A new controller is designed for performance improvement of a photovoltaic based microgrid (PVMG) system in this paper. The photovoltaic system is integrated to grid via an H-bridge voltage-source inverter (VSI). To enhance the power conversion from the solar panel, an incremental conductance (I&C) Maximum-Power-Point-Tracking (MPPT) controller is designed. The proposed controller comprises of two units namely for accomplishing power quality improvement and MPPT tasks. We design a sliding mode controller for improving power quality. This controller is designed to control the power-flow injection to the PVMG. The results are compared with that of the proportional-integral+proportional-integral-derivative (PI+PID) hybrid controller to evaluate its effectiveness. From the transient performance analysis, it is found that with the proposed controller, it is faster in response, with lesser harmonics and more robust compared to the PI+PID hybrid controller. Also, this system is capable controlling both active and reactive power of the line.
Artificial neural networks and their variants play an important role in the analysis and classification of different biomedical data. Deep learning is an advanced machine learning approach which has been used in many applications in the last few years. Worldwide breast cancer is a major disease for women; it is one of the most challenging jobs to detect at an early stage. The authors in this work have taken an attempt to classify the breast cancer data collected from the UCI machine learning repository. Malignant and benign two different types of breast cancer tumours are classified using deep neural network (DNN). Before classification two pre-processing steps are done for improving the accuracy. The correlation and one-hot encoding of the dataset was done for getting some relevant features that can be used as the input to the DNN. Around 94% of classification accuracy is achieved by using a six-layer DNN classifier. The result is also compared with some earlier works and it is found that the proposed classifier is providing better results as compared to others.
Considering the benefits of the human decision making, the efforts have been executed to implement it in machines. The chronic problem addressed in this implementation is the representation and manipulation of human knowledge which is full of uncertainties and imprecision due to its subjective nature. To deal with this problem a strong mathematical framework is investigated known as fuzzy logic. Initially the concept of fuzzy set has been developed by extending the Boolean crisp set logic. Further, type-2 fuzzy systems and interval type-2 fuzzy systems are investigated. This paper reviews the approaches and systems developed under the category of interval type-2 fuzzy systems along with the interpretability and accuracy issues in fuzzy systems.
This paper proposes a method for real-time visual tracking of moving hand in RGB videos without any segmentation process and background subtraction. We have used YCgCr converted version of YCbCr colour space for a more compact representation of the initial region of moving hand and then local feature SIFT to detect and track hand simultaneously. YCgCr has a high tendency for skin colour accretion and can effectively discriminate between the skin and non-skin colour regions. The approach demonstrates that using local features (SIFT) of only active region reduces the computation as well as make the method free from the challenges of freedom factor of hand and thus the methodology can detect the hand of any shape and size without being affected by background conditions. In general, researchers avoid using a normal camera for applications based on hand tracking, as RGB images are sensitive to illumination. Our work exhibits that the combination of YCgCr and two-stage feature matching through SIFT algorithm is successful in tracking non-rigid objects with less computation. The methodology is further evaluated with Kalman tracking in hand gesture recognition and is also compared with contemporary works.
In our previous study, FFT analysis has been used for spectral analysis of the EEG signal to investigate the effect of Om mantra meditation. It was proved that this mediation plays a role in providing relaxation. In the present study, we continued our work with wavelet analysis to firmly establish this benefit. Two-way repeated measures ANOVA was used on relative power obtained by FFT and DWT. The comparative results of both methods are presented. The same increasing and decreasing pattern of relative power are observed in each band with FFT and DWT. An increase in theta power in all regions of the brain has been observed with both the methods. Raised theta is a sign of deep relaxation. The study confirms that this 30 minutes of Om mediation offers relaxation; then it could be the way to de-stress if adopted as a daily routine.
Wireless sensor networks (WSN) are having high attention since there are huge developments and vast applications in the military and environmental applications. In this paper, the software implementation of energy efficient distributed receiver (EEDR) based protocol for WSN using MATLAB is discussed. The proposed mechanism uses information related to channel information, transmission range of sensor nodes and minimum hop. The main objectives of the proposed work include: 1) reduced delay; 2) reduced control packet overhead; 3) increased throughput; 4) high residual energy of all nodes in the network. The EEDR performance is compared with related research works such as traffic estimation-based receiver initiated MAC (TERI-MAC) and the receiver-initiated packet train (RIPT) protocol and also the performance variations due to fluctuations in the propagation conditions is evaluated. The result section discusses the attainment of reduced control overhead, reduced delay, high throughput, and high residual energy of all nodes in the network.
Unmanned aerial vehicle (UAV) is becoming the future of remote operation, monitoring and delivery system. For a UAV, remote operation requires a versatile control system that can maintain its position without disturbing the task at hand. This paper introduces a hexacopter which is able to pick and place an object by using a robotic arm, while it is flying. The arm is used to grip an object firmly and carry it to the desired destination. It maintains its position on air accurately while performing the pick and place operation. This UAV is able to withstand windflaw to maintain its position. This project can be used for rescuing, transportation of products, first aid supply etcetera.
The clustering based routing protocols enhance the performance and scalability of wireless sensor networks (WSNs). State-of-art routing methods perform clustering and cluster head (CH) based on the scheme of fixed time intervals. Repetitive task of the cluster formation and CH selection at each time interval, regardless of its necessity, leads to routing overhead and consumption of network energy. Along with clustering, efficient route formation is a challenge to WSN routing protocols. In this paper, an attempt is made to overcome these challenges based on dynamic hyper round policy and route optimisation strategy. The selection of CH and cluster formation is mainly performed using three key parameters such as density, distance from base station and residual energy. After the cluster formation, route formation is performed using ant colony optimisation (ACO). The simulation results reveal that the proposed routing protocol shows improved performance in terms of energy efficiency and quality of service.
In this paper an intelligent web search system is proposed based on recommendation of web page communities for personalised web search (PWS). Web page communities are set of web pages that provide the good quality resource on a given topic. The intelligent search system adapts the web search to the user's information need based on recommendation of web page communities. The groups of similar content clicked web pages in clusters are selected for generation of web page communities using maximum flow algorithm with hyperlink-induced topic search (HITS). The cluster of web page communities is selected for recommendations of relevant web pages to user during web search for effective web information retrieval. Experiment was conducted on collection of web query sessions in academics, entertainment and sports domain. The experimental results were compared with classic IR and PWS (HITS) based on same dataset and hence the results show the improvement in precision of search results using intelligent web search based on web page communities.
It is difficult to build model of accurate estimate due to the inherent uncertainty and similarity among different categories in development projects. In this paper, fault prediction is done using biogeography-based optimisation (BBO) with the goal of recognising the faults in software systems in more efficient way. Our methodology includes four steps as follows: 1) firstly pre-processing was employed to remove redundant data; 2) secondly, relevant features are extracted using principal component analysis; 3) thirdly, fault-prediction system based on the optimisation of regression parameter using biogeography-based optimisation (R-BBO) was proposed. The experiment employed over different fault related datasets using ten-fold cross validation. The results showed that proposed prediction system (R-BBO) yield an overall accuracy of 85.4% (predicted over five datasets) which is higher than the prediction using genetic algorithm (R-GA). The proposed R-BBO was effective in terms of classification accuracy, precision and recall.
