Browsing by Author "Nwulu, N.I."

Now showing 1 - 3 of 3

A survey of machine learning methods applied to anomaly detection on drinking-water quality data
(2019) Dogo, E.M.; Nwulu, N.I.; Twala, B.; Aigbavboa, C.O.
Traditional machine learning (ML) techniques such as support vector machine, logistic regression, and artificial neural network have been applied most frequently in water quality anomaly detection tasks. This paper presents a review of progress and advances made in detecting anomalies in water quality data using ML techniques. The review encompasses both traditional ML and deep learning (DL) approaches. Our findings indicate that: 1) Generally, DL approaches outperform traditional ML techniques in terms of feature learning accuracy and fewer false positive rates. However, it is difficult to make a fair comparison between studies because of different datasets, models and parameters employed. 2) We notice that despite advances made and the advantages of the extreme learning machine (ELM), its application is sparsely exploited in this domain. This study also proposes a hybrid DL-ELM framework as a possible solution that could be investigated further and used to detect anomalies in water quality data.
Evaluative analysis of next generation mobile networks in future smart grid in developing countries
(ACM, 2019) Dogo, E.M.; Salami, A. F.; Nwulu, N.I.
Smart grid (SG) promises an efficient system that provides effective monitoring, timely statuses and vital automation capabilities across generation, transmission and distribution spectrum of the power grid. SG applications have stringent and unique latency and bandwidth requirements. 4G LTE and the evolving 5G promises to support a wide range of applications in the SG. This research analyses the performance of 4G LTE and 5G networks in supporting big data analytics for SG in developing countries. In order to evaluate the technical practicality of using wireless cellular networks provided by local mobile operators, a comparative analysis of three 4G LTE networks operators on wide area network (WAN) application and an emulated future 5G networks is carried out in Nigeria. The latency (λ), throughput (τ) and packet loss rate (ψ) for the three local networks providers (denoted as OP1, OP2, OP3), and the emulated 5G networks (denoted as EFN1, EFN2, EFN3) were used for the experimentation using OMNET++ simulation tool. The obtained results indicate that OP2 is a better choice for WAN SG applications when the communication radius is below 1600m and OP3 is a preferable choice when communication radius grows up to 2400m and beyond. While on the other hand, the results obtained for the 5G networks show that, on average, EFN2 is a better choice for WAN SG applications when the communication radius is lesser than 1600m and EFN3 is a preferable choice when the communication radius extend beyond 2400m.
Toward Sustainable Domestication of Smart IoT Mobility Solutions for the Visually Impaired Persons in Africa
(Springer, 2020) Salami, A.F.; Dogo, E.M.; Nwulu, N.I.; Paul, B.S.
According to World Health Organization (WHO) estimates, Africa accounts for 10% of the global visually impaired persons (VIPs). This visual impairment burden is exacerbated by the shortage of specialist medical human resources, orientation and mobility specialists, and high cost of assessing primary eye care services. These render the majority of VIPs to rely heavily on human-assisted guides and ineffective navigation aids for their daily routines and movements. A viable technological solution that can fill this void and meet these mobility needs is the Internet of Things (IoT). This chapter provides an assessment of smart IoT mobility solutions pertinent to the African context. Furthermore, the barriers to the realization of technology domestication as well as growth catalysts are examined. Lastly, this chapter proffers technical recommendations for sustainable domestication of smart IoT mobility solutions for VIPs in Africa.