Seleman M. Ngwira

A survey on recommender systems

Nowadays mobile devices are becoming a major platform for information access and when combined with recommendation systems technologies they can become key tools for mobile users both for travel and business applications. Recommendation Systems (RSs) have been extensively utilized as a means of reducing the information overload and offering travel recommendations to tourists. The emerging mobile RSs are tailored to mobile device users and promise to substantially enrich tourist experiences, recommending rich multimedia content, context-aware services, and views/ratings of peer users. This article follows a systematic approach in reviewing the state-of-the-art in the field, proposing a classification of mobile tourism RSs and providing insights on their offered services. In this paper we review the major issues and opportunities that the mobile scenario opens to the application of recommendation systems.

Face recognition techniques, their advantages, disadvantages and performance evaluation

A human brain can store and remember thousands of faces in a persons life time, however it is very difficult for an automated system to reproduce the same results. Faces are complex and multidimensional which makes extraction of facial features to be very challenging, yet it is imperative for our face recognition systems to be better than our brains capabilities. The face like many physiological biometrics that include fingerprint, hand geometry, retina, iris and ear uniquely identifies each individual. In this paper we focus mainly on the face recognition techniques. This review looks at three types of recognition approaches namely holistic, feature based (geometric) and the hybrid approach. We also look at the challenges that are face by the approaches.

A context-aware proactive recommender system for tourist

With the fast growth in Information Communication Technology (ICT), the aspect of Recommender system have proved to be a great tool to /finding appropriate items/objects for users. Traditional user request response pattern are usually used to make these recommendations, adding context information and integrating proactivity to the process of recommending items/objects has improved recommender system so far. Context-Aware Proactive Recommender system can be of great assistance in giving appropriate recommendation in mobile devices. Therefore this study proposes a Context-aware proactive recommender system for tourists, it will also include contextual factors such as time, location and weather of the user and how a particular item satisfies users need, using Multi-criteria Collaborative filtering to make suggestions more efficient and accurate. Experiment will be conducted and the performance evaluation of the proposed system will be analysed to measure the efficiency and efficacy of the proposed techniques.

A survey of Context-aware Recommender System and services

The advancement of the Internet, mobile and wireless technologies have produced a rapid change of information in terms of volume and accessibility. The enormous volume of information can be devastating especially to mobile users exceeding human ability to differentiate information which is relevant and that which is irrelevant. For many yzears now, recommender system have become well-known, and have been studied in various domains such as e-learning, online shopping, tourism to help overcome information overload. Recommendations are produced based on users who have interests in a particular thing or item. This recommendation process was further enhanced by incorporating context such as time, weather, and location to make recommendations more accurate and efficient. However, these systems have introduced context-aware recommender systems. This paper presents a survey of Context-aware recommender systems, the background and algorithms of Context-aware Recommender System, and also discusses the open issues of context-aware recommender systems.

A survey of recommender system feedback techniques, comparison and evaluation metrics

Recommender system is an application that filtered personalized information based on user preference from large information obtained. However, in order to provide effective and efficient recommendation it is necessary to accurately construct users interest and taste. In constructing the user interest and taste there is need to obtain accurate feedback from user on the recommendation. In order to achieve this, various Recommender Systems techniques can be employed. This paper intends to highlight various Recommender Systems, their merits and demerits; and overview of recommender System is discussed.

MITIGATING FACE BIOMETRIC ON ELECTRONIC MEDICAL RECORD

With the current movement of patient filing system from paper-based system towards Electronic Medical Record (EMR) system, it is necessary to protect patient privacy on EMR efficiently. This research incorporate faces biometric system into EMR in order to provide a twolayer security for patient confidential information. However, the issue of face with distortion such as expressions, aging, background illumination etc. which often affects the performance of face biometric system during authentication stage was addressed. We utilized optimized Principal Component Analysis and Support Vector Machine (PCA-SVM) to extract features and address this issue of patient’s face with distortions. We conducted an experiment with 100 test cases. This result shows that facial biometrics can be used for securing patient electronic medical record in hospitals based on the system accuracy obtained. The result demonstrated 78% system performance accuracy with distorted face, which shows that optimized PCA-SVM exhibit a reliable performance for promising security work in term of False Rejection Rate(FRR) and False Acceptance Rate (FAR).

Incorporating a guided problem-solving method into ActiveMath using the House Model and logistic Regression

In the past few decades, our world has changed from an industrial to an information society. This change has brought the need for a new set of skills in the workplace, including the ability to solve problems. Introducing technology in education is one response to this reform. Intelligent tutoring systems are one form of e-learning. They are designed to reasonably adapt to each learner or user based on their background and progressive achievement. Because of the various advantages of these systems attempts are made to incorporate problem solving skill impartation abilities for learners. This paper describes an adapted version of ActiveMath, which explicitly teaches problem solving to students using the House Model framework. Results show the technique does contribute to improve the problem solving skills of learners.

Ubiquitous health care framework for the rural African environment

With the advancement of technology and telecommunication, ICT is in a position to play a major role in Public Health planning, disease eradication and containment. The introduction of Ubiquitous computing into the health care system will ensure that patient data is readily available to those authorized and can be collected and analyzed in real time. In this paper we designed and developed a Ubiquitous health care framework that is best suited for developing African states that will assist in health care planning, collection and management of patient records, decision and basic diagnostic support. The system proposed looks at all aspects of public health and envisages to integrate them into one.

Survey of smart city initiatives towards urbanization

The smart city concept is a recent phenomenon that seems to be drawing so much attention from both academia and industry. With a rapid and alarming influx of migrants into urban areas the service delivery, traffic congestion to and fro the city, air pollution, crime rate, energy crisis (load shedding), standard of living has become a burning issue for both city managers and management. This event has triggered the need for smart cities initiates as a solution to remedy the situation. Although a number of pilot projects seem to be showing sustainability and great success in Europe, Asia and United states, similar projects (initiatives) need to be carried out or tested particularly in developing countries. This paper provides a survey into smart cities initiatives towards urbanization challenges. Open issues and challenges are discussed, and then the impact of smart cities on science, technology and society are highlighted.

The feasibility of a WLAN based power substation monitoring platform

The industrial WLAN is gaining momentum in various applications in the industry. With reference to the power utility sector, WLAN communication could be used for less critical operations in power substation yards. The traditional wired data collection performed by Industrial Electronic Devices (IEDs) and Remote Terminal Units (RTUs) could be done wirelessly. This paper addresses the feasibility for implementing power substation monitoring applications using Wireless LAN based on IEEE 802.11b and IEEE 802.11g standards. A section of a power substation communication network is simulated in OPNET Simulator to assess the communication performance. Various key aspects and requirements including physical characteristics, transmit power, packet size and segmentation are described and the WLAN communication performance is analyzed with key indices considered, such as the transmission delay of the models with reference to the IEC 61850 timing requirements, the throughput and load of the networks. The analysis of the simulated results demonstrates that WLAN is feasible in power substations monitoring applications.