Papers by Munyaradzi Rushambwa
A content-based citation analysis study based on text categorization
Scientometrics, 2017
Publications and citations are important components for measuring research performance. Academics... more Publications and citations are important components for measuring research performance. Academics receive incentives, tenures, or awards from the number of citations they receive; however, the use of citations for research/er evaluation purposes can give rise to unethical practices and manipulation. Consequently, it is necessary to change the current approach to the use of citations. The main aim of this study was to conduct a content-based citation analysis study for Turkish citations. To achieve this aim, 423 peer-reviewed articles, the associated 12,881 references, and 101,019 sentences published in library and information science literature in Turkey were thoroughly examined. The citations were divided into four main categories; citation meaning, citation purpose, citation shape, and citation array. Then, each category was further divided into sub-categories. A tagging process with inter-annotator agreement was conducted and citation categories for the citation sentences determined. Weka software was used to apply the text categorization methods. The automatic citation sentence classification achieved at least a 90% success rate for all citation classes, which proved that using computational linguistics to evaluate citation contexts developing new techniques was possible and gave more detailed results.
Data Acquisition System for Web-based Multi-modal Data Repository
2021 Seventh International conference on Bio Signals, Images, and Instrumentation (ICBSII), 2021
The multimodal medical data with annotation helps to build different automated algorithms. Each r... more The multimodal medical data with annotation helps to build different automated algorithms. Each reported work has used a specific disease database and developed a CAD based on the considered database. Therefore, the availability and quality of medical database play the most crucial role in developing any CAD. However, it has been observed that most of the reported studies used public database (created by foreign universities/centers) or private database. Unfortunately, the availability of a national medical database in India is negligible. However, development of such medical database is possible. Such medical database can encourage new research activity and help a large research community. The proposed study focuses on developing an online public medical multimodal database platform. Here, the data acquisition software is build for collecting various information.
Emulation of a haemorrhage removal robot used during neurosurgical treatment of glioma
2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), 2020
Surgical treatment of glioma is used in surgery where there is need to puncture the human body sp... more Surgical treatment of glioma is used in surgery where there is need to puncture the human body specifically the brain. However, it results in the patients losing too much blood and consequently causing death or other unwanted complications. Haemorrhage also known as bleeding is defined as any profuse external or internal loss of blood from the blood vessels. The most common cause of haemorrhage is injury or trauma to the blood vessel. During a glioma surgical procedure not only does the manual blood removal delay the duration of the operation but also causes a 40 percent mortality rate due to blood clots formation. In this project we develop a robotic system that is made up of a blood detection unit and a robotic arm with 2 degrees of freedom that removes the blood in a few seconds and this system can effectively and safely evacuate considerable haemorrhage volume. The system is designed in a way that no damage or hurt will be caused to the surrounding tissue during blood removal. A...
Cloud based analysis and classification of EEG signals to detect epileptic seizures
Epileptic seizures are explained as the abnormal electrical activity occurring in the brain due t... more Epileptic seizures are explained as the abnormal electrical activity occurring in the brain due to an internal or external triggering factors. EEG (Electroencephalograph) is used to record brain activity and can be used to detect the seizures before, during or after they occur. These signal characteristics, however differ from patient to patient due to the different emotional and physical wellbeing of the various individuals. In normal circumstances, anti-epileptic medication is used to treat patients but very few systems have been developed to manage and track the seizures. In most extreme and rare cases, some patients undergo invasive surgery to treat the seizures and this is common in seizures that are caused by tumors or physical brain damage. Non-invasive surface electrode EEG measurement gives an estimate of the seizure onset but more invasive intracranial electrocorticogram (ECoG) are required at times for precise localization of the epileptogenic zone. This project aims at d...
Data Acquisition System for Web-based Multi-modal Data Repository
The multimodal medical data with annotation helps to build different automated algorithms. Each r... more The multimodal medical data with annotation helps to build different automated algorithms. Each reported work has used a specific disease database and developed a CAD based on the considered database. Therefore, the availability and quality of medical database play the most crucial role in developing any CAD. However, it has been observed that most of the reported studies used public database (created by foreign universities/centers) or private database. Unfortunately, the availability of a national medical database in India is negligible. However, development of such medical database is possible. Such medical database can encourage new research activity and help a large research community. The proposed study focuses on developing an online public medical multimodal database platform. Here, the data acquisition software is build for collecting various information.
Metacarpus flexion and palmar prehension using wrist movement based MEMS accelerometer
Many people lose their gripping action as a result of the metacarpus and phalanges fractures and ... more Many people lose their gripping action as a result of the metacarpus and phalanges fractures and amputations. The primary function of the hand is prehension which involves holding and manipulation of objects. There are various ways of replacing the flexion functioning of the hand which includes prostheses, orthotics and robotics. Prostheses tend to be minimally invasive and this work explores the possibility of replacing the malfunctioning of the hand's gripping function. A Micro Electro-Mechanical System (MEMS) based type tri-axis accelerometer can sense movement from anterior surface of the hand using acceleration in the different axes. A microcontroller is used to convert the acceleration from sensor and calculate the tilt angle and the angle is then used to control a prosthetic hand gripper. Depending on the set threshold angle, the prosthetic arm performs the grasping and ungrasping function.
Intelligent Wireless Real Time Surveillance System
A low cost High Definition (HD) security surveillance system with motion detection and device con... more A low cost High Definition (HD) security surveillance system with motion detection and device control over the internet is explained in this paper. The system is reconfigurable and can be applied to many applications with the advent of the Internet of things (IOT). However for the purposes of this project a system configured to monitor an office and office entry points is explained. Further configurability can make the system suitable for use in military surveillance, homes, bank vaults and locker rooms, shopping malls and authenticated areas depending on the devices to be controlled.
A low cost High Definition (HD) security surveillance system with motion detection and device con... more A low cost High Definition (HD) security surveillance system with motion detection and device control over the internet is explained in this paper. The system is reconfigurable and can be applied to many applications. However for the purposes of this project a system configured to monitor a home and home devices is explained. Further reconfigurability can make the system suitable for use in military surveillance, bank vaults and locker rooms, shopping malls and authenticated areas depending on the devices to be controlled. The real time surveillance is carried out by the D-Link DCS 930 IP wireless camera that works with both Wi-fi and Ethernet connection. The camera is powered by both mains supply and battery which then makes it suitable for continuous surveillance monitoring. An integration of the camera with a motion detector is also done to be able activate notifications (video, images and sound) that are sent via mail and in case of bad internet connection it uses the Subscriber...
Brain Tumor Detection and Classification of MRI Brain Images Using Morphological Operations
ICTMI 2017, 2019
Purpose Image processing is a vital aspect of medical science which enables visualization of vari... more Purpose Image processing is a vital aspect of medical science which enables visualization of various anatomical structures of human body. Planar imaging can be used for detecting and visualizing hidden abnormal structures which are not use to visualize using simple imaging. Magnetic resonance imaging (MRI) modality is one of the techniques which enables scan and capture of internal body soft tissues. This work describes the process implemented for detection and extraction of brain tumor from patient’s MRI scan images of the brain. Procedure The process includes some contrast enhancement, noise removal functions, segmentation, and morphological operations which are the basic terms of image processing. By using MATLAB software, we detected and extracted tumor from 24 MRI scan images of the brain. We calculated the tumor properties including area, perimeter, and eccentricity. Using those properties, we then used k-medoid clustering for classification. Results Detection of tumor was per...
Impact assessment of mental subliminal activities on the human brain through neuro feedback analysis
Neuro feedback is a type of biofeedback phenomena that shows the activity on the human brain thro... more Neuro feedback is a type of biofeedback phenomena that shows the activity on the human brain through Electroencephalogram (EEG). EEG measure the electrical activity of the human brain by electrodes placed on different parts of the brain cortex. Since the human brain has complex circular firing wave patterns, EEG allows us to non-invasively measure the electrical activity of the brain waves. The intensities of theses human brain waves vary from individual to individual and changes due to various physiological, mental and physical state of the human body. This work explores the effects of sleep, attention and music on the human brain. Analysis of these activities is used to show the correlation between specific EEG patterns and the aforementioned activities.
Implementation of Single Phase Cascaded H-Bridge Nine Level Inverter and Simulation Study with PI Controller
2018 International Conference on Smart Grid and Clean Energy Technologies (ICSGCE)
A new single phase cascaded H-bridge nine level inverter is presented in this paper. The PWM tech... more A new single phase cascaded H-bridge nine level inverter is presented in this paper. The PWM technique using multicarrier based PD (phase disposition) strategy is used to generate the pulses with the help of AT89C51 microcontroller. By varying the modulation indices value to 0.25, 0.5, 0.75 and 1, accordingly different levels of output voltages such as 3, 5, 7 and 9 levels can be achieved with R-L load. The working principle of the proposed circuit with different modes is explained in detail. In order to keep the output voltage constant and to have high dynamic performance even in the change in load condition, PI controller is used as a closed loop and verified with MATLAB/SIMULINK. In the proposed 9 level inverter with the modulation index of 1, THD of 13.55% is achieved in the output voltage. Based on power circuit component count and DC source, the proposed inverter is compared with conventional topologies. To verify the performance of the proposed architecture, simulation and experimentations are carried out on a prototype in open loop and the respective results are presented.
Development of a wearable wireless body area network for health monitoring of the elderly and disabled
IOP Conference Series: Materials Science and Engineering, Nov 1, 2017
Novel advancements in systems miniaturization, electronics in health care and communication techn... more Novel advancements in systems miniaturization, electronics in health care and communication technologies are enabling the integration of both patients and doctors involvement in health care system. A Wearable Wireless Body Area Network (WWBAN) provides continuous, unobtrusive ambulatory, ubiquitous health monitoring, and provide real time patient's status to the physician without any constraint on their normal daily life activities. In this project we developed a wearable wireless body area network system that continuously monitor the health of the elderly and the disabled and provide them with independent, safe and secure living. The WWBAN system monitors the following parameters; blood oxygen saturation using a pulse oximeter sensor (SpO2), heart rate (HR) pulse sensor, Temperature, hydration, glucose level and fall detection. When the wearable system is put on, the sensor values are processed and analysed. If any of the monitored parameter values falls below or exceeds the normal range, there is trigger of remote alert by which an SMS is send to a doctor or physician via GSM module and network. The developed system offers flexibility and mobility to the user; it is a real time system and has significance in revolutionizing health care system by enabling non-invasive, inexpensive, continuous health monitoring.
Uploads
Papers by Munyaradzi Rushambwa