An Efficient ResNetSE Architecture for Smoking Activity Recognition from Smartwatch

Smoking is a major cause of cancer,heart disease and other afflictions that lead to early mortality.An effective smoking classification mechanism that provides insights into individual smoking habits would assist in implementing addiction treatment initiatives.Smoking activities often accompany other activities such as drinking or eating.Consequently,smoking activity recognition can be a challenging topic in human activity recognition(HAR).A deep learning framework for smoking activity recognition(SAR)employing smartwatch sensors was proposed together with a deep residual network combined with squeeze-and-excitation modules(ResNetSE)to increase the effectiveness of the SAR framework.The proposed model was tested against basic convolutional neural networks(CNNs)and recurrent neural networks(LSTM,BiLSTM,GRU and BiGRU)to recognize smoking and other similar activities such as drinking,eating and walking using the UT-Smoke dataset.Three different scenarios were investigated for their recognition performances using standard HAR metrics(accuracy,F1-score and the area under the ROC curve).Our proposed ResNetSE outperformed the other basic deep learning networks,with maximum accuracy of 98.63%.

Automatic Recognition of Construction Worker Activities Using Deep Learning Approaches and Wearable Inertial Sensors

The automated evaluation and analysis of employee behavior in an Industry 4.0-compliant manufacturingfirm are vital for the rapid and accurate diagnosis of work performance,particularly during the training of a new worker.Various techniques for identifying and detecting worker performance in industrial applications are based on computer vision techniques.Despite widespread com-puter vision-based approaches,it is challenging to develop technologies that assist the automated monitoring of worker actions at external working sites where cam-era deployment is problematic.Through the use of wearable inertial sensors,we propose a deep learning method for automatically recognizing the activities of construction workers.The suggested method incorporates a convolutional neural network,residual connection blocks,and multi-branch aggregate transformation modules for high-performance recognition of complicated activities such as con-struction worker tasks.The proposed approach has been evaluated using standard performance measures,such as precision,F1-score,and AUC,using a publicly available benchmark dataset known as VTT-ConIoT,which contains genuine con-struction work activities.In addition,standard deep learning models(CNNs,RNNs,and hybrid models)were developed in different empirical circumstances to compare them to the proposed model.With an average accuracy of 99.71%and an average F1-score of 99.71%,the experimentalfindings revealed that the suggested model could accurately recognize the actions of construction workers.Furthermore,we examined the impact of window size and sensor position on the identification efficiency of the proposed method.

A Comprehensive Evaluation of State-of-the-Art Deep Learning Models for Road Surface Type Classification

In recent years,as intelligent transportation systems(ITS)such as autonomous driving and advanced driver-assistance systems have become more popular,there has been a rise in the need for different sources of traffic situation data.The classification of the road surface type,also known as the RST,is among the most essential of these situational data and can be utilized across the entirety of the ITS domain.Recently,the benefits of deep learning(DL)approaches for sensor-based RST classification have been demonstrated by automatic feature extraction without manual methods.The ability to extract important features is vital in making RST classification more accurate.This work investigates the most recent advances in DL algorithms for sensor-based RST classification and explores appropriate feature extraction models.We used different convolutional neural networks to understand the functional architecture better;we constructed an enhanced DL model called SE-ResNet,which uses residual connections and squeeze-and-excitation mod-ules to improve the classification performance.Comparative experiments with a publicly available benchmark dataset,the passive vehicular sensors dataset,have shown that SE-ResNet outperforms other state-of-the-art models.The proposed model achieved the highest accuracy of 98.41%and the highest F1-score of 98.19%when classifying surfaces into segments of dirt,cobblestone,or asphalt roads.Moreover,the proposed model significantly outperforms DL networks(CNN,LSTM,and CNN-LSTM).The proposed RE-ResNet achieved the classification accuracies of asphalt roads at 98.98,cobblestone roads at 97.02,and dirt roads at 99.56%,respectively.

Deep Pyramidal Residual Network for Indoor-Outdoor Activity Recognition Based on Wearable Sensor

Recognition of human activity is one of the most exciting aspects of time-series classification,with substantial practical and theoretical impli-cations.Recent evidence indicates that activity recognition from wearable sensors is an effective technique for tracking elderly adults and children in indoor and outdoor environments.Consequently,researchers have demon-strated considerable passion for developing cutting-edge deep learning sys-tems capable of exploiting unprocessed sensor data from wearable devices and generating practical decision assistance in many contexts.This study provides a deep learning-based approach for recognizing indoor and outdoor movement utilizing an enhanced deep pyramidal residual model called Sen-PyramidNet and motion information from wearable sensors(accelerometer and gyroscope).The suggested technique develops a residual unit based on a deep pyramidal residual network and introduces the concept of a pyramidal residual unit to increase detection capability.The proposed deep learning-based model was assessed using the publicly available 19Nonsens dataset,which gathered motion signals from various indoor and outdoor activities,including practicing various body parts.The experimental findings demon-strate that the proposed approach can efficiently reuse characteristics and has achieved an identification accuracy of 96.37%for indoor and 97.25%for outdoor activity.Moreover,comparison experiments demonstrate that the SenPyramidNet surpasses other cutting-edge deep learning models in terms of accuracy and F1-score.Furthermore,this study explores the influence of several wearable sensors on indoor and outdoor action recognition ability.

Pre-Impact and Impact Fall Detection Based on a Multimodal Sensor Using a Deep Residual Network

Falls are the contributing factor to both fatal and nonfatal injuries in the elderly.Therefore,pre-impact fall detection,which identifies a fall before the body collides with the floor,would be essential.Recently,researchers have turned their attention from post-impact fall detection to pre-impact fall detection.Pre-impact fall detection solutions typically use either a threshold-based or machine learning-based approach,although the threshold value would be difficult to accu-rately determine in threshold-based methods.Moreover,while additional features could sometimes assist in categorizing falls and non-falls more precisely,the esti-mated determination of the significant features would be too time-intensive,thus using a significant portion of the algorithm’s operating time.In this work,we developed a deep residual network with aggregation transformation called FDSNeXt for a pre-impact fall detection approach employing wearable inertial sensors.The proposed network was introduced to address the limitations of fea-ture extraction,threshold definition,and algorithm complexity.After training on a large-scale motion dataset,the KFall dataset,and straightforward evaluation with standard metrics,the proposed approach identified pre-impact and impact falls with high accuracy of 91.87 and 92.52%,respectively.In addition,we have inves-tigated fall detection’s performances of three state-of-the-art deep learning models such as a convolutional neural network(CNN),a long short-term memory neural network(LSTM),and a hybrid model(CNN-LSTM).The experimental results showed that the proposed FDSNeXt model outperformed these deep learning models(CNN,LSTM,and CNN-LSTM)with significant improvements.

Driving Activity Classification Using Deep Residual Networks Based on Smart Glasses Sensors

Accidents are still an issue in an intelligent transportation system,despite developments in self-driving technology(ITS).Drivers who engage in risky behavior account for more than half of all road accidents.As a result,reckless driving behaviour can cause congestion and delays.Computer vision and multimodal sensors have been used to study driving behaviour categorization to lessen this problem.Previous research has also collected and analyzed a wide range of data,including electroencephalography(EEG),electrooculography(EOG),and photographs of the driver’s face.On the other hand,driving a car is a complicated action that requires a wide range of body move-ments.In this work,we proposed a ResNet-SE model,an efficient deep learning classifier for driving activity clas-sification based on signal data obtained in real-world traffic conditions using smart glasses.End-to-end learning can be achieved by combining residual networks and channel attention approaches into a single learning model.Sensor data from 3-point EOG electrodes,tri-axial accelerometer,and tri-axial gyroscope from the Smart Glasses dataset was utilized in this study.We performed various experiments and compared the proposed model to base-line deep learning algorithms(CNNs and LSTMs)to demonstrate its performance.According to the research results,the proposed model outperforms the previous deep learning models in this domain with an accuracy of 99.17%and an F1-score of 98.96%.

Modeling curve dynamics and spatial geometry characteristics of rice leaves

The objective of this work was to develop a dynamic model for describing leaf curves and a the rice leaf （including sub-models for unexpanded leaf blades, expanded leaf blades, and dimensional （3D） dynamic visualization of rice leaves by combining relevant models detailed spatial geometry model of leaf sheaths）, and to realize three- Based on the experimental data of different cultivars and nitrogen （N） rates, the time-course spatial data of leaf curves on the main stem were collected during the rice development stage, then a dynamic model of the rice leaf curve was developed using quantitative modeling technology. Further, a detailed 3D geometric model of rice leaves was built based on the spatial geometry technique and the non-uniform rational B-spline （NURBS） method. Validating the rice leaf curve model with independent field experiment data showed that the average distances between observed and predicted curves were less than 0.89 and 1.20 cm at the tilling and jointing stages, respectively. The proposed leaf curve model and leaf spatial geometry model together with the relevant previous models were used to simulate the spatial morphology and the color dynamics of a single leaf and of leaves on the rice plant after different growing days by 3D visualization technology. The validation of the leaf curve model and the results of leaf 3D visualization indicated that our leaf curve model and leaf spatial geometry model could efficiently predict the dynamics of rice leaf spatial morphology during leaf development stages. These results provide a technical support for related research on virtual rice.

The roles of black phosphorus in performance enhancement of halide perovskite solar cells

Hybrid organic-inorganic perovskite solar cells(PSCs) are considered to be the most promising thirdgeneration photovoltaic(PV) technology with the most rapid rate of increase in the power conversion efficiency(PCE). To date, their PCE values are comparable to the established photovoltaic technologies such as crystalline silicon. Intensive research activities associated with PSCs have been being performed,since 2009, aiming to further boost the device performance in terms of efficiency and stability via different strategies in order to accelerate the progress of commercialization. The emerging 2 D black phosphorus(BP) is a novel class of semiconducting material owing to its unique characteristics, allowing them to become attractive materials for applications in a variety of optical and electronic devices, which have been comprehensively reviewed in the literature. However, comprehensive reviews focusing on the application of BP in PSCs are scarce in the community. This review discusses the research works with the incorporation of BP as a functional material in PSCs. The methodology as well as the effects of employing BP in different regions of PSCs are summarized. Further challenges and potential research directions are also highlighted.

A Solution for Scalable Routing in Depth Divisions-Based DUSNs via Adding a Scalable Parameter to Control Depth Clusters: Creating an Energy Efficient and Low Delay NI-Independent Communication Protocol

Due to effectiveness of network layer on general performance of networks, designing routing protocols is very important for lifetime and traffic efficiency in wireless sensor networks. So in this paper, we are going to represent an efficient and scalable version of depth-based routing (DBR) protocol that is limited by depth divisions-policy. In fact the new version is a network information independent routing protocol for acoustic communications. Proposed method by use of depth clustering is able to reduce consumed energy and end-to-end delay in dense underwater sensor networks (DUSNs) and this issue is proved by simulation.

Research on Ant Colony Algorithm in Vehicle Operation Adjustment Based on IOT

Automatic solution of vehicle operation adjustment is the important content in realizing vehicle traffic command automation on Internet of Things platform. Based on both the organization realization of Internet of Things platform and the merging vehicle operation adjustment into the Flow-Shop scheduling problem in manufacturing systems,this paper has constructed the optimization model with a two-lane vehicle operation adjustment. With respect to the large model solution space and complex constraints,a better solution algorithm is proposed based on ant colony algorithm for optimal quick solution. The simulation results show that the algorithm is feasible and the approximate optimal solution can be quickly obtained.

Microarray image processing by order morphology

An order morphology transform is presented to filter and segment which is done by different percentile. Filter Is done flexibly by different size structure element with several percent. The threshold which for normal segment way such as Ostu decides is more lower when a low SNR Image Is processing especially the foreground is small or dot. The foreground can not be identified effectively in those case. Adaptive multl-threshold segment Is defined by percent value of order morphology. Analysis and results indicate that this way is more adaptive to different SNR fluorescence images. It could be applied to process high-density chips.

H_∞ consensus control of a class of second-order multi-agent systems without relative velocity measurement

This paper studies consensus control problems for a class of second-order multi-agent systems without relative velocity measurement. Some dynamic neighbour-based rules are adopted for the agents in the presence of external disturbances. A sufficient condition is derived to make all agents achieve consensus while satisfying desired H∞ performance. Finally, numerical simulations are provided to show the effectiveness of our theoretical results.

Extended Dyna-Q Algorithm for Path Planning of Mobile Robots

This paper presents an extended Dyna-Q algorithm to improve efficiency of the standard Dyna-Q algorithm.In the first episodes of the standard Dyna-Q algorithm,the agent travels blindly to find a goal position.To overcome this weakness,our approach is to use a maximum likelihood model of all state-action pairs to choose actions and update Q-values in the first few episodes.Our algorithm is compared with one-step Q-learning algorithm and the standard Dyna-Q algorithm for the path planning problem in maze environments.Experimental results show that the proposed algorithm is more efficient than the one-step Q-learning algorithm as well as the standard Dyna-Q algorithm,especially in the large environment of states.

Design and Analysis of a Compact Band Notch UWB Antenna for Body Area Network

This paper presents the design of a small printed ultra wideband antenna with Band Notched characteristics. Both the free space and on-body performances of this antenna were investigated through simulation. The newly designed UWB antenna is more revised small form factor sized, with the ability to avoid interference caused by WLAN (5.15 - 5.825 GHz) and WiMAX (5.25 - 5.85 GHz) systems with a band notch. The return loss response, gain, radiation pattern on free space of the antenna were investigated. After that, the on-body performances were tested on 3-layer human body model with radiation pattern, gain, return loss, and efficiency at 3.5, 5.7, 8, 10 GHz and all the results were compared with free space results. As the on-body performance was very good, the proposed antenna will be suitable to be used for multi-purpose medical applications and sports performance monitoring.

Multi-Scale Network with Integrated Attention Unit for Crowd Counting

Estimating the crowd count and density of highly dense scenes witnessed in Muslim gatherings at religious sites in Makkah and Madinah is critical for developing control strategies and organizing such a large gathering.Moreover,since the crowd images in this case can range from low density to high density,detection-based approaches are hard to apply for crowd counting.Recently,deep learning-based regression has become the prominent approach for crowd counting problems,where a density-map is estimated,and its integral is further computed to acquire the final count result.In this paper,we put forward a novel multi-scale network(named 2U-Net)for crowd counting in sparse and dense scenarios.The proposed framework,which employs the U-Net architecture,is straightforward to implement,computationally efficient,and has single-step training.Unpooling layers are used to retrieve the pooling layers’erased information and learn hierarchically pixelwise spatial representation.This helps in obtaining feature values,retaining spatial locations,and maximizing data integrity to avoid data loss.In addition,a modified attention unit is introduced and integrated into the proposed 2UNet model to focus on specific crowd areas.The proposed model concentrates on balancing the number of model parameters,model size,computational cost,and counting accuracy compared with other works,which may involve acquiring one criterion at the expense of other constraints.Experiments on five challenging datasets for density estimation and crowd counting have shown that the proposed model is very effective and outperforms comparable mainstream models.Moreover,it counts very well in both sparse and congested crowd scenes.The 2U-Net model has the lowest MAE in both parts(Part A and Part B)of the ShanghaiTech,UCSD,and Mall benchmarks,with 63.3,7.4,1.5,and 1.6,respectively.Furthermore,it obtains the lowest MSE in the ShanghaiTech-Part B,UCSD,and Mall benchmarks with 12.0,1.9,and 2.1,respectively.

A Robust Alternative Virtual Key Input Scheme for Virtual Keyboard Systems

Towards virtual keyboard design and realization, the work in this paper presents a robust key input method for deployment in virtual keyboard systems. The proposed scheme harnesses the information contained within shadows towards robustifying virtual key input. This scheme allows for input efficiency to be guaranteed in situations of relatively lower illumination, a core challenge associated with virtual keyboards. Contributions of the paper are two-fold. Firstly the paper pre-sents an approach towards effectively applying shadow information towards robustifying virtual key input systems;Secondly, through morphological operations, the performance of this input method is boosted by means of effectively alleviating noise and its impacts on overall algorithm performance, while highlighting the necessary features towards an efficient performance. While previous contributions have followed a similar trend, the contribution of this paper stresses on the intensification and improvement of both shadow and finger-tip feature highlighting schemes towards overall performance improvement. Experimental results presented in the paper demon-strate the efficiency and robustness of the approach. The attained results suggest that the scheme is capable of attaining high performances in terms of accuracy while being capable of addressing false touch situations.

Design and Simulation of an Inverter Drive System with a Display for a Renewable Energy System in the Rural Isolated Communities of Uganda

In medical diagnostics, therapeutic, laboratory, intensive care unit devices, and machines application, two form of Electrical Energy is utilized. Alternatives current (AC) and Direct current (DC) form. In this paper an inverter driver system with a display model is made using MATLAB and its specific tool box of Simulink, the process will involve converting single phase alternating current power to direct current using rectifier made from ordinary normal diodes then converted to three phase using three-arm insulated gate bipolar transistors this is commonly known as inverter bridge which is sufficient enough to run three phase loads depending on the application requirement. The system uses a five-level inverter with low levels of distortions and ripples in the equipment output, this increase and improves the performance of the system. Using carefully selected passive and active elements such as capacitor resistors, inductors, diodes, and transistor system in inverter, decreases the number of switches and boosts the efficiency of the system. This inverter drive system helps us to run three phase machines in the health facility at the same frequency of single phase. The inverter system allows a smaller smoothing capacitor in the DC-AC link as proposed. Large smoothing capacitors are conventionally essential in such converters to absorb power ripple at twice the frequency of the power supply. The proposed network topology consists of an indirect matrix converter and an active snubber to absorb the power ripple, and does not necessitate a reactor or large smoothing capacitor. Simulation result is shown using MATLAB software and used to verify system operation principle as well as circuit development and their control mechanism for a single-to-three-phase power inverter system. The results from experiment show that for a 1 kW-class prototype circuit system, the power ripple at twice the frequency of the power supply can be adequately suppressed using a buffer capacitor of low values.

Neuropsychological detection and prediction using machine learning algorithms:a comprehensive review

Neuropsychological disorders(e.g.,dementia,epilepsy,brain cancer,autism,stroke,and multiple sclerosis)ad-versely affect the quality of life of patients and their families;moreover,in some instances,they may lead to loss of life.The primary aim was to evaluate and compare the use of machine learning in neuropsychological research in contrast to traditional approaches such as through case studies.This was achieved by referring to earlier studies on this subject.This article presented the use of support vector machines(SVMs)and convolu-tional neural networks(CNN)for detecting and predicting neuropsychological diseases,such as dementia and Alzheimer’s disease.Challenges in using these models include data availability,quality,variability,model inter-pretability,and validation.Experimental findings have demonstrated the potential of these models in this field.It has been shown that SVM models are robust and efficient in processing and classifying data,particularly in neuroimaging applications,such as magnetic resonance imaging(MRI).CNNs have excelled in handling visual input;thus,they have been used in neuroimaging segregation,recognition,and classification,with applications in brain tumor segmentation,radiation therapy,robotic neurosurgery,and disease prediction.Future research will explore asymmetric differences among left-and right-handed patients,incorporate longitudinal studies,and utilize larger sample sizes.The use of machine learning models has the potential to revolutionize the diagnosis and treatment of neuropsychological diseases,allowing for early detection and intervention.This approach could offer significant advantages to healthcare,such as cost-effective diagnosis and treatment,to help save lives and preserve the quality of life of patients.

A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements

The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks(DNNs).A significant challenge in this field is the limited availability of measurement data for full-scale structures,which is addressed in this paper by generating data sets using a reduced finite element(FE)model constructed by SAP2000 software and the MATLAB programming loop.The surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement devices.The proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential scenarios.To achieve the most generalized surrogate model,the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training process.The approach’s effectiveness,efficiency,and applicability are demonstrated by two numerical examples.The study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured data.Overall,the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms,which can be computationally intensive.This approach also shows potential for broader applications in structural damage detection.

Predicting the friction angle of clays using a multi-layer perceptron neural network enhanced by yeo-johnson transformation and coral reefs optimization

The accurate prediction of the friction angle of clays is crucial for assessing slope stability in engineering applications.This study addresses the importance of estimating the friction angle and presents the development of four soft computing models:YJ-FPA-MLPnet,YJ-CRO-MLPnet,YJ-ACOC-MLPnet,and YJCSA-MLPnet.First of all,the Yeo-Johnson(YJ)transformation technique was used to stabilize the variance of data and make it more suitable for parametric statistical models that assume normality and equal variances.This technique is expected to improve the accuracy of friction angle prediction models.The friction angle prediction models then utilized multi-layer perceptron neural networks(MLPnet)and metaheuristic optimization algorithms to further enhance performance,including flower pollination algorithm(FPA),coral reefs optimization(CRO),ant colony optimization continuous(ACOC),and cuckoo search algorithm(CSA).The prediction models without the YJ technique,i.e.FPA-MLPnet,CRO-MLPnet,ACOC-MLPnet,and CSA-MLPnet,were then compared to those with the YJ technique,i.e.YJ-FPA-MLPnet,YJ-CRO-MLPnet,YJ-ACOC-MLPnet,and YJ-CSA-MLPnet.Among these,the YJ-CRO-MLPnet model demonstrated superior reliability,achieving an accuracy of up to 83%in predicting the friction angle of clay in practical engineering scenarios.This improvement is significant,as it represents an increase from 1.3%to approximately 20%compared to the models that did not utilize the YJ transformation technique.