VOLUME 6, ISSUE 8, AUGUST 2018

Abstract: Manual identification, classification and taxonomy of a definite and specific species or plant disease are generally obstructed by several difficulties such as time consumption, the limited number of expert specialists and the increase in the number of the defined characteristics of each species. The steady progress of the computational technology over the last few years concerning the automated species recognition including plant structures is be easier particularly in the presence of huge databases of information and the enhancement of classification and analyzing image technology. Several investigators are currently working in agriculture field mainly those concerned with plant identification or of plant disease recognition through image processing, extraction of identical features and classifying them into exact classes. In this review, the integration of computer science with agriculture has been discussed to detect, quantify, predict, early identify and classify plant diseases as well as forecasting agricultural crops using different machine learning techniques. Weather forecasting, smart irrigation system, plant leaf identification, etc will also discussed. The aim of this paper is to provide the investigators particularly biologists with computational recognition techniques as well as the possibility of using image informative morphological features of a species or a group of related species in recognition of many biological organisms including plants and microorganisms.

Keywords: Artificial Intelligence, Agriculture, Image Processing, Recognition

Abstract: This thesis describes the detailed study of Multi-level Inverters for 5-level and 7-level Multi-level inverters and an improvement is seen in 7-level harmonic distortion by a significant amount. Numerous industrial applications have begun to require higher power apparatus in recent years. Some medium voltage motor drives and utility applications require medium voltage and megawatt power level. For a medium voltage grid, it is troublesome to connect only one power semiconductor switch directly. As a result, a multilevel power converter structure has been introduced as an alternative in high power and medium voltage situations. The THD in 7 –level is about 28%.

Keywords: MLI, Cascaded, THD, 5-level, 7-level

Abstract: Mobile is an electronic device which almost every person in the society possesses. The evolution of mobile phones has not only changed the way we communicate but now it also includes a wide range of sophisticated sensors such as Gyroscopes, Accelerometers, Proximity sensors etc. The smartphone acts as a gateway and provides a lot of features such as Bluetooth and WiFi. Such smartphones can help make the world around us smarter. One such example is discussed in this paper for a mobile gesture controlled car. The smartphone can act as remotes to the car and is capable of controlling the car by means of a gyroscope present inside the phones. This paper demonstrates the simple use of a mobile device to control a toy car using Bluetooth and an app for controlling the motion of the car. The mode of communication is Bluetooth communication.

Keywords: Bluetooth, Gesture control, Mobile communication

Abstract: The induction motor operate satisfactory on balanced normal conditions. It is low operating and maintenance cost and energy efficient electro mechanical drive. It is used in all industrial processes as there is no alternative to induction motor in industry. During operation, various stresses are developed in induction motor which may cause failure of motor. So, there is wastage of time and revenue loss. There is variation in supply conditions in distribution system. It is essential to diagnose the performance of motor on unbalanced supply conditions and stator inter turn short circuit fault. In this paper induction motor model is derived for symmetrical and asymmetrical conditions to diagnose the performance at unbalanced supply voltage and stator inter turn short circuit fault.

Keywords: Induction motor, inter-turn faults, diagnosis, balanced and unbalanced conditions

Abstract: This paper presents a Harmonic elimination using series active shunt passive filter based hybrid filter. Filter operation is based on PLL logic which comprised with PI controller and mathematical operation on voltage signals. The proposed approach is comprised of PLL based series active filter with shunt passive filter. Here passive filter design is done based particular frequency calculations. The series active filter switching gives better steady state operating conditions. The hybrid filter system is used for many simulation of different loads which reveals that it effectively compensate reactive power as well voltage and current harmonics.

Keyword : Hybrid Filter, Active filter , PLL

Abstract: This paper comparison between control techniques for Harmonic elimination using hybrid filter. In this, filter operation is based on PQ theory with PI control based active filter logic and PLL logic based hybrid filter is done. The proposed approach is comprised of PLL based series active filter with shunt passive filter. Here passive filter design is done based particular frequency calculations. The . The hybrid filter system is used for many simulation of different loads which reveals that it effectively compensate reactive power as well voltage and current harmonics.

Keyword : Hybrid Filter, Active filter , PLL, PQ theory with PI logic

Abstract: Main objective of clustering an image is dominant colors extraction from the images. By extracting the information from images such as texture, color, shape and structure, the image segmentation can be very important to simplify. Because of the information extraction in any images, the segmentation has been used in many fields such as Enhancing the image, compression, retrieval systems i.e., search engines, object detection, and medical image processing. From the past decades, there are so many approaches developed for the image segmentation. Among those, Fuzzy c-means (FCM) is a well-known method and very popular clustering scheme, which will segment the image into several parts based on the membership function. After FCM, the K-means algorithm has been proposed to reduce the computational complexity of FCM. Because of its ability to cluster huge data points very quickly, K-means has been widely used in many applications. Later years the Hierarchical clustering is also widely applied for image segmentation. Then after, Gaussian Mixture Model has been used with its variant Expectation Maximization for segmenting the images.

Keywords: FCM (Fuzzy c-mean), Fuzzy K Means, Segmentation, MRI

Abstract: This article describes an effective method for performing drowsiness testing through three well-defined stages. These three stages are using Viola Jones for facial characterization, eye tracking and yawn detection. Once the face is detected, the system illumination is left unchanged by separately segmenting the skin portion and considering only the color components to reject most of the non-face image background based on the skin color. Eye tracking and yawn detection are accomplished by correlation coefficient template matching. Feature vectors from each of the above stages are connected, and a binary linear support vector machine classifier is used to classify successive frames into fatigue and non-fatigue states, and alerts the former if it is above a threshold time. Extensive real-time experiments have proven that the proposed method is very effective in finding sleepiness and warning

Keywords: Drowsiness, Alertness, FFT, ANN, SVM , Face Detection; Eye's State; Drowsiness

Abstract: Increased use of nonlinear as well as sensitive loads and devices in the power system, the power quality of the system is becoming more and more crucial. The quality of electric power and disturbances occurred in power signal has become a major issue among the electric power suppliers and customers. The PQ detection and classification are valuable tasks for protection of power system network. Most of the disturbances are non-stationary and transitory in nature hence it requires advanced tools and techniques for the analysis of PQ disturbances. A number of PQ events are generated and decomposed using wavelet decomposition algorithm of wavelet transform for accurate detection of disturbances. This dissertation aims at classification of the power quality events. The objective of the study is to classify the various power quality events such as voltage sag, voltage swell, interruptions etc. In this work a new technique is used for categorizing PQ disturbances using wavelet transform and neural network. These process having gone through three main components. First, to accomplish this task a sample power system will be modeled with suitable simulation software (PSCAD) and the power quality events will be simulated. Second, these simulated events will then be processed with suitable signal processing technique (Wavelet Transform). Third, the features of each of the events will then be extracted for the application of Neural Network. Using an artificial neural network the power quality events will be classified with increased accuracy of classification. The power signal is decomposed by using modified wavelet transform and the classification is carried by using ANN.

Keywords: Power quality, Voltage sag, Voltage swell, Interruption, PSCAD simulation, ANN

Abstract: Dedicated Short Range Communication (DSRC) band is incapable to remove increasing demand on wireless traffic in vehicular network. The TV white Space band by FCC for cognitive access provides additional bandwidth to solve the DCRS spectrum problem. However, create a challenging environment for portable (e.g., vehicular) and fixed (e.g., IEEE 802.22) network which is FCC required portable device to use significantly lower transmitting power than fixed device. In this paper, first formulate the Mixed-Integer Non Linear Programming (MINLP) program, to which three algorithms are refined. The first algorithm converts the MINLP to a convex problem and gives the near-optimal solution to the initial MINLP. The other two algorithms, first convert the MINLP into an Integer Programming (IP) problem. Then, solve the linear program relaxation of the IP and obtain fractional solution. Consequently, two rounding algorithms are developed to round the fractional solution based on the column-sparse packing and dependent rounding techniques. In conclusion, compare the performance of the proposed algorithms with the optimal MINLP solver.

Keywords: Channel Allocation, Cognitive Vehicular Network, Linear Programming, Submodular Set Function