The threat of plastic waste pollution in African countries is increasing exponentially since the World Health Organisation declared the coronavirus infection as a pandemic. Fundamental to this growing threat are multiple factors, including the increased public consumption for single-use plastics, limited or non-existence of adequate plastic waste management infrastructures, and urbanisation. Plastics-based personal protective equipment including millions of surgical masks, medical gowns, face shields, safety glasses, protective aprons, sanitiser containers, plastics shoes, and gloves have been widely used for the reduction of exposure risk to Severe Acute Respiratory Syndrome (SARS) Coronavirus 2 (SARS-CoV-2). This paper estimates and elucidates the growing plethora of plastic wastes in African countries in the context of the current SARS-CoV-2 pandemic. A Fourier transform infrared (FTIR) spectral fingerprint indicates that face masks were characterised by natural and artificial fibres including polyester fibres, polypropylene, natural latex resin. Our estimate suggests that over 12 billion medical and fabric face masks are discarded monthly, giving the likelihood that an equivalent of about 105,000 tonnes of face masks per month could be disposed into the environment by Africans. In general, 15 out of 57 African countries are significant plastic waste contributors with Nigeria (15%), Ethiopia (8.6%), Egypt (7.6%), DR Congo (6.7%), Tanzania (4.5%), and South Africa (4.4%) topping the list. Therefore, this expert insight is an attempt to draw the attention of governments, healthcare agencies, and the public to the potential risks of SARS-CoV-2-generated plastics (COVID plastic wastes), and the environmental impacts that could exacerbate the existing plastic pollution epidemic after the COVID-19 pandemic.

Deep knowledge of how radio waves behave in a practical wireless channel is required for effective planning and deployment of radio access networks in urban environments. Empirical propagation models are popular for their simplicity, but they are prone to introduce high prediction errors. Different heuristic methods and geospatial approaches have been developed to further reduce path loss prediction error. However, the efficacy of these new techniques in built-up areas should be experimentally verified. In this paper, the efficiencies of empirical, heuristic, and geospatial methods for signal fading predictions in the very high frequency (VHF) and ultra-high frequency (UHF) bands in typical urban environments are evaluated and analyzed. Electromagnetic field strength measurements are performed at different test locations within four selected cities in Nigeria. The data collected are used to develop path loss models based on artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), and Kriging techniques. The prediction results of the developed models are compared with those of selected empirical models and field measured data. Apart from Egli and ECC-33, the root mean squared error (RMSE) produced by all other models under investigation are considered acceptable. Specifically, the ANN and ANFIS models yielded the lowest prediction errors. However, the empirical models have the lowest standard deviation errors across all the bands. The findings of this study will help radio network engineers to achieve efficient radio coverage estimation; determine the optimal base station location; make a proper frequency allocation; select the most suitable antenna; and perform interference feasibility studies.INDEX TERMS ANFIS, artificial neural networks, backpropagation, path loss, Kriging, radio propagation. I. INTRODUCTIONA study of the characteristics of radio waves in different propagation environments is needed for an effective network planning, and for the deployment of wireless communication systems [1], [2]. The magnitude and direction of electromagnetic waves in a practical wireless channel is usuallyThe associate editor coordinating the review of this manuscript and approving it for publication was Mauro Tucci.random and highly unpredictable [3]. Meanwhile, a good understanding of this phenomenon is needed to guarantee good Quality of Service (QoS) and high data transmission rate in radio access networks.The efficiency of a wireless communication system depends on the physical constituents of the propagation environment. The presence of buildings, mountains, bill boards, foliage, vehicles and other physical objects in a practical propagation environment usually obstructs the direct

Empirical measurement, monitoring, analysis, and reporting of learning outcomes in higher institutions of developing countries may lead to sustainable education in the region. In this data article, data about the academic performances of undergraduates that studied engineering programs at Covenant University, Nigeria are presented and analyzed. A total population sample of 1841 undergraduates that studied Chemical Engineering (CHE), Civil Engineering (CVE), Computer Engineering (CEN), Electrical and Electronics Engineering (EEE), Information and Communication Engineering (ICE), Mechanical Engineering (MEE), and Petroleum Engineering (PET) within the year range of 2002–2014 are randomly selected. For the five-year study period of engineering program, Grade Point Average (GPA) and its cumulative value of each of the sample were obtained from the Department of Student Records and Academic Affairs. In order to encourage evidence-based research in learning analytics, detailed datasets are made publicly available in a Microsoft Excel spreadsheet file attached to this article. Descriptive statistics and frequency distributions of the academic performance data are presented in tables and graphs for easy data interpretations. In addition, one-way Analysis of Variance (ANOVA) and multiple comparison post-hoc tests are performed to determine whether the variations in the academic performances are significant across the seven engineering programs. The data provided in this article will assist the global educational research community and regional policy makers to understand and optimize the learning environment towards the realization of smart campuses and sustainable education.

It is very important to understand the input features and the neural network parameters required for optimal path loss prediction in wireless communication channels. In this paper, an extensive investigation was conducted to determine the most appropriate neural network parameters for path loss prediction in Very High Frequency (VHF) band. Field measurements were conducted in an urban propagation environment to obtain relevant geographical and network information about the receiving mobile equipment and quantify the path losses of radio signals transmitted at 189.25 MHz and 479.25 MHz. Different neural network architectures were trained with varying kinds of input parameters, number of hidden neurons, activation functions, and learning algorithms to accurately predict corresponding path loss values. At the end of the experimentations, the performance of the developed Artificial Neural Network (ANN) models are evaluated using the following statistical metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Standard Deviation (SD) and Regression coefficient (R). Results obtained show that the ANN model that yielded the best performance employed four input variables (latitude, longitude, elevation, and distance), nine hidden neurons, hyperbolic tangent sigmoid (tansig) activation function, and the Levenberg-Marquardt (LM) learning algorithm with MAE, MSE, RMSE, SD and R values of 0.58 dB, 0.66 dB, 0.81 dB, 0.56 dB and 0.99 respectively. Finally, a comparative analysis of the developed model with Hata, COST 231, ECC-33 and Egli models showed that ANN-based path loss model has better prediction accuracy and generalization ability than the empirical models.INDEX TERMS Artificial neural network, path loss, radio propagation, wireless channel, machine learning.

No abstract

Embedded systems technology is undergoing a phase of transformation owing to the novel advancements in computer architecture and the breakthroughs in machine learning applications. The areas of applications of embedded machine learning (EML) include accurate computer vision schemes, reliable speech recognition, innovative healthcare, robotics, and more. However, there exists a critical drawback in the efficient implementation of ML algorithms targeting embedded applications. Machine learning algorithms are generally computationally and memory intensive, making them unsuitable for resource-constrained environments such as embedded and mobile devices. In order to efficiently implement these compute and memory-intensive algorithms within the embedded and mobile computing space, innovative optimization techniques are required at the algorithm and hardware levels. To this end, this survey aims at exploring current research trends within this circumference. First, we present a brief overview of compute intensive machine learning algorithms such as hidden Markov models (HMM), k-nearest neighbors (k-NNs), support vector machines (SVMs), Gaussian mixture models (GMMs), and deep neural networks (DNNs). Furthermore, we consider different optimization techniques currently adopted to squeeze these computational and memory-intensive algorithms within resource-limited embedded and mobile environments. Additionally, we discuss the implementation of these algorithms in microcontroller units, mobile devices, and hardware accelerators. Conclusively, we give a comprehensive overview of key application areas of EML technology, point out key research directions and highlight key take-away lessons for future research exploration in the embedded machine learning domain.

In this data article, we present a comprehensive dataset on electrical energy consumption in a university that is practically driven by Information and Communication Technologies (ICTs). The total amount of electricity consumed at Covenant University, Ota, Nigeria was measured, monitored, and recorded on daily basis for a period of 12 consecutive months (January–December, 2016). Energy readings were observed from the digital energy meter (EDMI Mk10E) located at the distribution substation that supplies electricity to the university community. The complete energy data are clearly presented in tables and graphs for relevant utility and potential reuse. Also, descriptive first-order statistical analyses of the energy data are provided in this data article. For each month, the histogram distribution and time series plot of the monthly energy consumption data are analyzed to show insightful trends of energy consumption in the university. Furthermore, data on the significant differences in the means of daily energy consumption are made available as obtained from one-way Analysis of Variance (ANOVA) and multiple comparison post-hoc tests. The information provided in this data article will foster research development in the areas of energy efficiency, planning, policy formulation, and management towards the realization of smart campuses.

Empirical models are most widely used for path loss predictions because they are simple, easy to use, and require less computational efficiency when compared to deterministic models. A number of empirical path loss models have been developed for efficient radio network planning and optimization in different types of propagation environments. However, data that prove the suitability of these models for path loss predictions in a typical university campus propagation environment are yet to be reported in the literature. In this data article, empirical prediction models are comparatively assessed using the path loss data measured and predicted for a university campus environment. Field measurement campaigns are conducted at 1800 MHz radio frequency to log the actual path losses along three major routes within the campus of Covenant University, Nigeria. Path loss values are computed along the three measurement routes based on four popular empirical path loss models (Okumura-Hata, COST 231, ECC-33, and Egli). Datasets containing measured and predicted path loss values are presented in a spreadsheet file, which is attached to this data article as supplementary material. Path loss prediction data of the empirical models are compared to those of the measured path loss using first-order statistics, boxplot representations, tables, and graphs. In addition, correlation analysis, Analysis of Variance (ANOVA), and multiple comparison post-hoc tests are performed. The prediction accuracies of the empirical models are evaluated based on Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Standard Error Deviation (SED). In conclusion, the high-resolution path loss prediction datasets and the rich data exploration provided in this data article will help radio network engineers and academic researchers to determine the empirical model that is most suitable for path loss prediction in a typical university campus environment.