Computer Engineering

Permanent URI for this collectionhttp://197.211.34.35:4000/handle/123456789/128

Computer Engineering

Browse

Start date: 2019End date: 2019

Search Results

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Development of A Model for Generation of Examination Time Using Genetic Algorithm
    (Federal University of Technology Minna, 2019-04-22) Ahmed, A., Umar, B. U., Abdullahi, I. M., Maliki, D., Anda, I., & Kamaldeen, J. A
    Examination time table scheduling problem is one of the complexes, NP-complete and typical combinational optimization problem faced by the university community across the globe. Many researches have studies the problem due to its NP-complete nature and highly-multi-constrained problem which seeks to find possible scheduling for courses. Creating an examination timetable for university is a very difficult, time-consuming and the wider complex problem of scheduling, especially when the number of students and courses are high. Several factors are responsible for the problem: increases number of students, the aggregation of schools, changes in educational paradigms, among others. In most universities, the examination time table schedule is usually ended up with various courses clashing with one another. I order to solve this problem of time table scheduling for University examination and effective utilization of resources, this research proposed a model for examination time table generation using Genetic Algorithm (GA) probabilistic operators. GA has been successful in solving many optimization problems, including University time table. This is based on the fact that GA is accurate, precise, free from human error and robust for complex space problem. GA theory was also covered with emphasis on the use of fitness function and time to evaluate the result. The effects of altered mutation rate and population size are tested. By using Genetic algorithm, we are able to reduce the time required to generate a timetable which is more accurate, precise and free of human errors. The implication of this research is a solution, minimizing the time taken in timetable allocation and the clashing that usually characterize time table schedule.
  • No Thumbnail Available
    Item
    A smart switch control system using ESP8266 Wi-Fi module integrated with an android application
    (IEEE, 2019) Makhanya, S. P.; Dogo, E. M.; Nwulu. N. I.; Damisa, U.
    There is an increase in demand for low-cost Smart Switch Control Systems (SSCS) that can remotely control home switches or devices in residential environments using mobile applications or websites. In this paper, an SSCS which uses open source software, and can be configured without any physical adjustment to the environment, is developed to automatically minimize energy consumption. The device comprises two parts: An Android application and a unit made up of a programmable Arduino board, ESP8266 Wi-Fi module, wall socket and an SD card. In the SSCS, the Android application is used to remotely control switches using the Wi-Fi technology. Tests carried out on the system proved its effectiveness and quick response to signals.
  • No Thumbnail Available
    Item
    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.
  • No Thumbnail Available
    Item
    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.
  • No Thumbnail Available
    Item
    Dataset for a wireless sensor network based drinking-water quality monitoring and notification system
    (Elsevier, 2019) Sithole, M. P. P.; Nwulu, N. I.; Dogo, E. M.
    This paper presents the collected experimental data for water quality monitoring which was conducted in ten experiments by using five different common sources of water contaminants namely soil, salt, washing powder, chlorine and vinegar and their combination. The data were collected indoors at room temperature during the day for several days using sensors that measure pH, turbidity, flow rate, and conductivity in water. The water consumption risk (CR) was calculated as deviation based on the water quality parameters standards proposed by the World Health Organisation (WHO) and the South African Department of Water Affairs (DWA), with respect to the sensor measurement readings obtained. While the error measurements were calculated based on the expected parameter measurement per conducted experiment and repeated for 26 measurements. Pure tap water was the benchmark of water safe for human consumption. The first five experiments were performed by introducing each contaminant into the water and thereafter, two contaminants in the sixth experiment and their additions until all different contaminants were experimented at once in the last experiment.