Combined CNN-LSTM Deep Learning Algorithms for Recognizing Human Physical Activities in Large and Distributed Manners:A Recommendation System

Recognizing human activity(HAR)from data in a smartphone sensor plays an important role in the field of health to prevent chronic diseases.Daily and weekly physical activities are recorded on the smartphone and tell the user whether he is moving well or not.Typically,smartphones and their associated sensing devices operate in distributed and unstable environments.Therefore,collecting their data and extracting useful information is a significant challenge.In this context,the aimof this paper is twofold:The first is to analyze human behavior based on the recognition of physical activities.Using the results of physical activity detection and classification,the second part aims to develop a health recommendation system to notify smartphone users about their healthy physical behavior related to their physical activities.This system is based on the calculation of calories burned by each user during physical activities.In this way,conclusions can be drawn about a person’s physical behavior by estimating the number of calories burned after evaluating data collected daily or even weekly following a series of physical workouts.To identify and classify human behavior our methodology is based on artificial intelligence models specifically deep learning techniques like Long Short-Term Memory(LSTM),stacked LSTM,and bidirectional LSTM.Since human activity data contains both spatial and temporal information,we proposed,in this paper,to use of an architecture allowing the extraction of the two types of information simultaneously.While Convolutional Neural Networks(CNN)has an architecture designed for spatial information,our idea is to combine CNN with LSTM to increase classification accuracy by taking into consideration the extraction of both spatial and temporal data.The results obtained achieved an accuracy of 96%.On the other side,the data learned by these algorithms is prone to error and uncertainty.To overcome this constraint and improve performance(96%),we proposed to use the fusion mechanisms.The last combines deep learning classifiers tomodel non-accurate and ambiguous data to obtain synthetic information to aid in decision-making.The Voting and Dempster-Shafer(DS)approaches are employed.The results showed that fused classifiers based on DS theory outperformed individual classifiers(96%)with the highest accuracy level of 98%.Also,the findings disclosed that participants engaging in physical activities are healthy,showcasing a disparity in the distribution of physical activities between men and women.

Evaluation of Thermal Comfort and Energy Usage for an Enclosed Cavity Indifferent Climatic Zones of India

The utilization of energy in building sectors comprises 30–40%of the entire global energy consumption.Most of the energy is being utilized for cooling&heating the buildings.These cooling and heating depend on the nature of climate for different places.In this,the detailed analysis of the building envelope across five areas(viz.Srinagar,Jaisalmer,New Delhi,Thiruvananthapuram and Bangalore)representing different climatic zones had been carried out.Simulations are performed for these locations using eQUEST and ANSYS software.Three of the result output from the eQUEST simulation are used to assess the different cases.These outputs are:total electrical energy consumption of the year,peak cooling load&peak heating load for a particular time of the year.Temperature variations and airflow for a fan with moisture influence are also simulated for five different locations by using the radiation model and shear stress transport in ANSYS.The internal temperature distribution in accordance with an occupant is also compared and discussed for the five regions.Lastly,the predicted mean vote and predicted percentage of dissatisfaction are found to be in the range of−0.50 to−0.99 for all zones that signifies 13%to 30%of people are dissatisfied with the indoor environment.

The Quantification and Reporting of Negawatt-Hours with Flexible Energy Conservation Measure Verification Software (ECM-Tool)

In order to promote digital innovations in the field of energy use and monitoring in all end customer sectors, the Federal Ministry for Economic Affairs and Energy (BMWi) has launched the “Pilotprogramm Einsparzähler” in 2016. The program promotes the development of digital platforms following the “Efficiency First” principle, focusing not on individual projects but on the establishment of a business model. smartB successfully applied for subsidies for the development of a software tool, the architecture of which is the content of this open source paper. The tool applies a multivariate regression-model to model a given system’s energy consumption (significant energy uses or SEUs), adjusted to relevant external factors (e.g. weather) and given output levels or product properties. Thereby comparing energy consumption before and after an energy conservation measure (ECM), the tool allows for a quantification and verification of achieved energy savings as laid out in international standards for energy management (ISO, 2014). Achieved energy savings induced by an ECM and energy efficiency improvements cannot be measured directly. We use the term “negawatt-hour”, defined as a unit of energy saved as a direct result of energy conservation measures. International norms provide accepted standards to derive quantified savings in negawatt-hours from a qualified comparison between consumption before and after an ECM, as presented at the beginning of the paper.

双燃料船用发动机废能回收系统的技术经济比较

Nowadays alternative and innovative energy recovery solutions are adopted on board ships to reduce fuel consumption and harmful emissions.According to this,the present work compares the engine exhaust gas waste heat recovery and hybrid turbocharger technologies,which are used to improve the efficiency of a dual-fuel four-stroke(DF)marine engine.Both solutions aim to satisfy partly or entirely the ship’s electrical and/or thermal loads.For the engine exhaust gas waste heat recovery,two steam plant schemes are considered:the single steam pressure and the variable layout(single or dual steam pressure plant).In both cases,a heat recovery steam generator is used for the electric power energy generation through a steam turbine.The hybrid turbocharger is used to provide a part of the ship’s electric loads as well.The thermodynamic mathematical models of DF engines,integrated with the energy recovery systems,are developed in a Matlab-Simulink environment,allowing the comparison in terms of performance at different engine loads and fuels,which are Natural Gas(NG)and High Fuel Oil(HFO).The use of NG always involves better efficiency of the system for all the engine working conditions.It results that the highest efficiency value achievable is 56%at 50%maximum continuous rating(MCR)engine load.

Selective capture of Tl2O from flue gas with formation of p-n junction on V_(2)O_(5)-WO_(3)/TiO_(2)catalyst under working conditions

Thallium(Tl)compounds,highly toxic to biology,are usually released into flue gas during fossil/minerals combustion,and further distributed in water and soil.In this work,we fundamentally investigated the capture of gaseous Tl_(2)O by industrial V2O5-WO3/TiO_(2)catalyst under working condition in Tl-containing flue gas.Experimental and theoretical results indicated that the Tl_(2)O has significant electron-feeding capacity and easily donate electron to unoccupied orbitals of TiO_(2),leading to dismutation of Ti 2p and inartificial formation of p-n junction on TiO_(2)surface,which prompted Tl_(2)O selectively interacted with TiO_(2)in flue gas.Herein,we proposed and verified an effective way to capture gaseous Tl_(2)O,which offered almost the best choice to eliminate Tl emission from flue gas and expanded the function of the TiO_(2)-based catalyst.The formation of p-n junction on commercial V2O5-WO3/TiO_(2)catalyst under working condition was revealed for the first time,which can be a valuable reference for both heterocatalysis and electro/photocatalysis.

A Comparative Study of Different Drying Processes for a Deformable Saturated Porous Medium

Drying of a deformable saturated porous medium based on convective tempering is a novel method that can enhance energy efficiency and the quality of the dried product itself.In this experimental investigation,the performances of this specific technique are compared with those of a standard stationary drying process in terms of deformation,drying kinetics,moisture redistribution,and energy consumption.In particular,the response of a deformable saturated porous medium(Kaolin)is considered.The results are critically discussed pointing out advantages and drawbacks.

Impact of Artificial Compressibility on the Numerical Solution of Incompressible Nanofluid Flow

The numerical solution of compressible flows has become more prevalent than that of incompressible flows.With the help of the artificial compressibility approach,incompressible flows can be solved numerically using the same methods as compressible ones.The artificial compressibility scheme is thus widely used to numerically solve incompressible Navier-Stokes equations.Any numerical method highly depends on its accuracy and speed of convergence.Although the artificial compressibility approach is utilized in several numerical simulations,the effect of the compressibility factor on the accuracy of results and convergence speed has not been investigated for nanofluid flows in previous studies.Therefore,this paper assesses the effect of this factor on the convergence speed and accuracy of results for various types of thermo-flow.To improve the stability and convergence speed of time discretizations,the fifth-order Runge-Kutta method is applied.A computer program has been written in FORTRAN to solve the discretized equations in different Reynolds and Grashof numbers for various grids.The results demonstrate that the artificial compressibility factor has a noticeable effect on the accuracy and convergence rate of the simulation.The optimum artificial compressibility is found to be between 1 and 5.These findings can be utilized to enhance the performance of commercial numerical simulation tools,including ANSYS and COMSOL.

Fluid Flow and Mixed Heat Transfer in a Horizontal Channel with an Open Cavity and Wavy Wall

Heat exchangers are utilized extensively in different industries and technologies.Consequently,optimizing heat exchangers has been a major concern among researchers.Although various studies have been conducted to improve the heat transfer rate,the use of a wavy wall in the presence of different types of heat transfer mechanisms has not been investigated.This study thus investigates the mixed heat transmission behavior of fluid in a horizontal channel with a cavity and a hot,wavy wall.The fluid flow in the channel is considered laminar,and the governing equations including continuity,momentum,and energy are all solved numerically.The numerical solution is stabilized by using a first-order multi-dimensional characteristic-based scheme in combination with a fifth-order Runge-Kutta method.The flow and heat transfer effects of varying Richardson numbers,Reynolds numbers,wave amplitude,wavelength,channel height,and cavity width are examined.The results indicate that the mean Nusselt number increases with an increase in Reynolds number,wave amplitude,and cavity width,while it decreases with an increase in Richardson number,wavelength,and channel height.The minimum Nusselt number is calculated to be 0.7,whereas the maximum Nusselt number is 27.09.The Nusselt number has only increased by 40%in the higher depths of the cavity,despite the Richardson number being 10,000 times larger.But this figure increases to 130%at lower depths.The mean Nusselt number is thus significantly influenced by channel height and cavity width.The influence of wave amplitude on the mean Nusselt number is twice that of wavelength.

Role of Calcination Temperature on Isosorbide Production from Sorbitol Dehydration over the Catalyst Derived from Ce(IV)Sulfate

Isosorbide is a multi-purpose chemical that can be produced from renewable resources.Specifically,it has been investigated as a replacement for toxic bisphenol A(BPA)in the production of polycarbonate(PC).In this study,the synthesis of isosorbide by sorbitol dehydration using a cerium-based catalyst derived from calcined cerium(IV)sulfate(300°C,400°C,450°C,500°C,and 650°C)was investigated.The reaction occurred in a high-pressure reactor containing nitrogen gas.Advanced instrumental techniques were applied to analyze the characteristics of the calcined catalyst.The results showed that the calcined catalysts demonstrated different crystalline structures and sulfate species at different temperatures.However,the acidic properties(strength and amount)of the catalyst did not change with the calcination temperature.The cerium(IV)sulfate calcined at 400°C exhibited the best catalytic performance,achieving the highest isosorbide yield(55.7%)and complete conversion of sorbitol at 180°C,20 bar of N2,and 6 h using CeSO-400.The presence of a sulfate group on the catalyst was the most important factor in determining the catalytic performance of sorbitol dehydration to isosorbide.This work suggests that CeSO-400 catalysts may play an important role in reducing reaction conditions.

Efficient acidic oxygen evolution reaction electrocatalyzed by iridium-based 12L-perovskites comprising trinuclear face-shared IrO6 octahedral strings

Development of cost-effective and highly active oxygen evolution catalysts operating well in acidic media is a critical challenge in proton exchange membrane water electrolysis.Herein,we present a class of iridium-based 12L-perovskites(Ba4MIr3O12;M=Pr,Bi,Nb)as novel low-iridium electrocatalysts for oxygen evolution reaction under acidic conditions.These 12L-perovskites contain trinuclear face-shared Ir O6octahedral strings—unique subunits that are not found in the previously-reported iridium-based electrocatalysts.The catalytic activities of 12L-perovskites(Ba4MIr3O12)are found to be related to the location of O 2p-band center,which is influenced by the B-site nonprecious element(i.e.,Pr,Bi or Nb).Our experimental results show that Ba4PrIr3O12is the most active electrocatalyst among the materials we synthesize,and contains 55%less iridium than the benchmark catalyst IrO2,while exhibiting higher catalytic activity.In the presence of Ba4PrIr3O12,transient leaching process of Ba and Pr takes place during electrochemical process,contributing to the surface reconstruction of the pristine catalysts.Further experimental results reveal that the formation of under-coordinated Ir Ox-rich surface and easier generation of active intermediate IrVare mainly responsible for the good activity of Ba4PrIr3O12.

Maximum Power Point Tracking Control Using Neural Networks for Stand-Alone Photovoltaic Systems

The employment of maximum power point tracking techniques in the photovoltaic power systems is well known and even of immense importance. There are various techniques to track the maximum power point reported in several literatures. In such context, there is an increasing interest in developing a more appropriate and effective maximum power point tracking control methodology to ensure that the photovoltaic arrays guarantee as much of their available output power as possible to the load for any temperature and solar radiation levels. In this paper, theoretical details of the work, carried out to develop and implement a maximum power point tracking controller using neural networks for a stand-alone photovoltaic system, are presented. Attention has been also paid to the command of the power converter to achieve maximum power point tracking. Simulations results, using Matlab/Simulink software, presented for this approach under rapid variation of insolation and temperature conditions, confirm the effectiveness of the proposed method both in terms of efficiency and fast response time. Negligible oscillations around the maximum power point and easy implementation are the main advantages of the proposed maximum power point tracking (MPPT) control method.

Modeling and Validation of the Ice Growth in an Ice Storage System

This work deals with the optimization of the icing process in an ice storage system.It is focused on the improvement of the icing behavior,which is to be achieved by different heat exchanger geometries in the ice storage tank.Therefore,CFD simulations were implemented to acquire and visualize the flow conditions,the temperature behavior and the growth of the ice layer during the cooling process.The results are compared and validated with model experiments on an experimental ice storage.It could be shown that the heat extraction of current technologies can be increased by more than 50% by using geometries that are more efficient.

利用声场双耳互相关函数和声源自相关函数计算音乐信号与脉冲响应卷积信号的IACC(英文)

双耳脉冲响应(BIRs)是用以表征音乐厅和歌剧院声场特征的参量.由于BIRs是表征声场的转移函数,因此,在消声室中录制的声源信号与BIRs卷积,就代表在实际声场中听到的信号.为了探究原信号的声学特征,一种有效的方法是计算其自相关函数(ACF),因为从ACF中导出的参量能与听者的主观优选良好相关.因此可以说,卷积与相关是室内声学中最重要的计算方法.文中通过将BIRs导出的双耳互相关函数(IACF)和将干信号与BIRs卷积后的IACF作比较,探讨了声源信号与声场之间的关系.在特定条件下,卷积与相关是等同的,此时,干信号与BIRs卷积后的IACC可直接由BIRs导出的IACC与干信号的ACF的有效时间τ_e来表示.

意大利歌剧院的体形、体量及材料对声场的影响(英文)

针对意大利歌剧院进行研究,着重研究建筑设计对厅堂音质的影响.对两个剧院的常规音质参量进行了测量.这两座剧院是由同一建筑师Antonio Galli Bibiena设计的,分别是波仑亚的市立剧院和曼图亚的科学剧院.二者具有相当近似的形式,但尺寸不同,所用的材料也各异,前者是用砖石建成,后者是用木料建成,因此在整修前采用了许多预应力钢筋混凝土结构.文中提供了不少数据并给出了对这些数据加以比较和分析的结果,特别是关于某些特征尺寸与扫频信号各可闻频率产生的空间听觉感受之间相关性的分析,以及若干有关材料和体型对IACC和EDT等音质参量的影响的思考.

在脉冲响应频率分析比较中对客观声学参数EDT的新认识(英文)

对于客观参量EDT,或者更确切地说,对于稳态声场衰变曲线的初始斜率与包括所有简正模式在内的平均阻尼常数之间关系的研究工作,已有一些研究者做过,如H.库特鲁夫就曾指出此参量与所测试环境的几何细节有密切关系.因此,文中选择它作为分析工具,以一种较为深入的方式,通过对一个歌剧院的研究,来检验这种关系.通过对脉冲响应在频域上进行分析,这在前人的工作中也采用过.文中对EDT从倍频程以及1/3倍频程加以研究,并利用在Matlab环境下开发的一些工具来探讨乐池的简正模式与从频带中心频率导出的最大的时间值之间的相关关系.研究表明,在所考察的环境中简正模式与衰变曲线的初始斜率之间有良好的相关关系,与自相关系数(ACF)也有良好的相关关系;研究还证实,用于分析的参量本身既是时间的函数,也是脉冲响应频率变化的函数.

Fast and Accurate Thoracic SPECT Image Reconstruction

In Single-Photon Emission Computed Tomography(SPECT),the reconstructed image has insufficient contrast,poor resolution and inaccurate volume of the tumor size due to physical degradation factors.Generally,nonstationary filtering of the projection or the slice is one of the strategies for correcting the resolution and therefore improving the quality of the reconstructed SPECT images.This paper presents a new 3D algorithm that enhances the quality of reconstructed thoracic SPECT images and reduces the noise level with the best degree of accuracy.The suggested algorithm is composed of three steps.The first one consists of denoising the acquired projections using the benefits of the complementary properties of both the Curvelet transformand theWavelet transforms to provide the best noise reduction.The second step is a simultaneous reconstruction of the axial slices using the 3D Ordered Subset Expectation Maximization(OSEM)algorithm.The last step is post-processing of the reconstructed axial slices using one of the newest anisotropic diffusion models named Partial Differential Equation(PDE).The method is tested on two digital phantoms and clinical bone SPECT images.A comparative study with four algorithms reviewed on state of the art proves the significance of the proposed method.In simulated data,experimental results show that the plot profile of the proposed model keeps close to the original one compared to the other algorithms.Furthermore,it presents a notable gain in terms of contrast to noise ratio(CNR)and execution time.The proposed model shows better results in the computation of contrast metric with a value of 0.68±7.2 and the highest signal to noise ratio(SNR)with a value of 78.56±6.4 in real data.The experimental results prove that the proposed algorithm is more accurate and robust in reconstructing SPECT images than the other algorithms.It could be considered a valuable candidate to correct the resolution of bone in the SPECT images.

High Efficiency Crypto-Watermarking System Based on Clifford-Multiwavelet for 3D Meshes Security

Since 3D mesh security has become intellectual property,3D watermarking algorithms have continued to appear to secure 3D meshes shared by remote users and saved in distant multimedia databases.The novelty of our approach is that it uses a new Clifford-multiwavelet transform to insert copyright data in a multiresolution domain,allowing us to greatly expand the size of the watermark.After that,our method does two rounds of insertion,each applying a different type of Clifford-wavelet transform.Before being placed into the Clifford-multiwavelet coefficients,the watermark,which is a mixture of the mesh description,source mesh signature(produced using SHA512),and a logo encrypted using the RSA(Ronald Shamir Adleman)technique,is encoded using Turbo-code.Using the Least Significant Bit method steps,data embedding involves modulation and insertion processes.Finally,the watermarked mesh is reconstructed using the inverse Cliffordmultiwavelet transform.Due to the utilization of a hybrid insertion domain,our technique has demonstrated a very high insertion rate while retaining mesh quality.The mesh is watermarked,and the extracted data is acquired in real-time.Our approach is also resistant to the most common types of attacks.Our findings reveal that the current approach improves on previous efforts.

Impact of Flow Rate in Integration with Solar Radiation on Color and COD Removal in Dye Contaminated Textile Industry Wastewater:Optimization Study

Dyes are an integral part of the dying industry and have significantly resulted in environmental pollution by altering the standardwater quality after their discharge into the water bodies.The culprits behind the altered water quality are the pretreatment chemicals used during dying manufacturing processes.Various advanced treatmentmethods using conventional and advanced treatment options including solar energy have been put forth by researchers for the treatment of the dying effluents but,these methods have not proved significantly considerable.Therefore,the present study intends to check the efficiency of solar parabolic trough collector for treating the dying effluents in terms of color and COD.However,other wastewater parameters(BOD,nitrate and phosphate)have also been considered for this experimental analysis.Four standard flow rates(0.5,1.3,1.95 and 2.6 L/M)were maintained during the experiment for six hours at solar intensity(849.3±21.2W/m^(2))and the optimized flow rate(1.95 L/M)was detected and considered for further study during the present experiment.The color concentration showed a significant reduction(≥76.4%)by treatment with the designed solar reactor.Similar significant results were also noticed in terms of COD(79%).In this context,the current experimental study provides ideas on the decolorization and COD reduction efficiency with optimal flow rate in terms of cost-effectiveness with designed experimental reactor which could be further used and implemented for advanced scientific purposes.