Prediction of neuro-degenerative disorders using sunflower optimisation algorithm and Kernel extreme learning machine: A case-study with Parkinson’s and Alzheimer’s disease

Parkinson’s and Alzheimer’s Disease are believed to be most prevalent and common in older people. Several data-mining approaches are employed on the neuro-degenerative data in predicting the disease. A novel method has been built and developed to diagnose Alzheimer’s (AD) and Parkinson’s (PD) in early stages, which includes image acquisition, pre-processing, feature extraction and selection, followed by classification. The challenge lies in selecting the optimal feature subset for classification. In this work, the Sunflower Optimisation Algorithm (SFO) is employed to select the optimal feature set, which is then fed to the Kernel Extreme Learning Machine (KELM) for classification. The method is tested on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and local dataset for AD, the University of California, Irvine (UCI) machine learning repository and the Istanbul dataset for PD. Experimental outcomes have demonstrated a high accuracy level in both AD and PD diagnosis. For AD diagnosis, the highest classification rate is obtained for the AD versus NC classification using the ADNI dataset (99.32%) and local dataset (98.65%). For PD diagnosis, the highest accuracy of 99.52% and 99.45% is achieved on the UCI and Istanbul datasets, respectively. To show the robustness of the method, the method is compared with other similar methods of feature selection and classification with 10-fold cross-validation (CV) and with unseen data. The method proposed has an excellent prospect, bringing greater convenience to clinicians in making a better solid decision in clinical diagnosis of neuro-degenerative diseases.

Code Optimisation Framework for Multicode Sonar Systems

<p>The ocean is a temporally and spatially varying environment, the characteristics of which pose significant challenges to the development of effective underwater wireless communications and sensing systems. An underwater sensing system such as a sonar detects the presence of a known signal through correlation. It is advantageous to use multiple transducers to increase surveying area with reduced surveying costs and time. Each transducers is assigned a dedicated code. When using multiple codes, the sidelobes of auto- and crosscorrelations are restricted to theoretical limits known as bounds. Sets of codes must be optimised in order to achieve optimal correlation properties, and, achieve Sidelobe Level (SLL)s as low as possible. In this thesis, we present a novel code-optimisation method to optimise code-sets with any number of codes and up to any length of each code. We optimise code-sets for a matched filter for application in a multi-code sonar system. We first present our gradient-descent based algorithm to optimise sets of codes for flat and low crosscorrelations and autocorrelation sidelobes, including conformance of the magnitude of the samples of the codes to a target power profile. We incorporate the transducer frequency response and the channel effects into the optimisation algorithm. We compare the correlations of our optimised codes with the well-known Welch bound. We then present a method to widen the autocorrelation mainlobe and impose monotonicity. In many cases, we are able to achieve SLLs beyond the Welch bound. We study the Signal to Noise Ratio (SNR) improvement of the optimised codes for an Underwater Acoustic (UWA) channel. During its propagation, the acoustic wave suffers non-constant transmission loss which is compensated by the application of an appropriate Time Variable Gain (TVG). The effect of the TVG modifies the noise received with the signal. We show that in most cases, the matched filter is still the optimum filter. We also show that the accuracy in timing is very important in the application of the TVG to the received signal. We then incorporate Doppler tolerance into the existing optimisation algorithm. Our proposed method is able to optimise sets of codes for multiple Doppler scaling factors and non-integer delays in the arrival of the reflection, while still conforming to other constraints. We suggest designing mismatched filters to further reduce the SLLs, firstly using an existing Quadratically Constrained Qaudratic Program (QCQP) formulation and secondly, as a local optimisation problem, modifying our basic optimisation algorithm.</p>

Code Optimisation Framework for Multicode Sonar Systems

<p>The ocean is a temporally and spatially varying environment, the characteristics of which pose significant challenges to the development of effective underwater wireless communications and sensing systems. An underwater sensing system such as a sonar detects the presence of a known signal through correlation. It is advantageous to use multiple transducers to increase surveying area with reduced surveying costs and time. Each transducers is assigned a dedicated code. When using multiple codes, the sidelobes of auto- and crosscorrelations are restricted to theoretical limits known as bounds. Sets of codes must be optimised in order to achieve optimal correlation properties, and, achieve Sidelobe Level (SLL)s as low as possible. In this thesis, we present a novel code-optimisation method to optimise code-sets with any number of codes and up to any length of each code. We optimise code-sets for a matched filter for application in a multi-code sonar system. We first present our gradient-descent based algorithm to optimise sets of codes for flat and low crosscorrelations and autocorrelation sidelobes, including conformance of the magnitude of the samples of the codes to a target power profile. We incorporate the transducer frequency response and the channel effects into the optimisation algorithm. We compare the correlations of our optimised codes with the well-known Welch bound. We then present a method to widen the autocorrelation mainlobe and impose monotonicity. In many cases, we are able to achieve SLLs beyond the Welch bound. We study the Signal to Noise Ratio (SNR) improvement of the optimised codes for an Underwater Acoustic (UWA) channel. During its propagation, the acoustic wave suffers non-constant transmission loss which is compensated by the application of an appropriate Time Variable Gain (TVG). The effect of the TVG modifies the noise received with the signal. We show that in most cases, the matched filter is still the optimum filter. We also show that the accuracy in timing is very important in the application of the TVG to the received signal. We then incorporate Doppler tolerance into the existing optimisation algorithm. Our proposed method is able to optimise sets of codes for multiple Doppler scaling factors and non-integer delays in the arrival of the reflection, while still conforming to other constraints. We suggest designing mismatched filters to further reduce the SLLs, firstly using an existing Quadratically Constrained Qaudratic Program (QCQP) formulation and secondly, as a local optimisation problem, modifying our basic optimisation algorithm.</p>

The Whale Optimization Algorithm Approach for Deep Neural Networks

One of the biggest challenge in the field of deep learning is the parameter selection and optimization process. In recent years different algorithms have been proposed including bio-inspired solutions to solve this problem, however, there are many challenges including local minima, saddle points, and vanishing gradients. In this paper, we introduce the Whale Optimisation Algorithm (WOA) based on the swarm foraging behavior of humpback whales to optimise neural network hyperparameters. We wish to stress that to the best of our knowledge this is the first attempt that uses Whale Optimisation Algorithm for the optimisation task of hyperparameters. After a detailed description of the WOA algorithm we formulate and explain the application in deep learning, present the implementation, and compare the proposed algorithm with other well-known algorithms including widely used Grid and Random Search methods. Additionally, we have implemented a third dimension feature analysis to the original WOA algorithm to utilize 3D search space (3D-WOA). Simulations show that the proposed algorithm can be successfully used for hyperparameters optimization, achieving accuracy of 89.85% and 80.60% for Fashion MNIST and Reuters datasets, respectively.

Research on a reference signal optimisation algorithm for indoor Bluetooth positioning

GPS has a sharp performance decline in terms of accuracy indoors due to the complex building structure. A combined algorithm, targeting at received signal strength indication (RSSI) calibration optimisation, depending on deep neural network training via input vector Γ and the target output vector Ψ, termed reference signal optimisation algorithm (RSOA) is proposed to improve the positioning accuracy in the indoor Bluetooth positioning networks. Experimental results show that the relative error of the proposed RSOA between the estimated results and the measured ones can reach as low as 0.2%, and the absolute errors can be reduced to 0.13 m at most within 10 m.

Regional Atmospheric Light Optimisation Algorithm for Heterogeneous Image Dehazing

Under foggy and other severe weather conditions, image acquisition equipment is not effective. It often produces an image with low contrast and low scene brightness, which is difficult to use in other image-based applications. The dark channel prior dehazing algorithm will cause the brightness of the image to decrease and sometimes introduce halos in the sky area. To solve this problem, we proposed a region similarity optimisation algorithm based on a dark channel prior. First, a vector comprising RGB layer dark channel value was obtained as the original atmospheric ambient light, and then, the proposed regional similarity linear function was used to adjust the atmospheric ambient light matrix. Next, the transmittance of different colour channels was derived and the multichannel soft matting algorithm was employed to produce more effective transmittance. Finally, the atmospheric ambient light and transmittance were substituted into the atmospheric scattering model to calculate clean images. Experimental results show that the proposed algorithm outperformed the existing mainstream dehazing algorithms in terms of both visual judgement and quality analysis with nonhomogeneous haze datasets. The algorithm not only improves the image details but also improves the brightness and saturation of the dehazing result; therefore, the proposed algorithm is effective in the restoration of the hazy image.