Manuscripts

Recent Papers

Research Paper

A new mechanism on hate speech detection with hateful and offensive expressions on Twitter using various machine learning techniques

A lethal online substance has turned into a noteworthy issue in this day and age because of an exponential increment in the utilization of the web by individuals of various societies and instructive foundation. Separating hate speech and offensive language is a key test in the programmed detection of dangerous content substance. In this paper, we propose a way to deal with naturally order tweets on Twitter into three classes: hateful, offensive and clean. Utilizing Twitter dataset, In this paper, we propose a way to deal with distinguish hate expressions on Twitter. Our methodology depends on unigrams and examples that are consequently collected from the preparation set. These examples and unigrams are later utilized, among others, as highlights to prepare a machine learning calculation. Our analyses on a test set made out of 2010 tweets demonstrate that our methodology achieves an exactness equivalent to 87.4% on identifying whether a tweet is offensive or not (twofold classification), and precision equivalent to 78.4% on distinguishing whether a tweet is hateful, offensive or clean (ternary classification).

Published by: Md. Ah Hassan Rayon Hussain

Author: Md. Ah Hassan Rayon Hussain

Paper ID: V5I2-1881

Paper Status: published

Published: April 16, 2019

Full Details
Review Paper

A review on casting defects reduction in a foundry shop using DMAIC technique

To become globally compatible and to gain business as well operational excellence industries are implementing various quality improvement initiatives like Lean manufacturing, ISO certification, Total Quality Management, Quality Circle, etc.. But results explored by these initiatives are time constrained and not that much profitable. So methodology, which can provide breakthrough improvement in a short time, is required to be introduced and implemented. Six Sigma is the same methodology which can provide breakthrough improvements in a short time period, so it is very essential to explore its application for gaining quantum gains and profit in terms of quality, market share and customer satisfaction.

Published by: Wasim Ahmad, Anil Verma, Priyanka Jhavar

Author: Wasim Ahmad

Paper ID: V5I2-1952

Paper Status: published

Published: April 16, 2019

Full Details
Review Paper

Gujarati word recognition

In this paper, we describe various techniques of character recognition for Gujarati text detection. We usually use OCR for character recognition. For the development of Gujarati text detection tool, we use the review of this paper. Recognition and its types can be described with the help of basics. A special property of the text can be taken into consideration while recognition process going on.

Published by: Monika Sudhakar Ugale, S. T. Patil

Author: Monika Sudhakar Ugale

Paper ID: V5I2-1878

Paper Status: published

Published: April 16, 2019

Full Details
Research Paper

Virtual reality of interior architecture

VR is an interactive computer-based on experience takes place within a simulated environment. It always gives in mainly auditory and visual feedback but may also allow other types of sensors. The environment created by virtual reality can be similar to the real world. By implementing our project in Virtual Reality, it has become convenient for the market value also for business purpose. Lots of manpower and resources are wasted in the civil engineering field. In order to use man power efficiently, the planning of jobs should be done well in advance. Usually, the 3D model is done using unity gaming software. In this virtual reality plays an important role in making the human efforts to the zero. In our project, we have implemented the sample room of a flat in the vr3d model. Basically in civil field builder spends lakhs of money In building the sample rooms to show to their customers, implementing VR room it has made very simple and efficient for the purpose of making sample rooms. It is very economical. The virtual reality is based applications require a significant level of effort in creating a virtual environment that represents the real world. To save the money that will be wasted by building sample rooms we can simply render the sample room in virtual reality. This will save the cost, resources, and manpower that will be needed for future development purpose.

Published by: Sneha More, Tejas Wagh, Yugant Suryawanshi

Author: Sneha More

Paper ID: V5I2-1916

Paper Status: published

Published: April 16, 2019

Full Details
Others

E-attendance system using face recognition

Traditionally, the attendance of the students has been a major concern for the colleges and the faculties have to spend quite some time of their lectures for taking the attendance manually. In this paper, we are introducing a new way of attendance monitoring by making use of smartphones available with the teachers. We have suggested the use of YOLO algorithm for face detection and Siamese network for face recognition. This system will automatically mark the attendance of the students and thereby save the time and efforts for the faculties. The designed system will be quite efficient and reliable as Siamese network has proven to render high accuracies in face recognition.

Published by: Aditya Ladage, Pooja Pache, Sahil Maniar, Sheetal Pereira

Author: Aditya Ladage

Paper ID: V5I2-1866

Paper Status: published

Published: April 16, 2019

Full Details
Research Paper

The Internet of Things: applications and security metrics with the Ugandan perspective

As the Internet of Things (IoT) increasingly becomes a reality, thousands of devices get connected to IoT platforms in smart cities and regions. These devices will actively send data updates to cloud-based platforms, as part of smart applications in various domains like healthcare, traffic, and education among others. Therefore, it is important to assess the ability of modern IoT systems to handle high rates of data updates coming from devices. The paper aims at developing metrics that can be used to assess the IoT cybersecurity status of a country in terms of the Intensity, Readiness, and Adoption with a special focus of Uganda as a case study. To achieve this, a design science approach was employed. Data were collected from a sample of 127 respondents from 7 firms around Kampala district. Finally, the impact of the proposed metrics is demonstrated through an application to the IoT assessment model.

Published by: Davis Matovu, Mugeni Gilbert B., Karume Simon, Mutua Stephen, Gilbert Gilibrays Ocen

Author: Davis Matovu

Paper ID: V5I2-1859

Paper Status: published

Published: April 16, 2019

Full Details