Browsing by Author "Machuve, Dina"

Now showing 1 - 20 of 29

Analysis of effectiveness of channels for information gathering and dissemination: Case of fisheries stakeholders in Mwanza and Mara regions of Tanzania
(Routledge, 2022-05-24) Kusyama, Sadiki; Machuve, Dina; Kisangiri, Michael; Mfanga, Abswaid
The fisheries sub-sector in Tanzania is challenged with limited use of Information and Communication Technology (ICT) for information gathering and dissemination. Fishers obtain fisheries information from extension officers and their fellow fishers through mainly word of mouth in physical meetings. Despite the growth in access and availability of ICT channels on Mobile phones and Internet in recent years, the fisheries sub-sector decision-makers mainly use conventional media (radio, television, personal communications) in gathering and disseminating fisheries information. Understanding the characteristics of communication channels and their effectiveness in fisheries information gathering and dissemination is of great importance. A comprehensive comparison of the six ICT channels (short message services, cellular phone call, television, radio, mobile application, and website) was done in this study using effectiveness probability. The findings from this study indicated that, short message service (SMS) and cellular phone calls are most effective for fishers. Mobile application, cellular phone calls, websites, and SMS are effective for fish traders and fisheries officers. However, the cellular phone call was not cost-effective compared to mobile applications and websites. This study recommends the development of multi-channel (SMS, web-based, and mobile application) fisheries information system to enhance fisheries information gathering and dissemination process to meet realistic information needs of all fisheries stakeholders.
Automatic vehicle over speed, accident alert and locator system for public transport (Buses) A case study of Tanzania
(International Journal Of Engineering And Computer Science, 2013-08) Kusyama, Sadiki Lameck; Michael, Kisangiri; Machuve, Dina
Over speed limit violation done by public transport (buses) is a common problem in most of major roads in Tanzania. This has been reported to be one of the traffic accident causes in Tanzania. Moreover road accidents in Tanzania have been incessant and to bar the loss of life due to accidents is more crucial. This research work proposed and implemented a prototype called Automatic Vehicle Over Speed Accident Alert and Locator System (AVOAALS). The system uses GPS and GSM network, especially GPRS function of the GSM network. The system monitors the speed and accident event of the bus. Once an event is detected, the system leads the current position of the bus using GPS. The event, bus registration number and position data are sent to the control database server as SMS via GPRS services of the GSM Network. The event, bus registration number and position data are then stored in the data base. SMS application software was developed using Microsoft visual studio package. Microsoft SQL saver was used for storing data because of its high performance query engine, tremendously fast data insert capability and strong support for specialized web functions. Using this SMS application software, end user was able to receive SMS on any standard mobile phone about event, position of the targeted object, date and time of event. The administrator at the control data base server was able to extract reports about accident and over speed offenders. This system is very much useful for monitoring speed limit violations, reckless driving, and minifying the accident occurrence as well as optimizing rescue operations. The system was implemented using Sunrom’s GPS receiver with active antenna, GSM modem SIM900D, PIC18F4520 Microcontroller, mobile phone handset Nokia 110 and laptop computer. Prototype was tested and worked perfectly notifying nearby police station, hospital and fire station whenever appropriate event occurred. This work extends the utilization of mobile communication coverage on major roads in Tanzania to enhance road safety.
A Battery Voltage Level Monitoring System for Telecommunication Towers
(Engineering, Technology & Applied Science Research, 2021-12) Uwamahoro, Rahab; Mduma, Neema; Machuve, Dina
Voltage fluctuations in batteries form a major challenge the telecommunication towers face. These fluctuations mostly occur due to poor management and the lack of a battery voltage level monitoring system. The current paper presents a battery voltage-level monitoring system to be used in telecommunication towers. The proposed solution is incorporated with a centralized mobile application dashboard for accessing the live data of the installed battery, integrated with voltage-level, current, temperature, fire, and gas sensors. An Arduino Uno microcontroller board is used to process and analyze the collected data from the sensors. The Global Service Message (GSM) module is used to monitor and store data to the cloud. Users are alerted in the case of low voltage, fire, and increase in harmful gases in the tower through Short Message Service (SMS). The experiment was conducted at Ngorongoro and Manyara telecommunication towers. The developed system can be used in accessing battery information remotely while allowing real-time continuous monitoring of battery usage. The proposed battery voltage-level monitoring system contributes to the elimination of battery hazards in towers. Therefore, the proposed battery voltage level monitoring system can be adopted by telecommunication tower engineers for the reduction of voltage fluctuation risks.
Common beans imagery dataset for early detection of bean rust and bean anthracnose diseases
(Elsevier, 2024-05-11) Laizer, Hudson; Mduma, Neema; Machuve, Dina; Maganga, Reinfrid
Common bean plays a crucial role in the agricultural sector in Tanzania. To most smallholder farmers, the crop serves as a principal source of protein and an essential source of income. Despite its significance, common bean production is often affected by diseases, particularly bean rust and bean anthracnose, resulting in low yields and diminished economic returns. To address this challenge, a comprehensive dataset of common bean leaf images has been collected by using smartphone cameras to capture the visual characteristics of healthy and diseased leaves. The dataset contains more than 59,072 labeled images, offering a valuable resource for developing machine learning models and user-friendly tools capable of early detection and diagnosis of bean rust and bean anthracnose diseases. The aim of generating this dataset is to facilitate the development of machine learning tools that will empower agricultural extension officers, smallholder farmers, and other stakeholders in agriculture to promptly identify and diagnose affected crops, enabling timely and effective interventions before causing significant economic loss. By equipping farmers with the knowledge and tools to combat these diseases, we can safeguard bean production, enhance food security, and strengthen the economic well-being of smallholder farmers in Tanzania and other parts of Africa.
Deep Convolutional Neural Network for Chicken Diseases Detection
(International Journal of Advanced Computer Science and Applications, 2021) Mbelwa, Hope; Machuve, Dina; Mbelwa, Jimmy
For many years in the society, farmers rely on experts to diagnose and detect chicken diseases. As a result, farmers lose many domesticated birds due to late diagnoses or lack of reliable experts. With the available tools from artificial intelligence and machine learning based on computer vision and image analysis, the most common diseases affecting chicken can be identified easily from the images of chicken droppings. In this study, we propose a deep learning solution based on Convolution Neural Networks (CNN) to predict whether the faeces of chicken belong to either of the three classes. We also leverage the use of pre-trained models and develop a solution for the same problem. Based on the comparison, we show that the model developed from the XceptionNet outperforms other models for all metrics used. The experimental results show the apparent gain of transfer learning (validation accuracy of 94% using pretraining over its contender 93.67% developed CNN from fully training on the same dataset). In general, the developed fully trained CNN comes second when compared with the other model. The results show that pre-trained XceptionNet method has overall performance and highest prediction accuracy, and can be suitable for chicken disease detection application.
A Deep Learning-based Mobile Application for Segmenting Tuta Absoluta’s Damage on Tomato Plants
(Engineering, Technology & Applied Science Research, 2021-10) Loyani, Loyani; Machuve, Dina
With the advances in technology, computer vision applications using deep learning methods like Convolutional Neural Networks (CNNs) have been extensively applied in agriculture. Deploying these CNN models on mobile phones is beneficial in making them accessible to everyone, especially farmers and agricultural extension officers. This paper aims to automate the detection of damages caused by a devastating tomato pest known as Tuta Absoluta. To accomplish this objective, a CNN segmentation model trained on a tomato leaf image dataset is deployed on a smartphone application for early and real-time diagnosis of the pest and effective management at early tomato growth stages. The application can precisely detect and segment the shapes of Tuta Absoluta-infected areas on tomato leaves with a minimum confidence of 70% in 5 seconds only.
Deign of Low Cost Blood Pressure and Body Temperature interface
(International Journal of Emerging Science and Engineering (IJESE), 2013-08) Mazima, Johevajile K.N; Michael, Kisangiri; Machuve, Dina
The objective of this work is to design a non-intrusive, accurate, and low cost biomedical sensor interface for processing blood pressure and body temperature vital signs. The work purposely deals with the signal conditioning of two vital signs: blood pressure, and body temperature. Blood pressure uses the methodology of Photoplethysmography to continuously monitor the systolic and diastolic blood pressure. Body temperature is dealt with a LM35 sensor. We design the signal conditioning interface based on the type of sensor such as pressure and temperature sensor. We simulate the circuits in proteus software to verify their accuracy. We also simulate the temperature simulated results in MATLAB to verify the linearity of the temperature against the output voltage. Therefore, the design will be useful for the patient monitoring systems which use microcontroller for interpretation before sending them to the doctor through mobile phone network assisted by GSM/GPRS modem.
Design of a Passenger Security and Safety System for the Kayoola EVs Bus
(IEEE, 2021-10-25) Koojo, Ivan; Machuve, Dina; Mirau, Silas; Miyingo, Simon
Kiira Motors Corporation seeks to avail customer satisfaction, by providing noteworthy passenger experience on its market entry product, the Kayoola EVs bus through deploying a passenger security and safety system to curtail rampant snags like passenger insecurity, loss of passenger property, shortcomings in management and accountability as well as the spread of contagious sicknesses like COVID-19 which are not alien occurrences on commuter taxis and buses in African cities. On this project, a comprehensive system was designed for remote CCTV video surveillance, video analysis for people detection, passenger count and social distance analysis, as well as digital contact tracing to solve the challenges. It denotes significant potential to improve the security of property and passengers, shrink the risk of the spread of contagious diseases, enable timely capture of contact tracing records and lessen the burden of management, monitoring and accountability for the numbers of passengers on buses for fleet owners.
Design of ECG Sensor Interface for Biosignal Extraction
(International Journal of Innovative Technology and Exploring Engineering (IJITEE), 2013-08) Mazima, Johevajile; Michael, Kisangiri; Machuve, Dina
The main objective of this paper is to propose the design of a sensor interface for gathering biosignal. This signal is acquired from the patient’s body by the ECG sensor. The interface includes the instrumentation amplifier, bandpass filter, notch filter and the gain amplifier for improving the weak signal captured from the human body. The interface designed is intended to be used in supporting remote monitoring devices for the patients living in areas with limited access to medical assistance or scarce clinical resources especially in rural areas. The patient monitoring systems are expected to use the GSM/GPRS network directly through GSM/GPRS modem instead of using additional devices like Personal Digital Assistant (PDA). Since, the network is currently available in remote area for access. The design is helpful to improve people’s quality of life, as well as to allow an improvement in the government attendance indices.
Development of an Access Point Positioning Algorithm under the Changing in Environment and Users’ density Estimation
(Asian Journal of Computer and Information Systems, 2014-06) Kazema, Twahir; Kisangiri, Michael; Machuve, Dina
In many wireless networks a single hop is all that is needed or in fact tolerable. The physical region where network is available is known as a coverage area. Generally, a transmitter and a receiver may exchange data by using one or more intermediate relays. In each case a path through the network must be found whereby each hop has a Signal to Interference Noise Ratio greater than ß. There are several ways to describe and compute network connectivity, but at the core, they all need that individual pairs are able to communicate, which is dictated by the SINR. This paper is going to develop an Access Point positioning algorithm by considering the changes of environment and users’ density estimation.
Development of Discharge Letter Module onto a Hospital Information System
(Journal of Health Informatics in Developing Countries, 2017-12-20) Wambura W, Wambura; Machuve, Dina; Nykanen, Pirkko
Hospital Discharge Letter (DL) is an important means to communicate the information of the patient's hospital visit, treatments and care plans to the next caregiver and, possibly also, to the patient. Timely, precise and comprehensive discharge information transfer between patients care providers is critical for ensuring patients safety and effective care. A growing number of hospitals in Tanzania are implementing an open source system, Care2x as health information system (HIS). One of the weaknesses for Care2x is that it cannot generate an electronic discharge letter. The main objective of this study was to develop an electronic discharge letter module and integrate it into Care2x HIS. Nine (9) physicians from three (3) hospitals, who were users of the Care2x system, were interviewed using a qualitative structured questionnaire to obtain their views and opinions on the contents of the discharge letter and corresponding usability requirements. Thereafter, a literature review on the key terms was done for Hospital Discharge Letter, Hospital Discharge Communication, and Care2x system. The DL module was developed and the users’ user experiences were collected on the use of the developed discharge letter. In this study, the users were very satisfied with the electronic discharge letter. The users saw that the discharge letter module solved many problems associated with the handwritten letter in terms of timeliness of production, the correctness of information, content, and legibility in hospitals which use Care2x. Further studies are required to incorporate also the patient’s requirements in the DL and to improve the exchange of DL between hospitals regardless of the HIS in use. However, to make this information exchange possible, there should first be interoperability and integration of Care2x HIS with other organizations’ patient information systems.
Early identification of Tuta absoluta in tomato plants using deep learning
(Elsevier B.V., 2020-11) Mkonyi, Lilian; Rubanga, Denis; Richard, Mgaya; Zekeya, Never; Sawahiko, Shimada; Maiseli, Baraka; Machuve, Dina
The agricultural sector is highly challenged by plant pests and diseases. A high–yielding crop, such as tomato with high economic returns, can greatly increase the income of small- holder farmers income when its health is maintained. This work introduces an approach to strengthen phytosanitary capacity and systems to help solve tomato plant pest Tuta ab- soluta devastation at early tomato growth stages. We present a deep learning approach to identify tomato leaf miner pest ( Tuta absoluta ) invasion. The Convolutional Neural Network architectures (VGG16, VGG19, and ResNet50) were used in training classifiers on tomato image dataset captured from the field containing healthy and infested tomato leaves. We evaluated performance of each classifier by considering accuracy of classifying the tomato canopy into correct category. Experimental results show that VGG16 attained the high- est accuracy of 91.9% in classifying tomato plant leaves into correct categories. Our model may be used to establish methods for early detection of Tuta absoluta pest invasion at early tomato growth stages, hence assisting farmers overcome yield losses.
An Ensemble Predictive Model Based Prototype for Student Drop-out in Secondary Schools
(Journal of Information Systems Engineering & Management, 2019-08-22) Mduma, Neema; Kalegele, Khamisi; Machuve, Dina
When a student is absent from school for a continuous number of days as defined by the relevant authority, that student is considered to have dropped out of school. In Tanzania, for instance, drop-out is when a student is absent continuously for a period of 90 days. Despite the fact that several efforts have been made to improve the overall status of education at secondary level, the student drop-out problem still persists. Taking advantage of advancement in technology, several studies have used machine learning to address the student drop-out problem. However, most of the conducted studies have used datasets from developed countries, while developing countries are facing challenges on generating public datasets to be used to address this problem. Using a dataset from Tanzania which reflect a local scenario; this study presents an ensemble predictive model based prototype for student drop-out in secondary schools. The deployed model was developed by soft combining a tuned Logistic Regression and Multi-Layer Perceptron models. A feature engineering experiment was conducted to obtain the most important features for predicting student drop-out. Furthermore, a visualization module was integrated to assist interpretation of the machine learning results and we used flask framework in the development of the prototype.
Machine learning approach for reducing students dropout rates
(International Journal of Advanced Computer Research, 2019-05-06) Mduma, Neema; Kalegele, Khamisi; Machuve, Dina
serious issue in developing countries. On the other hand, machine learning techniques have gained much attention on addressing this problem. This paper, presents a thorough analysis of four supervised learning classifiers that represent linear, ensemble, instance and neural networks on Uwezo Annual Learning Assessment datasets for Tanzania as a case study. The goal of the study is to provide data-driven algorithm recommendations to current researchers on the topic. Using three metrics: geometric mean, F-measure and adjusted geometric mean, we assessed and quantified the effect of different sampling techniques on the imbalanced dataset for model selection. We further indicate the significance of hyper parameter tuning in improving predictive performance. The results indicate that two classifiers: logistic regression and multilayer perceptron achieve the highest performance when over-sampling technique was employed. Furthermore, hyper parameter tuning improves each algorithm's performance compared to its baseline settings and stacking these classifiers improves the overall predictive performance. Keywords Machine learning (ML), Imbalanced
Mobile Application for Gate Pass Management System Enhancement
(IEEE, 2021-09-15) Hilary, Rambo; Machuve, Dina; Mirau, Silas
Gate pass management is a vital measure to keep records of people’s entrance and exit of company premises. Technological improvement steered gate pass management from paper-based logbooks to web-based systems that rely on the internet. Usually, a web-based system can be accessed through a computer browser or mobile browser. The technological evolution of smartphones lures many users in using mobile phones for access internet and web-based systems. The use of smart phone offers portability, flexibility, and a good user experience. Due to the small screen size and input method of smartphones, it’s challenging to use mobile phones to access web-based gate pass management systems. The development of mobile applications introduces a better user experience and easy access to gate pass users. The application provides added advantage in simplifying the whole process of gate pass management. Mobile phone portability and accessibility are utilized to ensure users can have access to gate pass management at any time and anywhere. Mobile application camera is an added feature utilized for scanning gate pass barcodes and taking pictures of gate pass users for more security records. Therefore, the enhancement of the gate pass management system brings an easy way for the user to manage the gate pass process through their smartphone phones.
Mobile-based Decision Support System for Poultry Farmers: A Case of Tanzania
(International Journal of Advanced Computer Science and Applications, 2021) Shapa, Martha; Trojer, Lena; Machuve, Dina
—Poultry farms in Tanzania are characterized by inadequate management practices which are mainly caused by the lack of adequate systems to guide the small-scale poultry farmers in decision making. It is well-established that information is a key factor in making effective decisions in numerous sectors including poultry farming. Furthermore, various researchers have identified the use of mobile decision support tools to be an effective way of aiding farmers in making informed decisions. In this paper, we present a mobile-based decision support system that will aid rural and small-scale poultry farmers in Tanzania to obtain reliable information that is crucial for making proper decisions in their farming activities. In this context, a mobile-based decision support system was achieved through a mobile application integrated with a chatbot assistant to provide a solution to various poultry farming-related problems and simplify their decision-making process. We used a data-driven approach towards developing an informational chatbot assistant for Android smartphones that is capable of interacting with small-scale poultry farmers through natural conversations by utilizing the RASA framework.
Overview applications of data mining in health care: The case study of Arusha region
(IJCER, 2013-08) Diwani, Salim; Mishol, Suzan; Kayange, Daniel; Machuve, Dina; Sam, Anael
Data mining as one of many constituents of health care has been used intensively and extensively in many organizations around the globe as an efficient technique of finding correlations or patterns among dozens of fields in large relational databases to results into more useful health information. In healthcare, data mining is becoming increasingly popular and essential. Data mining applications can greatly benefits all parties involved in health care industry. The huge amounts of data generated by healthcare transactions are too complex and voluminous to be processed and analyzed by traditional methods. Data mining provides the methodology and technology to transform huge amount of data into useful information for decision making. This paper explores data mining applications in healthcare in Arusha region of Tanzania more particularly; it discusses data mining and its applications in major areas such as evaluation of treatment effectiveness, management of healthcare itself and lowering medical costs
Participation-reputation based incentive game model (PRIGM) for trustworthy fisheries information collection and dissemination framework
(Accent Social and Welfare Society, 2020-09-01) Kusyama, Sadiki; Machuve, Dina; Kisangiri, Michael; Mfanga, Abuswaid
The fisheries and aquaculture sectors worldwide use Information and communication technologies (ICT) to collect and disseminate fisheries information. Currently, the African member state is significantly strengthening the use of ICT systems in data collection and dissemination to ensure timely access and accurate fisheries information. Fisheries stakeholders are obliged to submit and retrieve information honestly as well as provide feedback voluntarily. We conducted ancient literature reviews to discover worldwide and indigenous struggles towards developing and implementing fisheries data collection and dissemination systems. Existing worldwide and indigenous innovation systems bases on voluntary user participation and lacks effective incentive mechanisms. However, due to dishonest human behavior, such a promise is impractical. Without an efficient mechanism to incentivize fisheries stakeholders, it would not be easy to achieve the required system adoption and performance. This paper proposed an evolutionary participation-reputation incentive game-based mechanism (PRIGM) to motivate fisheries stakeholders to contribute accurate information, retrieve information, and return honest feedback to the system. Our proposed model adopts stakeholder participation and reputation as merit to incentivize the honest stakeholder and punish the dishonest one. Our proposed PRIGIM model modeled the stakeholder's participation as an evolutionary game and coded the model using the python programming language. We simulated the model in five cases using randomly generated data, each with four-game rounds plays, using a different number of stakeholder participants in each case. Lastly, we used a bar chart graph to evaluate stakeholder's honest and dishonest behavior. The simulation results show that no matter the population of stakeholders, many stakeholders choose a dishonest strategy at the beginning of the game; after several game rounds, most stakeholders will be motivated to choose a simple strategy. Our simulation results proved that PRIGIM effectively motivates stakeholders to use the system, contribute accurate information, and return truthful feedback.
Poultry diseases diagnostics models using deep learning
(Frontiers in Artificial Intelligence, 2022-08-01) Machuve, Dina; Nwankwo, Ezinne; Mduma, Neema; Jimmy, Mbelwa
Coccidiosis, Salmonella, and Newcastle are the common poultry diseases that curtail poultry production if they are not detected early. In Tanzania, these diseases are not detected early due to limited access to agricultural support services by poultry farmers. Deep learning techniques have the potential for early diagnosis of these poultry diseases. In this study, a deep Convolutional Neural Network (CNN) model was developed to diagnose poultry diseases by classifying healthy and unhealthy fecal images. Unhealthy fecal images may be symptomatic of Coccidiosis, Salmonella, and Newcastle diseases. We collected 1,255 laboratory-labeled fecal images and fecal samples used in Polymerase Chain Reaction diagnostics to annotate the laboratory-labeled fecal images. We took 6,812 poultry fecal photos using an Open Data Kit. Agricultural support experts annotated the farm-labeled fecal images. Then we used a baseline CNN model, VGG16, InceptionV3, MobileNetV2, and Xception models. We trained models using farm and laboratory-labeled fecal images and then fine-tuned them. The test set used farm-labeled images. The test accuracies results without fine-tuning were 83.06% for the baseline CNN, 85.85% for VGG16, 94.79% for InceptionV3, 87.46% for MobileNetV2, and 88.27% for Xception. Finetuning while freezing the batch normalization layer improved model accuracies, resulting in 95.01% for VGG16, 95.45% for InceptionV3, 98.02% for MobileNetV2, and 98.24% for Xception, with F1 scores for all classifiers above 75% in all four classes. Given the lighter weight of the trained MobileNetV2 and its better ability to generalize, we recommend deploying this model for the early detection of poultry diseases at the farm level.
Review on network performance: Meaning, quantification and measurement
(Journal of Internet and Information Systems, 2013-09) Kigodi, Omari J.; Michael, Kisangiri; Machuve, Dina
This paper surveys various literatures on network performance with main focus on three main issues: its meaning, quantification and measurement. The essence of performance in communication systems is discussed and its meaning explored. Further, we look at relationship between network performance and its characteristics. The weaknesses in literature are disclosed with respect to how performance is conceptualized and applied in networks. The study reveals that there is need to carry out further research to redefine and quantify network performance with intent to get rid of existing misconception and ambiguity.