Several problems faced by the visually impaired people were addressed over the past 3 decades. It includes transportation, text to voice conversion, alarm, and usage of the internet. There exist still several areas, where support and help for the visually impaired people are dependent on others. Among them is accessing the daily essential needs is of prime concern. Design and implementation of the visual system are proposed in this paper to help and support visually impaired people using Artificial Neural Networks (ANNs). Here deep learning technique is used for the identification of the objects and the distance of the object is measured using an ultrasonic sensor. The proposed methodology suits better for the conversion of the visual scenarios into voice messages along with the distinct location of the objects. The accuracy of the proposed visual model depends on the data sets used in the ANN algorithm. As the depth of the training data set increases, the performance of the prototype also increases with reduced processing delay in identifying the objects. OpenCV platform is used along with the python programming language to navigate through the surrounding.

In recent years there has been increase in development of human pursuing robots which can be used as daily life support robots. The primary goal is to design and fabricate a robot that not only tracks the target but also moves according to it. For implementing this project, a barcode was used as target that robot needs to follow. OpenCV provides an interface to capture live stream with camera. In order to detect the barcode, a program is written in python which is interfaced with OpenCV library. After capturing a video from the camera, it converts it into gray scale video and display it frame by-frame. After detecting the barcode from the video frame, black and white lines of an image is detected and the centroid will be calculated. Based on the position of the centroid, commands are given to the robot to move accordingly. Ultrasonic sensor is used to avoid collision between the robot and obstacles. As a result, the robot pursues the target and it can be used as an assisting system for handicapped people for carrying luggage or can be used in airports, railway stations as a luggage carrier.

Agriculture is the main livelihood source for 58% of the population of India. The Indian food industry is on the verge of massive growth, which each year increases its contribution to world trade in food because of its immense potential for added value. Particularly, in the food-processing industry which contribute to 16% of total GDP and 10% of exports. In this paper monitor agricultural land and displaying the parameters that has been sensed through Wireless Sensor Network (WSN). If anyone wants to include technology in agriculture, he should be aware of agriculture process. In this proposed work, we monitor the agriculture field at a distance by using XBee technology. We have connected various sensors to monitor field and depending on sensor values necessary actions will be taken. Main advantage of proposed work is consumption of power will be very less to communicate over other wireless communication technologies.

A novel method of Multiple lines of e-courts for various sports application controlled by Light Emitting Diode strips was proposed and experimentally analysed which accurately displays the court lines for the selected game. Here, an aurdino based microcontroller is used which supervises the work of the block chain and RFID tag which serves as an electronic key for accessing the sport court. The distinct court rule lines are shown for various sports like basketball, badminton, volleyball and kabaddi are set up and stored in the Application through which one can select particular court of interest. In this paper, we propose an efficient system design by providing security and quick access to multiple games at the same location. The designed module projects a series of lines in one touch onto the surface and also further transforms a basketball court to a volleyball court in seconds hence it utilize the space efficiently with multi-purpose single sporting space. This novel idea replaces the traditional court marking complexity for various games under single roof. The usage of various sensors like pressure sensor, IR sensors were utilized for monitoring the score points which offers added assistance to referees. Hence the idea is novel and the design concept is demonstrated and verified. This electronic court rule line system not only helps sportsmen and referees, but also connects them with audiences.

Quality of water may be an advanced exploration and production fundamental concept. The water quality is based on so many factors. Water infection is surely one of the essential crucial fears for the green globalization. With a view to deliver safe and secure water, real-time quality has to be monitored. The current system comprises a sensor network which is utilized to gauge both physical and synthetic boundaries of the water that are temperature, PH, turbidity, water glide sensor can be measured. These measured values from the sensors are processed via the Arduino UNO controller. Finally, the sensor values may be regarded using Wi-Fi module. This paper presents a cost efficient system for real time quality monitoring using Internet of Things (IoT).

In real world applications, Speech recognition system have grown due its significance in various online and offline applications such as security, robotic application, speech translator etc. These systems are widely used now-a-days where acquisition of signal is performed using various instruments which causes noise, source mixing and other impurities which affects the performance of speech recognition system. In this work, issue of source mixing in original speech signal is addressed which causes performance degradation. In order to overcome this we propose a new approach which utilizes non-negative matrix factorization modelling. This method utilizes scattering transform by applying wavelet filter bank and pyramid scattering to estimate the source and minimization of unwanted signals. After estimation the signals or sources, source separation algorithm is implemented using optimization process based on the training and testing method. Proposed approach is compared with other existing method by computing performance measurement matrices which shows the better performance

Voice is most prominent and primary mode of communication among of human being. Voice has potential of being unique and important mode of interaction with computer. This paper aims to identify a person through voice and card for bank locker security. A Voice recognition system is designed to identify an authorized person voice and Resistive card for unique id. Proposed work aims at providing two levels of security to user with respect to card and voice. For the result of testing the system, it successfully recognizes the specific user's voice and rejects other user voice. Using this method the accuracy of whole system is successfully maintained in recognizing the user's voice. And for further security purpose GSM sends a message to the user as authorized person or unauthorized person and wireless camera keep on monitoring as live video stream. After accessing voice and card of authorized person bank locker will be opened. If in case any of voice or card is not recognized, buzzer alerts an alarm.

Doubly Fed Induction Generator (DFIG) is the most popular variable speed wind energy conversion system (WECS). In this proposed work the performance of wind energy system based on Doubly-Fed Induction Generator (DFIG) is analyzed in grid tied mode by studying the different techniques such as grid integration, droop phenomenon, and power control. The results are obtained using the MATLAB/SIMULINK environment. It has several benefits such as better efficiency, rating of the converters is less because the power semiconductor units are connected with the rotor circuit; cost efficient, loss of those is minimum, easy power factor correction, possibility of four quadrant active and better utilization factor.

As energy is limited resource in Wireless Sensor Networks, it is required to utilize the resource carefully to maximize the life time of the network. The dramatic increase in data traffic leads to consume more energy in WSNs. Hence, to achieve an excellent Quality of Service (QoS), it is necessary to reduce the energy consumption and optimize the resource utilization efficiently to improve network performance. To attain this, WSNs often adapt Machine Learning techniques which provide practical solutions for many issues, maximize resource utilization, and prolong lifespan of the network. Cognition technique is adapted for efficient utilization of the spectrum. In this research article,we propose an algorithm that enhance end-to-end throughput in Cognitive Wireless Sensor Networks by exploiting available resources using machine learning techniques. With the increase in the throughput, the proposed algorithm proved there 62% improvement in the energy efficiency.