Skip to main content

Über dieses Buch

This book is a collection of papers from international experts presented at the International Conference on NextGen Electronic Technologies (ICNETS2). ICNETS2 encompassed six symposia covering all aspects of electronics and communications engineering, including relevant nano/micro materials and devices. Highlighting recent research in intelligent embedded systems, the book is a valuable resource for professionals and students working in the core areas of electronics and their applications, especially in signal processing, embedded systems, and networking. The contents of this volume will be of interest to researchers and professionals alike.



Design and Implementation of Dialysate Temperature Control System for Hemodialysis: A Pilot Study

In hemodialysis, the control of body temperature by altering the dialysate temperature would reduce the intradialytic complications. Several studies show that the constant dialysate temperature affects the patient’s quality of life due to their different temperature threshold. Thus, these factors serve as a motivation factor to design an individualized dialysate temperature control for hemodialysis patients, which can actively control the body temperature even in the case of any external disturbances. In this paper, a novel dialysate proportioning model has been proposed. Then, initial implementation of proposed model was designed with fuzzy logic control and implemented on a low-cost microcontroller—Raspberry Pi 3. A Simulink model was also designed by incorporating fuzzy logic control to implement in real time. The pumps’ flow rates are varied using Pulse Width Modulation (PWM) according to the controller signal, while the temperature sensors are placed to acquire actual temperature in this model. Subsequently, it has been tested and verified by comparing the simulation and experimental results. Furthermore, the dialysate temperature trend was studied for various input conditions to analyze its controller behavior in real-time implementation. The results showed the potential to develop robust control by optimizing the fuzzy rules and membership functions. The system response time is found to be minimal (less than 300 ms), and the performance error is acceptable (less than 0.55%). Further work is ongoing to implement the dialysate temperature controller incorporating in vitro studies.

Mohamed Haroon Abdul Jabbar, S. Anandan Shanmugam, Poi Sim Khiew

Raspberry Pi in Computer Science and Engineering Education

Sustainable Environmental Development is one of the hot topics nowadays. Industries were advised to reduce and control pollution by using pollution control equipment. Computers are also contributing some amount in the pollution and power consumption. On the other hand, miniaturization, less power consumption, and environment-friendly devices are invented by the researchers every day. One such device is Raspberry Pi. Size of the Raspberry Pi is not bigger than a credit card with high computing capacity and low power consumption. Pi can run Linux as well as Windows 10 in its higher versions. This paper aims to suggest the Pi can be used for practicing most of the laboratory courses in the computer science engineering curriculum. Most laboratory courses are practiced in C, C++, and Java languages. Apart from above-mentioned languages, some laboratory courses make use of front end and back end tools. Above-mentioned languages can be executed in Raspberry Pi. Following points are analyzed between normal computer and Pi, execution time, power consumption, and environmental effect. In all the comparison, Pi gives much higher advantage over existing system.

S. Alex David, S. Ravikumar, A. Rizwana Parveen

Advanced Tele-surgery with IoT Approach

Availability of special doctors during emergency surgeries is decreasing. It is very vital to assist doctors in their surgeries of surgical tools. As a solution to this problem, tele-surgery concept prevails and many simulators have been developed for education, planning rehearsal, and so on. Some of the defects in the existing systems are interaction between the surgeon and the remote surgical room, display of the image, camera motion, data transfer quality, and accuracy in the motion capturing. These issues are overcome in this approach with an enhanced vision-oriented VR goggle and hand motion acquisition system (a control system) accessed by the surgeon. Data transfer is done using IoT which makes this system stand superior to the other approaches of tele-surgery.

N. Shabana, G. Velmathi

Xilinx System Generator-Based FPGA Control of Power Flow for DC/DC Converter

In recent years, Xilinx system generator platform (XSG) is becoming more popular in real-time simulations. This is especially true for applications involving FPGA as controllers such as power electronic converter control. Since XSG is integrated with MATLAB/Simulink, it eliminates the need of special skills in VHDL or HDL and enables the user to design control techniques with the help of Xilinx block sets and to test these control designs simultaneously. This paper aims to design the power flow control method in dual active bridge (DAB) bidirectional DC/DC converter using XSG for real-time simulation and to verify the control strategy. The result obtained through XSG-based hardware-in-the-loop (HIL) simulation is helpful to know the controller performance a priori in real-time implementation.

Anurag Sharma, Rajesh Gupta, Muskan Gupta

An Improved Algorithm for the Estimation of Multibody Motion

The problem of estimating ego motion and eoru motions through a vehicle mounted with a camera is related in this paper. Localization of multiple moving objects and estimating their motion are crucial for autonomous vehicles, but it is not that much successful in estimating the motion of the moving vehicles and objects. Ego motion can be calculated only by conventional localization and mapping techniques. The framework for estimation of multiple motions in addition to the camera ego motion is presented. The video is processed through MATLAB for pre-processing. The video is then segmented into frames, and then the framework is done to estimate the multibody motion through different algorithms. The algorithms like block matching algorithms, corner detection, and background subtraction algorithm are used to estimate the multibody motions of the moving objects. From this, we can detect and estimate the motion and speed of the object in the frame. Then, it is processed in hardware (raspberry pi3) using the same algorithms, so that we can effectively use it in any autonomous cars.

K. Raghavan, R. Prithiviraj

An IoT-Based Smart Shopping Cart Using the Contemporary Barcode Scanner

An efficacious prototyping of an intelligent Internet of Things (IoT)-based smart cart that primarily enhances the shopping experience of the customers as well as owners. The assembly of the smart cart consists of a contemporary barcode scanner from the present-day shopping scenario, feedback systems providing product weight and product imaging to avoid discrepancies, a cloud-based database and an embedded hardware to connect the above. The mechanism facilitates the customer to add and remove products throughout the shopping, updating the bill instantaneously, and further reflecting changes in the inventory. The framework incorporates a Parse cloud-based inventory to ease the managerial task at the owner end. Further focus has been also given on the proper placement of all the components on a cart for the efficient working of the shop, keeping user’s ease of usage in mind.

V. N. Prithvish, Shraddha Agrawal, John Sahaya Rani Alex

Voting System for India

While many steps have been taken by the government, the voting percentage is not as per the expectations. In this paper, a new voting system is proposed for India. The proposed system is the combination of the currently working system as well the use of AADHAAR database. The voter’s data, i.e., the voter identity number mentioned on the election card provided by Election Commission of India and AADHAAR details are saved. This stored data are used at the time of voting, and the status of the voter will be updated.

Shrikant Subhash Warghade, B. Karthikeyan

Human–Robot Interaction Using Three-Dimensional Gestures

In the future of manufacturing industries, it is seen that the robots will replace most of the human workers to achieve faster production. All the industrial areas use automated robotic arms which do certain tasks assigned to them with amazing speeds and pinpoint accuracy. But areas such as medicine, space research, and military robotics require robot arms to be manually controlled to operate with objects that cannot be dealt with human hands. In order to achieve speed and accuracy like automated robots, a new approach, called the leap motion technology, a latest invention in human–computer interaction area is proposed. Hence, three-dimensional gestures are used and gesture recognition method using 3D pointing is schemed for interaction of human and robot using leap motion controller in real time. It facilitates the human pointing 3D gestures for the robot to understand in real time. The arm of robot captures the gestures shown by human partner to interact with the user’s gestures and perform the task immediately. The position of the human’s hand relative to the head is adjusted so that the speed of the robot is controlled. The status of the robot movement can be viewed in LCD. This proposal designs to advance a valuable 3D pointing gesture recognition system in real time for human–robot interaction.

K. Ponmani, S. Sridharan

Integration of the Smart Phone and IOT for Smart Public Toilet Hygiene Monitoring System

As the number of inhabitants in the nation is expanding day by day, it gets to be distinctly hard to deal with the cleanliness of the urban areas. One vital reason for this issue is some time for individuals it is hard to find the public toilet and even if one finds it then there may be an issue of cleanliness with the one found. With help of the recent technology known as IOT, we are proposing a solution for this issue. Sensors will be conveyed in different public toilets which will accumulate the cleanliness parameters and this acquired information will be uploaded to the database. This information can likewise be utilized by maintenance office for further activities. Utilizing this information, one can without much of a stretch get the exact location and the cleanliness level of the toilet utilizing our android application on his smart cell/tablets.

Prashant Namekar, B. Karthikeyan

Hyperelliptic Curve Cryptography-Based Lightweight Privacy-Aware Secure Authentication Scheme for Vehicular Ad Hoc Network

Authentication is one the important parameters in designing security for vehicular ad hoc network (VANET). Authentication protocols based on public key infrastructure (PKI), elliptical curve digital signature algorithm (ECDSA) suffer from overhead problem at the road side unit (RSU) and extracting of certificates from the trusted authority. Traditional identity-based signature scheme is used to provide the privacy and authenticate the vehicle-to-vehicle communication and vehicle-to-road side unit of the VANET. ID-based signature scheme employs elliptic curve cryptosystem form authentication process and also provides batch message verification mechanism. ECC-based traditional scheme requires 160-bit key size to encrypt the message transferred between RSU and vehicle. It requires large memory space as well as consumes more energy and leads to high communication and computational overhead. In order to overcome the above-mentioned limitation, a new lightweight privacy-aware secure authentication scheme is proposed for VANET. The proposed authentication scheme employs the advantage of hyperelliptic curve cryptosystem to sign the message transferred between RSU and vehicle. Since HECC requires lesser 80-bit key size than the traditional signature scheme, it provides greater level of security with less communication and computational overhead. It also traces the real identity of the vehicle using pseudo-identities which eliminates the process of extracting the certificates from the trusted authority. Finally, compare the performance analysis of both traditional and proposed ID-based signature scheme using the different simulation parameters.

Kirti A. Yadav, P. Vijayakumar

A Dynamic Approach of Energy Saving Control Strategy in Smart Homes

This paper focusses on the control analysis with energy saving strategy based on loss aversion analysis in energy management. In smart homes, need of smart meter roles down as an important element. Home area management is considered vital when considering the proper strategy inside the smart meters. Appliances strategy with smart meters at homes is considered in this work using Markovian stochastic Petri nets. The control approaches in the smart meters are analyzed using meta-heuristic algorithm for energy scheduling for appliances. This approach helps in analyzing the control analysis in the smart meters at the operational level building infrastructure. Further, the fulfillment of the consumers at smart homes using this dynamic approach is done. The loss aversion analysis is also considered at energy-level approach for the run time evolution in smart meters.

S. Sofana Reka, S. K. Pranesh

A Novel Approach for Night-Time Vehicle Detection in Real-Time Scenario

Intelligent transportation systems and computer vision have intensively been studied in the past decades since the need for intelligent transportation system increases as the growth of vehicles is increasing rapidly than ever before. Traffic surveillance is the important feature in intelligent transportation system which involves in detection and counting of vehicles. In this paper, a night-time vehicle detection system is proposed for effective detection and counting of the vehicles during night-time with the help of the headlights and also classification of the vehicles is carried out in this system. This system involves in processing the night-time traffic video in MATLAB, where image segmentation, background subtraction, blob analysis are done to detect and pair the vehicle headlights for the counting of vehicles. Different templates of headlights are created, and comparison is carried out with the headlight of the vehicles present in the traffic video to classify the types of vehicles present. The above algorithm for night-time detection and counting of vehicles is also implemented in system on chipboards, so that it can be effectively used for intelligent transportation system purposes.

M. Aswin, G. Suganthi Brindha

Local Visualization for Troubleshooting the RF Mesh Network in a Wireless Metering System

Objectives: To design a visualization of a network containing wireless meters installed with RF modules which uses RPL protocol for routing. Methods/Statistical analysis: Meters are linked wirelessly for obtaining the packets containing its details and other parameters, by using a Constrained Application Protocol (CoAP). Thus, details collected from each meter are used for the construction of the visualization, by dynamically assigning the position of each node. Findings: RPL, routing protocol, is used for the construction of the network. The advantage of its self-healing nature makes the whole system stable by removing the irresponsive meters, when detected, from the network and reconstructing it from the starting. Application/Improvements: Maintenance of such a network which switches its neighbors at different instances may be complicated. In such cases, these visualization methods can be included. In future, the firmware update options for each meter can be implemented along with visualization.

Parvathi L. Prabhakar, Kiran Thomas, S. Sreekumar, S. Muthulakshmi

Train Collision Avoidance System for Automatic Train Protection Using Internet of Things

Objective: The train collision avoidance system (TCAS) is a synergic approach for intervention of train in danger zone using Internet of things. Methods: The proposed system surveillance the signal condition and observe the disobedience of the track signal. A sensor is placed beneath the track, which senses the pressure, temperature, altitude of the track. The presence of train is observed by heavy pressure, change in temperature, and altitude on the track. Eventually, the system notifies the intervention of train being in danger zone using Internet of things by ThingSpeak IoT platform. An alarm is given to the train side that blow through Beaglebone black using Wi-fi module and if locomotive pilot does not respond, then the train stops by controlling braking system. Findings: Track signal plays a paramount role in cognizance of train’s direction. The disobedience of signal results in collision, derailment, and conflict. It is mainly occurred due to human error or rigid climate conditions like fog, rain and affects thousands of lives. TCAS-IoT prevails the problem of overshooting the track signal and acknowledging the locomotive pilot about intervention of train in danger zone. Conclusion/Improvement: The proposed TCAS-IoT can avoid train collision and capable of taking action before collision or derailment of trains. It is a unique way to synthesize the intervention of train in danger zone and can save lot of precious lives.

Mohit Savner, G. Gugapriya

Automatic Driver and Vehicle Safety Monitoring System

Background/Objectives: Accident is increasing rapidly and is mostly due to drunk driving and drowsiness of drivers. A novel approach is presented in this paper to monitor the physical condition of driver and alert system to reduce human errors by means of an embedded system. Methods: To find a particular person’s blood alcohol concentration in their bloodstream, breathalyzer which is also known as breath alcohol detector is used. IR sensor and biomedical sensors are used to detect the drowsiness by monitoring eyes pattern, EMG and EOG signals. These were the basic inspiration for creating the embedded system introduced here. The proposed system includes microcontrollers, alcohol sensor, biomedical sensor, IR sensor, camera modules, GPS, Wi-fi adapter, ZigBee module, solenoid valve and ignition switch circuitry. Findings: The proposed vehicle safety monitoring system will detect blood alcohol concentration (BAC) percentage from the particular person’s breath samples. The EOG, EMG and IR sensors are used to monitor driver condition. The warning alarm and ignition switch circuitry are enabled and disabled based on the input values of the monitoring system. Thus, the condition of the driver is continuously monitored and calibrated on a scale. When it exceeds a particular limit, the alarm unit is enabled. GPS and camera module are used to trace the vehicle and driver. The monitored values are serially transferred to the master controller and further upload the data to cloud space by means of Internet which can be accessed or streamed. This data is used to track the vehicle and detect who is driving the car at any instant of time. Conclusion/Improvements: Non-intrusive nature of this system helps to detect driver’s physical condition without making inconvenience to him. Real-time and online data transfer system of this system helps the respective authority to take immediate actions. This device can be very helpful for law enforcement department to solve vehicle theft, accident and hit-and-run cases.

S. Vijay Kumar, Abraham Sudharson Ponraj

Emergency and Traffic Congestion Avoidance Using Vehicle-to-Vehicle Communication

Intelligent transportation systems (ITSs), entitled with wireless communication, are supposed to improve the safety of passengers and effectiveness of our transportation network. Transceiver is used in vehicle to exchange critical information from host vehicle to preceding vehicle. Wireless short-range communication technology is very much fastest technology which is used for transferring information. Enabling vehicle to communicate with each other, information such as traffic environment, emergency situation can be shared with the help of wireless transceiver (Zigbee) in each vehicle and an embedded microcontroller. This leads to create a safer and comfortable drive, and also GPS module is used for detecting the position of the particular vehicle. Traffic congestion is one of the major issues in the urban areas. For traffic avoidance, when a vehicle passes the traffic congestion area, driver passes that message to the vehicle approaching to that area. In this case, driver can type the message using keypad and broadcast it through Zigbee, and the vehicle approaching to that area will get pre-alert.

Anirban Das, Mahadev Desai, Nilkanth Mugatkar, Abraham Sudharson Ponraj

Smart Mobile Diagnostic Laboratory and Doctor Annunciation System in Ambulances

Background/Objectives: Globally increasing health care issues have been an immense inconvenience to the mankind. Pre-treatment checkup in case of emergencies leads to catastrophic results. So this paper presents a method to carry out checkups in the ambulance on the way to the hospital. Methods/Statistical analysis: The two major setbacks which prevents the treatment of a patient at critical situations are the city traffic and the distance from remote area to the hospital. The main drawback of the existing system is that it provides only tele-assistance in ambulance which becomes difficult for the doctor to interpret the situation with the obtained information. Findings: This paper provides solution to the existing problem, wherein a diagnostic laboratory would be present inside the ambulance and all the required tests would be taken in prior. The entire system would be designed using FPGA as a stand-alone system with reconfigurable I/O ports using LabVIEW as software. A GUI is created with the patient details, and the data of the monitored parameters along with the vocal sheet of the patient and the image of the wound will be sent to the doctor via this GUI. Improvements/Applications: IoT can be included to update the monitored parameters to the doctor at any instant. And a Google Map can be created to show the exact location so the exact time taken for the ambulance to reach the hospital will be known. A few more sensors can also be added.

Nikita Bais, R. Shubha, V. Yamuna, M. Kalyan Chakravarthi

Magnetic Braking System for Automotives

Background: The existing braking systems suffer from a lot of drawbacks like inferior time-delay response and noise due to mechanical parts, wear and tear due to friction and contact, low performance and bulky size. Methods/Statistical analysis: In this paper, design implementation of an automotive electromagnetic brake has been discussed, so as to replace already existing complicated braking systems with a relatively simple electromagnetic system. In the proposed system, the mechanical parts of the braking systems are completely replaced by the electronic parts, where a magnet is attached to the rim of the tyre of the vehicle and an electromagnet is placed parallel to the face of the rim of the tyre. The motion of the vehicle is controlled by controlling the supply to the electromagnet. As the electromagnet is energised, it acts like a magnet and tries to lock with the magnet on the rim of the tyre. As a result, the tyre stops rotating and the braking action occurs. The working is similar to that of an antilock braking system. Findings: A study was conducted on a prototype model analogous to the real-time system, and the plausibility of the work was observed. The problems and the constraints based on the real-time scenario were accounted for and thus optimisation method is also suggested. Application/Improvements: The proposed work is most suited for hybrid vehicles and for four-wheel automotive systems. Since only an analogous prototype was implemented and researched upon, the future works involve implementation of real-time system and conduct its analysis.

Arjun Nair, K. Srivatsan

Raspberry Pi-Based Surveillance System with IoT

Background: The proposed system describes a surveillance system developed using Raspberry Pi and a camera, which keeps monitoring a certain highly secured region continuously. When the system recognizes a change in motion (human motion) compared to its previous frame, the system starts recording video and stores it primarily in its memory and also in the cloud (for the reason that even if the burglar tries to destroy the system his image/video will be saved in the cloud storage), and the user receives alert mail from the system stating “human motion detected” along with the captured image attached with the alert mail. The system contains database of face patterns of local suspects which is compared with the face pattern of the person triggering the system, and image processing is done in real time to correctly identify the detected face; the system also keeps tracking the face throughout the region even if the person moves out of the frame by a camera mounted over a servo motor. The system turns on a buzzer alarm when the burglar attempts to cause damage to the system. The system allows the user to remotely access the camera to monitor live streaming video output and control the rotation of the camera. Methods/Statistical analysis: In this project, different types of surveillance systems which already exist are analysed, and the methods of having a portable surveillance system were developed using Raspberry Pi. Image processing methods for facial identification and face recognition is used. Findings: A study based on various image processing techniques is done; it is found that Haar-cascade and linear binary pattern are the suitable algorithm for performing image processing in real time. Application/Improvements: For better surveillance, face tracking in introduced, which can track the detected face throughout the region even if the person goes out of the camera frame, and remote accessing with control of the camera through IoT is introduced.

Arvin Joseph Kumar Jayakumar, S. Muthulakshmi

Development of Roads Pothole Detection System Using Image Processing

Driving a vehicle on the roads, it is required to consider many parameters of roads which include distress like potholes, crack, patches size of road. Road conditions influence the comfort and safety of people who are sitting in the vehicle. Detection of pothole helps for early warning to the driver and assessment to the road maintenance authority. The position and structure of pothole can be shared with road maintenance authority. In this paper, an embedded system is designed to detect pothole from images of the road and sends the GPS location to road maintenance authority crew server and upload it in Google map. This system designed on small single-board computer Raspberry Pi in which it uses the computer vision library for processing the input video which is taken from a camera and identifications of road pothole present.

Harshad Sawalakhe, Ramchandran Prakash

Automated Interoperability Testing of Optical Network Terminals for VoIP Call Features Using Robot Framework

Background: Coexistence of different technologies, protocols and frameworks for Voice over IP results in many interoperability issues. The Gigabyte-capable Passive Optical Network (GPON) that uses fiber-based point-to-multipoint networking escalates the possibilities of VoIP. The GPON-based VoIP consists of Optical Line Terminal (OLT) which is present at the service provider or server side and many Optical Network Terminal (ONT) at the customer end. The inception of GPON technology into telecommunication, unfolded the possibility of triple play (transfer of voice, data and video). Methods/Statistical Analysis: This paper proposes an automated testing mechanism of Optical Network Terminals for the SIP-based voice call features over IP. Out of the triple play service (data, voice and video) provided by the Optical Network Terminal, this work concentrates only on the voice-related functionality. The proposed system uses the Robot Framework for automating the SIP-based Voice over IP test scenarios. The paper also covers implementation of Asterisk-based Voice over IP Client-Server setup on a Raspberry Pi to understand the background functionality. Findings: The automated system captures the software faults of the Optical Network Terminal beforehand and ensures proper interaction with other network elements without any interoperability issues. In addition to the ease in using Robot Framework, this method reduces the human interventions in testing process. Application/Improvements: Automated interoperability testing provides a better coverage for the functionality of the ONT considering the manual testing. Our future work is extending this current work in all data and voice and thus creating a complete testing mechanism for the ONT system.

Kavya Ajith, Kalaiselvan Ramalingam, Muddukrishna Dandu

Design and Implementation of Smart Helmet Using Low Power MSP430 Platform

An accident is an unexpected, unintended, and unusual external action that occurs at particular place and time which leads to a marked effect on human life. Most of the countries have rules for motorcycle users to wear a helmet for their safety purpose where the rate of two-wheeler accidents increasing day by day. Smart helmet automatically checks whether a person has undergone any accident and sends messages to the emergency numbers. This system finds the impact with which the head hits the ground when an accident occurs. It makes use of a low power MSP430 processor which receives the analog value from the piezoelectric disk sensor based on the impact of helmet and compares with critical value. Once the critical value is obtained, GSM transmits a message to emergency numbers. As an additional feature, there is a temperature sensor which senses temperature in helmet and checks the temperature at every instant based on the variations of temperature in helmet control cooling system when temperature is high.

Yogya Indupuru, K. Venkatasubramanian, V. Umamaheswari

Vision Intelligence System for Power Management Using Human Activity Detection System

Nowadays, scarcity of power has been increased at much higher rate due to improper power management. In this paper, the concept of power management is demonstrated with a Webcam and OpenCV tool. OpenCV is used for the implementation of face-detection algorithm. The system is a real-time embedded system product, which is employed with a camera fixed in a room, which detects the faces of the people present in the room using OpenCV software which is a computer vision tool; as soon as the faces of human are detected in the room, the system takes the necessary steps and accordingly controls (turn ON/OFF) the AC/DC loads (like fan and lights) of the room. Thus, in this way, the utilization of the power can be maintained in an efficient way.

Sukanya B. Pasupuleti, Prakash Ramachandran

Embedded System for Classification of Upper Limb Movement During Action Using EEG

The role of the upper limb in human life is not limited to physical or functional movements but is accompanied with purposes like gestures, communication, and sensation. Many people lose their limb during an accident in the work place or complexity arising out of diseases or infections arising after operations due to which they are unable to perform the daily actions using hands. A healthy brain receives the signals from its body and generates responses to it. Here, a method is devised to detect which part of the upper limb is about to move, and hence, the desired output could be used to control external devices like a robotic arm and for the purpose of neural prostheses.

Navya Tummala, K. Venkatasubramanian, V. Umamaheswari

Intelligent Digital Signage System Based on Gender Identification

This paper proposes an intelligent transformation of digital signage systems by making it more audience interactive. The increase in flexibility and enhancement of digital signage display system can be done by providing optimized information and appearance attractive multimedia content through the signage system. This emphasizes more on the advertisement industry especially in public spaces like hotels, airports. The system has been designed to broadcast the advertisement on the signage display system based on the demographic features like gender of the observer. Real-time computer vision algorithms are applied to provide an observer-specific advertisement broadcast on the display system.

Riya Elizabeth Abraham, M. Robert Kennedy

Speech Recognition System Using Open-Source Speech Engine for Indian Names

Speaker independence, continuous speech and huge vocabularies create most of the greatest challenges in automatic speech recognition. This paper describes Sphinx, a library that offers the feasibility of accurate, huge vocabulary, speaker-independent, continuous speech recognition. Using speech for device control is a proven hands-free solution. There are several products that use speech input for hands-free control. They usually cater the users with US/UK accent. In this paper, a speech recognition system is developed for the application of hands-free control system to be deployed in automotive environment for Indian users. This paper demonstrates the methodology and the challenges of customizing an open-source speech recognition engine for Indian users. It is demonstrated for the application of speech-based control of smartphone, and rear-view mirror rotation. Open-source package used is Pocketsphinx for speech recognition and festival for text-to-speech and pronunciation generation. All the implementations are done on a single-board computer, i.e. raspberry pi.

Nitin Arun Kallole, R. Prakash

Energy Estimation of Embedded Systems

Embedded systems are identified by the processors, on which application-oriented programs have to run. Most of the actions on the processor are controlled and coordinated by the software, and also, it has a fundamental role in the system design. In this paper, we are estimating and optimizing the energy consumed by the processor with the Lagrange principle, by considering the task and energy consumed by the particular task for a particular time instant by the core in Ubuntu as well as in arm development studio-5. This helps to improve the performance of the processors dynamically in the future generations. Now they are widely used in hand-held devices and many other portable consumer gadgets. The ARM processors provide tremendous achievement with less power consumption and compact size performance analysis.

Anagha Ram, M S Bala Murugan

Design of Communicating Power Supplies and Controlling the Electronic Devices Using Internet and Mobile Application

Conserving power inside houses is normally hampered by the lack of in-depth details about what exactly is using the power, how much it can be employing, along with how to remotely and automatically control electronic devices. This issue is especially for many smaller, power-consuming devices which can be used for both commercial buildings and residential. A large number of electronic devices use switching alternate current to direct current supply to operate electronic devices. The “communicating power supplies” (CPS) to enable the respective connection of one’s along with control data between device along with a making administration system or maybe additional central organizations. Here developed the proof-of-system concept involving Internet-connected communicating power supplies along with proven both equally power confirming along with control by using a customized, cloud-based data clarifying property. In the event that CPS technology started to be widespread inside devices, a mix of computerized along with human being interactive remedies might allow substantial number of power financial savings and the security system.

Gunta Krishna Kishore, M S Bala Murugan

Real-Time Human Detection and Tracking Using Quadcopter

Background: Detection and tracking of humans in real time is a challenging and important field of research. Human detection has many applications in detection of human and video surveillance. Nowadays, quadcopters are used in different fields like research, military and law enforcement, commercial fields for navigation, searching, and areal imagery. Methods: In this paper, the primary objective of the system is to detect and locate people who got isolated in some areas due to natural disasters like floods and earthquake. It is carried out using a single-board computer Raspberry Pi (RPI), and the image processing part is carried out with the help of OpenCV. The detection and tracking of humans is done using quadcopter. Quadcopter is equipped with camera, the video capture is processed using RPI, and live streaming along with human detection is sent to the base station over the wireless network. Applications: It is used in effective human detection in real time video streaming. It helps the rescue team to locate people and to know their current situation and thus to take necessary actions including medication and evacuation. Development/future work: A prototype model for human detection and tracking using quadcopter is designed and developed. Better battery pack for longer flying time and use of 3G USB dongle for large area surveillance.

Rana Praful George, V. Prakash

Sonar Data Processing Using Multicore Architecture Processor and Embedded Linux

Background: Traditionally, sonar signal processing is performed on dedicated signal processors to meet the real-time processing requirements. Recently, the computational capability in embedded general purpose processors has also multiplied with the introduction of multiple cores and vector processing units. Embedded Linux is the usage of Linux kernel and various open source components in embedded systems. The key advantage of Linux and open source in the embedded system is the ability to reuse components which allows to design and develop complicated products based on existing components and to have full control of the software part of the system. This project is aimed at bringing up a bare multicore power architecture processor board with Embedded Linux, benchmarking it for performance and implementing a digital signal processing application exploiting multiple cores and SIMD units in each core. Methods: The T4240RDB processor is developed using Yocto Project. Yocto is an open embedded project used to build custom-based Linux images. Next, the processor is benchmarked for its processing capabilities and then, signal processing application is done on the processor. Findings: Yocto Project can be used to develop architecture-specific images as well as images can be modified and additional recipes and packages can be added. The T4240RDB can easily do signal processing application. Application: The T4240RDB can be integrated with the sonar subsystem and can be used for real-time data processing.

Varun K. Jayan, A. K. Mohamed Husain

A Novel Black Box System for Automobiles

According to the World Health Organization (WHO) report, about 1.25 million people die due to road accident injuries every year. And majority of road crashes are caused by human error. The main objective of this research work is to design a dedicated black box system for automobiles which is used to determine the reason for the accident. Data acquisition is an important process that involves gathering information. By analyzing the various data recorded during road accident, the safety interventions and technology can be implemented to avoid such incident in the future. The black box acts as a data acquisition device, and the acquired data are stored in the Raspberry Pi. During the time of collision, the data acquired are transferred to the traffic control server’s mail id. Sensors play a vital role in the proposed system to identify and analyze the reason for the accident. Sensors list include accelerometer sensor, carbon monoxide sensor, flame sensor. This paper explores the various reasons for accident and the simultaneous catastrophic effects as the result of the collision. It introduces two concepts: One is to determine the possibility of carbon monoxide leakage inside the vehicle cabin space and the other is to determine whether the vehicle has entered into no entry region; this is done using ultrasonic sensor paired with an Arduino and ZigBee.

S. Sriram, V. Prakash

IOT-Based Automated Aeroponics System

Aeroponics is a soilless method of growing plants in air with the assistance of water vapor or mist environment, using an enriched nutrient solution sprayed as a mist, in order to attain faster plant growth. One of the key ideas behind aeroponics is to keep the growth environment pest- and disease-free, so that the plants can grow faster and healthier. In this paper, we propose an automated aeroponics system in which we use sensors for measuring the temperature, humidity, pH value of water, and the light exposure in the environment where plants are grown. An LED grow light is used as source of light for photosynthesis instead of sunlight. The key irrigation apparatus is spray jet which is used to spray nutrient-mixed mist directly to the dense root system. The temperature sensor will sense the temperature of the environment, and if it exceeds beyond the threshold value, the cooling/ventilation system will compensate for it. Similarly, for humidity, the spray jet and a dehumidifier are used to stabilize the environment. The pH control mechanism will keep the pH value around 6.0. We are incorporating Internet of Things (IoT) for continuous monitoring of data, data analysis, and data logging. Data from each sensor are collected at regular intervals of time and are uploaded to a cloud for monitoring, followed by data analysis, for increased productivity. This data can be used to streamline the automation process, and also for other users to increase crop yield.

Felin Francis, P. L. Vishnu, Manish Jha, Bharghava Rajaram
Weitere Informationen