Search

Utilization of rechargeable battery based bicycles has been significantly increased in India. In this study, battery powered electric vehicles have been implemented in MATLAB 2013a Simulink and real-time hardware systems. In order to design and integrate a working model of electric cycle, one needs to know about the different components involved in a system, such as lithium-ion batteries, Brushless DC motor (BLDC), and controller systems. The detailed study about the component selection has been described in this study. The drive testing has been implemented in both Simulink and real time respectively. Within a single charging system, the proposed model of electric cycle has been derived up to 25 kilo-meter up to speed of 30 kilo-meter per second respectively. The characteristics of electric vehicles such as torque (N-m) versus time (s), speed (km/h) versus time (s) and distance (km) versus time (s) have been discussed in this study. Based on characteristics study, reliability of the electric vehicle model has been enhanced in electric bicycle system by physical model confirmation.

One of the major causes of blindness across individuals of various age groups and genders is Diabetic Retinopathy (DR). It is mainly caused by Diabetes. The symptoms of DR include seeing an increased number of floaters, blurry vision, vision that changes from blurry to clear sometimes, seeing dark areas in the field of vision, poor night vision and so on. A patient who has been diagnosed with diabetes for a long time is prone to DR. This paper proposes a robust, deep learning based mobile application to address the said issue. The rationale behind the development of the mobile application is to detect DR in far-flung areas, which do not have regular access to healthcare facilities. An input image captured by an ophthalmoscope when fed to the mobile application can give result within a few seconds. The model utilizes convolution neural networks build upon the VGG model. The proposed system quantifies the “confidence level” with a high accuracy of 96 %. Another feature of the proposed system is that it can work offline without any network connectivity, thus making it more useful in remote areas. The application further has a user friendly and intuitive interface.

Electric vehicle (E-vehicle) will be an alternate transportation vehicle in this world due to unavailability of fossil fuel. The CO2 emissions from fossil fuel based vehicle have been considerably reduced. In this study, E-vehicle has been modelled for both open loop and closed loop using MATLAB/Simulink. The rechargeable lithium-ion battery has been adopted for proposed system, and it has become prominent energy storage device especially for E-vehicle application. Speed sensor has been incorporated in closed loop system. Speedometer also added in both open and closed loop system. Performance of the E-vehicle has been analysed and compared by ratio of output to input motor power. Error deviation has been estimated. The simulation results of closed loop system have been revealed that better stability in dynamic state of input. The proposed closed loop system has been attained the better efficiency than open loop and, moreover fluctuation and harmonic level were within the tolerance level. Through closed loop system, E-vehicle has been attaining the smooth working state at minimum duration than open loop. The E-vehicle parameters such as vehicle speed, travelling distance, torque, efficiency and output power have been estimated for both open and closed loop system. With help of sensor, performance of the closed loop system has been improved.

Utilization of Solar Photo Voltaic Cell (SPVC) has significantly increased in residential, commercial, and industrial due to freely available. From the power-voltage (P–V) curve, fluctuation has been revealed over an hour because of varying irradiance, and temperature of sun rays. Maximum power point tracking (MPPT) has been essential to track power and maximize the output from SPVC constantly. In this study, a novel Improved Incremental Conductance (IIC) MPPT technique is proposed, and integrated with a boost converter to take out the maximum power from SPVC. The output power has been provided to a brushless DC motor (BLDC). Pulse Width Modulation (PWM) commutation system has been employed to control the BLDC motor through the 3-level bridge converter. The proposed study has been implemented in MATLAB/Simulink. The complete analysis has been examined at different irradiation conditions. Power consumption, loss, and efficiency have been estimated. Simulation results have been compared with conventional incremental conductance (IC). The proposed IIC MPPT has an improved 5% of tracking efficiency than conventional MPPT techniques. The results show that the effectiveness of the proposed IIC technique has attained a steady state in varying irradiation levels. In spite of the low irradiation level of 250 W/m2, the system remains effective.

WSNs are now widely used for information gathering and transmission using WSN. Due to its low cost and simple communication, this type of network is widely used in many applications. Although hierarchical routing protocols may handle a variety of applications, choosing a Cluster Head (CH) and balancing network overload are difficult problems. This recommended strategy provides LEACH Protocol based on Novel Trust Management with Cryptographic RSA algorithm (NTM-LEACH-RSA) to extend the lifetime of network and to consume less energy. Here the proposed methodology includes two aspects for improving Security in WSN. Using the suggested NTM-LEACH technique, cluster formation and cluster head election are carried out in the first phase. Here, the threshold function value, the distance and density between nearby nodes, and the trust value are used to elect the cluster head. Based on the energy domain and the distance domain, the threshold function value is estimated in this case. The RSA cryptography technique is employed in the second phase to protect data transmission and guarantee data integrity. By using simulation tools, the proposed NTM-LEACH-RSA methodology's performance analysis is estimated. In comparison to other algorithms currently in use, it also offers higher performance results.

Steganography is the showing of disguising a message inside another message or a certifiable article like message, picture, or video is covered inside another record, message, picture, or video. The restricted intel is concealed so to speak that it not unmistakable to the normal eyes. Huge learning progression, which has arisen as a key asset in different applications including picture steganography, has gotten extended thought lately. Where generally single strategy is utilized in encryption which can be decoded effectively so to beat this method in this project three different procedures are utilized, for example, Recurrent Neural Network-based (RNN), which can consequently produce excellent message covers based on a mystery bitstream that should be covered up. Convolutional Neural Network (CNN) are profound learning calculations that are exceptionally strong for the examination of pictures, which is utilized to encode the produced text covers into a little picture. We prepared our model with an enormous number of misleadingly produced tests and acquired a great gauge of the measurable language model and HIGAN, which develops the encoding network made from holding up blocks to mask the combination secret picture into another grouping picture of the more unpretentious size to yield a lower bending and higher visual quality steganographic picture. The continuous endeavor means to use steganography for an image with another image using spatial region methodology.

The aim of this paper is to create a decentralized transparent voting and analysis system that can be implemented with blockchain to provide an efficient and highly secure justifiable method of election systems in countries where traditional physical voting with gameable securities is used, increasing the chances of rigged elections. This system is designed to focus on a secure voting system, lower costs, faster wait times, no disparities due to various erroneous proxies, high scalability, and geographic independence. Overall, an effective election mechanism to strengthen the democratic process. The proposed dApp allows voters to vote from the comfort of their own homes, saving time and reducing the number of false votes registered.

Aneurysms in the brain are more prevalent in those who have a common coronary illness. According to many studies, patients with a common cardiac problem are more prone to develop brain aneurysms. The expression “coronary illness” alludes to conditions that square veins and can prompt a cardiovascular failure, chest agony, or stroke. Heart conditions that influence the muscles, valves, or musicality of the heart lead to coronary illness, and the coronary supply route sidesteps a medical procedure or coronary mediation is utilized to resolve these issues. In this review, a proficient profound neural organization-based methodology is proposed for the recognition of cardiovascular infection (i.e., distinguishing patients with 50% decrease in significant coronary vein measurement). The dataset was grouped utilizing the K Means bunching calculation, and afterward, heart infections were anticipated utilizing bunch-based profound learning. The proposed strategy is contrasted and various boundaries for order calculations like DNN, direct SVM, polynomial SVM, KNN, ELM, ELM bunch and to show the proficiency of the framework in an efficient manner.

The safe use of a mechanical ventilator should be followed by the fascination of intensivists with different respiratory function parameters. Naturally, this leads to the fact that these parameters should be monitored carefully and accurately. This work describes the monitoring of pressure and flow sensors in ventilation. Although end-tidal CO2 surveillance has become regular in the ICU, it is typically achieved by hold control modules incorporated into the monitoring a machine pumps the necessary amount of air through the lungs when the lungs need encouragement to take in air. Nowadays pressure sensors used in ventilators are of strain gauge type. Variable inductance type is used often in the machine. Ventilators are the pressure bag using a feedback loop from the patient's own breath, they regulate the air volume, pressure, and rate and flow in part. Oxygen ventilation systems use pressurized tanks of pure medical oxygen combined with filtered oxygen because patients with lung damage cannot obtain enough oxygen in the blood from ambient air. Moisturized ambient air to provide the patient with an oxygen-rich mixture of air. Up to 100% oxygen may be needed, depending on the severity of the trauma. The proposed work of this paper is the usage of PID controller, PID based Tyreus Luyben method to improve the pressure, flow of the ventilator. Gaussian Process Regression is used to train the samples and to minimize the error performance of the controller.