Showing papers in "Journal of emerging technologies and innovative research in 2019"

Fake news detection using machine learning

Abstract: A lot of things read online, especially in the social media feeds, may appear to be true, often is not. Fake news is news, stories or hoaxes created to deliberately mislead or deceive readers. Usually, these stories are created to either influence people’s views, push a political agenda or cause confusion and can often be a profitable business for online publishers. The dissemination of fake news in today’s digital world has effected beyond a specific group. Mixing both believable and unbelievable information on social media has made the confusion of truth. That is, the truth will be hardly classified. This paper comes up with the applications of NLP (Natural Language Processing) techniques for discerning the 'fake news', which is the misguiding news that is being published through unknown sources.

Axial Flux Permanent Magnet Disc Machines: A Review

Abstract: Hub motion lasting magnet or permanent magnet (PM) machines are being produced for some applications due to their alluring highlights. A broad writing exists concerning the plan of an assortment of kinds of hub motion PM machines. A diagram of hub motion, slot less and opened different PM machines are introduced in this paper. Machine structures, points of interest and highlights of the Axial Flux PM machine (AFM) are explained. A few fascinating novel hub motion machine structures are likewise covered from an assortment of viewpoints.

Crop Prediction System using Machine Learning

Abstract: Looking at the current situation faced by farmers, we have observed that there is an increase in suicide rate over the years. The reasons behind this situation are weather conditions, debt, family issues. Sometimes farmers are not aware about the crop which suits their soil quality, soil nutrients and soil composition and rain fall value. The work proposes to help farmers check the soil quality depending on the analysis done based on data mining approach. Thus the system focuses on checking the soil quality and rainfall value to predict the suitable crop for cultivation and that can maximize the crop yield by using machine learning algorithm like decision tree algorithm and SMA.

SMART IRRIGATION SYSTEM USING IoT

Abstract: The agriculture sector is biggest sector of India it provides employment to 50% work force of India. Each and every sector of India is directly or indirectly connected to agriculture sector, despite of this the development in technology is very less. Farmers are still using conventional techniques for farming, the developed technologies are either expensive or does not required by farmer. In this paper a Smart irrigation system is discussed which is economical and have great impact on irrigation system. The system controlled in two modes first is manual and second is automatic control for controlling the operation of water pump. The pump is controlled by using Atmega328P IC which is programmable in nature using relay as switch and taking the feedback from soil moisture sensor and rain sensor for controlling the water pump. The manual control is done by using HTML webpage by BOLT IoT module.

ICT in 21st Century’s Teacher Education

Abstract: ICT, the term stands for Information Communication and Technology. ICT is widely used in handling information in the various fields and disciplines like Science, Engineering, Technology and Management (UNESCO, 2002). Modern science and technological societies require more knowledge of ICT trainees and the need to use ICT to provide teaching power; pre-service teachers also need during ICT's knowledge training program, as this integrated technical knowledge helps a prospective teacher get to know the world of technology better. Going Education Thidera can be applied to future development. Being broadly used and accepted in various spheres (Education, Technology, Communication etc) of life, it has become an important part of human life.

Iot based smart home automation system

Abstract: The Internet of Things (IoT) is the network of devices such as vehicles, and home devices that contain electronics, software, actuators, connectivity which allows these things to connect, interact and exchange data. Automation is the technology by which a process is performed with minimum human efforts. Automation or automatic control is the use of discrete control systems for operating equipment. This paper is focused on five different techniques such as home automation system by using symmetric encryption scheme, Eet-based Smart Home intelligent system, by using set of sensors, low-cost Wi-Fi based automation system for Smart Home, monitoring and controlling the home appliances via World Wide Web. Even though, some issues arises in every method which are analyzed in analysis and discussion section. To improve these issues, this paper has proposed a new home automation technique with the use of IOT, so as to reduce the existing problems and make home automation more smart and secure. Index Terms Internet of Things (IOT), Home automation system.

Hybrid renewable energy system: a review

Abstract: The requirement of electrical energy is increasing in domestic as well as industrial applications. To meet the necessity of energy more resources are needed and furthermore environmental health should be taken care of. Due to use of conventional sources such as petroleum and coal, environment is debasing. As electric energy is the most reliable source of energy, generation of electric energy by using natural or non-conventional resources such as wind and solar energy is necessary. For generating more and more energy these resources should be used in efficient and smart manner. For that purpose this paper proposes a review of using hybrid of solar tracker and vertical wind mill.

Heart Disease Prediction System using Data Mining Techniques

Abstract: Cardiovascular disease is one of the most prevalent causes of death around the world and has deemed as a vital illness in older and Middle ages. Coronary artery disease is a general cardiovascular disease involving high death rates. Angiography is more frequently than not, regarded as the best system for the examination of coronary artery disease; on the other hand, it is connected with significant side effects and high costs. Much investigation has been conveyed using data mining and machine learning to attempt alternative modalities. In this research work, a novel Thrice Filtered Information Energy based Particle Swarm optimization Feature Selection method for identifying the relevant features in the classification of heart disease. Diagnosing the existence of heart disease is really tedious process, as it entails deep knowledge and opulent experience. As a whole, the forecast of heart disease lies upon the conventional method of analysing medical report such as ECG (The Electrocardiogram), MRI (Magnetic Resonance Imaging), Blood Pressure, Stress tests by a Medicinal expert. Nowadays, a large volume of medical statistics is obtainable in medical industry and turns as a excessive source of forecasting valuable and concealed facts in almost all medical complications. Thus, these facts would really aid the doctors to create exact predictions. The innovative methods of Artificial Neural Network models have also been contributing themselves in yielding the main prediction accuracy over medical statistics. This work targets to predict the presence of heart disease utilizing back propagation MLP (Multilayer perceptron) of Artificial Neural Network with the help of MATLAB tool.

Patient Monitoring System Based on Internet of Things

Abstract: The increased use of mobile technologies and smart devices in the area of health has caused great impact on the world. Health experts are increasingly taking advantage of the benefits these technologies bring, thus generating a significant improvement in health care in clinical settings and out of them. Likewise, countless ordinary users are being served from the advantages of the MHealth (Mobile Health) applications and E-Health (health care supported by ICT) to improve, help and assist their health. Applications that have had a major refuge for these users, so intuitive environment. The Internet of things is increasingly allowing to integrate devices capable of connecting to the Internet and provide information on the state of health of patients and provide information in real time to doctors who assist. It is clear that chronic diseases such as diabetes, heart and pressure among others, are remarkable in the world economic and social level problem. The aim of this article is to develop an architecture based on an ontology capable of monitoring the health and workout routine recommendations to patients with chronic disease.

Internet banking in india

Abstract: In the present day, demand for financial services transmuting rapidly and deportment of customers regarding these service going to transmute rapidly. Accordingly, it’s compulsory for the banking sector additionally that lieu of the traditional banking it should adopt electronic banking for sustaining as well as attracting the customers. Internet banking is the most pioneering trend among the customers in the present era for more expeditious and secured financial services. The transfer from the traditional banking to internet banking has been an elevating amendment in banking dealing. Enlarged competition, the advancement of information and communications technologies, and transmuting business environment, etc have coerced banking services to transmute. This paper explored the online customer services provided by the banks in India

Moringa oleifera - The miracle tree

Abstract: Moringa oleifera is a “Miracle Tree” because of all its part are use for nutritional , pharmacological properties . It is a tropical species that is known by various regional name as Drumstick , Moringo ,Saijhan and Sajna . Moringa is a very valuable food crop ( It is highly nutritive , grow very fast and drought resistant) . Moringa oleifera is a multipurpose herbal plant used as human food . Moringa oleifera contains essential amino acid, carotenoids in leaves vitamin A ,vitamin C , protein calcium and potassium so that this plant as a nutritional supplements. The leaves and branches can be used as food for livestock and fish.Due to high nutrient content of the leaves moringa can be incorporated into the mulching system . Moringa leaf powder can be used as a supplement to boost or stimulate the immune system of HIV / AIDS positive people . Global industrialization and the increasing demand for environmental friendly products make moringa have great potential as a source of pharmaceutical dyes , Biofuels , Human food , Animal and fish food and water purification products

Anorexia nervosa on college going adolescent female students and their socio-economic status on balasore district: an empirical study

Abstract: From the whole study it was found that, there are no such relation beauty high, medium and low socioeconomic status with anorexia nervosa. The socio-economic status does not affect the anorexia nervosa disease in college going adolescent female students at Balasore district. Also the parents are much more conscious with health and beauty of their daughters and always try to maintain a healthy life.

An Ensemble Multi-Model Technique for Predicting Chronic Kidney Disease

Abstract: Chronic Kidney Disease (CKD) is a type of lifelong kidney disease that leads to the gradual loss of kidney function over time; the main function of the kidney is to filter the wastein the human body. When the kidney malfunctions, the wastes accumulate in our body leading to complete failure. Machine learning algorithms can be used in prediction of the kidney disease at early stages by analyzing the symptoms. The aim of this paper is to propose an ensemble learning technique for predicting Chronic Kidney Disease (CKD). We propose a new hybrid classifier called as ABC4.5, which is ensemble learning for predicting Chronic Kidney Disease (CKD). The proposed hybrid classifier is compared with the machine learning classifiers such as Support Vector Machine (SVM), Decision Tree (DT), C4.5, Particle Swarm Optimized Multi Layer Perceptron (PSO-MLP). The proposed classifier accurately predicts the occurrences of kidney disease by analysis various medical factors. The work comprises of two stages, the first stage consists of obtaining weak decision tree classifiers from C4.5 and in the second stage, the weak classifiers are added to the weighted sum to represent the final output for improved performance of the classifier.

Rotary Automated Car Parking System

Abstract: The present project work is aimed to design and develop a working model of a Rotary Automated Car Parking System for parking 8 cars. This system has been implemented to reduce the excess use of land space which is already very scarce in metro cities. The chain and sprocket mechanism are used for driving the parking platform and a motor shall be implemented for powering the system and indexing the platform. It is an amalgamation of the already developed parking systems with the added advantage of reduced space occupancy by the design of a simpler and compact parking system that is rotary and occupies circular parking space. By testing and analyzing the working model we can definitely get the view to develop the parking lots at difficult and busy commercial places.

Design and Fabrication of Eddy Current Braking System

Abstract: The design of an eddy current disc brake system requires a multidisciplinary approach. Eddy Current braking utilizes electronic and magnetic power based on the principle of relative motion between a magnetic source and a metal. This braking system is an upcoming alternative to the traditional braking systems which utilize friction forces to transform the kinetic energy of a moving body into heat, and proves to have remarkable safety features and applications along with reasonably low maintenance cost. In this research work, with a view to enhance the overall efficiency and effectiveness of the braking system, a prototype model for eddy current braking system is be designed, fabricated and analysed. Keywords— Eddy Current Braking, Auxiliary Braking system, Brake Disc Design, Self-Aligning Vice, Magnetostatic Analysis, SIMULINK Modelling

Plastic waste management

Abstract: A trend of significant increase in plastic waste generation has been recorded worldwide. This has been found due to over population growth rate, industrialization, urbanization and economic growth which have ultimately resulted in increased plastic accumulation. In India 70 percent of total plastic consumption is discarded as waste. Around 5.6 million tons annum (TPA) of plastic waste is generated in country, which is about 15,342 tons per day (TPD). An efficacious management needs to be materialized for better planet to live in. The proposed work implements an automated waste segregator household level using microcontroller to control the entire process with ease and simplicity. The sensing unit consists of a capacitive proximity sensor to detect and segregate plastic wastes. The proposed systems would be best applied in industries that handle plastic shipped in from many sources including multiple numbers of municipal recycling facilities. Each of the sorting methods currently being researched would show a great promise in the future.

Towards reference models for requirements traceability

Abstract: A Reference model in systems, enterprise and software engineering is abstract framework or domain specific ontology consisting of an interlinked set of clearly defined concepts produced by an expert or body of experts in order to encourage clear communication. There are many uses of reference models. Main use of reference model is to create standards for both the objects that inhibit the model and their relationships. By creating the standards, the work of engineers and developers who need to create objects that behave according to the standard is made easier. In this paper we are proposing S-cube model of Quality reference model. Reference models are therefore an abstraction of best practice, condensed from many case studies over an extended period of time, followed by more case studies to refine and evaluate the proposed reference model. There are challenges towards the service-based systems. The network of excellence on software services and systems (S-cube) performs cross –discipline research to develop solutions for those challenges. In this paper we outlined the S-cube reference model life cycle and how is used to know how a service is developed. S-cube knowledge model which is a continuously updated on-line encyclopedia and a reference library. In this paper we are presenting about S-cube framework which is used to align and bring together the involved disciplines and co-existing of services.

A Novel Hybrid Passive Optical Network, Free Space Optical and Visible Light Communication System

Abstract: In this work, a hybrid architecture employing Single Mode Fiber (SMF) link followed by Free Space Optic (FSO) transmission and Visible Light Communication is investigated. FSO is incorporated in the system after optical fiber in order to serve optical network units wirelessly where deployment of optical fiber is tedious or impossible such as in hilly areas, intra educational buildings etc. Further, VLC is incorporated in the system to serve ONUs inside building with Light Fidelity. For optical fiber based users, data rate of 10 Gbps is provided over 25 km and total 8 ONUs are served at guaranteed 2.5 Gbps. FSO link after 25 km SMF and 450 m free space distance served additional 8 users at same bit rate as optical fiber users. For LiFi link, total bit rate of 1 Gbps has been achieved over 2 m link. Therefore, our proposed system has provisions for optical fiber based users, wireless FSO based ONUs and intra building ONUs. IndexTerms – PON, FSO, VLC, OLT, ONU.

Real-time emotion recognition from facial images using Raspberry Pi

Abstract: Now a days growing of technology and understanding of a human expressions . emotion.Emotion can understand by test,vocal,verbal and facial expressions.Facial expression enrich source of communicative human behaviour activeness or dull mood ,it can be verified and emotion. Facial expression recognition is challenging problem upto now because of many region,moreover,it consists of three sub challenging face detection, facial featureextraction and expression classification.Automatic face images is an analysis of to identify human -machine interaction and interesting topic important application in the field of information and machine-human interaction driven animation ,it is a successful expression finding in the field of science and technology emotion expression recognition . Most of the system are able to recognize basic prototype emotion like Happy,Sad,Surprise, Anger ,fear and disgust.This general expression are detected using certain varitions of facial expression like broadening of mouth ,closing of eyes,twitching of noise,etc.. Applying the extraction of fast robudt facial image exyraction based on applying classified filter to the image filters to the image. The proposed method implements facial image capture from the web camera using three steps face detection, features extraction and classification classifier of emotions. The proposed method uses raspberry pi for implementing emotions recognition. Keywords— Feature extraction, Active shape Model, Adaboost classifier, Raspberry pi

Attendance system based on facerecognition

Abstract: Now-a-days most of the time is wasted for taking attendance in a class by a person manually. Still, students are manipulating the attendance by making false attendance, proxy and leading to incorrect attendance. We came with a proposal of attendance system based on face recognition. Face Recognition is widely used for security purpose and to verify attendance statistics of a student in the class room. The system uses a combination of techniques in machine learning. First, we detect a face in the given image then train the system with a detected face. Face detection is done using OpenCV. Training is done with a number of images of the same person taken at different angles with machine learning algorithms like neural networks, regression. During training, an image is given with details of the person. we also use focus points to distinguish people. Finally, after training system it takes input as video and detect face, identify the name and id of the person in the video and gives output as attendance to the student in excel format. To reduce wastage of time for taking attendance, false attendance and proxy we implement this project as one of the solutions.

On the lattice of - fuzzy ideals of a lattice

Abstract: In this paper we prove that for a lattice , the family of all -fuzzy ideals are also lattices.We further claim that the lattice of all -fuzzy ideals is infact a sublattice of the lattice of all -fuzzy sublattices.

AI Based Voice Assistant Using Python

Abstract: Artificial intelligence technologies are beginning to be actively used in human life, this is facilitated by the appearance and wide dissemination of the Internet of Things (IOT). Autonomous devices are becoming smarter in their way to interact with both a human and themselves. New capacities lead to creation of various systems for integration of smart things into Social Networks of the Internet of Things. One of the relevant trends in artificial intelligence is the technology of recognizing the natural language of a human. New insights in this topic can lead to new means of natural human-machine interaction, in which the machine would learn how to understand human’s language, adjusting and interacting in it. One of such tools is voice assistant, which can be integrated into many other intelligent systems. In this paper, the principles of the functioning of voice assistants are described, its main shortcomings and limitations are given. The method of creating a local voice assistant without using cloud services is described, which allows to significantly expand the applicability of such devices in the future.

A convolutional neural network (cnn) approach to detect face using tensorflow and keras

Abstract: Face recognition is used in a variety of aspects in the modern world. Face detection means to identify the face from a digital image. The deep neural network is considered a powerful tool as it can handle huge amounts of data .conventional neural network is one most popular tool to detect face detection. In this paper, a deep convolutional neural network (CNN) to extract features from input images. Keras is used for implementing CNN also D’lib and OpenCV for aligning faces on input images. Face recognition performance is evaluated using a custom dataset.

A Review Paper on E-Commerce

Abstract: E-commerce means E-commerce. It involves dealing with goods and services via the electronic media and the Internet. E-commerce includes the use of the Internet and the use of information technology such as Electronic Data Interchange (EDI), to run a business. ECommerce refers to a vendor's website on the Internet, which sells products or services directly from the company to the consumer. The platform uses a digital shopping cart or digital shopping basket system which makes payment by credit card, debit card or EFT (transfer of electronic funds). A more detailed definition is: e-commerce is the use of electronic communications and digital information management technologies in business transactions to establish, turn, and redefine value-creating relationships between or between companies and between individuals (C. Nisha and G. Sangeeta, 2012). The main types of online trade include: Business-to-Business (B2B); Business-to-Consumer (B2C); Business-to-Government (B2 G); Customer (C2C); and Mobile Commerce (Mcommerce).

On energy of graphs

Abstract: The concept of energy of graph was introduced by I. Gutman in the year 1978. Let G be a graph with n vertices and m edges and let A = (aij) be the adjacency matrix of a graph. The eigen values λ1, λ2, ... , λn of A assumed in non increasing order, are the eigenvalues of the graph G. As, A is real symmetric, the eigen values of G are real with sum equal to zero. The energy E(G) of G is defined to be the sum of the absolute values of the eigen values of G. i.e., E(G) = ∑ |λi| n i=1 . In this paper, the relation between the energies of some standard graphs are compared with their Middle, Inflated and Product graphs. AMS Subject Classification: 05C50

Impact of demonetization: organized and unorganized sector

Abstract: The argument posited in favour of demonetization is that the cash that would be extinguished would be “black money” and hence, should be rightfully extinguished to set right the perverse incentive structure in the economy. While the facts are not available to anybody, it would be foolhardy to argue that this is the only possibility. Therefore, it is imperative to evaluate the short run and medium-term impacts that such a shock is expected to have on the economy. Further, the impact of such a move would vary depending on the extent to which the government decides to demonetize. This paper elucidates the impact of such a move on the availability of credit, spending, and level of activity and government finances.

Evolution of Blockchain Technology in Business Applications

Abstract: Blockchain technology is an invention where digital transactions refer to distributed database without the need of third party intervention and authentication. In present time several organizations in various disciplines are adopting this technology which has transparency, integrity, efficiency in cost and time. Its unique technology is being adopted in various industries like banking, legal, healthcare, rentals, education and many more. The intention of this paper is to outline the Blockchain technology and its function in various domain.