Showing papers in "Maǧallaẗ al-abḥāṯ al-handasiyyaẗ in 2022"

Reduced oscillations based perturb and observe solar maximum power point tracking scheme to enhance efficacy and speed of a photovoltaic system

Abstract: This paper puts forward a reduced oscillation based perturb and observe (ROP&O) maximum power point (MPP) tracking (MPPT) technique to mitigate the probability of loss of tracking direction and to reduce oscillations around MPP when the solar photovoltaic (PV) array is subjected under periodically changing irradiance. The proposed technique retains the structure of conventional perturb and observe (P&O) technique additionally incorporating a unique structure of dynamic step sizing, along with proportional-integral (PI) controller which potently alters the duty cycle (𝐷) of the DC-DC boost power converter (BPC). The ROP&O MPPT technique is compared with conventional P&O and incremental conductance (IC) schemes in terms of tracking efficacy (𝜂), ripples in PV voltage and PV current, convergence time, and the error rates. The efficacy of the proposed scheme lies between 99.06% to 99.80%. Moreover, the time to obtain MPP is 0.018 sec. which is about five times faster than the P&O technique and fifteen times faster than the IC technique. Also, the proposed MPPT technique is benchmarked using three-phase grid integration, and the power quality of the grid current is observed in terms of total harmonic distortion (THD).

Dynamic smart random preference for higher medical image confidentiality

Abstract: It is essential to secure the information to store or transfer medical digital files without destruction. Currently, all used e-health files requests to be utilized in well-controlled, protected, and dependable style avoiding breaches and hacking. This research focuses on medical confidentiality encrypting grayscale health images for comfortable safe utilization. The work depends on resilience randomization and XOR operations for its medical-image cryptography. It tests performance of some random generators conveying the best every time running that is dynamically changing depending on e-health image variations. The research tests several randomizations structures processed as two sequenced encryption methods adopting substitution and transposition. The work tested random variations to encrypt different medical grayscale images revealing attractive remarks. The paper investigation intends to recognize appropriate preference via secrecy testing typical notations. The work indicates this flexibility of best applicable PRNG and its change features interesting privacy intellectual medical gray-image security for open e-health research direction to benefit from.

Physical, Mechanical and Morphological Characterization of A356/Si3N4 Nanoparticles Stir Casting Composites

Abstract: A356 alloy based composites are extensively used in different component industries like components of automobile parts owing to pronounced strength to weight ratio. In the current paper, A356/Si3N4 nanocomposites are fabricated by means of stir casting by varying Si3N4 reinforcement nanoparticles. Silicon Nitride (Si3N4) nanoparticle is intermixed to Al powder mechanically to develop their wettability among the particles of A356/Si3N4 nanocomposites. The Si3N4 nanoparticle is integrated by altering weight percentage. The electomechanical stirring process to produce the vortex is taken up to spread Si3N4 nanoparticles in the liquefied matrix dispensed into a permanent mould. Morphological investigation of the composite specimen is accomplished by TEM. Based on the study, it can be acquired that the strengthening by Si3N4 nanoparticles promotes the strength and hardness of the fabricated nanocomposites. The maximum tensile strength is depicted to be 319 MPa for A356/5%Si3N4 nanocomposites whereas hardness is increased from 43 HBN to 86 HBN. The physical properties such as density and porosity are also increased due to the presence of Si3N4 nanoparticles. The maximum porosity of 1.12% was predicted at 5 wt. % of Si3N4. The TEM examination discloses the presence of Si3N4 nanoparticles in the fabricated composites. Additionally, the current research guidance has ability to afford a monitor to the industrialized preparation of A356/Si3N4 nanocomposites.

A Generalized WECS System with Single Phase Multilevel Inverter having MPPT control with Neural Network

Abstract: This paper describes the efficient MPPT tracking for variable wind speed using an artificial neural network. The neural network has been trained using the backpropagation algorithm and Levenberg-Marquardt (LM) based optimization technique to achieve maximum power point. A multilevel inverter having 10 switches has been used to reduce voltage stress, THD and switching losses resulting in improvement in performance and reduction in the driver circuit for the switches. The proposed system has been validated and simulated in SIMULINK/MATLAB

Study on the influence of groove shape on the tensile strength of commercial steel

Abstract: In industry, welding is well known. There is a great demand for effective and quality welding. Manufacturers seek to remain competitive in the market. They rely on their manufacturing engineers and production personnel to quickly and effectively set up manufacturing processes for new products. Gas metal arc welding is one of the most widely used processes in the industry. Input factors such as welding current, welding voltage, Gas flow rate, wire feed speed, wire size and welding speed play a significant role in determining the welding quality. Taguchi's design has been a powerful and efficient optimization tool for better quality and performance output of manufacturing processes. In this study, Gas metal arc welding has welded commercial steel under preset factors of welding voltage, wire feed speed and groove shape. Base metal groove shape X welding obtained lower tensile strength and hardness than base metal groove shape V. Taguchi's design is to determine the optimal process factors for higher tensile strength and hardness. The analysis found that welding groove shape V had higher effect on the tensile strength and hardness of the welding, while the welding voltage has obtained higher tensile strength and hardness values. The optimum combination of welding factors was base metal groove shape V, 20 V and wire feed speed of 5.9 m/min.

Application of CRM Techniques for predicting the consequences of Laborers Sleep Deprivation in Construction Projects

Abstract: The purpose of this study is to develop a prediction model using a CRM (Customer Relationship Management) analysis approach that identifies the potential impact of sleep deprivation on construction laborers. Based on the data collected from India’s most populous city, Bengaluru Karnataka, employing nearly 800,000 to one million laborers in the construction industry, a dataset was created to establish the relationship of sleep deprivation on laborers. Upon establishing the datasets, CRM methodology using mathematical expressions and designs in the Solutions Box of Microsoft. CRM helped derive significant variables leading to the result, a statistical analysis method to indicate daily sleep cycle disturbances and the working hours are the most influential factors, followed by age, gender, service length, quality of work and nature of work. The results obtained should contribute to creating awareness among construction laborers and contractors about the consequences of sleep deprivation on laborers' health and work productivity. Thus, incorporating safety measures improves the health of the laborers and indirectly contributes to growth of the construction industry and the country’s economy.

Power Quality Improvement of Photovoltaic Distributed Generation System using Artificial Neural Network for Environmental Preservation

Abstract: Most of the economies are emerging with the growth in the renewable energy system. A solar photovoltaic system is one of the good sources of energy among them which provides clean and green energy. As it adds less pollution to the environment and hence advancement in technology of renewable energy system adds great effect on the environmental preservation. This paper describes a 1-ф photovoltaic distributed generation system having enhanced power quality features. Initially, the system has been implemented by using pulse width modulation-based switching schemes for the smooth control of the power flow between photovoltaic system, grid, and non-linear load. The system involves nonlinear current compensation and capacitor voltage balancing along with maximum power point tracking. Using this model, sample data has been collected for the training and testing of artificial neural networks. The artificial neural network was trained using the scaled conjugate gradient approach. The response of the neural network provides an estimated reference current for the controller to enhance power quality features. The inverter used in this work also acts as a shunt active power filter during night time. The system’s result is simulated and validated through MATLAB/Simulink.

A Novel Feature Selection Algorithm using Multi-Objective Improved Honey Badger Algorithm and Strength Pareto Evolutionary Algorithm-II

Abstract: An important task for classification is feature selection that removes the redundant or irrelevant features from the dataset. Multi-objective feature selection approach is mainly proposed by many researchers. However, these approaches failed to maintain the higher classification accuracy while removing redundancy in the features. In this work, a wrapper based feature selection technique is proposed with a hybrid of Multi Objective Honey Badger Algorithm (MO-HBA) and Strength Pareto Evolutionary Algorithm-II to maintain the balance between classification accuracy and removal of redundancy. Classification accuracy improvement and removal of redundant features are considered as the multi-objective optimization functions of the proposed multi-objective feature selection technique. The Levy flight algorithm is utilized to initialize the population to enhance the ability of the exploration and exploitation of MO-HBA. The regularized Extreme Learning Machine is used to classify the selected features. To evaluate the performance of the proposed feature selection technique, eighteen benchmark datasets are utilized and results are compared with the four well known multi-objective feature selection techniques in terms of accuracy, hamming loss, ranking loss, mean value, standard deviation, length of features, and training time. The proposed approach achieved maximum accuracy of 100% with the maximum value of selected features as 80. The minimum value of hamming loss, ranking loss, mean value and standard deviation value achieved by the proposed approach are 0.0092, 0.0003, 0.018 and 0.001 respectively. The experimental results show that the proposed approach can give improved classification accuracy while the removal of redundancy in large scale datasets.

Impacts of COVID-19 on the Middle East construction industry

Abstract: The impacts of COVID-19 pandemic on construction project management are not documented and not well understood, which leaves project stakeholders with no guiding information to respond to such threats and no lessons learned to speed up the recovery of the industry in the wake of the pandemic. Although researchers have studied the impacts of pandemics in other industries in various settings, there is little-to-no research specific to the construction industry and especially in the Middle East region. To address this knowledge gap, 202 construction professionals in the Middle East region were surveyed using a questionnaire survey to provide their perceptions of COVID-19 pandemic impact on project finance, construction materials and equipment, labor, contracts, and rental properties. Statistical analysis of the collected data reveals that labor and contracts are the principal classes impacted due to the complex procedures of hiring labor from East Asia, the tightening of health and safety precautionary measures on construction sites, and the expected contract revisions to Force Majeure, Change, and Claim clauses to address pandemic issues. The respondents indicated that many tasks can be safely accomplished by remote work. They also indicated that pandemic-related slowdown can be detrimental to the construction industry;governments need to inject stimulus funding to help keep construction activity momentum;and prolonged COVID-19 pandemic impact would be harsher than oil price collapse. As such, this study contributes to the body of knowledge in construction management by studying the impacts of COVID-19 pandemic and providing construction industry stakeholders with lessons learned and recommendations to response strategies that can alleviate pandemic risks. [ FROM AUTHOR] Copyright of Journal of Engineering Research (2307-1877) is the property of Kuwait University, Academic Publication Council and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Experimental investigations and parametric optimization during micro-EDM drilling of Ti -5.6Al-3.6V using ABC algorithm

Abstract: This work presents experimental investigations and parametric optimization during micro-Electric discharge Machining (EDM) drilling of Titanium alloy Ti-5.6Al-3.6V. The experiments have been designed by response surface methodology (RSM) based central composite design (CCD) taking current, pulse-on-time and pulse-off-time as input parameters; and drill rate and tool wear ratio as performance measures. After carrying out experiments, the effect of each input parameter on performance measures has been found. In order to study the microstructure of machined surface, scanning electronic microscope (SEM) has been performed. Single objective and multi-objective optimization have been done using artificial bee colony (ABC) algorithm to find the optimal combination of input parameters for the best yield of the process. Experimental verification of the obtained results has also been performed and a difference of less than 5% has been observed between experimental values and that obtained using ABC algorithm.

Comparative Analysis of Preamplifiers for Comparators

Abstract: In low power electronics technology, a lot of new technology has already been introduced to reduce the power consumption of comparator. This paper presents the comparative study of preamplifier circuit on power consumption and delay prospects. The preamplifiers are explained to make the clear difference in the state-of the art. Every circuit has their own importance in the different application such as analog-to-digital converter and comparator. The general trend to design an efficient preamplifier is that it should have low power consumption in their operation. Operating region of preamplifier circuit is observed as sub threshold and saturation. A small modification has been performed in preamplifier in comparator circuit and compared the power and delay with the reported comparator circuits. All the preamplifier circuits are implemented on 180nm CMOS technology node. The voltage supply used 1.2 V in implemented circuit.

Reasoning the social benefits of mixed land-use and population density in an Indian city

Abstract: Mixed land-use and higher population densities are endorsed in many urban planning concepts as crucial elements for urban vitality. They are said to make urban streets active due to the presence of people, leading to public vigilance and improved feeling of safety on streets. Moreover, higher densities and mixed land-uses are also said to promote social interactions and walkability. Indian cities are inherently mix and dense, and therefore, the noted benefits in the literature need to be verified in this local context. In this research, through the empiric al study of eight study areas of Pune, India, the efficacy of social benefits of mixed land-uses and population densities is established. A mixed land-use index for the selected study areas was computed to represent the mixed land-use intensities. Satisfaction levels of the residents regarding the presumed social benefits were surveyed and collated as urban vitality. The relationship between urban vitality and mixed land-uses and population densities is established through curvilinear (quadratic) regression analysis explained by parabola shape. The results of this study reveal that mixed land-uses and higher population densities initially lead to an increase in urban vitality to an extent and then reduce again with intense mixed land-use and high population density. Population density between 12000 to 14000 persons per square kilometer is most suited to achieve urban vitality.

Single Stage Active Power Factor Correction Circuit for Street LED Light with Battery Backup

Abstract: This paper proposes a single-stage active power factor correction circuit for street LED light with battery back-up. The buck–boost converter and flyback converter are combined to achieve optimal performance. The first part of the integrated LED driver, the buck–boost converter is used to adjust the power while operating in the discontinuous conduction operation. The second part of the driver, the flyback converter provides regulated voltage to the LEDs. The battery backup circuit charges the battery when ac input power is available and provides power to LED lamp when input power supply is not available. The proposed LED driver was designed for 100 W output power and tested by PSpice simulation. The simulation results obtained are given in the paper to demonstrates the functionality of the proposed LED driver system. The result show good operation and performance of proposed LED driver.

Time series forecast of Covid 19 Pandemic Using Auto Recurrent Linear Regression

Abstract: Covid 19 pandemic has done severe impact in the economy and lifestyle of the people since the beginning of 2020. Various data analytics has been tried on the data obtained from various sources. These analytics include symptoms prediction, time series forecasting and impact analysis. The forecast on when the pandemic ends is a challenge for many countries. Time series forecasting models have been proposed for various applications but a non-seasonal and non-stationary forecasting method is needed to predict the progression of the pandemic. An Auto Regressive Linear Regression (ARLR) Algorithm is proposed in this paper with a selected geography’s Covid data. The results of the proposed methodology sounds convincing when compared to the non-seasonal and non-stationary existing methodologies like linear regression and exponential smoothing variants. The performance measure of standard deviation and RMSE of the proposed method obtained 430.22 and 0.31 for active cases while 27.01 and 0.77 for rate of transmission with positive skew and platykurtic trend.

Study of flow characteristics of a savonius turbine inside nozzle diffuser duct

Abstract: In the present study, flow characteristics of savonius hydrokinetic turbines are analysed numerically. CFD simulations are done for the savonius turbine with and without duct. A special design of nozzle-diffuser duct in the present simulation exhibits a higher performance of the turbine. The simulations are done at different TSR (Tip Speed Ratio) for which the torque coefficient (CT) and Power coefficient (CP) are compared for both the cases at constant Reynolds number (2.0 x 106). A significant increase of 64.65% in Power coefficient (CP) is noticed for a ducted turbine when compared to a non-ducted turbine due to interesting vortices were formed in downstream of the duct.

Carboxymethyl Tamarind Kernel Gum based Controlled Drug Delivery Excipients: A Review

Abstract: The Carboxymethyl Tamarind Kernel Gum (CMTKG) is a natural based polysaccharide which has been derived from the Tamarind kernel gum (TKG) through the carboxymethylation process. The chemical alteration of TKG into CMTKG has resulted in amplifying swelling capacity, in situ gelations, wide pH tolerance, high drug holding efficiency, stability, release kinetics, and hydrophilicity. Out of many application-based areas, it has extensively been used in the field of drug delivery systems via developing various forms like nanoparticles, composites, films, hydrogels, and pellets. This article is planned to fill in as a helpful tool for research scholars, who are engaged in green polymers, and in giving almost every aspect of CMTKG in the sphere of drug delivery.

Load frequency control of three area power system using optimal tuning of fractional order proportional integral derivative controller with multi objective grey wolf optimization

Abstract: In an interconnected electrical power system, load frequency control is a most important ancillary service essential for maintaining the electrical system reliability at an adequate level. A Multi-Objective Grey Wolf Optimization (MOGWO) algorithm is introduced for maintaining a balance among exploitation and exploration stages and provides the best value of fitness. During the occurrence of the disturbance in the output of the system the optimization is implemented with Firefly Algorithm (FFA) and MOGWO which is tuned carefully and also the parameters are compared with three-area three-source model of the power system. A Fractional Order Proportional and Derivative (FOPID) controller is a PID controller whose derivative and integral orders are fractional rather than integer. The FOPID controller supports the better stability of the designed model with controlled deviation in frequency and grid tie line power deviations. In this proposed research work, optimal tuning of parameters of various controllers like PI, PID and FOPID in the power system is to regulate frequency in a multi-area multi-source model which is designed with the hydro-thermal-gas generation units. The output performance of the model designed is estimated from simulation results by means of MATLAB-SIMULINK tool. The dynamic performances of the system are studied with 1% or 2% step load perturbation in one Area. Sensitivity analysis reveals that the FFA and MOGWO optimized FOPID controller parameters obtained at nominal condition of loading, size and position of disturbance and system parameters are robust and need not be reset with wide changes in system.The simulation results show the effectiveness of FOPID controller in the presence and the absence of the FF and MOGWO algorithms considered and in that MOGWO algorithm is executed appropriately and it has improved the performance based on metrics such as overshoot, undershoot, and settling time.

Task Allocation in Distributed Agile Software Development Environment Using Unsupervised Learning

Abstract: In the paper, a novel approach for task allocation in DASD environment has been proposed. In the approach, new tasks (in the form of user – stories), are allocated to an employee, who is found to be ‘best’, on the basis of classification and rank ordering. For applying classification and rank ordering on data set of employees, Meta - Classifier Based Prediction Model (MCBPM) has been used that applied unsupervised learning. Results show that MCBPM – based task allocations provides accurate suggestions for the activity.

A circular economy in waste management carrying out experimental evaluation of compressed stabilized earth block using municipal solid waste incinerator fly ash

Abstract: The proper reuse and treatment Municipal solid waste incinerator fly ash is a is current a global concern. MSWI fly ashes possess a high concentration of SiO2, allowing them to be utilized as a raw material in the production of CSEB. This research looks into compressed stabilized earth blocks (CSEBs) that use municipal solid waste incinerator fly ash (MSWIFA) as an alternative to soil-sand mixture and sand. The experiment was divided into two phases: in the first, the effect of municipal solid waste incinerator fly ash on substituting soil-sand mix without affecting original performance, as well as resistance to sulfate attack, was emphasized. The effect of MSWIFA particle size and replacement ratio on replacing natural sand was then investigated. The analysis reveals that including MSWIFA into a soil-sand mixture considerably improved block performance, particularly under wetting–drying cycles and sulfate attack. MSWIFA particle size and replacement ratio have a significant influence on block strength and water absorption. Compressive and flexural strength are improved by the addition of 20% MSWIFA with a particle size of 0/4.75 mm. As a result, the research establishes a new investigation into the environmental recycling of MSWIFA in the context of the circular economy.

An energy efficient multipath routing protocol for MANET

Abstract: Energy consumption is a critical consideration in mobile ad hoc networks because the majority of mobile nodes run on low battery resources. A hectic problem was the minimization of energy, which was solved by the use of multipath routing protocols. This article proposes an energy-efficient multi-path routing protocol supported by the MANET optimization algorithm. The energy efficiency within the MANET is efficiently achieved by the use of cluster head selection with fuzzy clustering and fuzz NB. Multipath routing can be achieved by integrating the bird swarm optimization algorithm (BSA) with the whale optimization algorithm (WOA), which is called the Bird Swarm-Whale Optimization Algorithm (BSWOA). Optimal route selection is predicated on fitness variables like connectivity between the nodes, energy consumption, the maximum trust value of the route, and throughput. In comparison to existing methods, the suggested BSWOA obtained a minimum energy consumption of 8.72 J, a minimum delay of 0.00333 msec, and a maximum throughput of 0.912 bps.

Material Flow Behavior in Dissimilar Friction Stir Welds of AA2024 and AA5086 Aluminum Alloys

Abstract: This research aims to investigate the material flow behaviour and microstructure evolution in friction stir welded joints of dissimilar aluminium alloys AA2024/AA5086. AA2024 plate was placed on re- treating side; welded using threaded conical flat shoulder tool rotating at 635 rpm and moving along the joint line with a speed of 75mm/min. Mixing of both the material was clearly visible in stir zone and resulted in features typical to dissimilar friction stir welding and solid state flow patterns beside different zones. Onion rings, laminar flow, vertex flow was main flow features observed in the stir zone. Non- uniform mixing of different chemical composition base material is behind the formation of these flow features and inclusive chemical mixing may abolish solid state flow features.

Optimization and Performance Analysis of Residential Building for Sustainable Energy Design Through BIM

Abstract: The problems and effects of global warming stand a primary concern for most of the people in today’s world. As the demand for energy increases, the available energy resources noticeably decrease which rapidly upsurges the need for energy-efficient buildings. Housing is one of the largest energy consumers as it consumes about 40% of the total energy. This study aims to improve the energy consumption and the strength of houses in India compared to other materials in construction walls. The study includes the record of electricity life cycle, fuel consumption and Life Cycle Energy Costs (LCEC), the intensity of the annual energy consumption and the peak value of the annual demand, its evaluation and presents the comparison with the original planning. Finally, the measure of the total annual energy and total electricity and fuel life cycle costs for the building wall in the Indian scenario using sustainable energy efficient design and construction methods under BIM and tools like Revit, Insight360 and Green Building Studio are presented. An energy analysis model that integrates BIM to create precise residential performance forecasts with better optimization scenarios is represented.

Intellectual Human Behaviour On Business Environment On 3’c Model

Abstract: The implementation of a building project in any place largely depends on the integration of different stakeholders so that none of them can control or execute the project on their own. Both can be influenced by the practices of project management. There is no universal theoretical basis in the management of this work to define "communication, coordination, and cooperation" (3C). The role of various 3C concepts is explored in this paper. The business environment and human behaviour are identified as two major parts based on the analysis of selected articles in well-known construction management journals across the various domains. 3C and its connection to the performance of the construction project. The objective of this article is therefore to explain the definition of 3C and their relationship between them. The logic of communication and coordination exchange is an important link. As a result, collaboration becomes more difficult and requires more time and effort.

THD optimization in 15-level asymmetric reduced switch count multilevel PV inverter using optimization algorithms

Abstract: Philosophers and industries have focused on designing multilevel inverters, which use significantly fewer power switches and dc sources to achieve high power, low switching, and less harmonic output distortion for medium voltage applications. Even so, these multilevel inverters have some downsides like the use of many electronic components, electromagnetic interference (EMI), bulky driver circuit complexity, significant reverse recovery times, and voltage balancing issues. A modern asymmetrical multilevel inverter with fewer switches and drivers than standard topology is introduced in this article. The powerful analogy addresses traditional inverter topologies of a similar structure. The proposed MLI is relatively simple and easy to extend for many output levels. The proposed design of MLI is implemented for 15 level output with precise and high-quality near sinusoidal waveform using seven switches, three dc sources and three diodes and hence the volume, cost and driver circuit complexity is considerably reduced. The novelty in the proposed topology is that reduced ON state semiconductor switching devices. The output of the MLI is evaluated with the parameter of total harmonic distortion (THD). To minimize the THD, optimization algorithms such as GA, PSO, WOA and HHA were implemented at fundamental switching PWM control method. The comparative analysis of these algorithms on proposed inverter performance is integral for this research. The efficacy of this topology enhances the integration of renewable energy sources.

Grey relational analysis based optimization of process parameters for efficient performance of fused deposition modelling based 3D printer

Abstract: Rapid prototyping techniques such as three-dimensional (3D) printing have rapidly gained popularity in industry since material layers are added rather than removed. Additive manufacturing creates objects from 3D CAD model data by layering materials, thus saving time and money. Fused deposition modelling (FDM) is the most often utilized additive manufacturing technology. To find the best parameters simultaneously affecting tensile strength, flexural strength, and wear resistance, this research aims to make use of grey relational analysis (GRA). In this investigation, the effect of different combinations of layer height, extruder temperature, infill percentage and print speed on the three mechanical properties is examined in depth. GRA optimization is used to find the ideal design factor levels for achieving the lowest wear rate while still providing the maximum possible tensile and flexural strength for the data obtained for sixteen experiments as per L16 orthogonal array. It is crucial to do Analysis of Variance (ANOVA) analysis in order to figure out the parameter contribution ratios. The grey relational grade (GRG) for any combination can be predicted quite accurately using regression analysis. The findings of the confirmation experiments demonstrated that the information gleaned from regression analysis is in line with that acquired from the experiments themselves.

Land Use and Land Cover Change Detection in the Bhavani Basin of India through Remote Sensing Approach

Abstract: Using remote sensing data to detect changes in land use and land cover (LULC) is a valuable source of information for various decision support systems. Land use and land cover identification data was used to analyse land conservation, sustainable development, and water resource management. This research aims to determine how the Bhavani basin land use and land cover have changed over the period of time. Land cover changes were detected using Landsat Thematic Mapper (TM) 30 m resolution images in the GIS environment and with image processing techniques for the four years 1999, 2007, 2014, and 2020. The differences in the landuse and land cover classes are described using ERDAS imagine version 2015 and ARC GIS software. The four land cover classes viz. water body, built-up land, barren land, and vegetation were used to classify the region. The accuracy evaluation was assessed separately using the kappa coefficient after carefully examining the image pre-processing and classification. The overall accuracy in the basin was found to be 83.23%, 86.45%, 85.83%, and 88.75 % with a kappa coefficient of 0.79, 0.81, 0.87, 0.85 for the years 1999, 2007, 2014, and 2020 respectively. The Bhavani basin is mostly covered by barren and vegetation. According to the findings, the basin's built-up area has risen by 1.5 percentage to 3.5 percentage in the last 20 years. The increase in the vegetation area and reduction in the barren area may lead to low soil erosion.

Optimal Sizing of a Centralized Hybrid Photovoltaic System for Efficient Operation of Street Lights

Abstract: The photovoltaic energy generation system is one of the most promising technology to meet our future electricity demand as well as mitigate climate change. This study aims to design, simulate and evaluate the performance of hybrid photovoltaic (PV) system using PVsyst software to supply electricity for energy efficient streetlights in educational institute. Meteonorm database of daily and monthly irradiation, temperatures, precipitation and sunlight hours are utilized while performing the analysis. The photovoltaic system consists of 56 bifacial-polycrystalline 360-watt PV modules having 17.9% efficiency. The photovoltaic modules were installed at 0° azimuth angle and 15° tilt angle. Two hybrid inverters with rated capacity of 10 kW are used. The energy storage system consists of 16 batteries (2 in series x 8 in parallel) with a nominal capacity of 1600 ampere-hours and discharging minimum SOC is 20 %. A total of 100 streetlight poles with 8 working-hours/day are installed to cover both sides of the road, with monthly energy consumption of 672 kilowatt-hours. The average annual ambient temperature is 23.66℃, and the annual GH irradiation is 1693 kilowatt-hour/m2. The annual production of the hybrid PV system is 25.96 MWh/year, the specific energy production of the system is 1288 kWh/kWp/year with 70.38% performance ratio. By means of proposed photovoltaic system for energy efficient street lightning structure, 157.9t CO2 is reduced. The project can save 0.004737 million tonnes of CO2 emissions over its lifetime of 30 years. The proposed system is a viable solution for public lighting with the right selection of system components.

Ant Colony Optimization based Optimal Tuning of Fractional Order (FO) PID Controller for controlling the Speed of a DC Motor

Abstract: This paper deals with the use of a FOPID Controller for the direct current motor speed controlling process. FOPID Controller consists of fractional integral-derivative terms along with the integer order proportional terms. It is a specific controller in which orders of derivative and integral lie in between fractions of 0 and 1. Mathematical model of DC motor and controller is presented whose field has been excited by an external source. In this paper, the simulation part of a DC motor for controlling its speed using a FOPID Controller has been performed. There are five degrees of freedom in FOPID controller contrary to traditional PID controller which have only three. The values of the five parameters (Kp, Ki, Kd, λ, μ) of a FOPID Controller have been improved by reducing the ITAE (Integral Time Absolute Error) cost to best possible value using the ACO i.e. Ant Colony Optimization Technique. The closed loop ZNT (Ziegler-Nichols Tuning) method used for the tuning of DC motor. Simulink model of proposed system has been developed and simulated to find out the minimum cost. The intensification in the steady and transient behaviors of the system. The results also exhibit significant improvement in the rise time, settling time and peak overshoot as compared to the other optimization methods.

Stock Market Forecasting using Ensemble Learning and Statistical Indicators

Abstract: With a volume of 2 billion+ trades per day and a market capitalization of 2.56 trillion USD the national stock exchange (NSE), India is one of the largest stock exchanges in the world. Every day the value of stocks, commodities, bonds and futures fluctuate inducing volatility and forecasting these fluctuations to make money requires deep knowledge about the market and their historical data. Thus, a simple time series forecasting model is not enough to predict future movements as we need to know about the market sentiment, trend and industry fundamentals to bolster our stand of declaring a stock or commodity as bearish or bullish. In this research, using machine learning forecasting models like Attention integrated Long Short Term Memory (LSTM) Model and a Reinforcement Learning agent coupled with statistical indicators and trading strategies like Auto Regression Integrated Moving Average (ARIMA), Prophet, Momentum trading and Pairwise trading to quantify the trend and market sentiment an approach to predict movements is devised. Using this approach increases the accuracy of stand-alone algorithms and helps in generating a cumulative analysis of the stock on the basis of itself and its stock universe data.

The prediction of product return rates with ensemble machine learning algorithms

Abstract: There may not always be actual data available for planning. Predicted data are used especially for future planning. Due to errors in such planning based on prediction, many products enter the reverse logistics network without completing the shelf life. Especially in textile sector, because of fashion, it is the most important point of planning to be able to make accurate estimates in order to avoid unnecessary resource utilization and to provide minimum cost. It is difficult to establish a mathematical model because the prediction problems in real life have multivariate structure and unknown parameters. Most of the studies in literature have been based on time series prediction. But due to changing fashion and demands of consumers, there are significant differences between demand forecasts and real data. So, in the problems with unknown parameters and multivariate structure, Ensemble Machine Learning (EML) methods are preferred recently because they give more accurate results than other prediction methods. Unlike other studies, the product return rate in textile sector has been predicted with the Stacking and Vote algorithms from EML methods in this paper. In this direction, it is aimed to concentrate on the returns of the products sold with the preferences of the customers and to predict the returns more accurately. In this way, the consumer information obtained as a result of the analyzes can provide more accurate planning in avoiding unnecessary production, transportation and storage activities, reducing costs, resource utilization and environmental pollution. In addition, it is one of the main aims of the study to contribute to the literature by determining the parameters that can be used in predicting the return rates. Highest performance results were obtained with Stacking algorithm. The obtained results were given comparatively and the correlation coefficient of 86.07% was reached.