Arsenic is a natural element of the earth’s crust and is commonly distributed all over the environment in the air, water and land. It is extremely poisonous in its inorganic form. Arsenic (As) contamination is one of the leading issues in the south Asian countries, ground water is major sources of drinking water. The highest risk to public health from arsenic originates from polluted groundwater. Arsenic is naturally present at high levels in the groundwater of south Asian countries. Pakistan also one of them which is highly affected by this toxic element, especially rural areas of Sindh Pakistan, where Ground water is the only source of drinking. Due to climates changes day by day value of arsenic is increased in Ground water, that effects the human health in form of many diseases like skin cancer, blood cancer. The purpose of this study is to figure out the increasing level of Arsenic and Cancer rate in Tando Muhamad Khan Sindh Pakistan for next coming five years. For this we have developed model using Microsoft Azure Machine learning Techniques and algorithms including Bayesian Linear Regression (BLR), support vector machine (SVM), Linear Regression (LR), Boosted Decision tree (BDT), exponential smoothing ETS, Autoregressive Integrated Moving Average (ARIMA). Developed model will help us to forecast the increasing rate of Arsenic and its effects on human health in form of cancer.

Handwritten Identification is an ability of the computer to receive and translate the intelligible handwritten text into machine-editable text. It is classified into two types based on the way input is given namely: off-line and online. In Off-line handwritten recognition, the input is given in the form of the image while in online input is entered on a touch screen device. The research on off-line and online handwritten Sindhi character identification is on its very initial stage in comparison to other languages. Sindhi is one of the subcontinent's oldest languages with extensive literature and rich culture. Therefore, this paper aims to identify off-line Sindhi handwritten characters. In the proposed work, major steps involve in characters identification are training and testing of the system. Training is performed using a feed-forward neural network based on the efficient accelerative technique, the Back Propagation (BP) learning algorithm with momentum term and adaptive learning rate. The dataset of 304 Sindhi handwritten characters is collected from 16 different Sindhi writers, each with 19 characters. The novelty of proposed work is the comparison of the recognition rate for the single character, two characters and three characters at a time. Results showed that the recognition rate achieved for a single character is more than the recognition rate of multiple characters at a time.

One of the major concerns in teaching and learning programming concepts is the complexity of syntax and precision of semantics of programming languages. Traditional teaching methods are static and passive i.e. they do not engage students in an interactive manner thereby making it difficult for students to grasp the contents and instructors to convey the instruction. This obstacle even becomes challenging when programming courses are to be taught to beginners. To cope up with this challenge, this work has proposed and prototyped a system that is aimed to focus on students at their middle level of education. Multimedia technology i.e. videos have been used to plunge the students in an interactive environment where learning JavaScript programming becomes fun instead of a mind-burden. Visualization concepts have been incorporated to provide visual learning for variables, loops, control structures, functions etc. This application is dynamic in nature that is user can not only understand the programming concepts but can also run the codes using code panel. The designed system has been tested to ensure the functionality, performance and feedback from the targeted users as discussed in results section.

Traffic Analysis has been a problem that city planners have dealt with for years. Smarter ways are being developed to analyze traffic and streamline the process. Analysis of traffic may account for the number of vehicles in an area per some arbitrary time period and the class of vehicles. People have designed such mechanism for decades now but most of them involve use of sensors to detect the vehicles i.e. a couple of proximity sensors to calculate the direction of the moving vehicle and to keep the vehicle count. Even though over the time these systems have matured and are highly effective, they are not very budget friendly. The problem is such systems require maintenance and periodic calibration. Therefore, this study has purposed a vision based vehicle counting and classification system. The system involves capturing of frames from the video to perform background subtraction in order detect and count the vehicles using Gaussian Mixture Model (GMM) background subtraction then it classifies the vehicles by comparing the contour areas to the assumed values. The substantial contribution of the work is the comparison of two classification methods. Classification has been implemented using Contour Comparison (CC) as well as Bag of Features (BoF) and Support Vector Machine (SVM) method.