Michael Kisangiri

Bio: Michael Kisangiri is an academic researcher from National Institute of Advanced Industrial Science and Technology. The author has contributed to research in topics: Electrical capacitance tomography & Handover. The author has an hindex of 5, co-authored 22 publications receiving 203 citations.

A Survey on Non-Intrusive Load Monitoring Methodies and Techniques for Energy Disaggregation Problem

Abstract: The rapid urbanization of developing countries coupled with explosion in construction of high rising buildings and the high power usage in them calls for conservation and efficient energy program. Such a program require monitoring of end-use appliances energy consumption in real-time. The worldwide recent adoption of smart-meter in smart-grid, has led to the rise of Non-Intrusive Load Monitoring (NILM); which enables estimation of appliance-specific power consumption from building's aggregate power consumption reading. NILM provides households with cost-effective real-time monitoring of end-use appliances to help them understand their consumption pattern and become part and parcel of energy conservation strategy. This paper presents an up to date overview of NILM system and its associated methods and techniques for energy disaggregation problem. This is followed by the review of the state-of-the art NILM algorithms. Furthermore, we review several performance metrics used by NILM researcher to evaluate NILM algorithms and discuss existing benchmarking framework for direct comparison of the state of the art NILM algorithms. Finally, the paper discuss potential NILM use-cases, presents an overview of the public available dataset and highlight challenges and future research directions.

A Survey of Machine Learning Applications to Handover Management in 5G and Beyond

Abstract: Handover (HO) is one of the key aspects of next-generation (NG) cellular communication networks that need to be properly managed since it poses multiple threats to quality-of-service (QoS) such as the reduction in the average throughput as well as service interruptions. With the introduction of new enablers for fifth-generation (5G) networks, such as millimetre wave (mm-wave) communications, network densification, Internet of things (IoT), etc., HO management is provisioned to be more challenging as the number of base stations (BSs) per unit area, and the number of connections has been dramatically rising. Considering the stringent requirements that have been newly released in the standards of 5G networks, the level of the challenge is multiplied. To this end, intelligent HO management schemes have been proposed and tested in the literature, paving the way for tackling these challenges more efficiently and effectively. In this survey, we aim at revealing the current status of cellular networks and discussing mobility and HO management in 5G alongside the general characteristics of 5G networks. We provide an extensive tutorial on HO management in 5G networks accompanied by a discussion on machine learning (ML) applications to HO management. A novel taxonomy in terms of the source of data to be utilized in training ML algorithms is produced, where two broad categories are considered; namely, visual data and network data. The state-of-the-art on ML-aided HO management in cellular networks under each category is extensively reviewed with the most recent studies, and the challenges, as well as future research directions, are detailed.

Comparison of Empirical Propagation Path Loss Models for Mobile Communication

Abstract: Empirical propagation models have found favor in both research and industrial communities owing to their speed of execution and their limited reliance on detailed knowledge of the terrain In mobile communication the accuracy prediction of path losses is a crucial element during network planning and optimization However, the existence of multiple propagation models means that there is no propagation model which is precisely and accurate in prediction of path loss fit for every environs other than in which they were designed This paper presents few empirical models suitable for path loss prediction in mobile communication Experimental measurements of received power for the 900 MHz GSM system are made in urban, suburban, and rural areas of Dar es Salaam, Tanzania Measured data are compared with those obtained by five prediction models: Stanford University Interim (SUI) models [ 1 ], the COST-231 Hata model [ 2 ], the ECC-33 model [ 3 ], the ERICSSON model [ 4 ], and the HATA-OKUMURA model [ 5 ] The results show that in general the SUI, COST-231, ERICSSON, and Hata-Okumura under-predict the path loss in all environments, while the ECC-33 model shows the best results, especially in suburban and over-predict pathloss in urban area Keywords: Propagation pathloss, empirical models, radio coverage, mobile communications

The Challenges of Adopting M-Learning Assistive Technologies for Visually Impaired Learners in Higher Learning Institution in Tanzania

Abstract: In the past decades, the world has experienced major changes in the advancement of learning technologies which has enabled learners to engage in their learning activities anywhere. The penetration of mobile phone internet users in Tanzania has been increasing from 2 million in 2011 to 23mil in 2017 The adoption of mobile-based learning (M-learning) for students who are visually impaired in Tanzania has become a major bottleneck since most of the e-learning contents assume that learners have sight and thus include a lot of visualizations. This causes visually impaired students in higher learning Institutions (HLIs) to face challenges such as technical knowledge gaps. Lack of skills and inaccessibility of online contents, which then lead to drop out of the university. The aim of this study is to determine the awareness and usage levels of existing mobile assistive technologies for visual impairment, and the remaining challenges that visually impaired students face, when using such tools on smartphones to access m-learning content from HLIs. in Tanzania. The research was conducted an observational and contextual inquiry study at three major HLIs. We found that 67% of respondents did not have knowledge of m-learning assistive technologies, and their technology barriers for visually impaired students. Also, knowledge, accessibility of Assistive technology and affordability can hinder the adoption of m-learning in Higher Learning Institutions

On the Nature of the Function Expressive of the Law of Human Mortality

Abstract: We omit Gompertz’ method of fitting, which the reader will find in Makeham, below. Also omitted are Gompertz’ mortality tables, and his discussion of life expectancy and annuities under his Law. The hyperbolic logarithms in Art. 5 are the natural logs; we are not able to follow completely his integration, which is by Newton's method of fluxions.

The united republic of tanzania

Abstract: Since the 1990s, the per capita GDP in Tanzania has been increasing and Tanzania’s growth trend has been impressive. The annual GDP growth has averaged 6.4 percent between 2000 and 2004 and exceeded seven percent in 2002 and 2003 (Figure 2, Real GDP Growth). Tanzania’s growth rate of 6.3 percent in 2004 was well above the rate achieved in South Africa (3.7 percent). This strong growth performance reflects the fruits of responsible monetary and fiscal policy, concerted reforms, rapid export growth, and significant debt relief.

Bayesian-optimized Bidirectional LSTM Regression Model for Non-intrusive Load Monitoring

Abstract: In this paper, a Bayesian-optimized bidirectional Long Short -Term Memory (LSTM) method for energy disaggregation, is introduced. Energy disaggregation, or Non-Intrusive Load Monitoring (NILM), is a process aiming to identify the individual contribution of appliances in the aggregate electricity load. The proposed model, Bayes-BiLSTM, is structured in a modular way to address multi-dimensionality issues that arise when the number of appliances increase. In addition, a non-causal model is introduced in order to tackle with inherent structure, characterizing the operation of multi-state appliances. Furthermore, a Bayesian-optimized framework is introduced to select the best configuration of the proposed regression model, thus increasing performance. Experimental results indicate the proposed method’s superiority, compared to the current state-of-the-art.

Context Aware Energy Disaggregation Using Adaptive Bidirectional LSTM Models

Abstract: Energy disaggregation, or Non-Intrusive Load Monitoring (NILM), describes various processes aiming to identify the individual contribution of appliances, given the aggregate power signal. In this paper, a non-causal adaptive context-aware bidirectional deep learning model for energy disaggregation is introduced. The proposed model, CoBiLSTM, harnesses the representational power of deep recurrent Long Short-Term Memory (LSTM) neural networks, while fitting two basic properties of NILM problem which state of the art methods do not appropriately account for: non-causality and adaptivity to contextual factors (e.g., seasonality). A Bayesian-optimized framework is introduced to select the best configuration of the proposed regression model, driven by a self-training adaptive mechanism. Furthermore, the proposed model is structured in a modular way to address multi-dimensionality issues that arise when the number of appliances increases. Experimental results indicate the proposed method’s superiority compared to the current state of the art.