Advances in Smart Grid Technology

This paper deals with the implementation of online insulation monitoring of low-voltage unearthed distribution systems. The purpose of choosing and applying unearthed distribution systems is the various advantages it possesses in the industrial safety area such as continuity of service and prevention from risk of fire and shock. It is an important task to detect insulation fault in the energized (online) system without affecting the distribution system. The main purpose is to deal with the insulation fault in the energized system and maintain the continuity of the system supply. The idea is to continuously monitor the low-voltage distribution system and detect the insulation/ohmic faults in the ungrounded energized low-voltage distribution system using an insulation monitoring device (IMD). Basically, ‘online’ suggests real-time measurement and ‘insulation monitoring’ is the continuous insulation monitoring and leakage fault detection of ungrounded distribution systems. The IMD detects insulation faults between the energized system and earth. An external injection, generated by the IMD, is made in the distribution system to monitor the system. During the healthy condition of the distribution system, the IMD reads and displays high insulation values. When an insulation fault occurs, the IMD reading drops down to the corresponding value of insulation fault, which is proportional to the voltage. Evaluation of various studies has been made, and various cases have been studied and implemented using Multisim software. Based on these case studies, testing of the hardware and hardware implementation of one of the case studies has been showcased.

The role of induction motors is varied and of much importance in the field of electrical drives. For such induction motors, proper starting is required to improve versatility of the machine, reduce the starting current and mitigate power quality issues caused due to motor starting. There are different methods of starting, such as direct on line starter, electromechanical starting and autotransformer based starter. However star–delta starters are proved to be better in case of low and medium power motors, on account of cost and efficiency; however this gives transients when the circuit configuration is changed. In the proposed system power electronic switches are being used as soft starters for induction motor drives. Different power electronic switches are used and comparisons of the outputs provide a perspective on the effectiveness of the circuit.

Permanent magnet-assisted synchronous reluctance motor (PMa-SynRM) helps to reduce the dependency of rare earth magnets, particularly in electric vehicle applications. In this paper, the significance of magnet position in PMa-SynRM is discussed in detail. By keeping the magnet in appropriate position, it can be utilized effectively, which enhances the power density of the motor. A 1 kW PMa-SynRM is designed for electric two-wheeler, and its performance for various magnet positions is analyzed and compared.

Switched reluctance motor (SRM) has become admirable to conventional electrical machines due to its robust construction, a wide range of speed control, ruggedness, low cost, high torque to weight ratio and highly reliable. SRMs are gaining most attractive with these excellent features in the field of industrial applications such as electric vehicles, electric traction, aerospace, mining drives. By cause of harmonics in air gap flux leads to periodic speed pulsations and large torque ripple which leads to vibration and acoustic noise. Hence to overcome this problem, the intelligent controller like a fuzzy logic controller (FLC) is employed. In this paper, FLC-based classical converter fed SRM drive is presented. The main aim of this work is to control the speed of SRM drive with a fuzzy controller in the MATLAB/Simulink platform. To show the effectiveness of fuzzy controller, its performance is correlated with the conventional proportional integral (PI) controller. The statistical parameters like rise time, settling time for various speeds with constant load torque are reported. The comparative simulation results between the FLC and PI are also shown to validate the effectiveness of FLC to diminish periodic speed ripples and settling time.

In future, the electric vehicle will be expected to dominate the other transportation networks. Many commercial electric vehicles are being charged at common times due to their usage pattern. This results in sudden rise of power demand on the electricity networks. In this paper, dynamic economic dispatch considering the impact of commercial electric vehicles is proposed. The objectives of this work are minimization of fuel cost and network power loss. A novel methodology for charging the commercial electric vehicles is developed and is utilized in conjunction with dynamic economic dispatch. The proposed work is implemented on IEEE 30 bus system and the results show that this method is very effective.

Usage of electric vehicles by mankind is increasing rapidly. It is observed that most of the electric vehicles in a distribution system are being charged at common time which indirectly reflects as a considerable load. In this paper, the impact of these electric vehicles on distribution system performance is studied and a new methodology for reducing the power loss is implemented. A standard IEEE 33 bus radial distribution system with variable load profile is considered for analysis. This method uses a combined loss sensitivity factor and grasshopper optimization algorithm to determine the optimal location and size of distributed generation throughout the day. Various charging patterns for electric vehicles are analyzed and best possible approach for minimizing the power loss is presented.

This paper is aimed to apply the improved particle swarm optimization (IPSO) algorithm using line stability index (LSI) for the optimal positioning of unified power flow controller (UPFC) in standard IEEE test system as it can control real and reactive power simultaneously. It also provides series line compensation and independent controllable shunt compensation, which can maintain a stable and secure operation of modern deregulated power system. In this paper, MATLAB environment was employed to seek the optimum placement of UPFC considering practical constraints. This work expounds the capability of UPFC in terms of loss minimization, voltage stability enhancement, and power flow control. The reduced LSI values can indicate the stress relief over the transmission lines and conjointly indicating the congestion relief. To show the effectiveness, the proposed method was demonstrated on IEEE30 bus test system.

This research work focuses on power thermal power plant efficiencies, which are associated with many more indirect losses and have been broadly examined for proposeful solution for it. Waste heat can be primary point here, which be suitable to reuse at certain heating process, is a concept of efficiency improvement. Some of most sensitive points like draying of fuel, preheating air for combustion monitoring, and rising of feed water temperature are observed for better approach during this work plan. It is theoretically proved, minimisation of an extra 3% wt. on moisture of fuel and rise up to inlet air of 35 °C. Improving efficiency by 1% and saving of 50 ton of fuel on and average during a year. An intelligent process has been designed that operates, monitors and controls properly the heat recovery. Due analysis of traditional PID with proposed FUZZYPID after the result justifies its utility over nonlinear complex to nonlinear process. So, this proposed intelligent process is accepted for all range of operating condition with most expected developing of efficiencies.

The PMSM generates the magnetic flux on its own as the rotor has permanent magnet and thus the motor never depend on any exterior source. The torque and speed ripples are the some of the disadvantages which affect the performance of drive. This paper proposes the performance enhancement of PMSM employing ILC and SVPWM driven by FOC to reduce both the speed and torque ripple. The result is compared with conventional PI controller. The outcome shows the reduction in torque and speed ripple which enhances the drive performance by using the above technique. The hardware result is obtained from DSP controller.

Switched reluctance motor (SRM) is widely used for variable speed applications due to its enormous advantages like simplicity, ruggedness, and lower cost. In variable speed applications, detection and diagnosis of faults are vital. This paper investigates the performance of SRM drive under faulty condition and proposes a Hilbert transform-based technique to diagnose the faults. The faults considered in this work include phase open-circuit fault, short-circuit fault, interturn fault with uniform and non-uniform turns, and phase-to-phase short-circuit fault. The performance of the motor under normal and fault conditions is analyzed using finite element analysis-based package MagNet 7.5. The features extracted from Hilbert transform will aid in detection and classification of faults in the motor.

The energy drawn from the wind power plant and photovoltaics is considered to be essential sources in the recent distributed generation (DG) of electrical power. Since a day-to-day load demand for electricity is increasing rapidly and therefore the generation of power, needs to be improved for balancing the current demand. Because of this growing demand, non-renewable energy sources are on the brink of extinction. In order to solve this problem, the concept of integration of renewable energy sources has been introduced in the electrical distribution system and thereby improves the power quality and reliability to meet out the existing needs of the customers. Hence, the concept of installation of the DG has an impact on the operation and characteristics of the electrical distribution system. Installing the DG units near to the load centers may solve the basic problems such as power losses and voltage drops. The overall system is simulated in MATLAB environment in which, the three-phase grid-connected photovoltaic system is integrated with the parallel loads. The outputs are being measured in the form of the power, voltage and current at various points in the existing system and are analyzed in both the normal and faulty conditions. At Point of Common Coupling (PCC), variations in voltage and current under different types of fault conditions, intentional islanding and nuisance tripping of load cases are analyzed without protection device.

The main objective towards electrical-distribution system is to experience the consumer’s demands for energy later acquiring the huge electrical-energy from the transmission/substation. Various network compositions remain feasible to suit the needed supply reliability. Protection, control and supervising apparatus are implemented to empower the adequate process of distribution network. This effort mainly analyzes on 3phase, 3bus distribution system by introducing an UPQC with various load configurations. The outcomes are correlated as regards real-power, reactive power, voltage, current-THD. The Significance of the present work is to upgrade the quality of power for a 3-ph, 3-bus distribution network by introducing an UPQC with various load configurations.

In this paper, a Genetic Algorithm and Graph Theory-based approach has been proposed for the Protection Zone Selection for Distribution System. The Proposed method is designed and developed to split electrical distribution system into protection zones containing busses and protection relays or fault detectors and also to decrease the calculation burden in dealing with a large set of signal data. Genetic Algorithm based heuristic Search method is used to place fault detectors at optimal location, and it carried out in MATLAB. IEEE33 bus radial distribution system is tested for validating the proposed system.

Nowadays power quality issues are the greatest challenges to the upcoming development. Especially in case of using the sensitive loads the voltage disturbances will be high. Many research based solutions has been raised to overcome the PQ issues. One the best solution is power electronic switches based dynamic voltage restorer. The DVR becomes mature power quality device. The Converter structure and compensation schemes plays a major role in deciding the capability of the DVR. Hence in this paper, classification of DVR based on converter structure and compensation schemes have been analysed.

The Microgrid is a combination of the distributed generation (DG) systems that deliver power to its local networks. The DG system constitutes non-conventional sources such as wind turbine, fuel cell, battery, and Solar. By connecting microgrid to the non-linear loads, it generates harmonic current into the system, which disturbs the sinusoidal waveform and power factor. The power quality compensator is used for improvement of the reliability and efficiency of the system. In this paper, first power quality issues are analyzed by connecting loads. As the system is connected to load it disturbs the sinusoidal waveform by introducing harmonics. To reduce these harmonics, passive filters are used. But due to the certain drawbacks such as complication in design and huge size of filter shunt active power filter (SAPF) is introduced in this system. These SAPF is controlled by an instantaneous power theory, which works as on line power quality analyzer and limits THD according to the IEEE 519-1992 standard. Depending on the power requirement of the nonlinear load, the proposed control for SAPF allows balanced line with near sinusoidal current and also maintains unity power factor. The presented model is simulated in the Matlab/ simpower environment and results are validated.

A coal handling system equipment is a bulk material handling system; it plays an important role in key mechanical industries. It holds the important aspects of a country economy in mining, smelter plants, thermal power plants, process industries, etc. Considering operation attributes of the coal handling belt conveyors, various parameters have to be taken into account while designing, as it has to convey materials from one location to another continuously for most part of the year. In broad spectrum, the flat belt coal conveyor has to be with maximum load handling ability, for conveying over long distance in a single stroke. Hence, it has to be steadfast in design, with easy operation and maintenance and high dependability in function. Self-aligning conveyor roller (SACR) is an important element in coal belt conveyor. It is placed between the carrying conveyor idlers to vary the sideways dislocation caused by imbalance loading which is difficult to avoid in harsh loading conditions. When the coal conveyor belt moves against the carrying rollers, there is a difference in frictional force between two sides, which will make the top strand of the coal belt conveyor to twist toward the center. Further, the crisscross movement, offset from the center line, and damage of coal conveyor belt were competently prevented by self-aligning conveyor roller. As SACR is found to be critical in coal belt conveyor systems, it becomes compulsory to supervise its smooth and continuous functioning. To make sure this certain, condition monitoring of self-aligning conveyor roller (SACR) should be done periodically which principally creates a classification or categorization problem. Self-aligning conveyor roller is made of vital elements like groove ball bearing, main central shaft, and the external shell. In this case, it is categorized with the below mentioned cases such as coal handling belt conveyor with SACR running in no-fault condition (NFC), with groove ball bearing fault condition (BBFC), with main shaft fault (MSF), with combined ball bearing fault condition and main shaft fault (BFC & MSF). A model investigational arrangement has been made as per the actual coal handling belt conveyor operating conditions and research requirement. Followed by the fabrication of SACR setup, the vibration signatures were obtained from the model for frequently occurring fault discussed earlier. These vibration signatures are fed to digital convertor and transformed to digital signals. From the digital vibration signals, statistical features were calculated. Then, effective statistical features were extracted and provided as input to random forest algorithm, followed by categorization, which was performed by random forest algorithm. In the current work, the random forest algorithm achieved 90.2% categorization accuracy, which summarizes the algorithm correctness in fault prediction self-aligning conveyor roller failure and life assessment.

Reactive power resource management is a crucial and vital step in order to have a safe and cost-effective power system option when it comes to voltage stability. The optimal reactive power dispatch (ORPD) has a key aim to find out the appropriate control variable values, for example, shunt VAR compensator settings, generator bus voltages, and tap settings of on-load tap change (OLTC) transformers. This objective is designed, by taking the constraints into account, and to ensure that the objective function is reduced. In the current research work, the researchers proposed a levy interior search algorithm (LISA) in order to elucidate multi-objective optimal reactive power dispatch challenges that mitigate the real power loss, and at the same time, it also saves the voltage quality. In this research article, the researchers considered real power loss and voltage stability index as objective functions. The paper has a primary objective, i.e., by taking large-scale power system into account, the researchers proposed a multi-objective interior search algorithm in order to get rid of multi-objective ORPD problem and to yield the best results from the secure and cost-effective operation of electric power systems. The researchers simulated the setup under IEEE 57-bus and large-scale IEEE 300-bus system to emphasize the efficacy of LISA. From the results, it can be confirmed that the proposed approach yielded much better results than the existing algorithms.

The paper proposes feasible and acceptable distributed slack power flow (DSPF) formulation for the settlement process of active power market in deregulated system with single-sided bidding. In general market clearing is done using single slack bus model but whenever marginal bus changes loss price varies drastically. In order to prevent the sudden changes in loss price, optimization using distributed slack model is suggested in this paper. The loss factor approach is used in determining the feasible participation factor. The proposed strategy is verified using PJM 5 bus system.

Smart grids have become one of the most emerging technologies in power systems by its fashionable design, reliability, and efficiency. Smart grid is the integration of multiple DGs. In this context, DG (Distributed generation) plays a significant role in power system. When DG is connected to the distribution network, the impact of fault currents is high which can cause protection coordination failure in smart grids. In this paper, three phase fault current which is the highest fault current in distribution network and its effect on DG is discussed. Controlled Impedance Fault Current Limiter (CI FCL) combination of both resistive and reactive component is used to maintain fault currents. The problem is formulated as integer, non-linear constrained problem. Optimal location of DG and CI FCL sizing is determined by using Salp Swarm Algorithm (SSA) and it is tested on IEEE 33 and 69 standard distribution bus systems in MATLAB2017. A comparison between the developed SSA and PSO is executed in terms of complexity, No. of iterations, and computational time. The results show that the proposed method is effective.

This paper has been emphasized to develop a new methodology for optimal power flow (OPF) using delicate flower pollination algorithm (DFPA). Being an essential key factor in the ocean of power sector, its operational features and controlling attributes have been making the available power resources to flow in a fair manner. The DFPA, a nature intriguing algorithm, has originated from the pollinating characteristics of flowers. The proposed method has sounded very louder on the global optimum solution using DFPA through propagating the exploitation phase of optimization by considering two test-case studies such as shortened fuel cost and real power loss decrement. Simulation results on IEEE_Standard 30 bus test system have clearly exhibited that the proposed method outperforms the existing numerous strategies.

Polymeric insulators are being widely used over ceramic insulators due to their tremendous merits. However, due to absence of the intermediate metal part, electric field and potential distribution along these insulators are non-uniform, which can be minimized by using suitable corona ring and grading ring. The aim of this work is to provide an optimum design of corona ring and grading ring for a 400-kV suspension-type polymeric insulator. Finite element method-based software is used for simulation purposes. This paper presents the results of 3D finite element calculations of electric field distribution along a 400-kV polymeric insulator. An optimum dimensions are predicted using multi-objective genetic algorithm. The predicted electric fields are compared with the actual values.

This paper proposes a simple modified vector control scheme for restraining the impacts on permanent magnet synchronous generator (PMSG)-based wind power system (WPS) integration under various grid disturbances. Voltage sag and harmonics are the major causes of grid voltage disturbances. The percentage of voltage sag for which WPS remains to be connected with the grid is dictated by fault ride-through (FRT) characteristics. Moreover, voltage sag occurred due to short-circuit fault has its associated phase-angle jump. Hence, it is necessary to map the voltage sag with phase-angle jump to meet the broad range of FRT requirements. A new analysis with major types of faults that can occur at the point of grid integration is presented in this paper. In order to satisfy the grid code compliances and reduced harmonic distortions, the modified vector control scheme is modelled with additional voltage and current oscillation cancellation blocks without the need for dual vector control loop. Extensive analytical simulation has been carried out in PSCAD/EMTDC to validate the superiority of proposed control scheme over the conventional schemes in terms of transient overshoots and oscillations that appear in dc-link voltage and real and reactive power of grid when PMSG is subjected to various disturbances.

Distribution system is a complicated and significant contributor to the overall losses of power system, wherein the loss due to unbalanced loading at each bus is often overlooked and is vital to consider the same. Unbalance in the system can be mitigated by using one or more of the following techniques: network reconfiguration, Phase Balancing (PB), reactive compensation, distributed generations (DG) integration, etc. With the evolution of smart meters, PB of whole feeder by rephasing Consumer Service Mains (CSM) is achievable. As renewable generation at consumer level is making headway, balancing a distribution system by considering consumer load pattern in DG-integrated system is essential. With this motivation, the effect of PB at each bus in the presence of DG on system losses is examined and investigated in this paper. It is achieved through the development of phase balancing algorithm (PBA) in combination with backward sweep technique requiring an overall lesser computational effort. The developed algorithm is tested in MATLAB considering the IEEE 13 bus feeder along with optimally placed DGs. The performance of the developed algorithm is evaluated with an objective to reduce line losses, the number of rephasings, branch current and neutral current, thereby to enhance the bus voltage profile.

This paper focuses in estimating the payback period and percentage recovery with static var compensator (SVC) and thyristor controller series compensator (TCSC) in an SCUC problem applying artificial bee colony (ABC) algorithm. ABC algorithm mimics the foraging behavior of employed, unemployed, and scout bee in a bee colony system. SCUC problem aims in reducing the operating cost satisfying all system, unit, and security constraints. The SCUC problem is disintegrated as master problem (unit commitment—UC) and subproblem (security-constrained economic dispatch—SCED). The capability of SVC and TCSC to regulate the power flow in lines and alleviating the overloading is exploited here. The optimal location of the SVC and TCSC in a power system network is clearly illustrated. The profit obtained with SVC, TCSC, and the payback period of these devices are explained with respect to installation cost. The gain obtained with SVC and TCSC including annual maintenance cost for a certain period of time is illustrated. SVC and TCSC are modeled based on variable reactance modeling technique and incorporated in IEEE 118-bus and south Indian 86 bus systems at their optimal locations. The total generation cost obtained by solving SCUC using the heuristic approach is compared with existing methods in literature.

Combined heat and power economic dispatch is an important optimization problem in a power system integrated with cogeneration units. In addition to the optimal solution satisfying the power balance equality constraint and the bounds of the thermal units, it must also lie within feasible operating region of the cogeneration units. This increases the complexity of the problem, and a potent meta-heuristic algorithm is required to solve the problem. This paper investigates the optimal solutions of the combined heat and power economic dispatch problem obtained by a recent meta-heuristic salp swarm algorithm. Transmission losses of the power system and valve point loading have been taken into consideration in this work. The algorithm is tested on standard test system available in literature. The results indicate there is scope for improvement of the salp swarm algorithm to solve combined heat and power economic dispatch problem.

The necessity of Power Quality (PQ) is always in demand by the power consumers. This paper presents a review on Transformerless Dynamic Voltage Compensators (TDVC) topologies for voltage related PQ enhancement. Transformerless topology ensures that the device is less cost, smaller in size compared to ordinary compensators. This paper gives the knowledge of all past and recent TDVCs which helps engineers and researchers to find out which transformerless topology suites better for their compensation.

A novel index method to find out the optimal location and optimal size of DGs in a distribution system is presented with the objective of loss minimization and reduction in voltage deviation. To highlight the importance of nodes in terms of loss reduction and improvement in voltage profile, a new metric called Aggregate Loss and Voltage Sensitivity Index (ALVSI) is proposed. The optimal location and size are found out to maximize the Aggregate Loss and Voltage Sensitivity Index (ALVSI). A detailed analysis was presented for the CIGRE medium voltage distribution system benchmark. The simulation platform used is the Pandapower Python module.

An interesting attempt is taken to form a hybrid model by integrating Fuzzy Cognitive Map (FCM), the Delphi Method, and the DEMATEL method through the Haar ranking of Hexagonal Fuzzy Number. To examine this model, the problem of solid waste management is taken. Solid waste arises from human and animal activities can generate major health problems and horrible living environment when they are not dumped of safely and appropriately. The proper disposal of solid waste helps to reduce the terrible impacts on both human health and environment to sustain economic growth and better quality of life. Therefore, this present study analyzes the solid waste management through the Haar FCM with DEMATEL technique.

In order to meet the growing water demand, two sustainable options are available—desalination and wastewater recycle and reuse. The wastewater recycling and reuse concept, which is already prevalent in most of Europe and America, is currently in high demand in India with Swachh Bharat Mission and smart cities program of Government of India. The necessity to treat wastewater for recycling and reuse is slowly gaining grounds in industries, municipalities, and residential segments. The wastewater can be treated with different means—physical process like separation of suspended solids, chemical process like pH neutralization, and biological process to decompose organic substances. In pH neutralization of wastewater, the incoming untreated wastewater has a wide range of pH, and it is difficult to treat wastewater with such a high variability of pH. Neutralization is the process used for adjusting pH to optimize treatment efficiency. Neutralization may take place in a holding, rapid mix, or an equalization tank. In this work, a novel approach using NARX (Nonlinear Auto-Regressive eXogenous) model and enhanced moth flame optimization (EMFO) is proposed for pH neutralization of the wastewater and its performance is compared with ARX (Auto-Regressive eXogenous), ARMAX (Autoregressive Moving Average eXogenous), and BJ’s (Box-Jenkins) model performance in terms of ISE, IAE, MSE, settling time, and peak overshoot for evaluating controller performance. The outcomes are then evaluated for both proposed and existing approaches to prove the effectiveness of the proposed scheme for the case under study.

Increase in particulate matter (PM) in air causes a biggest threat in the twentieth century. In order to filtrate PM from air, filters are employed. These filters are called as particulate matter filter (PMF). These filters separate the PM from the polluted air. The processes followed by PMF to separate the PM from the polluted air are filtration and adsorption. Different filters are developed for this purpose. This chapter presents a critical review of different types of particulate filters. Porous- and fibrous-type filters are discussed in this chapter. This chapter explains the fabrication process of different PMF along with its advantages and limitations. This chapter helps researchers in choosing PMF for their specific application.

Crime is an unlawful event which affects the harmony of humanity. Whoever got victimized in a crime, it affects them both physically and mentally. Hence, they are haunted by the memories throughout their life. Due to the limitations, traditional data collection and analysis methods are not very effective now. Yesteryears, the researches were concentrating on demographic features of the population. Nowadays, the dynamic characteristics of individual or specific group could easily be extracted from the search engines, social media, e-commerce platforms, mobile applications, IOT devices, surveillance cameras, sensors and geographical information systems. The recent technological advancements are helpful in integration of data from various sources, classification of information into granular level, identification of crime sequences and designing a framework. Particularly, the artificial intelligence methodology called deep learning imitates the functions of human brain and able to acquire knowledge from unstructured data. It makes revolutionary changes in crime forecasting, predictive policing and legal strategy formulations. The following survey explores the possibilities of scrutinizing the data from huge repositories, analyzing various socioeconomic factors associated to the crime incidents, identifying the outliers, categorizing the patterns and designing effective computational models to predict crimes by using data mining and machine learning techniques.

Ambient Intelligence (AmI) is the Artificial Intelligence which is completely human-centric. It deals with a new world where computing devices are spread everywhere, allowing the human being to interact in physical world environments in an intelligent and unobtrusive way. These environments should be aware of the needs of people, customizing requirements and forecasting behaviors. AmI involves integrating the technology invisible in day-to-day life. According to Information Society Technologies Advisory Group (ISTAG) 1999, AmI1 should be the result of the convergence of three key technologies: ‘Ubiquitous Computing,’ ‘Ubiquitous Communication’ and ‘Intelligent User-Friendly Interfaces.’ AmI is unobtrusive and often invisible, being embedded in everyday objects such as furniture, clothes, vehicles, roads and smart materials. People will be surrounded by intelligent and intuitive interfaces recognizing and responding to the presence of individuals. Intelligence embedded in everyday objects and the surrounding environment such that the use of these smart objects is intuitive to the inhabitants of the environment. Combining both mobile and sensing technologies for providing a pervasive and unobtrusive intelligence and environment in supporting the main activities and interactions of the users. This forms the base of Ambient Intelligence. Technologies like face-based interfaces and affective computing are inherent ambient intelligence technologies. Many features being the crucial element in setting up an effective and efficient Ambient Intelligence environment, intelligent user interface is the key component. A vision of society of the future, where the people will find themselves in an environment of intelligent and intuitively usable interfaces, ergonomic space in a broad sense, encompassing better, secure and active living environment around them, capable of aiding them with daily chores and professional duties by recognizing the presence of individuals, reacting to it in a non-disturbing, invisible way, fully integrated into the particular situation.

Wind energy is one of the renewable energies, which has been utilized effectively to maintain the ecological balance of the environment. The wind speeds (m/s) at the 10 m level above the earth’s surface in Aluru Kona site (latitude of 14.920, longitude of 78.020) and Ellutala site (latitude of 14.559, longitude of 77.779) for a period of 01.01.2019 to 01.02.2019 are used to estimate wind power density. The benchmark data is obtained from MINES ParisTech Web portal. The research work is limited in the regions of Andhra Pradesh: Anantapur district, Tadipatri, for Aluru Kona village and Ellutala village wherein the wind power plants have located. In this work, an empirical method is being utilized for the evaluation of the Weibull probability distribution parameters (shape parameter and scale parameter) and cumulative function which provides an estimate of the wind power density.

Semantic technology approach in machine learning is an emerging technique to solve the problems in the machine learning. Semantic technology has been the improvised from decades according to the human needs and industrial demands. This new era is all about teaching a machine to learn on its own and to make it understand the concept and the purpose for what it is used, using algorithms. This paper, condenses the work of semantic technology approach in machine learning and its idea put forward. The introduction details with brief explanation followed by description of the semantic technology and machine learning, important role. The literature survey contains summarized view of the papers with a graph plotted on the analysis of paper throughout the decade; a table with summary of the related works and concluded with review analysis.

Senior citizens are prone to accidents due to their old age. The accidents may cause severe injuries and even to death if it is not identified and treated within a short period of time. Also, it is more risk if they stay alone in their homes. To mitigate the risk, an alert system is to be designed to alert the caretaker about the occurrence of the accident. By mounting three aerial microphones and one-floor acoustic sensor (FAS) in their room and monitoring the acoustic information received from the microphone and FAS, the acoustic information of the fall event is recorded. The acoustic features such as energy, spectral centroid, spectral flux, zero-crossing rate and Mel-frequency cepstral coefficients (MFCC) are extracted from the acoustic signal. Support vector machine (SVM) network and deep learning neural networks (DNN) with more than two hidden layers are trained with a reduced set of features obtained with principal component analysis (PCA) from the acoustic features. DNN classifier is proved to be better than SVM classifier. The obtained accuracy for DNN is 97%, the accuracy of the SVM classifier with MLP kernel and RBF kernel is 50% and 83%, respectively.

Learning the electrophysiological activities inside the human mind is a significant step toward studying the human brain. Systems, such as electroencephalography, are significant instruments for considering the neurophysiologic activities, in view of their high value of temporal and spatial resolution. In the biomedical research, identifying brain abnormalities such as autism spectrum disorder through electroencephalography (EEG) signals is an extremely exhausting issue for specialists and human services experts. The high volume of data available with EEG will be a useful biomarker for the classification of autism and typical children. Traditional techniques face challenges to deal with such big data. So we present a strategy for autism identification by analyzing the EEG signal through mathematical model. One such modeling using graph theory is applied in this work. The EEG signals are acquired from 3 autism and 3 typical children. The functional connectivity among the neuron regions are plotted through small world networks. From this graphical models using a software tool Gephi, the graphical parameters as betweenness centrality, degree, weighted degree, closeness centrality, modularity, and clustering coefficient are calculated. There is significant difference among these parameters between autistic and typical children.

Predictive Analytics is emerging as one of the popular branch of Machine Learning with huge amount of money spent on to research, build and test models to improve the accuracy of the outcome. In our paper we have implemented different regression models such as Logistic Regression, Support Vector Machines, Naive Bayes Classifier, and Neural Networks to forecast the result of the US Presidential election 2016. Social media websites have become a very popular communication platform among users. Millions of users share their opinions, extend their support, and vent their anger on various government policies and on different aspects of their life. Hence, social media websites contain huge amount of data for sentimental analysis. We have narrowed our attention toward Twitter, the most popular microblogging website for performing sentimental analysis using the opinions shared by the users on twitter.

This paper is designed to measure energy consumption in home and buildings and to generate its bill automatically. It is accomplished by utilizing a smart energy meter with the Internet of things (IoT) technology, which will permit the user to successfully observe the energy meter calibrations and verify the electricity bill via the online. Our projected scheme utilizes Arduino to track utilized energy and to send out the units along the cost charged over the Internet. The Liquid Crystal Display (LCD) module is interfaced with Arduino, and the measured voltage, current, power, and the corresponding bill are displayed to the consumers. Arduino also sends data to the Adafruit cloud using the Wi-Fi module NodeMCU ESP-12. This smart meter will permit both the consumer and electricity supplier to ensure the energy usage quickly among the cost charged online. Power cost analysis of a month for a smart home is done in a separate section. Finally, the hardware is implemented with various loads, and results are displayed via LCD.

Graduate attributes are the competencies and capabilities set by the college network as benchmark for its students during their time with the organization. The principle point of the paper is to assist students with their scholastic choices, by suggesting elective courses dependent on the graduating attributes scores. Students rate the significance of each course in improving their graduating qualities toward the end of every semester. The elective courses taken by peer students and rated similarly are identified by a collaborative filtering algorithm and prescribed to students. This paper predicts the rating for each course and graduating attribute. The elective courses with the greatest expected ratings are shortlisted for proposal. Also, the aggregated GA score is determined for each student at end of every semester. The shortlisted courses that can improve the feeble GA scores are at prescribed to students.

Lane lines play a key role in indicating traffic flow and directing vehicles; lane detection serves as a core component in most of the modern-day advanced driver assistance systems (ADASs). Computer vision-based lane detection is an essential technology for self-driving cars. This paper proposes a lane detection system to detect lane lines in urban streets and highway roads under complex background. In order to nullify the distortions caused by the camera lenses, we generate a distortion model by calibrating images against a known object, and apply a generalized filtering approach using Sobel operator (Canny edge detection) in HLS color space. A bird eye view of image is generated using perspective transformation. A special search strategy using sliding window algorithm is used to detect lane lines, and later, curve fitting is done using polynomial regression. Thus, the obtained lane detector is overlaid upon a video to fill the detected portion of the lane. Then, it is applied to the video to detect lane lines. The image processing pipeline is written in Python using OpenCV libraries, and video processing is done using MoviePy. In this paper, the system developed is tested by applying it on a video taken from a camera mounted over the car. The environment used to implement the system is Anaconda. The results obtained show that the proposed system for lane detection, self-calibration and vehicle offset estimation is effective, accurate for both straight and curved lanes and robust to challenging environments.

With increasing energy demand and the necessity to fulfill the energy requirement, it is mandatory to increase the energy generation. However, shortage of supply resources stands as a blockade in this present scenario. Hence, an efficient energy management system is required. This paper demonstrates a working prototype of intelligent energy management system. It is an IoT-based energy management system with Web server-type manual control. It involves serial communication between microcontrollers such as Arduino Uno and NodeMCUs, sensors and computational intelligence. The sensors used in this case are LDR, thermistor, and PIR motion sensor. The system includes LED lights and fans as load. The raw data from the sensors is read by the Arduino and it serially communicates the raw data to both the NodeMCUs. The data is then converted to standard formats and uploaded to the ThingSpeak cloud server for data logging and analysis by one of the NodeMCU. Using the second NodeMCU, a Web server is created and used for manual control of the loads. This Wi-Fi server sends data to the NodeMCU as per the user input from the browser and this NodeMCU controls the load accordingly. A current sensor is also connected along the supply line for power measurement. The current sensor is an ACS712 20 A sensor which is connected to the NodeMCU and is responsible for uploading data to the ThingSpeak cloud server. The working model has three rooms for demonstration purpose but can be increased accordingly as per need with certain changes in system hardware model.