Papers by Emmanuel Adetiba, Ph.D
IEEE Access
Cloud computing is a technology for efficiently using computing infrastructures and a business mo... more Cloud computing is a technology for efficiently using computing infrastructures and a business model for selling computing resources and services. However, intruders find such complex and distributed infrastructures appealing targets for cyber-attacks. Cyber-attacks are severe threats that can jeopardize the quality of service provided to clients and compromise data integrity, confidentiality, and availability. Cyberattacks are becoming more complex, making it more challenging to detect intrusions effectively. Due to the high traffic and increased malicious activities on the Internet, a single Intrusion Detection System (IDS) can be overwhelmed. Despite the various Deep Learning (DL) approaches that have been proposed as alternative solutions, there are still pertinent security issues to be addressed especially in federated cloud computing domains. This work proposes a Secure Federated Intrusion Detection Model Version 1 (SecFedIDM-V1) using blockchain technology and Bidirectional Long Short-Term Memory (BiLSTM) Recurrent Neural Network (RNN). The Cobourg Intrusion Detection Dataset (CIDDS) was acquired, preprocessed and split into 60:20:20, 70:15:15, and 80:10:10 for training, testing, and validation respectively to develop the proposed intrusion traffic classification component of the proposed model. The developed SecFedIDM-V1 was later deployed as a Python-based web application that captures network packets for classifying attacks into normal or an attack type. The attack packets are recorded in a Hyperledger Fabric (a private blockchain technology) to serve as a signature database to be used by other nodes in the network. From the evaluation results of the intrusion classifier, the 80:10:10 BiLSTM network performed better than GRU with a Precision of 0.99624, Recall of 0.99906, F1 Score of 0.99614, False Positive Rate (FPR) of 0.00094, False Negative Rate (FNR) of 0.00395 and True Positive Rate (TPR) of 0.99605. The SecFedIDM-V1 can be deployed alongside Firewalls in a federated cloud computing environment to reinforce the security of the infrastructure. INDEX TERMS Blockchain, intrusion detection, deep learning, recurrent neural network. The associate editor coordinating the review of this manuscript and approving it for publication was Nitin Gupta .
Lecture notes in networks and systems, Nov 10, 2022
Lecture notes in networks and systems, 2023
International Journal of Computing and Digital Systems, Aug 1, 2023
In conventional farming, farmers have to go around the farmland physically frequently to estimate... more In conventional farming, farmers have to go around the farmland physically frequently to estimate the various environmental parameters like temperature, humidity, light intensity and soil moisture to harvest the ready crops at the appropriate time in the best soil possible. Although this conventional farming technique has been utilized for many years, it is irregular and fails to exhibit a high productivity rate because farmers sometimes cannot precisely assess all of the environmental parameters. Greenhouse farming, on the other hand, is a technique whereby the farmers grow crops in ecosystem habitats where all environmental factors are modified to suit the crop type. Automation in a greenhouse is a technology through which farmers may monitor and regulate the greenhouse environment automatically from anywhere in the globe at any time. This work aims to develop an automated greenhouse monitoring and controlling system, which integrates multiple sensors such as a temperature sensor, humidity sensor, light-dependent resistor sensor, and soil moisture sensor to obtain potential environmental parameters of the greenhouse, as well as integrate ESP32 development board, to store, process data and provide WiFi functionality. With the help of the Light Dependent Resistor (LDR), Temperature and humidity sensor and soil moisture sensor, the lighting of the bulb, fan activation and pump triggering can be controlled, respectively, whenever the environmental parameters are below the threshold value. Furthermore, with the help of the WiFi capability of the ESP32 development board, the Internet of Things (IoT) is utilized to store data in a database, process the acquired data, and eventually deliver the information to a user's web application for monitoring the environmental parameters in the greenhouse..
Active Speaker Detection (ASD) refers to the process of predicting who amongst a number of speake... more Active Speaker Detection (ASD) refers to the process of predicting who amongst a number of speakers whose faces appear on screen is speaking (if any) at any given time within the duration of a video. This paper proposes a novel method for determining active speakers in videos based on the standard deviations of Color Histograms (CHs) of the mouth region from frame-to-frame. The reasoning behind this is that the lips of an active speaker will open and close exposing and concealing the inner contents of the mouth such as the vocal cavity, teeth and tongue at fairly regular intervals in the process which are of different colors. Therefore, if the mouth region can be accurately localized and the changes in the color activities in that region analyzed during speaking such information can be used to detect if a person is actively speaking or not. The lips of a non-speaker are usually closed and at rest, so the CHs for such mouth region are expected to be fairly constant and as such the standard deviations should be low. If an experimentally determined threshold could be set, it can draw the line between active and non-active speakers. In this work, 53 videos available online from Channels TV news, one of Nigeria’s most popular TV stations were used to create 250 video clips totaling 3.6 hours, each ranging from between 15 seconds to 1 minute in such a way that the faces of two speakers were always simultaneously visible in any order in the duration of each video clip. The active speakers in each second of the video clips were manually labeled and used to evaluate the performance of the proposed methodology which achieved a prediction accuracy of up to 99.19%.
Lecture notes in electrical engineering, 2022
Social Science Research Network, 2022
IEEE Access
Cervical dilation is the most important parameter that is assessed during childbirth to validate ... more Cervical dilation is the most important parameter that is assessed during childbirth to validate that a woman is truly in labour and whether labour is progressing as expected. It is the opening of a mother's cervix from when it is closed at 0 cm to when it is fully dilated at 10 cm, for the baby to pass through and be delivered. The cervix is a cylinder-shaped tissue that connects the uterus to the vagina. Cervical dilation is majorly assessed through a highly subjective, painful, error-prone, and infection-prone Vaginal Examination method. The method involves a doctor or midwife wearing sterilized gloves and inserting his or her fingers through the vagina to manually assess cervical dilation and mentally visualize it. Hence, in this research, a prototype of a novel low-intensity light imaging probe was developed to acquire images of cervical dilation simulation models for further processing and analysis. The probe was designed with 3D computeraided design software. Finite element analysis was carried out on the design before it was rapid prototyped. Then, a camera and a light source were inserted into the probe to capture 2,880 cervical dilation images in low-light intensities of 28 Lux and 50 Lux, due to the penetration depth of bright light intensity and heat into tissues. Image preprocessing was carried out on the images by applying a low-light image enhancement technique. This research demonstrated the use of a low-intensity light imaging probe as a possible objective alternative to the subjective insertion of fingers in vaginal examination. INDEX TERMS Cervical dilation, computer-aided design, medical imaging, medical image processing, low-light image enhancement. I. INTRODUCTION In obstetrician practice, improving the quality of care and assessing vital parameters during pregnancy, childbirth, and the immediate postnatal period have been identified as impactful strategies for preventing and reducing maternal deaths [1], [2], [3]. Quality of care during childbirth involves The associate editor coordinating the review of this manuscript and approving it for publication was Santosh Kumar. access to quality obstetric emergency care, availability of skilled obstetric workforce, strengthening of health systems and services, investments in health systems and technologies, quality training of midwives, doctors, and health workers, inter-professional and multidisciplinary collaboration, and innovative leadership and governance initiatives [4], [5], [6], [7], [8]. Development and deployment of innovative childbirth monitoring systems and devices will enhance the early
2023 International Conference on Science, Engineering and Business for Sustainable Development Goals (SEB-SDG)
Lecture notes in networks and systems, 2023
Mathematical modelling of engineering problems, Dec 13, 2022
In the vehicle industry, connectivity and autonomy are becoming increasingly important features. ... more In the vehicle industry, connectivity and autonomy are becoming increasingly important features. One of the most used protocols for in-vehicle communication is the Controller Area Network (CAN) bus which manages the communication between networked components. However, the CAN bus, despite its critical importance, lacks sufficient security features to protect its network as well as the overall car system. Thus, vehicle network security is becoming increasingly crucial. Methods of intrusion detection help to improve the security of the in-vehicle network. This work aims to provide a model that enables effective detection of attacks such as fuzzy, DoS, and impersonation using the Deep Feedforward Neural Network (DeepFNN) model as well as the Long Short-Term Memory model. Moreover, the LSTM model presents the most satisfying outcome in terms of precision and recall metrics.
2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON)
2022 30th Southern African Universities Power Engineering Conference (SAUPEC), 2022
For high-frequency microwave systems, rain attenuation is the most severe impairment to propagati... more For high-frequency microwave systems, rain attenuation is the most severe impairment to propagation. To determine the suitable transmission and reception quality, system design engineers require knowledge of the cumulative distribution of the rainfall rates and the rain-induced attenuation throughout the coverage region. This work provides a catalog of rain-rate and rain-attenuation contour maps useful for sizing network power and planning links over the Southern African region. They were created using rainfall rates determined from a 32-year precipitation product from the Climatic Research Unit (CRU) and attenuation estimates for hypothetical space-earth networks for receiving digital satellite television content over selected countries in the Southern African subregion.
IOP Conference Series: Materials Science and Engineering, 2021
Mobility has been identified to be a major characteristic of living things. Humans who are depriv... more Mobility has been identified to be a major characteristic of living things. Humans who are deprived of efficient mobility either by natural or man-made factors loose significant relationship with their environment. The growing demand to produce effective rehabilitation devices for the aged population and disabled individuals, have spurred us to develop a reliable and easy to use biosignal based auto control wheelchair. This is to ensure independent mobility of persons with disabilities and the aged. In this paper, a Recurrent Neural Network (RNN) architecture called Long Short Term Memory (LSTM) is engaged for the classification EMG signals to the corresponding hand-gesture category. The LSTM model in this study yielded a validation accuracy that provides a basis for an improved solution towards real-time deployment.
Path loss model is essential to achieving a successful cellular network planning and deployment. ... more Path loss model is essential to achieving a successful cellular network planning and deployment. Despite the benefits derived from models that have become standard and are widely adopted, the actual applicability of these models depends on the local ambient characteristics of the environment. This means that environments that substantially differ from those used to create the models will not be adequately characterized, and so the resulting cellular planning fails to some extent. Therefore, the models used may substantially benefit from calibration to ensure fitness with the actual measurements collected over a given area. This paper presents a calibration procedure based on the Standard Propagation Model (SPM), and applies to the 900 MHz and 1800 MHz bands. In particular, signal strength data were collected along four routes in residential areas, and the results were then processed using the ATOLL network planning tool. Overall, we find that, after a proper calibration, the SPM pro...
Polygenic risk score (PRS) analysis is a powerful method been used to estimate an individual’s ge... more Polygenic risk score (PRS) analysis is a powerful method been used to estimate an individual’s genetic risk towards targeted traits. PRS analysis could be used to obtain evidence of a genetic effect beyond Genome-Wide Association Studies (GWAS) results i.e. when there are no significant markers. PRS analysis has been widely applied to investigate the genetic basis of several traits including rare diseases. However, the accuracy of PRS analysis depends on the genomic data of the underlying population. For instance, several studies showed that obtaining higher prediction power of PRS analysis is challenging for non-Europeans. In this manuscript, we reviewed the conventional PRS methods and their application to sub-saharan Africa communities. We concluded that the limiting factor of applying PRS analysis to sub-saharan populations is the lack of sufficient GWAS data. Also, we recommended developing African-specific PRS tools. keywords Prediction medicine, GWAS, post-GWAS, PRS analysis,...
Journal of Physics: Conference Series, 2021
The rising demand for data and its machine-aided dynamics calls for more deliberate effort on sta... more The rising demand for data and its machine-aided dynamics calls for more deliberate effort on standardized collection, especially in formats suitable for identifying relationships between its features. This paper reports the implementation of cloud-based biometric attendance system to address the limitations associated with the traditional attendance system, which is still predominantly in use across institutions in developing countries. The cloud-based attendance uses a fingerprint recognition system for authenticating attendance, displays user identity via Organic Light Emitting Diode (OLED) display and uploads the processed attendance data into cloud with the aid of the ESP32 microcontroller and its development board. At the point of taking the attendance, the system exclusively authenticates and processes the attendance of the pre-registered candidates whose fingerprints matches those pre-stored and uploads the result into the cloud for access by the administrator remotely. The system is simple and modular with an impressive performance, recording authentication and loading to cloud at an average of 2-5 seconds per candidate. With this system in place, it would be easier to get the required data to enforce the eligibility criteria for assessment and this invariably would also encourage punctuality and students’ participation in classroom activities.
Journal of Physics: Conference Series, 2019
Heat Transfer—Asian Research, 2016
Magnetohydrodynamic (MHD) natural convection flow and associated heat convection in an oriented e... more Magnetohydrodynamic (MHD) natural convection flow and associated heat convection in an oriented elliptic enclosure has been investigated with numerical simulations. A magnetic field was applied to the cylindrical wall of the configuration, the top and bottom walls of the enclosure were circumferentially cooled and heated, respectively, while the extreme ends along the cross‐section of the elliptic duct were considered adiabatic. The full governing equations in terms of continuity, momentum, and energy transport were transformed into nondimensional form and solved numerically using finite difference method adopting Gauss–Seidel iteration technique. The selected geometrical parameters and flow properties considered for the study were eccentricity (0, 0.2, 0.4, 0.6, and 0.8), angle of inclination (0°, 30°, 60°, and 90°), Hartmann number (0, 25, and 50), Grashof number (104, 105, and 106), and Darcy number (10−3, 10−4, and 10−5). The Prandtl number was held constant at 0.7. Numerical re...
Uploads
Papers by Emmanuel Adetiba, Ph.D