← Back to Archives
VOLUME 7, ISSUE 2, FEBRUARY 2019
Survey on Monitoring Crowd Conditions using Mobile Consumer Devices
K Amuthabala, Shashank N, Shilpa A
Development and Implementation of Seven Level Inverter Using Space Vector Modulation Technique for PV Application
G.Indumathi, Dr.S.U.Prabha
Mechanism Assessment of Air Circuit Breaker and Identification of Faults by Testing Method
Rashmi Kurhade, Pauravi Patel, Akshata Raut, Komal Sapkale, Sachin Angchekar
Survey on Air Price Prediction using Machine Learning Algorithms
Abhilash, Ranjana Y, Shilpa S, Zubeda A Khan
Distributed Power Systems Automation using SCADA System
Mohini Chaube, Gaurang Singh, Mrunmayee Kore, Shruti Nema
Survey on Sentiment Analysis
Sheba Jebakani, Sujith Surendranath, Vinay Kumar B U, K R Nagendra
Power Monitoring and Billing System using IoT
Kavitha Patil, Anushka D, Bhagyashree Bhat, Farheen Shariff
|DOI: 10.17148/IJIREEICE.2019.7207
USDO based Control of Current Sensorless Boost Combined Inverter with Load Variations
Abhishek D S, Dr. Arun Kishore W C, Alina C R
Detection of Cancer using Machine Learning
Omprakash B, Raksha K R, Sheetal M, Soujanya B, Yogitha K R
Single Phase Active Power Filter using ZVS Full- Bridge Inverter
Sooraj R S, Dr. Lekshmi A
An Isolated High Step-Up DC–DC Converter for PV Applications
Anju K, Remya Mol N, Ajmal I
Switched Capacitor Based Multilevel Inverter Topology Compatible with Multiple Inputs
Sajina S, Frieda Mohan
Prediction of Bike Rentals
Dr. Shanthi Mahesh, Aditya Warrier, Deepthi P, Dimple K H
High Efficient Transformerless Single Stage Inverter Topology for Single Phase Grid Connected Photovoltaics System
Archa Sarath J, Dr. Dinesh Pai A, Swathy Soman
Motion Analysis of Volleyball Sport
Kavitha S Patil, Pooja B Karnak, Rakshitha M, Zeenath Fathima S N
Secret Message Transmitter for Defence Outposts
Dr Neha Mangla, Ishu Tiwari, Aishwarya R, Aishwarya VM
The End to End Literature Survey on Machine Learning with Artificial Intelligence
Kadija Oshin, Kavya Prakash, Meghana B, Srinivas B V
Statistical Learning for Predicting Probable Drug-Drug Interactions using Machine Learning Classifiers
Suhas A Bhyratae, Abhishek A, Mallesh M Jolad, Manoj S
Paddy Leaf Disease Detection Using Image Processing and Machine Learning
Dr. Neha Mangla, Priyanka B Raj, Soumya G Hegde, Pooja R
Abstract
Survey on Monitoring Crowd Conditions using Mobile Consumer Devices
K Amuthabala, Shashank N, Shilpa A
Abstract: Presenting a systematic study and optimization of crowd monitoring methods based on tracking consumer devices with activated Wi-Fi or Bluetooth interfaces using stationary scanners with directional antennas. Analysing crowd with the help of Wi-Fi and Bluetooth is necessary as they do not need the corporation of audience present in the event or place. Monitoring without the need of audience places a major role in providing and maintaining security at mass events or in places with huge human crowd. Analysis of RF signals is a well-known technique for human activity monitoring. We use a raspberry pi to scan the surrounding for the devices of audience and push the data into system for data processing and after data processing we produce a heatmap and timeline for proper analysis of an individual based on requirements.
Keywords: Wireless communication, Wi-Fi, RF signals, Features from Accelerated Segment Test (FAST)
Keywords: Wireless communication, Wi-Fi, RF signals, Features from Accelerated Segment Test (FAST)
Abstract
Development and Implementation of Seven Level Inverter Using Space Vector Modulation Technique for PV Application
G.Indumathi, Dr.S.U.Prabha
DOI: 10.17148/IJIREEICE.2019.7201
Abstract: Multilevel Inverters (MLI) play an important role in medium / high voltage and high power applications due to its capability to convert DC input voltage to AC output voltage with reduced Total Harmonics Distortion (THD) and low Electromagnetic Interference (EMI). Multilevel inverters generate sinusoidal voltages from discrete voltage levels, and Pulse Width Modulation (PWM) strategies accomplish this task of generating sinusoids of variable voltage and frequency. Modulation methods for Hybrid Multilevel Inverter can be classified according to the switching frequency methods. Many different PWM methods have been developed to achieve the following: Wide linear modulation range, less switching loss, reduced Total Harmonic Distortion (THD) in the spectrum of switching waveform Differential Evolution (DE) algorithm is a new heuristic approach mainly having three advantages; finding the true global minimum regardless of the initial parameter values, fast convergence, and using few control parameters. DE algorithm is a population based algorithm like genetic algorithms using similar operators; crossover, mutation and selection. In this work, we have compared the performance of DE algorithm to that of some other well-known versions of genetic algorithms. The three-dimensional space vector modulation schemes are supersets of, and thus are compatible with, conventional two-dimensional space vector modulation schemes. An LC Filter is used to eliminate the output voltage harmonics. A conventional Proportional Integral (PI) controller is used to control the output load voltage.
Keywords: Genetic Algorithm, Differential Evolution, Multilevel Inverter
Keywords: Genetic Algorithm, Differential Evolution, Multilevel Inverter
Abstract
Mechanism Assessment of Air Circuit Breaker and Identification of Faults by Testing Method
Rashmi Kurhade, Pauravi Patel, Akshata Raut, Komal Sapkale, Sachin Angchekar
DOI: 10.17148/IJIREEICE.2019.7202
Abstract: Air Circuit Breakers (ACBs) are popularly used for low voltage application in many industries and distribution panels. ACBs possess fault interruption capabilities such as high making and breaking capacity. ACB operates on the mechanism of sensing current through Static Release (SR) action which results in Free Return Charging Device (FRCD) being operated. The reliability greatly depends on the smooth mechanism operation of ACB. This paper illustrates root causes of various faults on ACB during its lifespan using Ishikawa diagram. ACB serves a vital part of the protection of power system, it’s reliability gains importance. The testing of ACB in the company is carried out as per International Electrotechnical Commission (IEC) codes using on field fault conditions which ensures its reliability in market as guaranteed by the organization. The industry carries out testing on test bench by creating on field fault condition such as overload, short circuit, earth fault which is based on the principle of primary and secondary injection methods. The reliability of ACB can be predicted by detailed analysis of testing results.
Keywords: Air Circuit Breaker, Free Return Charging Device, Microprocessor based Static Release.
Keywords: Air Circuit Breaker, Free Return Charging Device, Microprocessor based Static Release.
Abstract
Survey on Air Price Prediction using Machine Learning Algorithms
Abhilash, Ranjana Y, Shilpa S, Zubeda A Khan
DOI: 10.17148/IJIREEICE.2019.7203
Abstract: The existing airfare prediction method uses very complicated methods and algorithms for the prediction. They consider several financial and commercial factors and the prices changes dynamically which makes it difficult for customers to purchase the air ticket. Airlines implement dynamic pricing for their tickets, and base their pricing decisions on demand estimation models. The reason for such a complicated system is that each flight only has a set number of seats to sell, so airlines have to regulate demand. In the case where demand is expected to exceed capacity, the airline may increase prices, to decrease the rate at which seats fill. On the other hand, a seat that goes unsold represents a loss of revenue, and selling that seat for any price above the service cost for a single passenger would have been a more preferable scenario.
Keywords: Air fare, Random forest, Linear regression
Keywords: Air fare, Random forest, Linear regression
Abstract
Distributed Power Systems Automation using SCADA System
Mohini Chaube, Gaurang Singh, Mrunmayee Kore, Shruti Nema
DOI: 10.17148/IJIREEICE.2019.7204
Abstract: Electricity plays a vital role in both day to day life of people and the economic development of a nation. Though the demand and generation of electric power have kept on increasing at comet’s pace, maintaining systems’ reliability has been an issue we are struggling with today. To ensure a sustainable supply of electricity and energy security, the efficient management of the electricity distribution network through the use of intelligent devices that can monitor and control power flows in real time has become necessary. In order to bring efficiency and sustainability in the electricity distribution sector, automation of the same using SCADA system is mentioned in this paper; wherein components of the SCADA systems, its operating principle, advantages, disadvantages and other applications are also explained. The overall objective of this paper is to ensure 24*7 stable supply of electricity to all consumers, reduce losses and equipment failure rate, and increase the efficiency of the systems through automation of distributed power systems using SCADA system.
Keywords: Distribution Systems, SCADA, RTU, RMU, FRTU, Master Controller.
Keywords: Distribution Systems, SCADA, RTU, RMU, FRTU, Master Controller.
Abstract
Survey on Sentiment Analysis
Sheba Jebakani, Sujith Surendranath, Vinay Kumar B U, K R Nagendra
DOI: 10.17148/IJIREEICE.2019.7206
Abstract: Sentiment analysis fundamentally implies the way toward recognizing and characterizing an assessment or explanation in light of the extremity communicated in it particularly to decide the sentiments communicated by the reviewer. In this new period of the web with consistently developing information as the content, we require an approach to group the content into positive, negative and once in a while unbiased. These feelings or sentiments are of high incentive to organizations, establishments, and different associations to enhance their administrations and items in view of clients' input.
Keywords: NLP, Deep learning, CNN, Sentiment analysis, Twitter data
Keywords: NLP, Deep learning, CNN, Sentiment analysis, Twitter data
Abstract
USDO based Control of Current Sensorless Boost Combined Inverter with Load Variations
Abhishek D S, Dr. Arun Kishore W C, Alina C R
DOI: 10.17148/IJIREEICE.2019.7208
Abstract: The Existing domestic Energy meter reading systems universally exist many problems, such as difficulty in construction, too narrow bandwidth, too low rate, poor real time, not two way communication quickly etc. To solve above problems, this paper uses the wireless technology for Automatic Meter Reading and billing System. This proposed method provides the communication between the Electricity Board section and the consumer section using Internet of Things (IOT) for transmitting the customer’s electricity consumption and bill information that is calculated using Arduino. The information regarding the bill and payment details are communicated to the consumer via GSM (Global System for Mobile communication). The electricity consumption details and billing information is continuously transmitted and monitored by the Electricity Board section.
Keywords: Arduino Mega (microcontroller), IOT, GSM900, Wi-Fi module, Web server
Keywords: Arduino Mega (microcontroller), IOT, GSM900, Wi-Fi module, Web server
Abstract
Detection of Cancer using Machine Learning
Omprakash B, Raksha K R, Sheetal M, Soujanya B, Yogitha K R
DOI: 10.17148/IJIREEICE.2019.7209
Abstract: A current sensorless sliding mode control scheme is developed to remove the effects of mismatched load disturbance and higher order harmonics of a conventional inverter. Normally the problems associated with an inverter is, to maintain the output voltage regulated and there harmonics eliminations. The output voltage is normally affected by the load variations. In case of EV system, the variations range from no load to full load, the control performance also has an impact on these. The input variations are avoided by inserting a dc-dc converter circuit. For the control, to sense the output current, wide band current sensors are required. It will increase the cost of the system as well as the size. This problem is avoided by the observer method. The voltage is observed continuously and is used to develop the inductor current. By integrating the estimations into the design of sliding surface, a current sensorless sliding mode controller is proposed. The simulation of the proposed system is modelled and evaluated with desirable results in MATLAB/Simulink.
Keywords: USDO - Universal State Disturbance Observer, SMC-Sliding Mode Control, PWM – Pulse width modulation, EV- Electric vehicle.
Keywords: USDO - Universal State Disturbance Observer, SMC-Sliding Mode Control, PWM – Pulse width modulation, EV- Electric vehicle.
Abstract
Single Phase Active Power Filter using ZVS Full- Bridge Inverter
Sooraj R S, Dr. Lekshmi A
DOI: 10.17148/IJIREEICE.2019.7210
Abstract: Cancer is a heterogeneous disease. There are various options available for cancer treatment. Type of cancer treatment is influenced by various factors such as cancer type, the severity of cancer and the most important is genetic heterogeneity. So in such complex environment, the targeted drug treatments are likely to be irresponsive or respond differently. To study the anticancer drug response we need the classification of cancerous profile. Hence, there is a need to analyze cancer data for predicting optimal treatment option. Analysis of cancerous profile predicts and discovers potential drugs and drug targets. Main aim is to provide machine learning based classification technique for cancerous profile.
Keywords: Cancer, Machine learning techniques, Neural Network (NN) and Support Vector Machine (SVM)
Keywords: Cancer, Machine learning techniques, Neural Network (NN) and Support Vector Machine (SVM)
Abstract
An Isolated High Step-Up DC–DC Converter for PV Applications
Anju K, Remya Mol N, Ajmal I
DOI: 10.17148/IJIREEICE.2019.7211
Abstract: Wide use of power electronics circuits resulted in harmonic distortion in power system in large extent. Traditional filters have poor dynamic response while harmonic component changes. Active power filters are used to improve power quality by injecting reactive and harmonic current, because of its better dynamic response in different load patterns. In this paper a conventional Zero Voltage Switching (ZVS) full-bridge inverter is investigated and reconfigured as Single Phase Shunt Active Power Filter (SAPF). Hysteresis current control scheme is employed because of its simplicity and ease of implementation. The ZVS scheme is incorporated with hysteresis controller followed by reference current generation. The simulation of the proposed SAPF is modelled and evaluated with desirable results in MATLAB/SIMULINK.
Keywords: Power Quality (PQ), Shunt Active Power Filter (SAPF), ZVS–Zero-Voltage Switching (ZVS) inverter, Hysteresis band control
Keywords: Power Quality (PQ), Shunt Active Power Filter (SAPF), ZVS–Zero-Voltage Switching (ZVS) inverter, Hysteresis band control
Abstract
Switched Capacitor Based Multilevel Inverter Topology Compatible with Multiple Inputs
Sajina S, Frieda Mohan
DOI: 10.17148/IJIREEICE.2019.7212
Abstract: For the requirement of clean energy there is an increased dependency on the renewable energy resources like Photovoltaics cells. A PV panel normally generates low dc voltage that need to be boosted before converting it to ac voltage. Therefor an isolated high gain dc-dc converter is proposed to obtain a high voltage gain. The converter is a cascade combination of the boost and buck boost converter. The Incremental Conductance (INC) method is employed to track the maximum power from the panel and it will offer a smooth transition to the maximum power point. To improve the dynamic performance of the high gain dc-dc converter a double closed loop control strategy has been used. A simulation of the proposed system is modelled and evaluated with desirable results in MATLAB/Simulink.
Keywords: DG – Distributed Generation, PV – Photovoltaics Panel, MPPT – Maximum Power Point Tracking, PWM – Pulse width modulation
Keywords: DG – Distributed Generation, PV – Photovoltaics Panel, MPPT – Maximum Power Point Tracking, PWM – Pulse width modulation
Abstract
Prediction of Bike Rentals
Dr. Shanthi Mahesh, Aditya Warrier, Deepthi P, Dimple K H
DOI: 10.17148/IJIREEICE.2019.7213
Abstract: A switched capacitor based multilevel inverter employing asymmetric source configuration is proposed. Multilevel inverters are mainly used to improve the harmonic profile of the output by increasing the number of levels. Due to the advancement in renewable energy, asymmetrical DC voltage sources are more common. The significant reduction in switch count of multilevel inverters has served as the greatest advantage over years. Various modulation schemes have been proposed in the literature to enhance the performance of multilevel inverters. This include Sinusoidal PWM (SPWM), Space Vector Modulation (SVM), Selective Harmonic Elimination (SHE) etc. The switching strategies used for the control of switches influence the harmonic content of output voltage. Most of the modulation techniques, however contributed less in reducing the distortion at the output. In order to control the noise signals, lower order harmonics should be controlled. A modified Reduced carrier PWM scheme is proposed to control the harmonic content of the output voltage and thereby reduce the Total Harmonic Distortion. The simulation of the proposed system is modelled and evaluated with desirable results in MATLAB/Simulink.
Keywords: Switched-capacitor, H-Bridge, multilevel inverter, high frequency inverter, Total Harmonic Distortion, Reduced carrier PWM
Keywords: Switched-capacitor, H-Bridge, multilevel inverter, high frequency inverter, Total Harmonic Distortion, Reduced carrier PWM
Abstract
High Efficient Transformerless Single Stage Inverter Topology for Single Phase Grid Connected Photovoltaics System
Archa Sarath J, Dr. Dinesh Pai A, Swathy Soman
DOI: 10.17148/IJIREEICE.2019.7214
Abstract: Bike rental predictions forecasts the demand for bikes rentals in dependency of weather conditions like the temperature and calendric information e.g. holidays. To make predictions machine learning is used. The dataset contains some time features which we translate to indicator variables, as well as weather information for that day. Generally in bike rental systems it is very important that the administrators should know how many bikes are to be placed in each station, knowing this count enables them in arranging the required number of bikes at the stations and decide whether a particular station needs to have extra number of bikes or not. So in this research work we study prediction associations to enhance their administrations and items in view of clients' input.
Keywords: Random Forest, Neural Network, Prediction, Result Analysis.
Keywords: Random Forest, Neural Network, Prediction, Result Analysis.
Abstract
Motion Analysis of Volleyball Sport
Kavitha S Patil, Pooja B Karnak, Rakshitha M, Zeenath Fathima S N
DOI: 10.17148/IJIREEICE.2019.7216
Abstract: Sports skill discrimination using motion picture data, focused on volleyball attack skill is performed. We attempt to certify the hypothesis that expert skills have relatively low frequency motions rather than novice skills as the similarity of human postural control. We carry out experiments and analyze sports skills as for frequency of motion using time series motion pictures of volleyball attacks. The volleyball play is analyzed with motion picture data recorded by hi-speed cam-coder, where we do not use physical information such as body skeleton model, and so on. From motion picture data Time series data are obtained with four marking points, and analyzed using Fast Fourier Transform (FFT) and clustering data mining method. As the experiment results, we have found that y-axes of novice data have more high-frequency data, and that implies novice motions have high frequency motions, and that may support our hypothesis.
Keywords: Motion picture data, high speed camcorder, Fast Fourier Transform (FFT), Clustering
Keywords: Motion picture data, high speed camcorder, Fast Fourier Transform (FFT), Clustering
Abstract
Secret Message Transmitter for Defence Outposts
Dr Neha Mangla, Ishu Tiwari, Aishwarya R, Aishwarya VM
DOI: 10.17148/IJIREEICE.2019.7217
Abstract: The paper proposes the Morse code [3][4] which is the earliest method used in Radio Telegraphy. It is about a vision and mission for helping the soldiers, who relentlessly stand in the sun and snow to protect our borders. At the outposts, whenever they are transmitting messages over radio, frequencies tend to get hacked by the enemies and the messages are exposed to them. What if we had a system which will not only confuse enemies but even leave them behind with no clues. This work is using the android device of any kind, having the facility of keyboard to transmit the message. The messages are fed via an android device to a microprocessor (i.e., Raspberry Pi)[6][7][8] over Wi-Fi, which will convert the message into code of (“._._”) and then transmit using the general light bulb by flashing it. At the receiver’s side, a camera will record the flashes and feed it as input to the microprocessor at that side, which will in turn decode it to get the original message, hence the enemies will feel it to be fluctuations in power rather than a message. We have improved the internationally used Morse Codes, to a personalised level and that is being used to transmit the message from one defence outpost to other. It can also be implemented if the lightning inside the posts is switched off for security reasons by using Torches which are available with the soldiers. The microprocessor is connected to the light source to send the flashing instructions by the use of codes.
Keywords: Radio Telegraphy, Universal Morse Code, US Model Straight Key, Photoresistor or camera
Keywords: Radio Telegraphy, Universal Morse Code, US Model Straight Key, Photoresistor or camera
Abstract
The End to End Literature Survey on Machine Learning with Artificial Intelligence
Kadija Oshin, Kavya Prakash, Meghana B, Srinivas B V
DOI: 10.17148/IJIREEICE.2019.7218
Abstract: Suggested instruction (CAI) has been in use for many years, fetching the power of the computer to bear on the educational scenario. Now artificial intelligence methods are being applied to the development of Intelligent Computer–Assisted Instruction (ICAI) systems in trial to create computerized "tutors" that shape their teaching techniques to fit the learning patterns of individua students. This work provides some information and conclusions which author gained during analyzing and projecting of such systems.
Keywords: Artificial Intelligence, CAI Systems, ICAI Systems
Keywords: Artificial Intelligence, CAI Systems, ICAI Systems
Abstract
Statistical Learning for Predicting Probable Drug-Drug Interactions using Machine Learning Classifiers
Suhas A Bhyratae, Abhishek A, Mallesh M Jolad, Manoj S
DOI: 10.17148/IJIREEICE.2019.7219
Abstract: Drug-Drug Interaction (DDI) is a change in the effect of a drug when patient takes another drug. Characterizing DDIs is extremely important to avoid potential adverse drug reactions. DDIs are representing as a complex network in which nodes refer to drugs and links refer to their potential interactions. Recently, the problem of link prediction has attracted much consideration in scientific community. The process of link prediction as a binary classification task on networks of potential DDIs are presented. By using link prediction techniques for predicting unknown interactions between drugs in arbitrary chosen large-scale DDI databases namely Two-Sides and Drug bank. The performance of link prediction is estimated using a series of experiments on DDI networks. The link prediction is performed using some of the machine learning classifiers such as random forest; Gradient Boosting .The applied methodology can be used as a tool to help researchers to identify potential DDIs.
Keywords: Random Forest, DNN, Gradient boosting. Pharmacology, Pharmacokinetics
Keywords: Random Forest, DNN, Gradient boosting. Pharmacology, Pharmacokinetics
Abstract
Paddy Leaf Disease Detection Using Image Processing and Machine Learning
Dr. Neha Mangla, Priyanka B Raj, Soumya G Hegde, Pooja R
DOI: 10.17148/IJIREEICE.2019.7220
Abstract: The spread of plant pests and diseases has increased dramatically in recent years. Globalization, trade and climate change, as well as reduced resilience in production systems due to decades of agricultural intensification, have all played a part. Plant pathogens can be fungal, bacterial, viral or nematodes and can damage plant parts above or below the ground. Identifying symptoms and knowing when and how to effectively control diseases is crucial. In this paper, we propose the idea of leaf detection using leaf images.
Keywords: Leaf disease detection, Image Processing, Image Segmentation, Machine Learning, Feature Extraction
Keywords: Leaf disease detection, Image Processing, Image Segmentation, Machine Learning, Feature Extraction