Research Interests:
Research Interests:
For one to remain afloat in business, the best marketing technique is to maintain the current customers rather getting new ones [1]. [2] Shows that it costs more to get a fresh client than maintaining the available ones. An organization... more
For one to remain afloat in business, the best marketing technique is to maintain the current customers rather getting new ones [1]. [2] Shows that it costs more to get a fresh client than maintaining the available ones. An organization that intends to keep its customers must speculate which of them is at risk of abandoning their service and put all their concentration on those customers in an effort to retain them. This paper’s contribution is to create a prototype, which aid banks to foretell clients that are prone to abandon their service. This paper makes use of four algorithms namely Gradient boost, Random forest, Adaboost and Decision tree to classify and segment bank clients based on a number of features. The paper then selects the best performing algorithm, that is Random forest , to build a prediction model that can used by banks to identify the most likely clients to churn away.
Research Interests:
Research Interests:
In our daily lives, we take our friends opinions and sometimes influenced by them in our decision making process. Any kind of organization usually makes use of suggestion box to ascertain how its stakeholders feel about their services,... more
In our daily lives, we take our friends opinions and sometimes influenced by them in our decision making process. Any kind of organization usually makes use of suggestion box to ascertain how its stakeholders feel about their services, but few people make use of it. More people are using internet on a daily basis, the researchers developed an internet based system to enable stakeholders to input their opinions. Sentiment analysis has been used to evaluate the stakeholder’s comments. Vadersharp was used as the basis for opinions, which is a common lexicon that contains data that have the same semantic meaning or sense across different domains. The opinions are analyzed and classified into positive, negative or neutral sentiment. Sentiment analysis computationally analyses the public emotions and attitude towards a particular subject. It is useful in monitoring business operations as it allows decision makers to gain an insight of the public opinion behind certain topics. Index Terms ...
Mobile application development of mobile applications is a fast growing as well as challenging field because of many diverse platforms and their software development kits. In a bid to ease the cost of software development and reach out to... more
Mobile application development of mobile applications is a fast growing as well as challenging field because of many diverse platforms and their software development kits. In a bid to ease the cost of software development and reach out to many users across several platforms, developers are preferring to use cross platform application development tools. This paper, looks at several write-once-run-anywhere tools like HTML 5, Codename One, Xamarian and Apache Cordova. It looks at their requirements, strengths and weaknesses. A comparative analysis is done on the available cross platform mobile application tools on the market together with a discussion on the general architecture for cross platform application development. This paper also looks at the possible future of mobile application development. Keywords-Android, Xamarian, Codename One, HTML 5, Cordova, Phone gap, Mobile development, cross platforms
Research Interests: Business, Mathematics, Computer Science, Algorithms, Software Engineering, and 15 moreProgramming Languages, Human Computer Interaction, Information Technology, Technology, Educational Technology, Web Design, Software Engineering education, Zimbabwe, Application Programming, JSON, Computer Science Engineering, Payment, Application Programming Interfaces, Computer Science and Engineering, and Application Programming Interface (API)
Research Interests:
Research Interests:
In the context of exploratory testing (ET), human knowledge and intelligence is applied as a test oracle. The exploratory tester designs and executes the tests on fly and compares the actual output produced by the application under test... more
In the context of exploratory testing (ET), human knowledge and intelligence is applied as a test oracle. The exploratory tester designs and executes the tests on fly and compares the actual output produced by the application under test with the expected output in the testers' mind. The shortcoming of human oracle is that they are fallible, that is exploratory testers do not always detect a failure even when a test case reveals it. Depending on a human tester to evaluate program behaviour has also some problems such as cost and correctness. Therefore, in this paper an effort has been made to explore the feasibility of using a multilayer perceptron neural network (MLP-NN) as an exploratory test oracle. The MLP-NN was improved by adding another weight on each connection to perfectly generate reliable exploratory test oracles for transformed different data formats.
Research Interests:
In this paper, the performance and feasibility of a hybrid wavelength division multiplexing/time division multiplexing passive optical network (WDM/TDM PON) system with 128 optical network units (ONUs) is analysed. In this system, triple... more
In this paper, the performance and feasibility of a hybrid wavelength division multiplexing/time division multiplexing passive optical network (WDM/TDM PON) system with 128 optical network units (ONUs) is analysed. In this system, triple play services (video, voice and data) are successfully communicated through a distance of up to 28 km. Moreover, we analysed and compared the performance of various modulation formats for different distances in the proposed hybrid WDM/TDM PON. NRZ rectangular emerged as the most appropriate modulation format for triple play transmission in the proposed hybrid PON.
Research Interests:
The role of the intrusion detection system is to enforce the pattern matching policies decided for the network. Basically Proposed IDS executes on the KDD'99 Data set, this data set is used in international level for... more
The role of the intrusion detection system is to enforce the pattern matching policies decided for the network. Basically Proposed IDS executes on the KDD'99 Data set, this data set is used in international level for evaluating/calculating the performance of various intrusion detection systems (IDS). First step is association phase in which frequent item set are produced by apriori algorithm. The second step is clustering phase in which clusters are created by k-Means. Proposed technique uses the standard KDD99 (knowledge Discovery and Data Mining) intrusion detection contest data set. Proposed system can detect the attacks/intrusions and classifies them into different categories: U2R (User to Root), probe, R2L (Remote to Local), and Denial of Service (DoS). The prime task of the proposed IDS is to improve effectiveness with efficiency. An experiment is carried out to evaluate/calculate the performance of the proposed approach using KDD 99' data set. Here the result shows that the proposed IDS technique performs better in term of efficiency(Execution Speed) & effectiveness.