RP-Department of Electronics Engineering

Permanent URI for this collection

https://repository.ku.ac.ke/handle/123456789/5397

Browse

Now showing 1 - 12 of 12

A Hybrid Model for Detecting Insurance Fraud Using K-Means and Support Vector Machine Algorithms
(Open Journal for Information Technology, 2023) Muthura, Brian Ndirangu; Matheka, Abraham
Private stakeholders and governments across the globe are striving to improve the quality and access of healthcare services to citizens. The need to improve healthcare services, coupled with the increase in social awareness and improvement of people’s living standards, has seen an increase in medical policyholders in the insurance industry. Even so, the healthcare sector is grappled with increased costs every other year, leading to revision of premiums and increased costs for the policyholders. One of the main factors contributing to the increased costs is fraudulent claims raised by the service providers and the policyholders, leading to unprecedented risks and losses for insurance firms. The insurance industry has set up fraud detection and mitigation systems to mitigate losses brought about by fraudulent claims, which come in two flavors: rule-based systems and expert claims analysis. With rule-based systems, conditions such as missing details, location of the claim vis a vis the location of the policyholder, among other rules, are evaluated by systems to assess the validity of the claims. On the other hand, insurance firms rely on the human intervention of experts using statistical analyses and artificial rules to detect fraudulent claims. The rule-based and expert analysis methods fail to detect patterns or anomalies in claims, which is central to efficient fraud detection. Data mining and machine learning techniques are being leveraged to detect fraud. This automation presents enormous opportunities for identifying hidden patterns for further analysis by insurance firms. This research aims to analyze a hybrid approach to detect medical insurance fraud using both K Means (unsupervised) and Support Vector Machines (supervised) machine learning algorithms.
Adaptation of technology
(Intercontinental Publishers Limited, 2013-05) Nzomo, M.M.; Mambo, Shadrack Maina
The subject of industrial technology has received significant attention in various international dialogue on economic development issues. This has been due largely to the gradual understanding of the vital role of industry in economic growth and the recognition of the role of technology in the process of industrial development. Technology Technology may be described as a matrix consisting of a set of techniques, each of which is associated with a vector of characteristics. These characteristics include the nature and specifications of the product, the input use, the scale of production, associated managerial techniques etc. The characteristics are designed to fit in with the economic, institutional and technical circumstances of the economy for which they were designed. In a general sense, technology includes choice of material, methods, machinery including equipment and tools, money (amount of sources), for a market (given or potential) appropriate to a country depending on its raw materials resources, availability of labour (level of skills and numbers), climate conditions, other human factors and level of social economic development at any given point of time. The technical know – how is not static, but is a continuous process of growth. For any country, developed or developing, it is not possible to remain in complete isolation. There is a prevailing lead – between developed countries which in some areas like electronics is quite high. Developing countries cannot afford to reduce this lead – time by indulging in own R & D programmes starting from the basics. Any disproportionate effort and money spent on grass root research with a view to catch up with developed countries will only increase the existing lead – time. This lead time can be shortened only by importing the technology initially and then using adaptive research to modify the performance. Even developed countries import technical know-how backed up by an intensive follow up Research and Development activity. Choice and acquisition of technology Choice of technology is a very important factor for the planned and balanced development of any sector of the economy. The investments made in an obsolete or old technology which may look very cheap and attractive to begin with, would prove very costly in the long – run due to high cost of production and non availability of spare parts. On the other hand, the input of very high and sophisticated technology would be costly and would also require a very large scale of production to be economically viable. A phased programme of indigenous manufacture with increasing self reliance and based primarily on domestic market needs is considered essential. Obsolescence of technology Obsolescence occurs with economic development and technical change, and is the product of the interaction between the two. There are many sources of obsolescence: generally speaking, the relevance of the source of obsolescence varies according to the nature of the economy. Some sources of obsolescence tend to make the technique obsolete in any society while others only apply in so far as other changes are occurring and may be applicable to developed countries and not to developing or underdeveloped countries. Obsolescence may be one of the methods of production to produce a given product. This is called product obsolescence associated with changes in the economic structure – obsolescence which would not occur without such changes; and obsolescence associated with increase in efficiency that makes previous technique obsolete irrespective of economic changes. In addition there is obsolescence independent of economic changes and of changes in the efficiency of substitute techniques, such as occurs with changes in the technology used in use in the rest of the system. Transfer and development of technology The process of assimilation of new techniques of industrial production and their adaptation to the condition prevailing in a particular country entails far more than the introduction of new equipment and the training of staff to operate it. The country’s technological capability is developed to other sectors of the economy and to society as a whole. The benefits are maximized if technology is transferred in such a way that the recipient country develops a capacity to modify and improve the technology in the future. The government of a developing country faces two main policy issues in connection with the transfer and development to technology for industrialization. The first is the extent to which policies and institutional arrangements are needed to ensure that the technology of modern manufacturing processes used in industrially advanced countries is adapted to the special needs and circumstances of developing countries using those processes. The second is the extent to which the Government should rely on imported technical know-how and, the nation’s technological capability. Insufficient attention has in the past been paid to the development of new types of technology for use by industrial enterprises in developing countries. Each developing country has different resource endowments and it is therefore usually worth while creating a national industrial research institution to tackle this and other problems encountered in adapting technological processes originally developed in industrial advanced countries with different resources endowments. In the industrially advanced countries, many branches of industry have formed research organizations on their own initiative and at their own expenses. It is difficult to say at what stage of the development of a branch of industry this form of organization will be appropriate in a developing country. However in those branches of industry where a government is especially desirous of developing a national and self supporting process of technological development, some initial financial support from government might be considered. Role of engineering education in generation & transfer of technology It has been argued that one of the major sources of bias in the generation and choice of technologies used in developing countries is the character of the education received by their engineers. Many of the engineers from developing world still receive their education in the universities of industrialized countries, because resources for their training and the technical assistance received for their establishment are often strongly influenced by the intellectual patterns of the industrialized countries. It is claimed, therefore, that engineers from developing countries trained in the molds receive “inappropriate education”. Absorption and adaption of technology The absorption and adaptation of technology can be described as a three-stage process after a foreign collaboration agreement has been entered into. Depending on the type of collaboration agreement and management decision, these three stages may start simultaneously or they can follow in a sequence. During the first stage, the emphasis is on setting up plants and facilities and leaving to manufacture the given product for which the collaborator supplies the complete set of drawings and manufacturing technology. Initially some of the components requiring complex production processing or proprietary technology may be imported from the collaborator, but the complete assembly is carried out at the local plant. The second stage of technology absorption starts when the local firm learns to design either new products or carry out alterations in the basic product design supplied by the collaborator following the design know-how and principles supplied by the collaborator. During the final stage of technology absorption, the local firm generates its own design know-how and principles based on indigenous research and development in the product areas, as well as in the basic sciences or engineering applicable to the product. If developing countries are to be able to choose and adapt technology, they must have available range of choices. First and foremost developing countries’ priority problem has been to find employment for large reserves of manpower by investing in industries which were sometimes of doubtful profitability and often based on the wrong choices of technology. In addition the engineering farms commissioned to make the techno-economic studies are often connected with plant manufacturers and slant their reports towards the choice of certain processes and types of plant.
Design and Computational Fluid Dynamics Modeling for a Municipal Solid Waste Incineration Process
(Scientific Research Publishing Inc., 2021-11) Sarakikya1, Halidini; Mashingo1, Peter; Kilonzo2, Fidelis
Municipal Solid Waste (MSW) incineration is among the important opportunities to control the pollutions caused by improper dumping and flue gas emissions so as to meet the environmental guidelines. The objective of this study was to design and develop a model for the MSW incineration process. The paper explains the design and development of MSW incinerator involving details of the Computational Fluid Dynamics (CFD) procedures through model design to the post process. CFD model was developed to reveal these features of the incineration process in the MSW incinerator. The model predicts the temperature in combustion chambers as well as at stack outlet of the incinerator. The solid waste characterization was done, and the laboratory analysis shows that, the Higher Heating Value (HHV) of the MSW is 11.65 MJ/kg on dry basis. The elemental composition MSW consists of 54.8%, 5.27%, 34.61%, 2.37% and 0.3% for Carbon, Hydrogen, Oxygen, Nitrogen and Sulphur respectively which are the input parameters for the CFD. The model simulation was positively achieved during combustion process and temperature in combustion chambers ranged between 930 K and 1700 K.
Design and Performance Evaluation of a Geothermal Dryer for Maize Drying
(CIGR, 2024-03) Gitu, Patrick; Osodo, Booker; Ambusso, Willis
Dynamic Construction of Outlier Detector Ensembles with Bisecting K-means Clustering
(IEEE, 2023) Ramadan, Rasha; Yassine, Inas A.; Wahed, Manal Abdel; Madete, June K.; Rushdi, Muhammad
Outlier detection (OD) is a key problem, for which numerous solutions have been proposed. To deal with the difficulties associated with outlier detection across various domains and data characteristics, ensembles of outlier detectors have recently been employed to improve the performance of individual outlier detectors. In this paper, we follow an ensemble outlier detection approach in which good outlier detectors are selected through an enhanced clustering-based dynamic selection (CBDS) method. In this method, a bisecting K-means clustering algorithm is employed to partition the input data into clusters where every cluster defines a local region of competence. Among the initial pool of detectors, the outputs of the detectors with the most competent local performance were combined through four possible schemes to produce the final OD results. Experimental evaluation and comparison of our method were carried out against four variants of locally selective combination in parallel (LSCP) outlier ensembles. The CBDS-based schemes compare well with the LSCP-based ones on 16 public benchmark datasets and incur considerably lower computational costs. The CBDS method consistently achieved superior average scores of the area under the curve (AUC) of the receiver operating characteristic (ROC), and particularly outperformed the LSCP method on nine of the 16 datasets in terms of the AUC score. In addition, while the CBDS and LSCP methods have similar computational costs on small datasets, the CBDS method achieves significant time savings compared with the LSCP method on large datasets.
Effects of Coronavirus Pandemic Spread on Science, Technology, Engineering and Mathematics Education in Higher Learning Institutions
(IEEE, 2021) Mambo, Shadrack Maina; Omusilibwa, Fidel Makatia
The traditional pedagogical methods of delivering content for Science, Technology, Engineering and Mathematics (STEM) related subjects have been shaken to their core. Normal delivery under ideal conditions was a face to face approach with the tutor in front of the class. Practical subjects that have laboratory exercises are carried out in the designated laboratory areas with the assistance of technicians or technologists. With the advent of coronavirus pandemic, where isolation and social distancing has been implemented to stop its spread and transmission, these modes of content delivery are not feasible. To fill in the gap and ensure the much needed STEM education continues despite the fear of coronavirus pandemic spread, online delivery mode of various subjects offered has been adopted. This is done using such platforms as Learning Management System, Zoom Meeting and Google Scholar. However, solving the problem of practical laboratory exercises requires much more than online teaching. This paper proposes the use of virtual reality, simulation and modeling platforms as a substitute of face to face laboratory exercises in training STEM related subjects, especially in institutions of higher learning in developing countries. Pre- recorded versions of practical experiments will be offered to students and related assignments given for practice purposes. Short webinars with details recorded will guide recipients in carrying out experiments without the need for neither technicians nor technologists. The students will then be able to attend the laboratory session virtually and submit the required reports. Several other types of content deliver exist and a combination of them can also be used depending on the areas to be covered. The exploitation of the suggested content delivery will resolve change of the attitude in learning behavior, thereby ensuring high quality and effective understanding of the subject area.
Energy Generation from Biomass in Tanzania Impacts and Challenges: An Overview
(International Journal of Engineering Research & Technology (IJERT), 2020) Omari, Arthur Mngoma; Tesha, Janet; Sarakikya, Halidini
— At present, much attention is on how to find the appropriate and proper renewable energy source which will offer sufficient energy output to replace the use of conventional fossil fuel sources. The energy stored in various biomasses available in Tanzania is huge and can provide sufficient energy to supply the rural societies. The energy crises facing rural societies in Tanzania can be solved and minimized by proper harnessing the substantial biomass available in the Country. The energy conversion process from the biomass and the type of energy required plays a vital role in identifying the type of biomass required in the process. The objective of this paper is to address different types of energy from various biomass sources, highlight the challenges and impact of each type.
Frequency Stability Enhancement of Microgrid Using Optimization Techniques-Based Adaptive Virtual Inertia Control
(Hindawi, 2023-11) Yegon, Philemon; Singh, Mukhtiar
In recent years, a sharp increase in integration of renewable energy sources (RESs) in power system network has been observed. High penetration of RES interfaced with power electronics converters-inverters with reduced or no inherent inertia compromises modern power system’s overall stability. Due to low inertia, voltage and frequency deviations far of the allowable threshold occur. To overcome this challenge, an adaptive inertia control strategy based on optimization technique is proposed. Te improved particle swarm optimization (PSO) and genetic algorithm (GA) optimization techniques-based PID controller has been used to generate the appropriate virtual inertia coefcient for efective emulation of inertia in the presence of energy storage system. Te conventional PSO sufers local optima stagnation, resulting in premature convergence during searching process in order to achieve global and local position. To address this issue, the velocity update equation was modifed on inertia weight (w) using an additional exponential term with linear decreasing inertia weight PSO (LDIW-PSO). In this paper, exponential power is taken strategically instead of squaring it in order to reduce the number of iterations for faster convergence. Finally, a microgrid based on wind and solar energy is simulated using MATLAB/Simulink where three cases, 2% disturbance, 3% disturbance, and 4% disturbance, have been considered. Here, the evaluation of proposed system is carried out based on four main performance indices (ITAE, IAE, ISE, and ITSE). Furthermore, validation was done through hardware prototype to get experimental results in real time. Te results from MATLAB simulation and experimental setup are in sync.
Nurturing Next-Generation Biomedical Engineers in Africa: The Impact of Innovators’ Summer Schools
(University of Cape Town Libraries, 2020) Atwine, Daniel; Karanja, Yvonne Wanjiku; Ahluwalia, Arti; De Maria, Carmelo; Assefa, Dawit; Konde, Victor; Khundi, Edwin; Makobore, Philippa Ngaju; Moshi, Mainen; Nzomo, Martin; Rushdi, Muhammad Ali; Ssekitoleko, Robert Tamale; Madete, June
The mission of healthcare systems in Africa to deliver compassionate and effective care has been constrained by growing populations, increasing burden of disease, political conflict and limited resources. The impacts of these constraints can be substantially alleviated, and the healthcare services strengthened, through the creation and adoption of affordable, accessible and appropriate biomedical engineering systems and technologies. There is an urgent need for building capacities in biomedical engineering, innovation and entrepreneurship in African countries. The African Biomedical Engineering Consortium has been organising a series of Innovators’ Summer Schools to meet this need by empowering students and researchers with entrepreneurial and innovative skills, and facilitating the design and development of robust, appropriate, and commercially viable medical systems and devices. In this paper, we analyse and discuss the impact of six of these schools held between 2012 and 2017. We used a questionnaire-based survey to collect responses from students who had attended the summer schools. The results of this study demonstrate that the teaching-learning model adopted in the ABEC summer schools was largely effective in promoting biomedical engineering skills, career choices, professional networks and partnerships amongst young African engineers and life scientists who attended the summer schools.
Optimization of Battery/Ultra-Capacitor Hybrid Energy Storage System for Frequency Response Support in Low-Inertia Microgrid
(WILEY, 2024-04) Yegon, Philemon; Singh, Mukhtiar
Modern power system networks are under statutory obligations to integrate renewable energy sources (RES). The primary reason is to meet ever-increasing energy demand and also to curtail environmental pollution by greenhouse gases. However, the higher penetration of RES has the tendency of reducing inertia of overall power system network. Consequently, frequency stability is affected and deviates beyond allowable permissible limits leading to power blackouts, load shedding, and even total system failure. To address the issues associated with reduced inertia, an optimal control of hybrid energy storage system (HESS) has been proposed. HESS is basically a combination of battery and ultracapacitor, where ultracapacitor addresses rapidly varying power component by mimicking inertia while the battery compensates long-term power variations. Thus, the HESS is effectively controlled to compensate the loss of inertia by regulating its energy flow. For the purpose of improved efficiency and better power management of the HESS, an improvised particle swarm optimization (MPSO)-based virtual inertia control design has been proposed. The proposed MPSO is utilized to tune the gains of bidirectional dc–dc converter in such a way that improves frequency nadir with faster response to transient disturbances. This proposed method is simulated in MATLAB and its merits are validated in real time using hardware in loop. On analysing of the results, it can be observed that frequency nadir is improved by 48.96% with significant reduction in rate of change of frequency in comparison to conventional particle swarm optimization.
Performance of a 2-Element Plane Reflector Augmented Galvanized Pipe Flat Plate Collector for Solar Water Pasteurization
(2009) Ako, E.O.; Thoruwa, T. F. N.; Maingi, S. M.; Njagi, E.N.M.
About 80% of all infectious diseases including diarrhoea, typhoid, and cholera in developing countries are transmitted through consumption of contaminated water. This study reports on the concept of heating water using low cost solar thermal energy systems to kill disease-causing microorganisms and gives the design philosophy, construction and measured thermal performances of a 2-element plane reflector augmented flat plate solar collector. A solar water pasteurization system was designed and constructed using locally available materials for direct water heating using solar energy in a flow-through system made of copper pipes. Standard car radiator thermostat valve was used to regulate pasteurization temperature at 82°C. The results demonstrated that solar heating of contaminated water could be achieved through a 2 m2 flat plate collector with mounted with a 2-element plane mirror reflector with an aperture area of 4 m2. The experimental collector was constructed with 20 mm diameter galvanized pipe fixed onto mild steel absorber plate. The collector without reflectors was used as control experiment. Under fair weather conditions, it was observed that the use of mirrors tremendously improved the performance of the collector by up to 94% producing 49-95 L of pasteurized water using the galvanized pipe collector. The microbiology water quality tests using presumptive test for total coliform and confirmed by Eijkman test showed no presence of E. coli in the solar pasteurized water samples. On the basis of the results, it was concluded that the solar water pasteurization system developed provides a cheaper alternative for water disinfection in Kenya and other sunny countries.
A Review on Medical Image Registration Techniques
(World Academy of Science, 2018) Mambo, Shadrack; Djouani, Karim; Yskandar, Hamam; Van Wyk, Barend; Siarry, Patrick
This paper discusses the current trends in medical image registration techniques and addresses the need to provide a solid theoretical foundation for research endeavours. Methodological analysis and synthesis of quality literature was done, providing a platform for developing a good foundation for research study in this field which is crucial in understanding the existing levels of knowledge. Research on medical image registration techniques assists clinical and medical practitioners in diagnosis of tumours and lesion in anatomical organs, thereby enhancing fast and accurate curative treatment of patients. Literature review aims to provide a solid theoretical foundation for research endeavours in image registration techniques. Developing a solid foundation for a research study is possible through a methodological analysis and synthesis of existing contributions. Out of these considerations, the aim of this paper is to enhance the scientific community’s understanding of the current status of research in medical image registration techniques and also communicate to them, the contribution of this research in the field of image processing. The gaps identified in current techniques can be closed by use of artificial neural networks that form learning systems designed to minimise error function. The paper also suggests several areas of future research in the image registration.

Browse

Browsing RP-Department of Electronics Engineering by Title

Results Per Page

Sort Options