M. MIREA Russian Technol Univ Inst Artificial Intelligence Moscow 119454 Russia

Liquid crystal image classification is a vital part of modern biosensors. Recent studies have shown that this problem can be solved using computationally intensive intelligent analysis tools, such as convolutional neural networks (CNNs) and support vector machines (SVMs). This article proposes a new method of microscopic image classification for liquid crystals-based biosensors with fast response. This method is based on topological analysis and provides 95% accuracy. Moreover, on the same hardware, it reaches eightfold performance compared to CNNs, which are usually used in similar applications. Finally, it has only nine parameters. Most of those parameters are independent and can be easily tuned based on the properties of the liquid crystals suspension and the microscope. This is a significant benefit compared to machine learning approaches that require large training datasets. The proposed solution can be considered a new step toward the creation of fully automatic biosensors for industrial water quality assessment systems.

关键词： Biosensor classification graphics processing unit (GPU) image processing liquid crystal pattern recognition sensor data processing

来源：评论

学校读者我要写书评

暂无评论

Sensing and Machine Learning for Automotive Perception: A Review

引用

IEEE sensorS JOURNAL 2023年第11期23卷 11097-11115页

作者： Pandharipande, Ashish Cheng, Chih-Hong Dauwels, Justin Gurbuz, Sevgi Z. Ibanez-Guzman, Javier Li, Guofa Piazzoni, Andrea Wang, Pu Santra, Avik NXP Semicond NL-5656 AE Eindhoven Netherlands Fraunhofer IKS D-80686 Munich Germany Delft Univ Technol TU Delft Dept Microelect NL-2628 CD Delft Netherlands Univ Alabama Dept Elect & Comp Engn Tuscaloosa AL 35487 USA Renault F-78064 Guyancourt France Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China Nanyang Technol Univ Ctr Excellence Testing & Res AVs Interdisciplinary Grad Programme ERI N Singapore 639798 Singapore Mitsubishi Elect Res Labs Cambridge MA 02139 USA Infineon Technol Irvine CA 92618 USA

Automotive perception involves understanding the external driving environment and the internal state of the vehicle cabin and occupants using sensor data. It is critical to achieving high levels of safety and autonomy in driving. This article provides an overview of different sensor modalities, such as cameras, radars, and light detection and ranging (LiDAR) used commonly for perception, along with the associated data processing techniques. Critical aspects of perception are considered, such as architectures for processing data from single or multiple sensor modalities, sensor data processing algorithms and the role of machine learning techniques, methodologies for validating the performance of perception systems, and safety. The technical challenges for each aspect are analyzed, emphasizing machine learning approaches, given their potential impact on improving perception. Finally, future research opportunities in automotive perception for their wider deployment are outlined.

关键词： sensors Automotive engineering sensor systems Monitoring Cameras Safety Planning Advanced driver assistance system (ADAS) automotive perception autonomous driving cameras light detection and ranging (LiDAR) radars safety sensor data processing

来源：评论

学校读者我要写书评

暂无评论

Optimized Dissolved Oxygen Prediction Using Genetic Algorithm and Bagging Ensemble Learning for Smart Fish Farm

引用

IEEE sensorS JOURNAL 2023年第13期23卷 15153-15164页

作者： Khan, Prince Waqas Byun, Yung Cheol Gachon Univ Sch Comp Seongnam Si 13120 Gyeonggi Do South Korea Jeju Natl Univ Dept Comp Engn Major Elect Engn Inst Informat Sci & Technol Jeju 63243 South Korea

The field of aquaculture is one of the numerous scientific disciplines that benefit greatly from machine learning (ML). The amount of dissolved oxygen (DO), an important indicator of water quality in sustainable fish farming, affects the yield of aquatic production. It is essential to make DO projections in fishing ponds to carry out the process of artificial aeration. We present DO forecasts utilizing time series analysis based on data obtained from Hanwha Aqua Planet Jeju, located in South Korea. This information could form the basis of a data foundation for an early detection system and improved aquaculture farm management. This research presents a unique genetic algorithm (GA) called GA-based XGBoost, CatBoost, and extra tree (GA-XGCBXT) bagging ensemble model based on GAs. This model is built on extreme gradient boosting (XGBoost), CatBoost (CB), and extra trees (XTs). To select the most outstanding features, various methodologies that exhibit a strong association with the primary data were applied. The performance of the proposed model was evaluated by comparing it to actual sensor data that had been observed, both in the training and validation sets. The precise evaluation accuracy of the anticipated results of the recommended GA-XGCBXT model was determined using various performance indices. By utilizing the strategy we suggested, we acquired a root mean square error of 0.310. Our objective is to enhance the ML model for aquaculture so that academics and practitioners can employ applications for smart fish farming with complete reliability.

关键词： Fish Temperature sensors Predictive models Aquaculture Bagging Genetic algorithms Intelligent sensors Bagging ensemble learning dissolved oxygen (DO) electrical conductivity (EC) genetic algorithm (GA) oxidation-reduction potential (ORP) sensor data processing smart fish farm

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of a Multispectral-Sensing System With Automated Machine Learning for Multiplex Detection

引用

IEEE sensorS JOURNAL 2023年第19期23卷 22600-22607页

作者： Huerta, Juan M. Pirbhai, Munir Univ Texas Austin Dept Comp Sci Austin TX 78712 USA

Many analytical tests rely on colorimetric and fluorescent probes. A key factor that influences the adoption of these tests in resource-limited communities is the availability of inexpensive, user-friendly instruments able to detect their signals. In this work, we have built and tested such an instrument. It uses an off-the-shelf multispectral sensor interfaced with a Raspberry Pi Zero. We demonstrate its potential for detecting multiple analytes by monitoring the fluorescence from mixtures of quantum dots (QDs) of different colors. It was able to detect the signal from concentrations as low as 0.3 nM, making it suitable for biological applications. Instead of using complicated spectral deconvolution methods to extract the concentration of analytes present from the spectra acquired by the system, we implemented and evaluated the performance of six machine-learning (ML) algorithms for this application. We found that random forest regression (RFR) and Gaussian process regression (GPR) yielded the best fits between the predicted values and ground truths.

关键词： Quantum dots sensors Multiplexing Monitoring Fluorescence sensor phenomena and characterization Antibodies Optoelectronic/photonic sensors sensor data processing sensor phenomenology

来源：评论

学校读者我要写书评

暂无评论

DANA: Dimension-Adaptive Neural Architecture for Multivariate sensor data

引用

PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT 2021年第3期5卷 1-27页

作者： Malekzadeh, Mohammad Clegg, Richard Cavallaro, Andrea Haddadi, Hamed Imperial Coll London London England Queen Mary Univ London London England

Motion sensors embedded in wearable and mobile devices allow for dynamic selection of sensor streams and sampling rates, enabling several applications, such as power management and data-sharing control. While deep neural networks (DNNs) achieve competitive accuracy in sensor data classification, DNN architectures generally process incoming data from a fixed set of sensors with a fixed sampling rate, and changes in the dimensions of their inputs cause considerable accuracy loss, unnecessary computations, or failure in operation. To address these limitations, we introduce a dimension-adaptive pooling (DAP) layer that makes DNNs flexible and more robust to changes in sensor availability and in sampling rate. DAP operates on convolutional filter maps of variable dimensions and produces an input of fixed dimensions suitable for feedforward and recurrent layers. Further, we propose a dimension-adaptive training (DAT) procedure for enabling DNNs that use DAP to better generalize over the set of feasible data dimensions at inference time. DAT comprises the random selection of dimensions during the forward passes and optimization with accumulated gradients of several backward passes. Combining DAP and DAT, we show how to transform existing non-adaptive DNNs into a Dimension-Adaptive Neural Architecture (DANA), while keeping the same number of parameters. Compared to existing approaches, our solution provides better average classification accuracy over the range of possible data dimensions at inference time and does not require up-sampling or imputation, thus reducing unnecessary computations. Experimental results on seven datasets (four benchmark real-world datasets for human activity recognition and three synthetic datasets) show that DANA prevents significant losses in classification accuracy of the state-of-the-art DNNs and, compared to baselines, it better captures correlated patterns in sensor data under dynamic sensor availability and varying sampling rates.

关键词： Deep Neural Networks sensor data processing Adaptive Sampling sensor Selection

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：