C. K. Ayo

Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction

This paper examines the forecasting performance of ARIMA and artificial neural networks model with published stock data obtained from New York Stock Exchange. The empirical results obtained reveal the superiority of neural networks model over ARIMA model. The findings further resolve and clarify contradictory opinions reported in literature over the superiority of neural networks and ARIMA model and vice versa.

Stock Price Prediction Using the ARIMA Model

Stock price prediction is an important topic in finance and economics which has spurred the interest of researchers over the years to develop better predictive models. The autoregressive integrated moving average (ARIMA) models have been explored in literature for time series prediction. This paper presents extensive process of building stock price predictive model using the ARIMA model. Published stock data obtained from New York Stock Exchange (NYSE) and Nigeria Stock Exchange (NSE) are used with stock price predictive model developed. Results obtained revealed that the ARIMA model has a strong potential for short-term prediction and can compete favourably with existing techniques for stock price prediction.

A Case-Based Reasoning approach for speech-enabled e-Learning system

E-Learning plays an important role in our society today; hence, higher institutions now offer courses through distance learning. Several studies and methodologies towards improving e-Learning have been proposed and provided. However, not too many works are dedicated to the design and implementation of e-Learning for the visually impaired learners. Sight challenge is a serious form of disability, yet, the existing e-Learning platform (web, mobile, etc) have not devoted enough attention to the plight of the visually impaired particularly in the area of usability. The objective of this paper is to present an intelligent speech-based e-Learning system with dual interface -Voice User Interface (VUI) and Web User Interface (WUI). Case-Based Reasoning (CBR) was engaged to provide intelligent services. Voice Extensible Markup Language (VoiceXML) was used to develop the VUI, Hypertext Preprocessor (PHP) for the WUI and Apache as the middle ware. The VUI and WUI are accessed through mobile phone by dialing a telephone number and the WUI using the Internet respectively. The e-Learning system will especially be useful for students who are visually impaired and those with dyslexia ailment that make reading, writing and spelling difficult. The application will complement the existing e-Learning systems such as web-based learning, m-Learning and others.

E-banking users’ behaviour: e-service quality, attitude, and customer satisfaction

Purpose – The purpose of this paper is to investigate factors affecting e-banking usage based on electronic service (e-service) quality, attitude and customer satisfaction. Design/methodology/approach – A conceptual model to investigate factors that influence e-banking usage was developed based on review of existing literature. The model employed e-services quality variable, diffusion of innovation construct and self-efficacy to better reflect the users’ views of e-banking usage. Data collected from 254 e-banking users were used to test the model. The data were analysed based on PLS-SEM using SmartPLS 3.0. Findings – The result reveals that perceived e-service quality has a strong influence on customer satisfaction and use of e-banking, which means that greater quality of e-service has the potential to increase satisfaction and consequently result in to more use of e-banking. In this research findings, competence of e-service support staff, system availability, service portfolio, responsiveness and reliab...

An Estimate of the Incidence of Prostate Cancer in Africa: A Systematic Review and Meta-Analysis.

Background Prostate cancer (PCa) is rated the second most common cancer and sixth leading cause of cancer deaths among men globally. Reports show that African men suffer disproportionately from PCa compared to men from other parts of the world. It is still quite difficult to accurately describe the burden of PCa in Africa due to poor cancer registration systems. We systematically reviewed the literature on prostate cancer in Africa and provided a continent-wide incidence rate of PCa based on available data in the region. Methods A systematic literature search of Medline, EMBASE and Global Health from January 1980 to June 2015 was conducted, with additional search of Google Scholar, International Association of Cancer Registries (IACR), International Agency for Research on Cancer (IARC), and WHO African region websites, for studies that estimated incidence rate of PCa in any African location. Having assessed quality and consistency across selected studies, we extracted incidence rates of PCa and conducted a random effects meta-analysis. Results Our search returned 9766 records, with 40 studies spreading across 16 African countries meeting our selection criteria. We estimated a pooled PCa incidence rate of 22.0 (95% CI: 19.93–23.97) per 100,000 population, and also reported a median incidence rate of 19.5 per 100,000 population. We observed an increasing trend in PCa incidence with advancing age, and over the main years covered. Conclusion Effective cancer registration and extensive research are vital to appropriately quantifying PCa burden in Africa. We hope our findings may further assist at identifying relevant gaps, and contribute to improving knowledge, research, and interventions targeted at prostate cancer in Africa.

The burden of road traffic crashes, injuries and deaths in Africa: a systematic review and meta-analysis

Abstract Objective To estimate the burden of road traffic injuries and deaths for all road users and among different road user groups in Africa. Methods We searched MEDLINE, EMBASE, Global Health, Google Scholar, websites of African road safety agencies and organizations for registry- and population-based studies and reports on road traffic injury and death estimates in Africa, published between 1980 and 2015. Available data for all road users and by road user group were extracted and analysed. We conducted a random-effects meta-analysis and estimated pooled rates of road traffic injuries and deaths. Findings We identified 39 studies from 15 African countries. The estimated pooled rate for road traffic injury was 65.2 per 100 000 population (95% confidence interval, CI: 60.8–69.5) and the death rate was 16.6 per 100 000 population (95% CI: 15.2–18.0). Road traffic injury rates increased from 40.7 per 100 000 population in the 1990s to 92.9 per 100 000 population between 2010 and 2015, while death rates decreased from 19.9 per 100 000 population in the 1990s to 9.3 per 100 000 population between 2010 and 2015. The highest road traffic death rate was among motorized four-wheeler occupants at 5.9 per 100 000 population (95% CI: 4.4–7.4), closely followed by pedestrians at 3.4 per 100 000 population (95% CI: 2.5–4.2). Conclusion The burden of road traffic injury and death is high in Africa. Since registry-based reports underestimate the burden, a systematic collation of road traffic injury and death data is needed to determine the true burden.

Building an Ontology-Based Framework for Tourism Recommendation Services

The tourism product has an intangible nature in that customers cannot physically evaluate the services on offer until practically experienced. This makes having access to credible and authentic information about tourism products before the actual experience very valuable. An Ontology being a formal, explicit specification of concepts of a domain provides a viable platform for the development of credible knowledge-based tourism information services. In this paper, we present an approach aimed at enabling assorted intelligent recommendations services in tourism support systems using ontologies. A suite of tourism ontologies was developed and engaged to enable a prototypical e-tourism system with various knowledge-based recommendation capabilities. A usability evaluation of the system yields encouraging results as a demonstration of the viability of our approach.

Closing the Cancer Divide Through Ubuntu: Information and Communication Technology-Powered Models for Global Radiation Oncology

“The chance for a cure, the chance to live, should no longer remain an accident of geography” (1). This is one of the key messages in “Closing the cancer divide: A blueprint to expand access in low and middle income countries” (1). This article highlights the growing burden of global cancer disparities and makes a compelling case that the time for unified action to close this divide is now. There is growing consensus that information and communication technologies (ICTs) have tremendous potential to catalyze global health collaborations. Advanced ICTs can be used to leverage the recent major upsurge in global health interest into greater space-time flexible collaborative action against cancer and for enhancing greater effectiveness of existing global health initiatives. The recent call for greater action in closing the cancer divide through collaborations, including that in International Journal of Radiation, Oncology, Biology, Physics (IJROBP), inspired the 2015 Global Health Catalyst cancer summit, which brought together a unique combination of global oncology leaders, diaspora leaders, and ICT and palliative care experts, industry, nonprofits, and policy makers. The summit provided a forum for networking, knowledge sharing, and discussion of some of the emerging models for ICT-powered global health collaborations in radiation oncology care, research, and education, as well as avenues for complementary outreach, including engagement with the diaspora. This article summarizes the discussions and recommendations from the summit and highlights the emerging ICT-powered models for radiation oncology global health, avenues for greater outreach (ubuntu, a term signifying the idea that “I am because we are,” or human connectedness [see discussion below]) for greater impact and sustainability, as well as emerging areas for scaling up and increased action toward closing the cancer divide. At the primary level, a distressing illustration of the cancer divide can be seen in Africa, where most of Africa’s more than 2000 languages do not even have a word for cancer (2). Thus, in that geography, many people die painfully of cancer and, sadly, do not know it. In areas more familiar with cancer, a great lack of cancer prevention education or awareness of the importance of early detection contributes to over one third of preventable cancer deaths (3). This problem is further exacerbated by a culture of silence and strong social stigma associated with the disease (4); even young doctors do not want to specialize in oncology, a medical area that talks only about pain and death. The stigma also means that the overwhelming majority of patients only present late with the disease when it is too late to cure them; the ensuing deaths then further reinforce the stigma that cancer is essentially a death sentence. At a secondary level, the cancer divide is illustrated by the lack of capacity to manage patients once their disease is diagnosed, a problem inherent in poor health care systems. For example, approximately half of Africa’s 54 countries still have no radiation therapy services typically needed in the treatment of more than 50% of cancer patients (5). Limitations to radiation therapy in low- and middle-income countries (LMICs) include the number of radiation therapy centers, the number of treatment units, the critical shortage in health care workforce, the lack of safety regulatory infrastructure, and the perception that radiation therapy is a complex and expensive solution. Without greater investment and collaboration in radiation therapy services, this will only exacerbate the burden of cancer and make the cancer divide worse. Meanwhile, at the tertiary level, the cancer divide is appropriately captured by what has been called “the pain divide” (6). Here, many people dying with cancer do so in excruciating pain, due to a lack of basic pain medication and other palliative options. Such harrowing deaths with needless suffering bolster the physical and social trauma of cancer and the reason why many people in LMICs do not even want to talk about cancer. A word of African origin, which people do like to talk about, is ubuntu. Popularized worldwide by African Nobel Prize winners Desmond Tutu and Nelson Mandela, ubuntu signifies the idea that “I am because we are,” or human connectedness. This ethos rings particularly true in today’s hyperconnected world, where we all share in the bounty of the expanding internet or ICTs and where local health has become global health and vice versa. Ubuntu also represents an operating system underlying ICTs used for cloud computing, including in radiation oncology. The recent call for greater action in closing the cancer divide through collaborations (1, 7–9), including more recently in radiation oncology (8), inspired the 2015 Global Health Catalyst (GHC) cancer summit (10), which brought together a unique combination of global oncology leaders, industry, policy makers, and African diaspora leaders. Here the African diaspora refers to Africans settled outside of the African continent. Building on a recent publication (11), a central theme of the summit was the use of ICTs to catalyze high-impact international collaborations in cancer care, research, and education with Africa. This article summarizes the summit proceedings and highlights the emerging ICT-powered models for radiation oncology global health, avenues for greater partnership (ubuntu), and outreach beyond the traditional, as well as emerging areas for scaling up and increased action toward closing the cancer divide.

Framework for Mobile Money Implementation in Nigeria

A sizeable number of people in developing nations, particularly Africa countries are rural dwellers who seldom have access to banking services despite their heavy reliance on remittances from economic migrants for social protection and poverty alleviation. There is therefore a dire need for the development of an effective mechanism for funds remittance especially for the rural dwellers. The development of mobile money (m-Money) will facilitate access to finance through the mobile platform, which has the largest rate of adoption all over the world (two-thirds of the world population has access) among other information and communication technology (ICT) facilities. This paper proposes a framework for m-Money implementation in Nigeria as a poverty alleviation tool for sending money from cities and towns to the rural dwellers. The objective is to design a simple, cheap and secure way of sending money better than the existing transfers. The developed framework is premised on the public and private partnership (PPP) initiatives that combine both account-based and electronic currency systems. It employs a 2-factor authentication using the phone and the national ID card, which doubles as an identity card and a payment card. The model will help jumpstart the implementation of bank-toATM, ATM-to-bank and mobile-to-ATM funds transfer in Nigeria among others as well as increase accessibility to funds.

Implementation of an Intelligent Course Advisory Expert System

Academic advising of students is an expert task that requires a lot of time, and intellectual investments from the human agent saddled with such a responsibility. In addition, good quality academic advising is subject to availability of experienced and committed personnel to undertake the task. However, there are instances when there is paucity of capable human adviser, or where qualified persons are not readily available because of other pressing commitments, which will make system-based decision support desirable and useful. In this work, we present the design and implementation of an intelligent Course Advisory Expert System (CAES) that uses a combination of rule based reasoning (RBR) and case based reasoning (CBR) to recommend courses that a student should register in a specific semester, by making recommendation based on the student’s academic history. The evaluation of CAES yielded satisfactory performance in terms of credibility of its recommendations and usability.