Prediction of Geopolymer Concrete Compressive Strength Using Convolutional Neural Networks

Geopolymer concrete emerges as a promising avenue for sustainable development and offers an effective solution to environmental problems.Its attributes as a non-toxic,low-carbon,and economical substitute for conventional cement concrete,coupled with its elevated compressive strength and reduced shrinkage properties,position it as a pivotal material for diverse applications spanning from architectural structures to transportation infrastructure.In this context,this study sets out the task of using machine learning(ML)algorithms to increase the accuracy and interpretability of predicting the compressive strength of geopolymer concrete in the civil engineering field.To achieve this goal,a new approach using convolutional neural networks(CNNs)has been adopted.This study focuses on creating a comprehensive dataset consisting of compositional and strength parameters of 162 geopolymer concrete mixes,all containing Class F fly ash.The selection of optimal input parameters is guided by two distinct criteria.The first criterion leverages insights garnered from previous research on the influence of individual features on compressive strength.The second criterion scrutinizes the impact of these features within the model’s predictive framework.Key to enhancing the CNN model’s performance is the meticulous determination of the optimal hyperparameters.Through a systematic trial-and-error process,the study ascertains the ideal number of epochs for data division and the optimal value of k for k-fold cross-validation—a technique vital to the model’s robustness.The model’s predictive prowess is rigorously assessed via a suite of performance metrics and comprehensive score analyses.Furthermore,the model’s adaptability is gauged by integrating a secondary dataset into its predictive framework,facilitating a comparative evaluation against conventional prediction methods.To unravel the intricacies of the CNN model’s learning trajectory,a loss plot is deployed to elucidate its learning rate.The study culminates in compelling findings that underscore the CNN model’s accurate prediction of geopolymer concrete compressive strength.To maximize the dataset’s potential,the application of bivariate plots unveils nuanced trends and interactions among variables,fortifying the consistency with earlier research.Evidenced by promising prediction accuracy,the study’s outcomes hold significant promise in guiding the development of innovative geopolymer concrete formulations,thereby reinforcing its role as an eco-conscious and robust construction material.The findings prove that the CNN model accurately estimated geopolymer concrete’s compressive strength.The results show that the prediction accuracy is promising and can be used for the development of new geopolymer concrete mixes.The outcomes not only underscore the significance of leveraging technology for sustainable construction practices but also pave the way for innovation and efficiency in the field of civil engineering.

Multi-Features Disease Analysis Based Smart Diagnosis for COVID-19

Coronavirus 2019(COVID-19)is the current global buzzword,putting the world at risk.The pandemic’s exponential expansion of infected COVID-19 patients has challenged the medical field’s resources,which are already few.Even established nations would not be in a perfect position to manage this epidemic correctly,leaving emerging countries and countries that have not yet begun to grow to address the problem.These problems can be solved by using machine learning models in a realistic way,such as by using computer-aided images during medical examinations.These models help predict the effects of the disease outbreak and help detect the effects in the coming days.In this paper,Multi-Features Decease Analysis(MFDA)is used with different ensemble classifiers to diagnose the disease’s impact with the help of Computed Tomography(CT)scan images.There are various features associated with chest CT images,which help know the possibility of an individual being affected and how COVID-19 will affect the persons suffering from pneumonia.The current study attempts to increase the precision of the diagnosis model by evaluating various feature sets and choosing the best combination for better results.The model’s performance is assessed using Receiver Operating Characteristic(ROC)curve,the Root Mean Square Error(RMSE),and the Confusion Matrix.It is observed from the resultant outcome that the performance of the proposed model has exhibited better efficient.

THD Reduction for Permanent Magnet Synchronous Motor Using Simulated Annealing

Any nonlinear behavior of the system is analyzed by a useful way of Total Harmonic Distortion(THD)technique.Reduced THD achieves lower peak current,higher efficiency and longer equipment life span.Simulated annealing(SA)is applied due to the effectiveness of locating solutions that are close to ideal and to challenge large-scale combinatorial optimization for Permanent Magnet Synchronous Machine(PMSM).The parameters of direct torque controllers(DTC)for the drive are automatically adjusted by the optimization algorithm.Advantages of the PI-Fuzzy-SA algorithm are retained when used together.It also improves the rate of system convergence.Speed response improvement and har-monic reduction is achieved with SA-based DTC for PMSM.This mechanism is known to be faster than other algorithms.Also,it is observed that as compared to other algorithms,the projected algorithm yields a reduced total harmonic distor-tion.As a result of the employment of Space Vector Modulation(SVM)techni-que,the system is resistant to changes in motor specifications and load torque.Through MATLAB&Simulink simulation,the experiment is done and the per-formance is calculated for the controller.

Influence of bimodal grain size distribution on the corrosion behavior of friction stir processed biodegradable AZ31 magnesium alloy

In the present study,AZ31 magnesium alloy sheets were processed by friction stir processing(FSP)to investigate the effect of the grain refinement and grain size distribution on the corrosion behavior.Grain refinement from a starting size of 16.4±6.8µm to 3.2±1.2µm was attained after FSP.Remarkably,bimodal grain size distribution was observed in the nugget zone with a combination of coarse(11.62±8.4µm)and fine grains(3.2±1.2µm).Due to the grain refinement,a slight improvement in the hardness was found in the nugget zone of FSPed AZ31.The bimodal grain size distribution in the stir zone showed pronounced influence on the corrosion rate of FSPed AZ31 as observed from the immersion and electrochemical tests.From the X-ray diffraction analysis,more amount of Mg(OH)_(2) was observed on FSPed AZ31 compared with the unprocessed AZ31.Polarization measurements demonstrated the higher corrosion current density for FSPed AZ31(8.92×10^(−5)A/cm^(2))compared with the unprocessed condition(2.90×10^(−5)A/cm^(2))that can be attributed to the texture effect and large variations in the grain size which led to non-uniform galvanic intensities.

Effect of aluminum content on machining characteristics of AZ31 and AZ91 magnesium alloys during drilling

Magnesium(Mg)and its alloys are now becoming the promising choice for various structural applications due to their low density and high specific strength compared with other light metals such as aluminum and its alloys.Among all Mg alloys,AZ(aluminum and zinc)series is the most widely used alloy system for various structural applications.But,machining of magnesium and its alloys involves certain issues due to their brittle nature and risk of inflammability unlike other nonferrous metals.Particularly,alloys with considerable amount of secondary phase may exhibit different machining characteristics during metal cutting operations.In the present study,two AZ series alloys AZ31 and AZ91 were selected and drilling operation was performed to assess the effect of the secondary phase amount and distribution on machining characteristics.Drilling operation was carried out at different sets of process parameters and cutting forces were obtained and the chips which have been produced during drilling were analyzed.From the results,it can be clearly understood that the presence of secondary phase(Mg_(17)Al_(12))has a significant influence on cutting forces.Increase in cutting speed has reduced the required cutting force and load fluctuations in all the cases.

Magnesium based surface metal matrix composites by friction stir processing

Surface metal matrix composites(MMCs)are a group of modern engineered materials where the surface of the material is modified by dispersing secondary phase in the form of particles or fibers and the core of the material experience no change in chemical composition and structure.The potential applications of the surface MMCs can be found in automotive,aerospace,biomedical and power industries.Recently,friction stir processing(FSP)technique has been gaining wide popularity in producing surface composites in solid state itself.Magnesium and its alloys being difficult to process metals also have been successfully processed by FSP to fabricate surface MMCs.The aim of the present paper is to provide a comprehensive summary of state-of-the-art in fabricating magnesium based composites by FSP.Influence of the secondary phase particles and grain refinement resulted from FSP on the properties of these composites is also discussed.

Joining of AZ31 and AZ91 Mg alloys by friction stir welding

Two dissimilar magnesium(Mg)alloy sheets,one with low aluminium(AZ31)and another with high aluminium(AZ91)content,were successfully joined by friction stir welding(FSW).The effect of process parameters on the formation of hot cracks was investigated.A sound metallurgical joint was obtained at optimized process parameters(1400 rpm with 25 mm/min feed)which contained fine grains and distributed β(Mg_(17)Al_(12))phase within the nugget zone.An increasing trend in the hardness measurements has also confirmed more amount of dissolution of aluminium within the nugget zone.A sharp interface between nugget zone and thermo mechanical affected zone(TMAZ)was clearly noticed at the AZ31 Mg alloy side(advancing)but not on the AZ91 Mg alloy side(retreating).From the results it can be concluded that FSW can be effectively used to join dissimilar metals,particularly difficult to process metals such as Mg alloys,and hot cracking can be completely eliminated by choosing appropriate process parameters to achieve sound joint.

Joining of AZ91 Mg alloy and Al6063 alloy sheets by friction stir welding

In the present work,the effect of process parameters on joining of AZ91 Mg alloy and Al6063 aluminum alloy sheets during friction stir welding(FSP)was studied.A successful joint was achieved at 1100 r.p.m.tool rotational speed and 25 mm/min tool travel speed.Combination of tool rotational speed and tool travel speed has observed a profound effect on the material flow mechanisms at the nugget zone.From the microstructural studies,the joint formation was observed as mainly due to mechanical mixing of the materials.The level of metallurgical continuity at the nugget zone was observed as poor and a sharp interface at the joint was noticed.The microhardness measurements across the weld joint also revealed the lack of establishment of a perfect metallurgical bonding.X-ray diffraction analysis of weld zone showed presence of both magnesium and aluminum.Hence from the preliminary observations,it can be understood that the joining of AZ91 Mg alloy and Al6063 alloy can be achieved by FSP;however,complex issues in material mixing still need further investigations.

Integrated water vapor during active and break spells of monsoon and its relationship with temperature,precipitation and precipitation efficiency over a tropical site

Global Positioning System(GPS)measurements of integrated water vapor(IWV)for two years(2014 and 2015)are presented in this paper.Variation of IWV during active and break spells of Indian summer monsoon has been studied for a tropical station Hyderabad(17.4°N,78.46°E).The data is validated with ECMWF Re-Analysis(ERA)91 level data.Relationships of IWV with other atmospheric variables like surface temperature,rain,and precipitation efficiency have been established through cross-correlation studies.A positive correlation coefficient is observed between IWV and surface temperature over two years.But the coefficient becomes negative when only summer monsoon months(June,July,August,and September)are considered.Rainfall during these months cools down the surface and could be the reason for this change in the correlation coefficient.Correlation studies between IWV-precipitation,IWVprecipitation efficiency(P.E),and precipitation-P.E show that coefficients are-0.05,-0.10 and 0.983 with 95%confidence level respectively,which proves that the efficacy of rain does not depend only on the level of water vapor.A proper dynamic mechanism is necessary to convert water vapor into the rain.The diurnal variations of IWV during active and break spells have been analyzed.The amplitudes of diurnal oscillation and its harmonics of individual spell do not show clear trends but the mean amplitudes of the break spells are approximately double than those of the active spells.The amplitudes of diurnal,semidiurnal and ter-diurnal components during break spells are 1.08 kg/m^(2),0.52 kg/m;and 0.34 kg/m;respectively.The corresponding amplitudes during active spells are 0.68 kg/m^(2),0.41 kg/m;and 0.23 kg/m;.

MADCR:Mobility Aware Dynamic Clustering-Based Routing Protocol in Internet of Vehicles

Internet of Vehicles(IoV)is an evolution of the Internet of Things(IoT)to improve the capabilities of vehicular ad-hoc networks(VANETs)in intelligence transport systems.The network topology in IoV paradigm is highly dynamic.Clustering is one of the promising solutions to maintain the route stability in the dynamic network.However,existing algorithms consume a considerable amount of time in the cluster head(CH)selection process.Thus,this study proposes a mobility aware dynamic clustering-based routing(MADCR)protocol in IoV to maximize the lifespan of networks and reduce the end-to-end delay of vehicles.The MADCR protocol consists of cluster formation and CH selection processes.A cluster is formed on the basis of Euclidean distance.The CH is then chosen using the mayfly optimization algorithm(MOA).The CH subsequently receives vehicle data and forwards such data to the Road Side Unit(RSU).The performance of the MADCR protocol is compared with that ofAnt Colony Optimization(ACO),Comprehensive Learning Particle Swarm Optimization(CLPSO),and Clustering Algorithm for Internet of Vehicles based on Dragonfly Optimizer(CAVDO).The proposed MADCR protocol decreases the end-toend delay by 5–80 ms and increases the packet delivery ratio by 5%–15%.

An Attention Based Neural Architecture for Arrhythmia Detection and Classification from ECG Signals

Arrhythmia is ubiquitous worldwide and cardiologists tend to provide solutions from the recent advancements in medicine.Detecting arrhythmia from ECG signals is considered a standard approach and hence,automating this process would aid the diagnosis by providing fast,costefficient,and accurate solutions at scale.This is executed by extracting the definite properties from the individual patterns collected from Electrocardiography(ECG)signals causing arrhythmia.In this era of applied intelligence,automated detection and diagnostic solutions are widely used for their spontaneous and robust solutions.In this research,our contributions are two-fold.Firstly,the Dual-Tree Complex Wavelet Transform(DT-CWT)method is implied to overhaul shift-invariance and aids signal reconstruction to extract significant features.Next,A neural attention mechanism is implied to capture temporal patterns from the extracted features of the ECG signal to discriminate distinct classes of arrhythmia and is trained end-to-end with the finest parameters.To ensure that the model’s generalizability,a set of five traintest variants are implied.The proposed model attains the highest accuracy of 98.5%for classifying 8 variants of arrhythmia on the MIT-BIH dataset.To test the resilience of the model,the unseen(test)samples are increased by 5x and the deviation in accuracy score and MSE was 0.12%and 0.1%respectively.Further,to assess the diagnostic model performance,AUC-ROC curves are plotted.At every test level,the proposed model is capable of generalizing new samples and leverages the advantage to develop a real-world application.As a note,this research is the first attempt to provide neural attention in arrhythmia classification using MIT-BIH ECG signals data with state-of-the-art performance.

Genetic diversity for grain Zn concentration in finger millet genotypes:Potential for improving human Zn nutrition

Nearly half of the world population suffers from micronutrient malnutrition,particularly Zn deficiency.It is important to understand genetic variation for uptake and translocation behaviors of Zn in relevant crop species to increase Zn concentration in edible parts.In the present study,genetic variation in grain Zn concentration of 319 finger millet genotypes was assessed.Large genetic variation was found among the genotypes,with concentrations ranging from 10 to 86 μg g^(-1)grain.Uptake and translocation studies with Zn/^(65) Zn application in 12 selected low-Zn genotypes showed wide variation in root uptake and shoot translocation,with genotypes GEC331 and GEC164 showing greater uptake and translocation.Genotypes GEC164 and GEC543 showed increased grain Zn concentration.Genotypes GEC331 and GEC164 also showed improved yield under Zn treatment.Appreciable variation in grain Zn concentration among finger millet genotypes found in this study offers opportunities to improve Zn nutrition through breeding.

Content-based image retrieval using Gaussian-Hermite moments and firefly and grey wolf optimization

Rapid growth in the transfer of multimedia information over the Internet requires algorithms to retrieve a queried image from large image database repositories.The proposed content-based image retrieval(CBIR)uses Gaussian-Hermite moments as the low-level features.Later these features are compressed with principal component analysis.The compressed feature set is multiplied with the weight matrix array,which has the same size as the feature vector.Hybrid firefly and grey wolf optimization(FAGWO)is used to prevent the premature convergence of optimization in the firefly algorithm.The retrieval of images in CBIR is carried out in an OpenCV python environment with K-nearest neighbours and random forest algorithm classifiers.The fitness function for FAGWO is the accuracyof the classifier.The FAGWO algorithm derives the optimum weights from a randomlygenerated initial population.When these optimized weights are applied,the proposed algorithm shows better precision/recall and efficiency than other techniques such as exact legendre moments,Region-based image retrieval,K-means clustering and Color descriptor wavelet-based texture descriptor retrieval technique.In terms of optimization,hybrid FAGWO outperformed various optimization techniques(when used alone)like Particle Swarm Optmization,Genetic Algorithm,Grey-Wolf Optimization and FireFly algorithm.

An investigation on the hardness and corrosion behavior of MWCNT/Mg composites and grain refined Mg

In the present work,multi walled carbon nanotubes(MWCNT)reinforced magnesium(Mg)matrix composite was fabricated by friction stir processing(FSP)with an aim to explore its mechanical and electrochemical behavior.Microstructural observations showed that the thickness of the produced composite layer was in the range of 2500μm.FSP resulted uniform distribution of CNT near the surface while agglomerated layers in the subsurface.Grain refinement of Mg achieved by FSP improved the hardness but significant enhancement in the hardness value was observed for FSPed MWCNT/Mg composites.Potentiodynamic polarization studies revealed that the increase in corrosion current density was observed for MWCNT/Mg composite compared with grain refined Mg and pure Mg,implying the significance of secondary phase(MWCNT)in decreasing the corrosion resistance of the composite.

Damage modeling of ballistic penetration and impact behavior of concrete panel under low and high velocities

This work presents a numerical simulation of ballistic penetration and high velocity impact behavior of plain and reinforced concrete panels.This paper is divided into two parts.The first part consists of numerical modeling of reinforced concrete panel penetrated with a spherical projectile using concrete damage plasticity(CDP)model,while the second part focuses on the comparison of CDP model and Johnson-Holmquist-2(JH-2)damage model and their ability to describe the behavior of concrete panel under impact loads.The first and second concrete panels have dimensions of 1500 mm1500 mm150 mm and 675 mm675 mm200 mm,respectively,and are meshed using 8-node hexahedron solid elements.The impact object used in the first part is a spherical projectile of 150 mm diameter,while in the second part steel projectile of a length of 152 mm is modeled as rigid element.Failure and scabbing characteristics are studied in the first part.In the second part,the comparison results are presented as damage contours,kinetic energy of projectile and internal energy of the concrete.The results revealed a severe fracture of the panel and high kinetic energy of the projectile using CDP model comparing to the JH-2 model.In addition,the internal energy of concrete using CDP model was found to be less comparing to the JH-2 model.

Impact of Cyclone Nilam on Tropical Lower Atmospheric Dynamics

A deep depression formed over the Bay of Bengal on 28 October 2012, and developed into a cyclonic storm. After landfall near the south coast of Chennai, cyclone Nilam moved north-northwestwards. Coordinated experiments were conducted from the Indian stations of Gadanki（13.5？N, 79.2？E） and Hyderabad（17.4？N, 78.5？E） to study the modification of gravity-wave activity and turbulence by cyclone Nilam, using GPS radiosonde and mesosphere–stratosphere–troposphere radar data. The horizontal velocities underwent large changes during the closest approach of the storm to the experimental sites. Hodograph analysis revealed that inertia gravity waves（IGWs） associated with the cyclone changed their directions from northeast（control time） to northwest following the path of the cyclone. The momentum flux of IGWs and short-period gravity waves（1–8 h） enhanced prior to, and during, the passage of the storm（±0.05 m2s-2and ±0.3 m2s-2, respectively）, compared to the flux after its passage. The corresponding body forces underwent similar changes, with values ranging between ±2–4m s-1d-1and ±12–15 m s-1d-1. The turbulence refractivity structure constant（C2n） showed large values below 10 km before the passage of the cyclone when humidity in the region was very high. Turbulence and humidity reduced during the passage of the storm when a turbulent layer at ～17 km became more intense. Turbulence in the lower troposphere and near the tropopause became weak after the passage of the cyclone.

A Resource Management Algorithm for Virtual Machine Migration in Vehicular Cloud Computing

In recent years,vehicular cloud computing(VCC)has gained vast attention for providing a variety of services by creating virtual machines(VMs).These VMs use the resources that are present in modern smart vehicles.Many studies reported that some of these VMs hosted on the vehicles are overloaded,whereas others are underloaded.As a circumstance,the energy consumption of overloaded vehicles is drastically increased.On the other hand,underloaded vehicles are also drawing considerable energy in the underutilized situation.Therefore,minimizing the energy consumption of the VMs that are hosted by both overloaded and underloaded is a challenging issue in the VCC environment.The proper and efcient utilization of the vehicle’s resources can reduce energy consumption signicantly.One of the solutions is to improve the resource utilization of underloaded vehicles by migrating the over-utilized VMs of overloaded vehicles.On the other hand,a large number of VM migrations can lead to wastage of energy and time,which ultimately degrades the performance of the VMs.This paper addresses the issues mentioned above by introducing a resource management algorithm,called resource utilization-aware VM migration(RU-VMM)algorithm,to distribute the loads among the overloaded and underloaded vehicles,such that energy consumption is minimized.RU-VMM monitors the trend of resource utilization to select the source and destination vehicles within a predetermined threshold for the process of VM migration.It ensures that any vehicles’resource utilization should not exceed the threshold before or after the migration.RU-VMM also tries to avoid unnecessary VM migrations between the vehicles.RU-VMM is extensively simulated and tested using nine datasets.The results are carried out using three performance metrics,namely number of nal source vehicles(nfsv),percentage of successful VM migrations(psvmm)and percentage of dropped VM migrations(pdvmm),and compared with threshold-based algorithm(i.e.,threshold)and cumulative sum(CUSUM)algorithm.The comparisons show that the RU-VMM algorithm performs better than the existing algorithms.RU-VMM algorithm improves 16.91%than the CUSUM algorithm and 71.59%than the threshold algorithm in terms of nfsv,and 20.62%and 275.34%than the CUSUM and threshold algorithms in terms of psvmm.

Biochemical and Metabolomics on Rice Cultivars

Plant metabolites are important for both plant life and human nutrition. However, the genetic control of plant metabolome remains largely unknown. Here, we performed a genetic analysis of the different rice metabolome and isozymes which are highly versatile and non-destructive as bio-markers. Five isozymes peroxidase, catalase, malate dehydrogenase, alcohol dehydrogenase(ADH), polyphenol oxidase were studied to characterize the thirty rice cultivars and two hybrids KRH-2 and KRH-4 along with their parental lines. Among the zymograms, ADH was found to be useful for the detection of cultivars, like CTH1, IR64, IR30864, with an Rm value of 0.549. The metabolomics of rice cultivars by using gas chromatography coupled with mass spectrometry instrument with selected reaction monitoring mode software identified the 66 metabolites in the rice samples, including amino, organic, fatty acids, alcohols and sugars(mono-/dis-accharides). All metabolites investigated varied significantly among rice samples. Jaya had the higher number of metabolites(15) with a peak for each metabolite, followed by Jyothi(13). This study demonstrated a powerful tool and provided a high-quality data for understanding the plant metabolome and isozymes, which may help bridge the gap between the genome and phenome.

FPGA Implementation of 5G NR Primary and Secondary Synchronization

The 5G communication systems are widely established for highspeed data processing to meet users demands.The 5G New Radio(NR)communications comprise a network of ultra-low latency,high processing speeds,high throughput and rapid synchronization with a time frame of 10 ms.Synchronization between User Equipment(UE)and 5G base station known as gNB is a fundamental procedure in a cellular system and it is performed by a synchronization signal.In 5G NR system,Primary Synchronization Signal(PSS)and Secondary Synchronization Signal(SSS)are used to detect the best serving base station with the help of a cell search procedure.The paper aims to determine the Physical Cell Identity(PCI)by using primary synchronization and secondary synchronization blocks.The PSS and SSS detection for finding PCI is implemented on Zynq-7000 series Field Programmable Gate Arrays(FPGA)board.FPGA are reconfigurable devices and easy to design complex circuits at high frequencies.The proposed architecture employs Primary Synchronization Signal(PSS)and Secondary Synchronization Signal(SSS)detection aims with high speed and low power consumption.The synchronization blocks have been designed and the synthesized design block is implemented on the Zynq-7000 series Zed board with a maximum operating clock frequency of 1 GHz.

Impact of integrated package of agrotechniques on growth and yield of aerobic rice

A field experiment was conducted during Kharif, 2011-2012 and 2012-2013 at GKVK, Bengaluru, Karnataka to study the effect of integrated package of agrotechniques on growth and yield of aerobic rice. The predominant weed flora observed in the experimental field were, Eleusine indica, Digitaria marginata L., Dactyloctenium aegyptium L., Alternanthera sessilis, Mollugo distica L., Celosia argentia and Borreria hispida. Treatments receiving integrated weed management practices recorded significantly lower weed population and weed dry weight as compared to pre-emergence application of pyrazosulfuron ethyl alone. Application of RDF + FYM + Biofertilizers + FeSO4 +IWM practices (T8) recorded significantly higher growth, yield parameters and yield as compared to RDF + FYM + IWM practices and was being on par with RDF + FYM + Biofertilizers + IWM practices (T5).