Asian Journal of Convergence in Technology
Not a member yet
868 research outputs found
Sort by
Operator Certification Using Face Recognition Technique
Get PDFA facial recognition system is a technology capable of identifying or verifying a person from a digital image or a video frame from a video source. There are multiple methods in which facial recognition systems work. But in general, they work by comparing selected facial features from given image with faces within a database. Real time video face recognition will happen using Raspberry pi 3 and web camera. This technique is used for operator verification using operator’s face
Performance Evaluation of Kernel SVM on Sparse Datasets with Large Attributes
Get PDFSupport Vector Machines (SVM) is a Machine Learning Algorithm which is used for Classification and Regression in many applications. The vital characteristic of SVM is that the classification decision function is formulated using very few points in the training dataset. We have provided the less publicized mathematical formulation of Hard Margin SVM Classifier, Soft Margin SVM Classifier and the Kernel Trick. In this paper we have used two sparse data sets, we found that Kernel SVM shows significantly better generalization and prediction accuracy for sparse datasets. We have compared the classification performance with other Machine Learning algorithms such as Logistic Regression, Neural Networks, Bayesian Network, KNN, Bagging and Random Forest
DESIGN AND ESTIMATION OF SOLAR PV SYSTEM FOR EDUCATIONAL CAMPUS
Get PDFThis paper discusses the potential of implementing solar panels at rooftops of the blocks at Institute of Technology, Nirma University (ITNU) to harvest solar energy. The design is conducted using HelioScope simulation tool, specifying all the mechanical parameters and the electrical components used in the proposed PV system.The expected system power is estimated to be at least 2 times the campus energy demand and around 8% decrease in AC consumption due to shadowed rooftops
Planar Inter Digital Capacitive Sensor for Real time Transesterification Progress Monitoring of Karanja (Pongamia) Oil
Get PDFTransesterification is a well known chemical process of producing biodiesel from edible and non-edible oils, animal fats and cooked oils. Base catalytic transesterification of non-edible oil is a popular method for production of biodiesel. Biodiesel production from Karanja or Honge (Pongamia pinnata) seed oil is gaining momentum in India and other parts of world. The real time monitoring of transesterification reaction progress is essential step towards automating biodiesel production. Two planar inter digital capacitive sensors (IDCS) are fabricated for the purpose of monitoring the transesterification progress of Karanja oil and their performance are evaluated. The repeatability and sensitivity of fabricated sensor is reliable and acceptable. The sensor with associated signal conditioning circuit will be useful in automating the biodiesel production process and play vital role in energy efficiency and the quality of end products
HV Switchgear Switching System
Get PDFHV switchgears are normally well built and accidents are rare but when they do happen, the consequence to human life, downtime, financial losses and image of the company and stakeholders can be very significant. Therefore, it is always best to perform any HV switching from a safe distance away. Statistically, accidents are caused by human or mechanical issues which creeps up over time. In this work, after much deliberation an electropneumatic system was developed to trigger HV switching from 25 m away. Much trial and error were done to achieve the finalized system The Switchgear Safety System developed was tested to be capable of switching a 11kV OCB, the racking in and out of the cubicle type VCB and even replacing the human finger to push the push-button type of motorized HV switchgears which is commonly sold today. Though these latest push-button type switchgears look safe, only the high muscular strength human hand action is replaced by an electric motor, the mechanical engineering system behind, is still the same and therefore should be switched from a safe distance away.  
Automatic Plant Watering System
Get PDFThis paper illustrates the implementation of an automatic plant watering system using the Atmega328p and ESP-01 Wi-Fi module. The paper includes the working of the relay circuit and the activation of the pump. The automatic plant watering system is designed to help people in the daily activities of watering plants or lawns which require utmost attention as an appropriate watering pattern is essential to ensure that the plants and the lawn stay green and healthy. Considering the current scenario it has become difficult for people to look after their plants with their hectic schedules as a result there is a strong need to automate this process in order to overcome this challenge. Automatic plant watering system has everything in store which is necessary to provide a garden with the watering action it demands
Application of Machine Learning in Classification and Prediction of Breast Cancer
Get PDFCancer misdiagnosis is extremely common. We attempt to build different machine learning models that can predict occurrences of cancer traits in a patients. Being said that cancer is often misdiagnosed, when it comes to cancer, spotting the disease earlier can quite literally mean the difference between life and death. Predictive models obtained by using machine algorithms may be a key in such cases. This can be used by any medical institutes for faster, economical and accurate cancer diagnosis. Machine learning incorporates varieties of statistical, probabilistic and optimization techniques that allow computers to “learn” from past examples and to detect hard-to-diagnosed patterns from massive, noisy or complex datasets This project allows us make fast, real-time and accurate diagnosis and prediction of breast cancer. The software uses support vector machine algorithm to do the prediction and diagnosis of breast cancer. The simplicity and almost accurate results for support vector machine algorithm is very suitable for implementation
A Survey On: Classification of Twitter data Using Sentiment Analysis
Get PDFSentiment means classify the opinions which are in the form of text .As we are classifying the text it must having different unstructured contains with information of particular subject. There are various social media sites which gives us information with their thoughts but twitter is biggest among them where any one who having account on twitter can tweet their opinions of any subject in any certain or uncertain way. Hence we get extra scope in mining of such data. The analysis is done with the help of machine learning algorithms on the dataset. Classification is done by the classifier algorithms. The reviews data is used for performing sentimental analysis. This paper gives idea about how the analysis is done on twitter data by using various algorithms and machine learning concepts. It is a survey of different papers for analyzing the sentiments of text
Creativity in machines: Music composition using artificial intelligence
Get PDFIn this paper we propose a framework to take the next step towards making creative machines. Taking cue from Turing’s Mind Paper (1950) to more recent studies by Riedl in ‘’The Lovelace 2.0 test of artificial creativity and intelligence’ we try to examine a very creative area of human creativity – music. We have summarized the different works published on artificial intelligence and machine learning implemented for algorithmic music composition. Comparison of different algorithms-techniques including key features, advantages, disadvantages, common issues, trade-off and future aspects are discussed in detail. We then propose our own framework of how machines can be made to learn creativity
Serial Rapid IO high speed optical interface protocol for Indigenous MRI
Get PDFThis paper presents the available literature on high speed Serial Rapid Input Output communication protocol. The MRI gradient amplifier system consists of a cabinet with a power supply and three Gradient Amplifiers. It is a three axes Gradient Amplifier system, which can be used in a MRI system to control the X, Y and Z Gradient Coils. The optical interface this current setpoint can be transmitted digitally to the Gradient Amplifier. The gradient amplifier system possess optical interface which is a high speed interface intended for communication of current setpints, system clock, control diagnostics by the MRI system host. This optical interface benefits from digital optical isolation and removes cable, conversion loses and noise on the current setpoint