Worldwide, suicide rate is considered one of the most significant issue. With each passing year, the number of suicide is getting increased phenomenally and because of this reason, this research is carried out to predict the causes of suicide in India by using the machine learning algorithms and data mining techniques in order to identify the root causes behind the suicide so that the authorities can take advantage in order to prevent the suicide cases by creating awareness and by rectifying the predicted causes of suicides. According to a research, about 800,000 people commit suicide worldwide every year. Out of these, 135,000 (17%) are residents of India, a nation with 17.5% of world population. In this research, we have analyzed the pattern of suicide cases and predict the causes of future suicides by using machine learning algorithms, the Artificial Neural Network and Support Vector Machine.

Requirement engineering (RE) process is an important step of software development lifecycle and it includes a variety of activities starting with requirement elicitation to requirement documentation. This form of engineering is the backbone of a quality product. This research focus on the attention for requirement engineers to understand the criticality of requirement specification and how a complete, consistent requirement can be extracted using an Ontology. It covers the intrinsic knowledge of the domain into machine readable easy format and requirement represented in Ontology serves as the formal representation of natural language context in a model. It is often the case in software development that requirement creep leads to an unpredictable stage in software lifecycle which becomes hard to handle. Many techniques to improved requirement specification has been tested but this paper address how user stories are represented in Ontology model by extracting the main classes of Role, Object and Action from the user and later building a model based on these core concepts along with property link for relating the three basic root classes for completion.

Traffic controlling and management is a severe issue of urban cities as well as on high ways in developing countries like South Asian countries but here particularly, in Pakistan. The traffic congestion problem is becoming more severe with time. The main reason behind all this is a drastic increase in number of running vehicles and no proper road infrastructure. Not only, the traffic congestion is a problem, whereas, the other problems are also associated with this issue are air pollution, wastage of resources like fuel, energy, time etc. are the foremost anomalies faced by every human being of third world countries. It is also one of the major reasons of global warming and exploitation of natural life system. Currently, in Pakistan traffic controlling is done through time based traffic control signal system normally. In this paper, we have proposed a system which dynamically controls and manage the road traffic through image processing on real time and will take the decision on actual grounds for traffic routes and on traffic signal timing. In this system, we utilize the latest technologies of image processing which collects, organize and transmits the information to existing system to incorporate the new real time data for traffic timing control. It will save the people from road accidents and unnecessary wastage of fuel resources and more importantly make the life little bit more relax then others.

A foreign object, commonly called as a ghost artifact, is integrated in the HDR output image when there is a moving object in the photography scene. The problem is persisting even after numerous models proposed by researchers. The most advanced techniques for capturing HDR photographs are still struggling with the produced output till date. The majority of the existing techniques are unable to tackle the situation where luminance varies in the input images. This ultimately causes the algorithms to compromise on quality by reducing the input images. In this research, two techniques are presented that help in getting rid of ghost artifacts from HDR output. The first method that is used in this research is a vintage method that uses structural similarity index measurement. The second method is using Convolutional Neural Network that is proved to be the best configuration of neural network for image recognition purpose. The first method using structural similarity is based on the vintage method of matching two images. This method works by comparing the objective image with the reference image and the algorithm estimates the degree of similarity in context of luminance, contrast and structural information. The second method is the use of convolutional neural network. Since convolutional neural network is a specialized tool for image processing, a convolutional neural network is designed and trained to estimate the index of similarity of two or more images.

The internet is playing a major role in providing financial services in Banking, leading to competitive edge in gaining banking customers, who would like essential banking services to be availed anywhere and at any time. The purpose of this research is to analyze the effect of Technology Acceptance Model (TAM) on internet banking in Pakistan, Perceived Security Concern and Perceived Privacy Concern on Intention to Use fulfilling the academic gap identified as there is a lack of organized and comprehensive studies analyzing practical implications of Technology Acceptance Model in Internet Banking in Pakistan. This cross-sectional study is based on the deductive approach and the explanatory strategy. Upon doing a correlation analysis between the variables, findings suggest a strong positive correlation between TAM, Perceived Security Concern, Perceived Privacy Concern and Perceived Trust on Intention to Use.