Asian Journal of Convergence in Technology
Not a member yet
868 research outputs found
Sort by
Analyzing the Classification Accuracy of Deep Learning and Machine Learning for Credit Card Fraud Detection
Get PDFThe purpose of this study is to classify a dataset of credit card security problems by employing six different machine learning (ML) approaches. The Support Vector Machine (SVM), Random Forest (RF), Bagged Tree, K-Nearest Neighbor (KNN), Naive Biased Classifier, and Extreme Gradient Boosting were selected as the classifiers to use (XGBoost). The classification accuracy of the machine learning algorithms was compared with that of a technique for categorization that is based on deep learning called Long Short-Term Memory (LSTM). The KNN machine learning approach had a maximum accuracy of 97.50 percent, while the LSTM machine learning method had an accuracy of more than 96 percent and promised to give biologically appropriate control of upper-limb movement. In addition to enhancing accuracy, the research has investigated how the effects of removing the channel with the most noise from the algorithms can have on accuracy. This was done in an effort to handle data in a more effective manner
A Review on Comparative analysis and methods of Early detection of Brain tumor using Deep Learning CNN
Get PDFAccording to the last Report of International Association of Cancer Registries which is a Global cancer observatory of World health organization has reported 28,000 cases in India each year and more than 24,000 people reportedly die due to brain tumor annually. Harmful Brain tumor have three types that is Glioma, Meningioma and Pituitary tumor. For image data of brain tumor, MRI and CT Scan are mostly used. But as per research study, MRI is used more compare to CT scan and others. Deep learning has a capability to work on very deep neural network process. Convolutional neural network works on more efficient way to improve object detection. The Aim of this paper is to compare different pretrained convolution neural network based developed methods and models to predict or detect tumour symptoms early through Image data using Deep Learning technique. The main focus of this paper about study and review of different CNN models, algorithms, datasets and compared their results for accuracy as well as pictorial view of the tumor shape
Chrome Extension for Misinformation Detection
Get PDFMisinformation can be stories, hoaxes, or news deliberately created to spread false news and deceive readers. Fake news has always been a part of our lives. However, it has become a topic of interest only recently. Majorly due to the rise of SOCIAL MEDIA. As stated in news articles the Supreme Court condemns these actions and advice a regulatory mechanism. As the use of social media has increased so, has the number of unreliable sources. During covid, there was a variety of misinformation floating around like, applying cow dung can cure covid. In reality, cow dung can't cure covid but can cause black fungal infection. Some other examples include inciting religious sentiments, causing chaos, and harming someone's reputation. Therefore, detecting fake news and stopping it from spreading is necessary. In this model, I have applied TF-IDF vectorizer and Passive Aggressive Classifiers to train my model. After the training and testing have been completed, a local server using Flask has been set up to assist in the development of the second phase of the project, which is Chrome Extension. The Chrome Extension is called Gossip Checker and sends selected data to the model and returns a predicted score of 0 and 1, where 0 means the data is reliable and 1 is not
Sustainable Path for Successive Internet Marketing in India
Get PDFInternet marketing is a platform which used to promote the market products, to make strategies, understand the market structure to take decisions. The purpose is to using internet marketing to sell goods and services, & advertising over the internet. Now a days business are practiced internet marketing to promote their goods & services with cost effective. The purpose of this research paper is to study the impact of digital marketing and how important it is for marketers. This paper begins with an introduction of digital marketing, how it effects to organizations and marketers. It highlights the customer perception towards internet marketing factor, revenue increasing factors of internet marketing, analyse the swot analysis of the market and industry, importance of digital marketing in today’s era. It is the avenue of electronic communication which is used by the marketers to endorse the goods and the services towards the marketplace. The research area covered in Mysore region; the 450 respondents were collected as samples. The research followed convenience sampling technique. The research is based on primary and secondary data sources
From Technology to a Business Offer: An Approach based on Design Innovation towards a workaid for Technologists as Startup Entrepreneurs
Get PDFTechnology has a critical role to play in fulfilling a certain human need. But technologists often look for guidance to take the technology to market. This is where a perspective through Design Innovation can aid to convert the technology into a Business Offer, which is the first step for the technologists as Startup Entrepreneurs to go to market.Design Innovation is at the core of the intersecting dimensions of human desirability, technological feasibility, and financial viability. It is harnessed through the practice of creativity based Design extending to Innovation. Design Innovation addresses the entire realm of technology intervention fulfilling a human need through the respective business offer.By introducing the perspective on Design Innovation, it provides for the required guidance and approach for technologists, as they endeavor to go to market as Startup Entrepreneurs. This paper is about developing this approach based on Design Innovation, in adherence with Design Research Methodology
Additive Manufacturing: A Brief Study on Selecting Laser Melting Technology
Get PDFIn today’s day and age of technological advancement, manufacturing plays a vital role in safeguarding our present and building our future. The different ways of machining materials has evolved gradually from the Stone Age to the Iron Age and so on and has reached a point where human civilization has achieved creation of unimaginable technologies to build this world in a better and more efficient way. Additive manufacturing is such an aspect of this technological milestone which is developing vastly. This is a work on additive manufacturing technologies, specifically the use of Selective Laser Melting methods and a discussion of different aspects related to it, such as the processing parameters and the material properties and characteristics of the fabricated part. In simple words, Selective Laser Melting is an Additive Manufacturing method where a high power laser beam is used to melt powdered form of material and put this molten material layer by layer to fabricate the desired part. This review work enlightens the use of Selective Laser Melting in today’s world. This review work provides vital information with regards to the parameters, material properties, material selection and an overview of additive manufacturing specifically the selective laser melting method
Image Captioning from Wikipedia for Multi-Language using Deep Learning Models
Get PDFWith the advancement in deep learning, the consolidation of text classification and image processing has agitated enormous scrutiny in the past years. Captioning images are advanced research mainly in the field of computer vision. Identification of relevant items, their properties, and their connection in images is required for image captioning. This image captioning is a complex and challenging task, several developments are done in this field by researchers. But now, Technology can develop a model that can bring out the closest text or captions explaining an image because of the advancement in deep learning methodologies and the enormous amounts of data that is available. In the beginning, it was contemplated impractical that a computer could characterize an image
Blockchain and Edge computing for Industrial Internet of Things (IIoT) Applications.
Get PDFToday IIoT is widely used in a wide range of Internet applications for items outside the consumer space and the iot business market, such as the umbrella name for applications and case applications in many industrial sectors. The goal of this paper is to highlight the ease of application of iiot(Industrial Internet Of Things) using Blockchain and Edge computing it also highlight various challenges of blockchain for iiot and with respect to that their approachable solutions. It also gives a detailed study of Deployment of edge computing in iiot sector
Utilizing the Internet of Things, Monitoring and Protecting System for Automated Teller Machines
Get PDFFor the vast majority of people in modern society, ATMs are the preferred method of cash withdrawal. ATM robberies have happened even in locations where CCTV cameras are installed at the ATM facility. The security mechanism will need to be tweaked. To combat these types of robberies, we developed a theft protection system for ATMs that makes use of cutting-edge technology. This system also looks at various physical assaults using ATMs. The device we propose to utilize to take an image of the individual entering the system is a Face Recognizing Camera. Anomaly behavior at an ATM can be detected using sensors that measure tilt and vibration. Any strange conduct will be detected by the LED light and buzzer, which will alert security personnel, the ATM machine will act like money withdrawing. Our system’s main goal is to send out a warning via email or other social media. IoT and GSM networks are used by both Facebook and Instagram. An alert will sent to the security force and a fake transaction process will be set to confuse the suspect. To avoid the unwanted incident after a certain time some anesthetic gas will be released, to make the suspect unconscious. Monitoring and control are now become easier because to this technology
The use of IoT to solve Farming Problems
Get PDFAs with every other field, IoT is moving into farming, providing plants with the right amount of water, nutrients, sunlight and heat. Though historically planting has always been in soil, they do not consume SiO2. Water and nutrients can be supplied if the roots are in a container of water and the plants are provided mechanical support; such hydroponics have achieved 30-50% faster growth, utilizing much less space/output, using 1000% less water and light either from the sun through greenhouses or from LEDs. Such systems have enabled the tiny country of Netherlands to become the second largest exporter of food in the world. If such technologies are exported, the world will be free from the ever-worrisome food crisis. For this research, tomato plants were grown in a coco pit mixed with perlite in four Dutch buckets and compared to the control plants grown in pots left in the prevailing environment outside and watered daily. The variables monitored are moisture, temperature, pH and nutrient levels. Data from sensors were sent to a laptop over Bluetooth. The usage of solar panels to power the system was also studied. The result indicates a 34 - 67% better characteristics for the plants grown with the modern techniques compared to the control.