Search

Indian road conditions are very concerning as they are traffic prone in many locations. Further, the road surface conditions are not uniform in several places which may lead to a sudden impact on the vehicle dwellers on the highways. Furthermore, the driver may be the cause of accidents due to ignorance and improper focus on the road during driving. Statistical sources show that there are many reasons regarding the risk of road accidents to consider while calculating the reasons and the risk of road accidents. Various factors lead to road accidents and hence a strong methodology and the support of computer-aided support is required to solve such critical problems. The current work deals with the application of the deep learning approach to predict critical road accidents.

The smart wheelchair developed for people with inabilities dependent on the eye-tracking and by utilizing the voice assistant module. The smart wheelchair contains two modules, including a module for processing the image, a wheelchair-controlled voice associate module and constrained by appliances. The module for picture processing comprises a camera mounted on the wheelchair that can capture the picture and handling those images. The captured picture moved into a Raspberry Pie micro controller process using Open CV to get pupil movement in the 2D bearing. The movement of pupil is then moved remotely to the module for managing a wheelchair. The eyeball movement is also used as the controller to regulate the operations. Speech recognition technology is a technology that provides a way of interaction for human with the wheel chair. Hence, the problems faced by the people can be easily solved by using this technology for controlling the wheel chair. This can be implemented by using the smart phone or smart assistant enabled device as an interface between the human and the wheel chair.

Quotidian, the perspective of cyber attacks. New malware divergent are provoked almost daily, the number of attacks is up by 56%. Many see cyber-security alliterative in the form of machine learning and artificial intelligence ability crease into modern-day tools and platforms. This research elucidates a literature anatomization of cyber threads attacks. In this paper, we cover a wide array of cyber-attack types including malware, threats, spam. There by learning techniques are been imparted for attack detection and mitigation in network system.

Presently a days remarkable improvement of the web innovation and sensor innovation, the worldwide spatial information, alongside its huge volume and multi-scale highlights, clarifies higher prerequisites for information association. The spatial network has been generally utilized in many guide list. In any case, when spatial articles have multi-scale, the spatial matrix list with proportionate networks has been critized for its low-efficiencies. To tackle this issue, here proposed an intelligent list just as upset record dependent on GeoSOT subdivision lattices. By methods for this list, we can accomplish question task productively paying little heed to the sizes of spatial articles.

Test quality is an essential for accomplishing creation framework superiority. The idea of value is in various dimensions, the vast majority of the exertion in trying setting has been tested near estimating test adequacy. In the testing of the software for every project, user acceptance testing (UAT) is a era of program design progression in which the invention is tried in ”this present reality” by the goal cluster. The meetings of the primary clients are referred back to the plans who roll out positive developments earlier clearing the product industrially. In SDLC life cycle this UAT should be done statistically. Normally there are 3 main testing levels in UAT which are Unit testing, Integration testing and System testing. While we test the software at every level of testing the overall cost is reduced for the testing in addition to the agile model practices.

Applications that interact with external devices such as robotic arm or wheelchair by employing Brain Computer Interfaces (BCIs) have recently emerged as potential aid in rehabilitation of those affected by neurodegenerative disorders such as Amyotrophic lateral sclerosis (ALS) or Locked In Syndrome (LIS). Traditional monitoring of neural activity using uncomfortable electrode array helmets has been replaced with unobtrusive, robust and user friendly brain wave acquisition involving dry electrodes placed in the ear. In this study, haptic and auditory stimuli are used to elicit electroencephalographic (EEG) responses. These signals are in turn used to operate an iOS device using standard accessibility features in the operating system.

Brain-Computer Interface (BCI) systems can be used to perform daily life actions by utilizing brain activity to distinguish between different commands. For example, a robotic arm controlled with BCI. A robotic arm can allow patients diagnosed with Amyotrophic lateral sclerosis (ALS), Locked in syndrome (LIS), or any other neurodegenerative disease to grip objects and move them around the area. This system can potentially be used to perform a variety of useful tasks such as opening doors, picking up objects and to restore a level of everyday function. The presented system utilizes Electroencephalography (EEG) signals to create a BCI which can control a robotic arm. Specifically, Steady State Visual Evoked Potential (SSVEP) based signals are captured from a user's brain to serve as the controller for three servo motors. The user is presented with three sets of LEDs with different frequencies to distinguish between each of the three degrees of freedom (DOF). The frequencies and servos are paired in the following manner: 7 Hz => servo 1, 11 Hz => servo 2, and 15 Hz => servo 3. Servo 1 changes the orientation of the arm, servo 2 changes the angle of the claw, and servo 3 controls the opening and gripping of the claw. The first experiment is intended for the subjects to get familiar with the system by attempting to activate each of the three servos ten times. The subjects were able to complete this experiment with an average accuracy of 85.56%. The final experiment allowed the subjects to perform a more essential task, which is swapping the items at two locations. On average, the subjects were able to complete the swap experiment in 4:31 minutes.

Obstructive Sleep Apnea (OSA) is a sleep disorder that affects mainly the adult and elderly population. In OSA the person has one or more pause in breathing and shallow breaths while sleeping. The person suffering from OSA has breathing ceased more than 5 seconds and occurs more than three times per sleep hour. This causes limited supply of oxygen to the body causing many deadly diseases. The limitations of current diagnosis leads to high percentage of patients who remains undiagnosed. Healthcare professionals are constantly looking for ways to improve the ease of diagnosis and comfort for this kind of patients. Relating to this scenario, the proposal records the various parameters of the person via portable devices. The ECG waveform of the patient is taken by three-lead system. The respiration is monitored using respiratory sensor and the position is also measured by accelerometer sensor. These parameters are then stimulated in MATLAB by microprocessor. Thus by comparing the stimulated output with normal person the OSA is detected.

Millions of tons of food are processed and packaged by individuals and machines. As such, the possibility exists that food manufacturers and the suppliers will not catch every object that does not belong in the product. When a person consumes a food that has a foreign object in it, he or she may suffer a physical or emotional injury. This paper describes a working prototype that non-destructively identifies the presence of foreign object in food products. The infrared sensor module consists of a source and detector which will detect the presence of foreign object and thereby sends the signal to the PIC16F877A microcontroller which thereby indicates the defective edible and non-defective and edible food products using LED indications.

Growing power demand and depletion of conventional energy resources are the predominant reasons for distributed generators (DG) penetration into micro grid. The conventional protection schemes are not suitable for micro grid due to bidirectional power flow. This paper proposes a novel adaptive over current (OC) protection scheme for micro grid. This scheme employs dual simplex algorithm to identify the time multiplier setting (TMS) and time of operation (top) of relays for any topology of micro grid, which are saved in a look up table (LUT) in central protection system (CPS). In the event of fault identification, the records in LUT facilitate in providing appropriate relay coordination in the reconfigured micro grid with minimum number of feeder disconnection

An intelligent micro grid controller system with over current protection capability in both the grid-connected and the islanded modes of operation is proposed. To achieve the above strategy a model of small portion of distribution network as if it were a micro grid will be developed and considered. The processor based relays that provide over current protection functions in addition to performing control, measurement, and communication functions will be suitably employed.

Protection system includes a series of devices whose main purpose is to protect people and primary electric power equipment from the effects of faults. Fault currents cause damage to equipment and are also hazardous to personnel. Thus, there should be a primary and a backup system with proper time grading between systems, i.e. Tripping time should be maximum for the point farthest from the fault location. Over current (OC) relays are used as backup protection against these faults. The coordination time interval must be maintained among relays during faults. Various algorithms are used to optimize the time of operation of these OC relays. This paper implements Dual Simplex and Genetic Algorithms (GA) on a radial network and identifies the time multiplier setting (TMS) of the relay. This facilitates in achieving suitable OC relay coordination of the network.

This paper presents Big-M method and Dual Simplex method for optimum time coordination of over current relays in a distribution network. These methods are used to find the optimized values of time multiplier settings (TMS) of relays using linear programming problem (LPP). Objective function contains artificial variables in Big-M method. Dual simplex gives the optimum solution without introducing any artificial variables. Over current (OC) relay plays a major role in power distribution system. It protects electrical power systems against excessive current which are caused by faults like short circuits, ground faults, etc. The fault is cleared within a least possible time. Big-M and Dual simplex technique are presented in this paper for optimum time coordination of OC relays in a radial fed distribution system.

CT image is sensitive to bones whereas PET image indicates the brain function with low spatial resolution. This paper focuses on fusion methods for eight sets of PET and CT images based on the Discrete Wavelet Transform (DWT), the most popular tool for image processing. For fusing low frequency coefficients maximum and average rule and for high frequency coefficients contrast, gradient and maximum rules are applied for fusion. On comparing the different fusion results, it could be observed that the best method for low frequency coefficients is average fusion rule and for high frequency coefficients it is gradient fusion rule. From the observation of different fusion rules, entropy and Peak Signal to Noise Ratio values are high whereas Root Mean Square Error and Standard Deviation values get decreased for average-gradient method.

In the Digitalized world, the problem exists in transmitting and concealing highly secured and important information. This results in developing better technique/algorithm for the secure and safe transmission of information with data hiding. Here comes our study in Audio Steganography. With the existing scenario we say that Differential Pulse Code Modulation (DPCM) is better than Pulse Code Modulation (PCM). If Steganography is implemented in the audio signal, the above result is contrary. We focus on the audio steganography for analyzing the behavior for different modulation schemes. The result is controversial (i.e.) PCM is better option for transmitting an encoded audio signal with text information. This result has not been proved yet in terms of coding. The coding is developed in MATLAB. In the algorithm, using the scattering method, the encoded text is embedded into digitized audio signal. Here comes the case study of each method of modulation, ultimately proving that PCM is better method compared to Differential PCM (DPCM).

Thermal co-simulation of coaxial output couplers (including the coaxial RF window and the RF connector) of a medium power CW helix TWT has been carried out using CST Microwave Studio and thermal solver of the CST Studio Suite. The RF losses as obtained from the frequency domain analysis are used in the co-simulation and the temperature profile of the window and the connector has been analyzed using suitable thermal boundaries and actual material properties. The co-simulation could be used for optimizing the design of a coupler with a considered decision on the thermal management.