Browsing by Author "Aibinu, A. M."

Now showing 1 - 20 of 26

A modified Otsu’s algorithm for improving the performance of the energy detector in cognitive radio
(Urban & Fischer, 2017-09-01) Onumanyi, A. J.; Onwuka, E. N.; Aibinu, A. M.; Ugweje, O. C.; Salami, Momoh-Jimoh E.
In this paper, we present a modified Otsu’s algorithm for solving the automatic threshold estimation problem in energy detection based Cognitive Radio (CR) application. The modified algorithm was tested extensively and compared with other known algorithms using both simulated and real datasets. In particular, our findings reveal that the modified algorithm provides an averagely lower false alarm rate than the other techniques compared with in this paper. Furthermore, the results obtained show that the algorithm is independent of the bandwidth’s size, while having a total complexity of O (V), where V is the total sample size. Thus, from the results of this paper, full and effective automatic blind spectrum sensing using an Energy Detector is possible in CR. This can be achieved at a Signal-to-Noise Ratio of 5 dB to meet the IEEE 802.22 draft standard of P D> 90% and P FA< 10%.
A new method of vascular point detection using artificial neural network
(IEEE, 2012-12-17) Kader, S.; Aibinu, A. M.; Salami, Momoh-Jimoh E.
Vascular intersection is an important feature in retina fundus image (RFI). It can be used to monitor the progress of diabetes hence accurately determining vascular point is of utmost important. In this work a new method of vascular point detection using artificial neural network model has been proposed. The method uses a 5×5 window in order to detect the combination of bifurcation and crossover points in a retina fundus image. Simulated images have been used to train the artificial neural network and on convergence the network is used to test (RFI) from DRIVE database. Performance analysis of the system shows that ANN based technique achieves 100% accuracy on simulated images and minimum of 92% accuracy on RFI obtained from DRIVE database.
A novel hybrid artificial intelligence technique for colpitts oscillator design
(Springer US, 2014-02-01) Ghazali, Mohamad; Amsa, Ameer; Aibinu, A. M.; Salami, Momoh-Jimoh E.
In the design of the common base Colpitts oscillator, the resistance values of Thevenin’s resistors significantly influenced the transient time and steady state response of the resulting circuit. Various traditional approaches such as intuitive reasoning, mathematical calculation, and simulation-based techniques have been proposed in the literature for this purpose. Some of the aforementioned techniques involve rigorous mathematics, intuition, and experimentation in determining appropriate component values for optimal performance, stable steady state performance, and short transient response time from the resulting oscillator. In this paper, a new method of designing Colpitts oscillator using hybrid artificial intelligence comprising evolutionary-based Genetic Algorithm (GA) and artificial neural network (ANN) has been proposed. GA has been used in selecting various optimum resistance values of Thevenin’s resistors for maximizing long-term stability of the output waveform thus ensuring stable steady response of the designed circuit. ANN has been utilized in learning the nonlinear relationship between Thevenin’s resistors and transient time response of the Colpitts oscillator. Upon ANN convergence, optimum resistance values of obtained from GA process are fed into the trained ANN in predicting transient response time of each circuit. Optimized values with the shortest transient response time are finally selected for the Colpitts oscillator. The designed circuit successfully achieved optimization between its transient time response and steady state response. Hence, successfully reducing computation associated with existing traditional techniques in designing similar optimum Colpitts oscillator and achieving stable steady state output. Furthermore, this work has also demonstrated that ANN is capable of predicting the transient time of circuit with reasonable accuracy.
A novel palmprint segmentation technique
(IEEE, 2011-12-12) Rotinwa-Akinbile, M. O.; Aibinu, A. M.; Salami, Momoh-Jimoh E.
Recent paradigm shift from the conventional contact based palmprint recognition to contactless based systems (CBS) has necessitated the development of a variety of these systems. A major challenge of these systems is it robustness to illumination variation in unconstrained environment, thus making segmentation difficult. In this paper, the acquired image undergoes color space conversion and the output is filtered using coefficients obtained from the training of an artificial neural network (ANN) based model coefficient determination technique. Performance analysis of the proposed technique shows better performance in term of mean square error, true positive rate and accuracy when compared with two other techniques. Furthermore, it has also been observed that the proposed method is illumination invariant hence its suitability for deployment in contactless palmprint recognition systems.
A real valued neural network based autoregressive energy detector for cognitive radio application
(Hindawi, 2014) Onumanyi, A. J.; Onwuka, E. N.; Aibinu, A. M.; Ugweje, O. C.; Salami, Momoh-Jimoh E.
A real valued neural network (RVNN) based energy detector (ED) is proposed and analyzed for cognitive radio (CR) application. This was developed using a known two-layered RVNN model to estimate the model coefficients of an autoregressive (AR) system. By using appropriate modules and a well-designed detector, the power spectral density (PSD) of the AR system transfer function was estimated and subsequent receiver operating characteristic (ROC) curves of the detector generated and analyzed. A high detection performance with low false alarm rate was observed for varying signal to noise ratio (SNR), sample number, and model order conditions. The proposed RVNN based ED was then compared to the simple periodogram (SP), Welch periodogram (WP), multitaper (MT), Yule-Walker (YW), Burg (BG), and covariance (CV) based ED techniques. The proposed detector showed better performance than the SP, WP, and MT while providing better false alarm performance than the YW, BG, and CV. Data provided here support the effectiveness of the proposed RVNN based ED for CR application.
A Review of Forecasting Techniques
(The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp), 2012) Ghazali, Mohamad; Amsa, Ameer; Aibinu, A. M.; Salami, Momoh-Jimoh E.; Balogun, Wasiu
This work examines recent publications in forecasting in various fields, these include: wind power forecasting; electricity load forecasting; crude oil price forecasting; gold price forecasting energy price forecasting etc. In this review, categorization of the processes involve in forecasting are divided into four major steps namely: input features selection; data pre-processing; forecast model development and performance evaluation. The various methods involve are discussed in order to provide the overall view about possible options for development of forecasting system. It is intended that the classification of the steps into small categories with definitions of terms and discussion of evolving techniques will provide guidance for future forecasting sytem designers.
Adaptive Short Time Fourier Transform (STFT) Analysis of seismic electric signal (SES): A comparison of Hamming and rectangular window
(IEEE, 2012-09-23) Astuti, W.; Sediono, W.; Aibinu, A. M.; Akmeliawati, R.; Salami, Momoh-Jimoh E.
Seismic electric signal (SES) is one of features for predicting earthquakes (EQs) because of its significant changes in the amplitude of the signal prior to the earthquake. This paper presents detailed analysis of SES recorded prior to earthquake that occurred in Greece in the period from January 1, 2008 to June 30, 2008. During this period of time 5 earthquakes were recorded with magnitudes greater than 6R. In this analysis STFT involving adaptively sliding window technique is used, in which Hamming and rectangular window functions are applied and compared. The comparison shows that Hamming window gives better results in analyzing the first significantly changes of SES prior to the EQ. The application of Hamming window resulted in less rippled spectrum shape which is more suitable to be used in characterizing the SES.
Analysis of transient multiexponential signals using cepstral deconvolution
(Academic Press, 2010-07-01) Jibia, Abdussamad U.; Salami, Momoh-Jimoh E.; Khalifa, Othman O.; Aibinu, A. M.
We propose and test a new method of multiexponential transient signal analysis. The method based on cepstral deconvolution is fast and computationally inexpensive. The multiexponential signal is initially converted to a deconvolution model using Gardners' transformation after which the proposed method is used to deconvolve the data. Simulation and experimental results indicate that this method is good for determining the number of components but performs poorly in accurately estimating the decay rates. Influence of noise is not considered in this paper.
Animal sound activity detection using multi-class support vector machines
(IEEE, 2005-05-17) Astuti, W.; Aibinu, A. M.; Salami, Momoh-Jimoh E.; Akmelawati, R.; Muthalif, Asan G. A.
On March 11th 2011, the whole world was taken aback by another tragic experience of Tsunami triggered by a magnitude 9.8 earthquake in Japan. Just few days after that, on March 25th 2011, another earthquake of magnitude 6.8 hit Myanmar deaths and destructions. Despite the loss incurred on properties and human being, available data show that relatively few numbers of animals died during most natural disasters. Prior to the occurrence of these disasters, available reports shows that animals do migrate to higher level or leave the areas en masse ahead of the event. Other related account show that animal sometimes behaves in unusual ways prior to the occurrence of these natural disasters. These overwhelming evidences point to the fact that animals might have the ability to sense impending natural disaster precursor signals ahead of time. This paper discusses the preliminary results obtained from the use of support vector machine (SVM) and Mel-frequency cepstral coefficients (MFCC) in the development of animal sound activity detection (ASAD) which is an integral part in the development of earthquake and natural disaster prediction using unusual animal behavior. The use of MFCC has been proposed for the features extraction stage while SVM has been proposed for classification of the extracted features. Preliminary results obtained shows that the MFCC and SVM can be used for features extraction and features classification respectively.
Application of intelligent technique for development of Colpitts oscillator
(IEEE, 2013-04-07) Salami, Momoh-Jimoh E.; Aibinu, A. M.
In this paper, new method of Colpitts oscillator designing through combination of Genetic Algorithm and Artificial Neural Network (ANN) has been suggested. The Thevenin's resistors for the common base Colpitts oscillator are optimized through application of GA and ANN. The developed common base Colpitts oscillator has shortest transient time response and stable Direct Current (DC) stability in the long term operation. Involvement of GA and ANN successfully optimize between transient time response and steady state response of common base oscillator. Application of these two artificial intelligent techniques assist faster selection of optimizes components values such as resistance values during circuit development rather than conventional method which used intuition techniques to develop the circuit.
Application of modeling techniques to diabetes diagnosis
(IEEE, 2010-11-30) Aibinu, A. M.; Salami, Momoh-Jimoh E.; Shafie, A. A.
In recent times, the introduction of complex-valued neural networks (CVNN) has widened the scope and applications of real-valued neural network (RVNN) and parametric modeling techniques. In this paper, new expert systems for automatic diagnosis and classification of diabetes using CVNN and RVNN based parametric modeling approaches have been suggested. Application of complex data normalization technique converts the real valued input data to complex valued data (CVD) by the process of phase encoding over unity magnitude. CVNN learn the relationship between the input and output phase encoded data during training and the coefficients of Complex-valued autoregressive (CAR) model can be extracted from the complex-valued weights and coefficients of the trained network. Classification of the obtained CAR or RVAR model coefficients results in required distinct classes for diagnosis purpose. Similar operations can be performed for real-valued autoregressive technique except for CVD normalization. The effect of data normalization techniques, activation functions, learning rate, number of neurons in the hidden layer and the number of epoch using the suggested techniques on PIMA INDIA diabetes dataset have been evaluated in this paper. Results obtained compares favorably with earlier reported results.
Assessment of Mould Growth on Building Materials using Spatial and Frequency Domain Analysis Techniques
(IJCSNS, 2009-07) Aibinu, A. M.; Salami, Momoh-Jimoh E.; Shafie, A.; Ali, M.; Bamgbopa, I. A.
The phenomenon of Sick Building Syndrome (SBS), Building Related Illness (BRI) and some other indoor related diseases have been attributed to mould and fungi exposure in the indoor environment. Despite the growing concern over mould and fungi infestations on building materials, little has been reported in the literature on the development of an objective tool and criteria for measuring and characterizing the shape and the level of severity of such parasitic phenomenon. In this paper, an objective based approach of mould and fungi growth assessment using spatial and frequency domain information is proposed. The spatial domain analysis of the acquired Mould Infested Images (MII) is achieved using Ratio Test (RT), Compactness Test (CT) and Visual Test (VT) while the frequency domain analysis uses the popular Discrete Fourier Transform (DFT) implemented in the form of Fast Fourier Transform (FFT) in analyzing the boundary pixel sequence. The resulting frequency components (Fourier Descriptors (FD)) can now be analyzed or stored for reconstruction purposes. Application of structural similarity measures on the reconstructed MII in spatial domain shows that the use of relative low number of FD is sufficient for analyzing, characterizing and reconstruction of the original spatial domain boundary pixels.
Automatic diagnosis of diabetic retinopathy from fundus images using digital signal and image processing techniques
(International Conference on Robotics, Vision, Information, and Signal Processing, 2011-11-28) Aibinu, A. M.; Iqbal, Muhammad I.; Nilsson, M.; Salami, Momoh-Jimoh E.
Automatic diagnosis and display of diabetic retinopathy from images of retina using the techniques of digital signal and image processing is presented in this paper. The acquired images undergo pre-processing to equalize uneven illumination associated with the acquired fundus images. This stage also removes noise present in the image. Segmentation stage clusters the image into two distinct classes while the abnormalities detection stage was used to distinguish between candidate lesions and other information. Methods of diagnosis of red spots, bleeding and detection of vein-artery crossover points have also been developed in this work using the color information, shape, size, object length to breadth ration as contained in the acquired digital fundus image. The algorithm was tested with a separate set of 25 fundus images. From this, the result obtained for Microaneurysms and Haemorrhages diagnosis shows the appropriateness of the method.
Classification of Retinal Images Based on Statistical Moments and Principal Component Analysis
(IEEE, 2014-09-23) Salami, Momoh-Jimoh E.; Khorshidtalab, A.; Baali, A.; Aibinu, A. M.
Early diagnosis of Diabetic Retinopathy (DR) has been suggested as a good measure of preventing blindness associated with Diabetes. Some of the reported methodologies of Retinal Images (RI) classification for early diagnosis of DR have been shown to involve several steps and approaches for effective and accurate diagnosis. Thus, this paper investigates the classification of RI using a two-stage procedure. The first stage includes the extraction of blood vessels from RI belonging to healthy and diabetes retinal images using a modified local entropy thresholding algorithm. In the second stage, different features are extracted including statistical moments and principal components. The set of extracted features is combined into one feature vector and fed into a Sequential Minimal Optimization (SMO) classifier. The obtained result is encouraging with an average accuracy of 68.33 %.
Comparing autoregressive moving average (ARMA) coefficients determination using artificial neural networks with other techniques
(Proc. of World Academy of Science, Engineering and Technol, 2008-06-28) Aibinu, A. M.; Salami, Momoh-Jimoh E.; Shafie, Amir A.; Najeeb, Athaur R.
Autoregressive Moving average (ARMA) is a parametric based method of signal representation. It is suitable for problems in which the signal can be modeled by explicit known source functions with a few adjustable parameters. Various methods have been suggested for the coefficients determination among which are Prony, Pade, Autocorrelation, Covariance and most recently, the use of Artificial Neural Network technique. In this paper, the method of using Artificial Neural network (ANN) technique is compared with some known and widely acceptable techniques. The comparisons is entirely based on the value of the coefficients obtained. Result obtained shows that the use of ANN also gives accurate in computing the coefficients of an ARMA system.
Damage index: Assessment of mould growth on building materials using digital image processing technique
(IEEE, 2008-05-13) Bamgbopa, I. A.; Aibinu, A. M.; Salami, Momoh-Jimoh E.; Shafie, A.; Ali, M.; Kassim, Jahn P. S.
There is a growing concern over the adverse health effects of exposure to high concentration of mould spores in the indoor environments. Copious epidemiological studies have shown a direct relationship between the exposure to indoor mould and several adverse health effects. The phenomenon of Sick building syndrome (SBS) and Building Related Illness (BRI) have also been attributed to moulds exposure in the indoor environment. In spite of this growing concern, little have been reported on the development of an objective mould assessment particularly criteria for visual inspection of mould growth on building materials. The main premise of this study is that visual inspection related with mould damaged material can lead to objective ranking of the severity of damaged material, and reduce the subjective nature of mould dam-aged estimation by the use digital image processing (DIP) techniques. A four stage technique procedure, involving image preprocessing, Image segmentation and mould analysis and classification stage for the detection of mould growth is examined in this paper. Results obtained when this proposed algorithm was applied to acquired digital images collected from different infested building materials indicates the appropriateness of this method in enhancing the visual assessment and grading associated with mould growth on building materials
Detection of vascular intersection in retina fundus image using modified cross point number and neural network technique
(IEEE, 2008-05-13) Iqbal, Muhammad I.; Aibinu, A. M.; Nilsson, Mikael; Tijani, I. B.; Salami, Momoh-Jimoh E.
Vascular intersection can be used as one of the symptoms for monitoring and diagnosis of diabetic retinopathy from fundus images. In this work we apply the knowledge of digital image processing, fuzzy logic and neural network technique to detect bifurcation and vein-artery cross-over points in fundus images. The acquired images undergo preprocessing stage for illumination equalization and noise removal. Segmentation stage clusters the image into two distinct classes by the use of fuzzy c-means technique, neural network technique and modified cross-point number (MCN) methods were employed for the detection of bifurcation and cross-over points. MCN uses a 5x5 window with 16 neighboring pixels for efficient detection of bifurcation and cross over points in fundus images. Result obtained from applying this hybrid method on both real and simulated vascular points shows that this method perform better than the existing simple cross-point number (SCN) method, thus an improvement to the vascular point detection and a good tool in the monitoring and diagnosis of diabetic retinopathy.
Development of an intelligent scorpion detection technique using vibration analysis
(IEEE, 2014-06-03) Aibinu, A. M.; Sadiq, B. A.; Joseph, E.; Salau, Bello H.; Salami, Momoh-Jimoh E.
A possible solution to address the problem of Scorpion stings is the capability of detecting its presence earlier before it stings. This paper presents efforts in Scorpion detection using substrate vibration modelling approach. An eight stage approach has been presented in this work. Using sinusoidal signal, signal representing Scorpion behaviour was firstly sampled and then amplified before transmitting to a nearby receiving module. The received signal undergoes filtering for noise removal before being modelled for coefficients determination. The computed coefficients were then clustered for analysis of behavioural determination. Results obtained in this work show that the proposed technique can be used for Scorpion detection.
Development of hybrid artificial intelligent based handover decision algorithm
(Elsevier, 2017-04-01) Aibinu, A. M.; Onumanyi, A. J.; Adedigba, A. P.; Ipinyomi, M.; Folorunso, T. A.; Salami, Momoh-Jimoh E.
The possibility of seamless handover remains a mirage despite the plethora of existing handover algorithms. The underlying factor responsible for this has been traced to the Handover decision module in the Handover process. Hence, in this paper, the development of novel hybrid artificial intelligent handover decision algorithm has been developed. The developed model is made up of hybrid of Artificial Neural Network (ANN) based prediction model and Fuzzy Logic. On accessing the network, the Received Signal Strength (RSS) was acquired over a period of time to form a time series data. The data was then fed to the newly proposed ahead ANN-based RSS prediction system for estimation of prediction model coefficients. The synaptic weights and adaptive coefficients of the trained ANN was then used to compute the ahead ANN based RSS prediction model coefficients. The predicted RSS value was later codified as Fuzzy sets and in conjunction with other measured network parameters were fed into the Fuzzy logic controller in order to finalize handover decision process. The performance of the newly developed ahead ANN based RSS prediction algorithm was evaluated using simulated and real data acquired from available mobile communication networks. Results obtained in both cases shows that the proposed algorithm is capable of predicting ahead the RSS value to about ±0.0002 dB. Also, the cascaded effect of the complete handover decision module was also evaluated. Results obtained show that the newly proposed hybrid approach was able to reduce ping-pong effect associated with other handover techniques.
Electricity Theft Prediction on Low Voltage Distribution System Using Autoregressive
(International Journal of Research in Engineering and Technology, 2012) Abdullateef, A. I.; Salami, Momoh-Jimoh E.; Musse, M. A.; Aibinu, A. M.; Onasanya, Onasanya
Electricity consumers tend to avoid the payment of electricity dues through various methods such as tampering with energy meter and illegal tapping via direct connection to the distribution feeder. This has led to huge revenue losses by the electricity supplying corporation and the related government or private agencies. A new approach of detecting electricity theft on low voltage distribution systems, either single or three phase, based on the advanced signal processing using linear prediction is presented in this paper. Consumer data were analyzed using Autoregressive (AR) model in order to predict the quantity of power consumed within the specified interval and consequently, compare the result obtained with the actual data recorded against the consumer under study. Thus the model developed was used to predict power consumption at 30minutes interval ahead, thereby facilitating the detection of electricity theft if there is a wide variation between the actual and the predicted data.