Nowadays, online reviews have become a valuable resource for customer decision making before purchasing a product. Research shows that most of the people look at online reviews before purchasing any product. So, customers reviews are now become a crucial part of doing business online. Since review can either promote or demote a product or a service, so buying and selling fake reviews turns into a profitable business for some people now a days. In the past few years, deceptive review detection has attracted significant attention from both the industrial organizations and academic communities. However, the issue remains to be a challenging problem due to the lack of labeled dataset for supervised learning and evaluation. Also, study shows that both the state of the art computational approaches and human readers acquire an error rate of about 35% to 48% in identifying fake reviews. This study thoroughly investigated and analyzed customers’ online reviews for deception detection using different supervised machine learning methods and proposes a machine learning model using stochastic gradient descent algorithm for the detection of spam review. To reduce bias and variance, bagging and boosting approach was integrated into the model. Furthermore, to select the most appropriate features in the feature selection step, some rules using regular expression were also generated. Experiments on hotel review dataset demonstrate the effectiveness of the proposed approach.

Monitoring and Evaluation (M&E) system are used across the world by organizations or governments to track progress, measure and evaluate outcomes of projects. Organizations can improve their performance, effectiveness and achieving results in project success by strengthening their monitoring and evaluation systems. Moreover, various studies reveal the need for information and communication technology systems in monitoring and evaluation activities because most of the government organizations do not employ computerized monitoring and evaluation systems and those having these systems lack a systematic early informing mechanism of the projects' progress. Currently, the Ministry of Health in Tanzania monitors and evaluates its projects manually, due to this, they face the risks and challenges during the implementation of projects because of a lack of having timely adoption of remedial action. Monitoring and evaluation staffs spent a lot of time in manual work, manual compilation of data, due to data being in separate systems, delay in submission of data, data is lost between primary registries to monthly summaries, from monthly to quarterly summaries, system does not contain all details about projects/program as well as budget information, no early alert information about the status of the project, poor information sharing among stakeholder.
In this study, we collect representative data from three monitoring and evaluation staff, four ICT staff and five project members by using interviews, focus group discussion and document review. The result showed that the electronic monitoring and evaluation system will solve a presented challenge. Development of a web-based monitoring and evaluation system for the ministry of health projects will provides timely, accurate information, that for tracking the implementation progress of projects improved monitoring and evaluation.

The voting system in the world has been characterised with many fundamental challenges, thereby resulting to a corrupt contestant winning an election. Researchers have been emotionally, physically, socially and intellectually concerned about the election malpractices recorded at various levels of electing a representative. Questions on how corrupt stakeholders in elections could be prevented from fraudulent activities such as rigging and impersonation called for discussion and answers. Consequences of declaring a corrupt contestant as a winner are bad governance, insecurities and diversification of public funds for personal gains. There must be approaches to tackle the problems of voting systems. This paper focused on a comprehensive review of electronic voting systems by different scholars as a platform for identifying shortcomings or drawbacks towards the implementation of a highly secured electronic voting system. The methods used by different scholars were technically reviewed so as to identify areas that need improvement towards providing solutions to the identified problems. Furthermore, countries with history on the adoption of e-voting systems were reviewed. Based on the problems identified from various works, a novel for future work on developing a secured electronic voting system using fingerprint and visual semagram techniques was proposed.

Artificial Intelligence (AI) has a huge scope in automating, stream- lining, and increasing productivity of Music Industry. Here, we look upon AI based techniques for classifying a piece of music into multiple genres and then later converting it into another user-specified genre. Plenty of work has been done in classification, but using traditional machine learning models which are limited in term of accuracy and rely heavily on features to train the model. The novelty of this work lies in its attempt to covert genre of music from one type to another. This paper focuses on classification achieved by using a model trained via Convolutional Neural Networks. Conversion of music genre, a relatively less worked upon field has been discussed in this paper along with details of implementation. For Conversion, we initially convert the input file to spectrogram. A database of all genre is maintained at all times and a random file from user selected genre is also converted to spectrogram. Later, these spectrograms are processed and converted back to signals. Finally the user can listen to the converted audio file. Validation of the conversion was performed via a survey with the help of end users. Thus, a novel idea of doing Music Genre Conversion was put forth and was validated with positive outcomes.

From the past decade there has been drastic development and deployment of digital data stored in electronic health record (EHR). Initially, it is designed for getting patient general information and performing health care tasks like billing, but researchers focused on secondary and most important use of these data for various clinical applications. In this paper we used deep learning based clinical note multi-label multi class approach using GloVe model for feature extraction from text notes, Auto-Encoder for training based on model and Navie basian classification and we map those classes for multi- classes. And we perform experiments with python and we used libraries of keras, tensor flow, numpy, matplotlib and we use MIMIC-III data set. And we made comparison with existing works CNN, skip-gram, n-gram and bag-of words. The performance results shows that proposed frame work performed good while classifying the text notes.