Two proposals submitted by researchers in the A2IR2 have been shortlisted for the award of TETFUND National Research Fund grants for the 2020 cycle.
NgDroneNet
The first proposal titled “Development of a Smart Drone Network for Urban Security, Environmental Monitoring, and Development” aims to develop a network of autonomous quadcopter UAVs capable of intelligently extracting events of interest, thereby demonstrating the effectiveness of such platforms for significantly improving situational awareness in Nigerian cities towards security, environmental monitoring, and intelligent transportation system applications.
Security problems are now an apparently unavoidable fact of life in Nigeria. Insurgency, kidnapping and other crimes are on the increase around the country. Such security problems discourage foreign investment and are a major factor in the accelerating human capital flight as many young professionals emigrate, apart from losses in terms of lives, livelihoods and properties.
The potential of sensor-equipped Unmanned Aerial Vehicles (UAVs) to gather information-rich data over a vast region and their high mobility makes them attractive in comparison with traditional approaches used in situational awareness. However, getting the right trade-off of UAV features is challenging. The best situational awareness trade-off scenarios use large numbers of drones, which necessitates low-cost UAVs such as small four-motor UAVs called quadcopters. Such quadcopters however have short flight times. There is therefore a need for a system that allows the extension of cumulative flight time for quadcopters while deploying them for intelligent situational awareness functions. This research will develop a quadcopter network consisting of low-cost sensor-equipped quadcopters and control nodes to tackle the lack of low-cost situational awareness infrastructures for security, environmental and planning uses.
The multi-institution, multidisciplinary research team includes Dr. K.P. Ayodele (Principal Investigator), Prof. P.O. Ogunbona, Dr. F.B. Offiong, Dr. A. A. Ogunseye, and Mr. S. P. Olayiwola.
MMN and EEG for Schizophrenia Management
The second grant was shortlisted under the Science, Technology and Innovation category, and aims to develop a theoretical framework by which accurate biomarkers for schizophrenia can be identified, and used as the basis for laboratory tests for the disease.
Schizophrenia is a debilitating mental disorder and one of the ten leading causes of disability worldwide. It is a chronic mental disorder associated with significant and long-lasting health, social and financial/economic burden, not only to sufferers but also on their families, public health care system as well as the wider society. Therefore, early diagnosis of schizophrenia is very important as the longer the period of untreated psychosis, the poorer the prognosis. In addition, life expectancy in patients with schizophrenia is one to two decades shorter when compared to the general population. Hence, prompt and correct diagnosis of schizophrenia is of public health importance. In the clinical setting, the diagnosis of schizophrenia is made using diagnostic criteria based on symptoms, this is unlike other medical specialties where diagnosis is often based on aetiology and supported by objective laboratory investigations. For schizophrenia our understanding of its aetiology, neurophysiology and neuropathology is still limited, and there are no objective laboratory investigations for diagnosis of schizophrenia due largely to the poor understanding of its aetiology.
The observation that mismatch negativity (MMN) is consistently impaired in schizophrenia has made it one of the most viable measures upon which objective laboratory tests for this condition can be based. Further investigation on the use of MMN however has shown that while MMN outperforms other candidate measures, it solely is not accurate enough for clinical use. Hence, this project proposes a technique to improve the accuracy of MMN by combining its performance with those of fuzzy entropy and Auditory Steady-State Response (ASSR) extracted from the patient’s electroencephalography recordings. It is expected that the integration of these multiple measures into a single index will result in an objective and more accurate diagnosis and classification of schizophrenia in addition to existing clinical diagnostic criteria. This study could lead to an accurate and easy-to-administer laboratory test for the diagnosis and classification of schizophrenia, which would have profound impact on the management of the disorder globally.
The project is led by Prof. K.S. Mosaku of the Department of Mental Health. Dr. K.P. Ayodele leads the Engineering team, which also includes Dr. O. B. Akinwale and Dr. E. Obayiuwana.