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.
Effective requirements management that embraces both explicit and implicit aspects is a prerequisite for successful software development. Although, different researchers and practitioners have identified the importance of implicit requirements (IMR) for overall successful outcome of software development, there is a need to correlate these theoretical assumptions about implicit requirements with the state of the practice. This paper empirically investigates the perception and handling of implicit requirements in small and medium-sized software organisations. The survey was undertaken through a web-based questionnaire to which 56 participants from 23 countries responded. The study found that critical organisational factors such as number of years in business of an organisation, the years of experience of an organisation in requirements engineering, and size of software development team have positive correlation with the perception and handling of implicit requirements within an organisation. It also recommends that a comparative evaluation of the existing support tools for implicit requirements is necessary in order to validate the potential of these tools to solve existing challenges, and determine gaps that still exist.
Abstract The Insider Threat Detection(ISTD), is commonly referred to as the silent killer of organizations. The impact is greatly felt because it is usually perpetrated by existing staff of the organization. This makes it very difficult to detect or can even go undetected. Several authors have researched into this problem but no best solution has been discovered. This study therefore considers the insider problem as a classification problem. It provides a lay man’s understanding of a typical classification problem as faced in the insider threat detection research scope. It then highlights five (5) commonly used binary classification algorithms, stating their strengths and weaknesses. This work will help researchers determine the appropriate algorithm to consider for the employee dataset available for classification.
In recent years, the shortage of medical specialists and access to medical information has necessitated a growing interest for cost effective and efficient telemedicine tools for healthcare delivery. Mobile telemedicine applications are aimed at meeting the mobility requirements of patients and doctors by integrating wireless communications for different health care services and education.Although, telemedicine holds great promises in enhancing health care delivery in rural area and developing countries, only a few applications exist because of poor frameworks for their deployments. This paper, aims at providing a deployable framework for Mobile Telemedicine Applications for Tropical Diseases (MTATD).MTATD presented here, provides access to a telemedicine unit via hand held devices over a PSTN/GSM and the Internet for a collaborative health care delivery and education between patients and care providers.
Prior knowledge of the social aspects of prospective destinations can be very influential in making travel destination decisions, especially in instances where social concerns do exist about specific destinations. In this paper, we describe the implementation of an ontology-enabled Hybrid Destination Recommender System (HDRS) that leverages an ontological description of five specific social attributes of major Nigerian cities, and hybrid architecture of content-based and case-based filtering techniques to generate personalised top-n destination recommendations. An empirical usability test was conducted on the system, which revealed that the dependability of recommendations from Destination Recommender Systems (DRS) could be improved if the semantic representation of social attributes information of destinations is made a factor in the destination recommendation process.
The accessibility of cloud storage over the internet as a result of cloud computing technology provides the opportunity to store, share and upload data online with the use of digital devices which can be accessed anytime and anywhere. These benefits can also be exploited by the cybercriminals to perform various criminal activities including storing and exchanging of illegal materials on cloud storage platforms. The logs of malicious usages can be obtained from the cloud service providers for forensic investigations but the privacy issue among other factors make it difficult for such logs to be shared. Therefore, there is a need to perform client-side forensics to be able to carry out forensic investigation on digital devices as related to the activities on cloud storage. This study identifies relevant artifacts that can be forensically extracted from the registry of a window 10 device that accessed iDrive cloud storage. The study explores different experimental setups for the forensic analysis and adopted an integrated conceptual digital forensic framework in the investigation process to detect relevant forensic artifacts from the registry of a windows 10 device. This study increases the knowledge of cloud storage forensics and the significance of registry analysis during digital investigations.
The problem of existing customer relationship management (CRM) system is not lack of information but the ability to differentiate useful information from chatter or even disinformation and also maximize the richness of these heterogeneous information sources. This paper describes an improved text mining approach for automatically extracting association rules from collections of textual documents. It discovers association rules from keyword features extracted from the documents. The main contributions of the technique are that, in selecting the most discriminative keywords for use in association rules generation, the system combines syntactic and semantic relevance into its Information Retrieval Scheme which is integrated with XML technology. Experiments carried out revealed that the extracted association rules contain important features which form a worthy platform for making effective decisions as regards customer relationship management. The performance of the improved text mining approach is compared with existing system that uses the GARW algorithm to reveal a significant reduction in the large itemsets, leading to reduction in rules generated to more interesting ones due to the semantic analysis component being introduced. Also, it has brought about reduction of the execution time, compared to the GARW algorithm.
Several systematic literature reviews (SLRs) have been published on many aspects of Software engineering (SE) in the last two decades. However, researchers are yet to evaluate the quality of those studies in order to determine the reliability of their findings. This work employed SLR method and performed automated search of studies published between 2012 and 2017 aiming at evaluating the quality of the recent SLRs published in SE. This paper adapted Dyba and Dingsoyr quality criteria using dichotomous scale of grading to assess the quality of the primary studies in SLRs. A total of 15 of 53 primary studies have suitable recruitment strategy for their research aims, and 19 mentioned the control group (s) with wish their methods were compared. All the 53 papers passed all the standard quality conditions. The quality of the SLRs are high with only very small percentage failing in three out of 11 quality criteria. The research methodologies applied in their primary studies are comprehensive and were based on clear description of the context, thereby making their findings valid and reliable. The current SLRs in SE are of good quality but adequate consideration should be given to the relationship between the researchers and the participants.
Modern healthcare delivery services embrace the use of leading edge technologies and new
scientific discoveries to enable better cures for diseases and better means to enable early
detection of most life-threatening diseases. The healthcare industry is finding itself in a
state of turbulence and flux. The major innovations lie with the use of information
technologies and particularly, the adoption of mobile and wireless applications in
healthcare delivery [1]. Wireless devices are becoming increasingly popular across the
healthcare field, enabling caregivers to review patient records and test results, enter
diagnosis information during patient visits and consult drug formularies, all without the
need for a wired network connection [2]. A pioneering medical-grade, wireless
infrastructure supports complete mobility throughout the full continuum of healthcare
delivery. It facilitates the accurate collection and the immediate dissemination of patient
information to physicians and other healthcare care professionals at the time of clinical
decision-making, thereby ensuring timely, safe, and effective patient care. This paper
investigates the wireless technologies that can be used for medical applications, and the
effectiveness of such wireless solutions in a healthcare environment. It discusses challenges
encountered; and concludes by providing recommendations on policies and standards for
the use of such technologies within hospitals.
Decline in the level of citizens’ participation due to disconnect between citizens and their
representatives has been identified as one of the prominent challenges facing most democratic societies in the
world today. E-democracy has been identified to have the potentials to reduce the contemporary
estrangement between the democratic actors by creating new forms of engagement, deliberation, and
collaboration in polity to make the democratic processes more inclusive and transparent. However, edemocracy
initiatives in many countries have had mixed success as most e-democracy implementations have
been unable to justify the essence of huge investments made into it. This research paper reviews existing edemocracy
development processes and agenda of nations among the top twenty countries in e-participation
implementation as rated in the UN Global E-Government Evaluation, 2010. The sample composed of secondary
data sourced from information system centric academic journals, book chapters, conference proceedings,
database of international development organisations (OECD, UN, EU) on e-democracy implementation reports
and database of research institutions and centres that focus on e-government and e-democracy
implementation. Findings revealed that most countries do not have well established framework and agenda
setting for e-democracy implementation, but only based their e-democracy implementation on one of the
objectives of their e-government implementation. As a result, policy content is largely missing in most edemocracy
strategies at both conceptual and implementation stage. This paper therefore, presents a guideline
for e-democracy agenda setting and discusses issues germane to establishing e-democracy agenda. It submits
that for a successful e-democracy implementation, the agenda-setting phase should capture the legal and
political processes of the country. In addition, e-democracy strategic vision, strategic aim and objectives,
strategic policy, mode of implementation and overseeing body should be well articulated in the agenda setting
phase of e-democracy implementation plan. The discussion will benefit both researchers, government and
practitioners on successful e-democracy implementation as basis for societal development.
'%3e%3cpath fill='%23001489' d='M0 0v6h9V0z'/%3e%3cpath fill='%23e03c31' d='M0 0v3h9V0z'/%3e%3cg stroke='%23fff' stroke-width='2'%3e%3cpath id='d' d='m0 0 4.5 3L0 6m4.5-3H9'/%3e%3cuse xlink:href='%23b' stroke='%23ffb81c' clip-path='url(%23c)'/%3e%3c/g%3e%3cuse xlink:href='%23d' fill='none' stroke='%23007749' stroke-width='1.2'/%3e%3c/g%3e%3c/svg%3e)