Browsing by Author "Taherkhani, Aboozar"
Now showing 1 - 12 of 12
Results Per Page
Sort Options
Item Embargo 3D Object Reconstruction with Deep Learning(Springer, 2024-05-06) Aremu, Stephen S.; Taherkhani, Aboozar; Liu, Chang; Yang, ShengxiangRecent advancements and breakthroughs in deep learning have accelerated the rapid development in the field of computer vision. Having recorded a huge success in 2D object perception and detection, a lot of progress has also been made in 3D object reconstruction. Since humans can infer and relate better with 3D world images by just a single view 2D image of the object, it is necessary to train computers to think in 3D to achieve some key applications of computer vision. The use of deep learning in 3D object reconstruction of single-view images is rapidly evolving and recording significant results. In this research, we explore the Facebook well-known hybrid approach called Mesh R-CNN that combines voxel generation and triangular mesh re-construction to generate 3D mesh structure of an object from a 2D single-view image. Although the reconstruction of objects with varying geometry and topology was achieved by Mesh R-CNN, the mesh quality was affected due to topological errors like self-intersection, causing non-smooth and rough mesh generation. In this research, Mesh R-CNN with Laplacian Smoothing (Mesh R-CNN-LS) was proposed to use the Laplacian smoothing and regularization algorithm to refine the non-smooth and rough mesh. The proposed Mesh R-CNN-LS helps to constrain the triangular deformation and generate a better and smoother 3D mesh. The proposed Mesh R-CNN-LS was compared with the original Mesh R-CNN on the Pix3D dataset and it showed better performance in terms of the loss and average precision score.Item Open Access A Machine Learning Method on a Tiny Hardware for Monitoring and Controlling a Hydroponic System(InTech Open Journals, 2025-01-24) Sharma, Arpit; Taherkhani, Anahita; Orba, Ezekiel; Taherkhani, AboozarThe implementation of artificial intelligence on very tiny chips plays an important role in the future of IoT. Generally, these chips do not conduct artificial intelligence operations locally. They just send collected data to a cloud, where artificial intelligence is located to make the decisions. This leads to time lag and intense dependency of the system on the internet connection that making it unsuitable for systems required immediate action. In a hydroponic system, it is required to control the speed of a pump immediately to control the pH level. But there are many challenges to design the intelligent system using low-powered chips that have low computational power. Therefore, achieving high AI accuracy is very difficult for them. Additionally, the tiny devices need to communicate with the user to conduct IoT operations. To overcome these challenges, in this research a hydroponic system was designed to incorporate an ESP32 chip-based microcontroller with sensors and actuators attached to it to conduct AI on edge and IoT tasks simultaneously. A dedicated android app was implemented to monitor and control the system remotely via IoT. The results show that the predicted pump speed just falls behind the expected speed by an average of 2.94%. The overall designed system is stable and reliable. Komatsuna plants were grown in a hydroponic system and the yield was compared with the plants grown in standard potting compost. The hydroponic system was monitored by the proposed method to produce a higher yield compared to the potting compost.Item Open Access AdaBoost-CNN: An Adaptive Boosting algorithm for Convolutional Neural Networks to classify Multi-Class Imbalanced datasets using Transfer Learning(Elsevier, 2020-05-12) Taherkhani, Aboozar; Cosma, Georgina; McGinnity, T.M.Ensemble models achieve high accuracy by combining a number of base estimators and can increase the reliability of machine learning compared to a single estimator. Additionally, an ensemble model enables a machine learning method to deal with imbalanced data, which is considered to be one of the most challenging problems in machine learning. In this paper, the capability of Adaptive Boosting (AdaBoost) is integrated with a Convolutional Neural Network (CNN) to design a new machine learning method, AdaBoost-CNN, which can deal with large imbalanced datasets with high accuracy. AdaBoost is an ensemble method where a sequence of classifiers is trained. In AdaBoost, each training sample is assigned a weight, and a higher weight is set for a training sample that has not been trained by the previous classifier. The proposed AdaBoost-CNN is designed to reduce the computational cost of the classical AdaBoost when dealing with large sets of training data, through reducing the required number of learning epochs for its ingredient estimator. AdaBoost-CNN applies transfer learning to sequentially transfer the trained knowledge of a CNN estimator to the next CNN estimator, while updating the weights of the samples in the training set to improve accuracy and to reduce training time. Experimental results revealed that the proposed AdaBoost-CNN achieved 16.98% higher accuracy compared to the classical AdaBoost method on a synthetic imbalanced dataset. Additionally, AdaBoost-CNN reached an accuracy of 94.08% on 10,000 testing samples of the synthetic imbalanced dataset, which is higher than the accuracy of the baseline CNN method, i.e. 92.05%. AdaBoost-CNN is computationally efficient, as evidenced by the fact that the training simulation time of the proposed method is 47.33 seconds, which is lower than the training simulation time required for a similar AdaBoost method without transfer learning, i.e. 225.83 seconds on the imbalanced dataset. Moreover, when compared to the baseline CNN, AdaBoost-CNN achieved higher accuracy when applied to five other benchmark datasets including CIFAR-10 and Fashion-MNIST. AdaBoost-CNN was also applied to the EMNIST datasets, to determine its impact on large imbalanced classes, and the results demonstrate the superiority of the proposed method compared to CNN.Item Open Access Classifying Imbalanced Multi-modal Sensor Data for Human Activity Recognition in a Smart Home using Deep Learning(IEEE, 2020-07-24) Alani, A.A.; Cosma, Georgina; Taherkhani, AboozarIn smart homes, data generated from real-time sensors for human activity recognition is complex, noisy and imbalanced. It is a significant challenge to create machine learning models that can classify activities which are not as commonly occurring as other activities. Machine learning models designed to classify imbalanced data are biased towards learning the more commonly occurring classes. Such learning bias occurs naturally, since the models better learn classes which contain more records. This paper examines whether fusing real-world imbalanced multi-modal sensor data improves classification results as opposed to using unimodal data; and compares deep learning approaches to dealing with imbalanced multi-modal sensor data when using various resampling methods and deep learning models. Experiments were carried out using a large multi-modal sensor dataset generated from the Sensor Platform for HEalthcare in a Residential Environment (SPHERE). The data comprises 16104 samples, where each sample comprises 5608 features and belongs to one of 20 activities (classes). Experimental results using SPHERE demonstrate the challenges of dealing with imbalanced multi-modal data and highlight the importance of having a suitable number of samples within each class for sufficiently training and testing deep learning models. Furthermore, the results revealed that when fusing the data and using the Synthetic Minority Oversampling Technique (SMOTE) to correct class imbalance, CNN-LSTM achieved the highest classification accuracy of 93.67% followed by CNN, 93.55%, and LSTM, i.e. 92.98%.Item Open Access A Deep Convolutional Neural Network for Time Series Classification with Intermediate Targets(Springer, 2023-10-28) Taherkhani, Aboozar; Cosma, Georgina; McGinnity, T.M.Deep Convolutional Neural Networks (CNNs) have been successfully used in different applications, including image recognition. Time series data, which are generated in many applications, such as tasks using sensor data, have different characteristics compared to image data and accordingly there is a need for specific CNN structures to address their processing. This paper proposes a new CNN for classifying time series data. It is proposed to have new intermediate outputs extracted from different hidden layers instead of having a single output to control weight adjustment in the hidden layers during training. Intermediate targets are used to act as labels for the intermediate outputs to improve the performance of the method. The intermediate targets are different from the main target. Additionally, the proposed method artificially increases the number of training instances using the original training samples and the intermediate targets. The proposed approach converts a classification task with original training samples to a new (but equivalent) classification task that contains two classes with a high number of training instances. The proposed CNN for Time Series classification, called CNN-TS, extracts features depending the distance of two time series. CNN-TS was evaluated on various benchmark time series datasets. The proposed CNN-TS achieved 3.5% higher overall accuracy compared to the CNN base method (without an intermediate layer). Additionally, CNN-TS achieved 21.1% higher average accuracy compared to classical machine learning methods, i.e. linear SVM, RBF SVM, and RF. Moreover, CNN-TS was on average 8.43 times faster in training time compared to the ResNet method.Item Open Access Enhancing Prediction in Cyclone Separators through Computational Intelligence(IEEE, 2020-07) Ogun, Oluwaseyi; Enoh, Mbetobong; Cosma, Georgina; Taherkhani, Aboozar; Madonna, VincenzoPressure drop prediction is critical to the design and performance of cyclone separators as industrial gas cleaning devices. The complex nonlinear relationship between cyclone Pressure Drop Coefficient (PDC) and geometrical dimensions suffice the need for state-of-the-art predictive modelling methods. Existing solutions have applied theoretical/semi-empirical techniques which fail to generalise well, and some intelligent techniques have also been applied such as the neural network which can still be improved for optimal equipment design. To this end, this paper firstly introduces a fuzzy modelling methodology, then presents an alternative Extended Kalman Filter (EKF) for the learning of a Multi-Layer Neural Network (MLNN). The Lagrange dual formulation of Support Vector Machine (SVM) regression model is deployed as well for comparison purposes. For optimal design of these models, manual and grid search techniques are used in a cross-validation setting subsequent to training. Based on the prediction accuracy of PDC, results show that the Fuzzy System (FS) is highly performing with testing mean squared error (MSE) of 3.97e-04 and correlation coefficient (R) of 99.70%. Furthermore, a significant improvement of EKF-trained network (MSE = 1.62e-04, R = 99.82%) over the traditional Back-Propagation Neural Network (BPNN) (MSE = 4.87e-04, R = 99.53%) is observed. SVM gives better prediction with radial basis kernel (MSE = 2.22e-04, R = 99.75) and provides comparable performance to universal approximators. In comparison to conventional theoretical and semi-empirical models, intelligent approaches can provide far better prediction accuracy over a wide range of cyclone designs, while the EKFMLNN performance is noteworthy.Item Embargo Graph convolutional networks for predicting mechanical characteristics of 3D lattice structures(Springer, 2024-05-06) Oleka, Valentine; Zahedi, Mohsen; Taherkhani, Aboozar; Baserinia, Reza; Zahedi, Abolfazl; Yang, ShengxiangRecent advancements in deep learning methods encouraged researchers to apply them to process 3D objects. Initially, convolutional neural networks which have shown their ability in the processing of 2D images were used for 3D object processing. These methods need a complex process to convert 3D objects to 2D images. This conversion leads to increased computation cost and possible information loss during the transformation. This research introduces a Graph Convolutional Network approach for predicting mechanical properties of custom-designed 3D lattice structures for tissue engineering applications. Seventeen scaffold geometrics were generated for training while eight were used for testing. Unlike traditional preprocessing into images, this methodology reduces preprocessing by leveraging GCNs to directly process 3D geometrics in graph form. The experimental results show the efficiency of our proposed method in predicting 3D lattice structures.Item Embargo Hand Gesture Recognition Using a Multi-modal Deep Neural Network(Springer, 2024-05-06) Fulsunder, Saneet; Umar, Saidu; Taherkhani, Aboozar; Liu, Chang; Yang, ShengxiangAs devices around us get more intelligent, new ways of interacting with them are sought to improve user convenience and comfort. While gesture-controlled systems have existed for some time, they either use additional specialized imaging equipment, require unreasonable computing resources, or are simply not accurate enough to be a viable alternative. In this work, a reliable method of recognizing gestures is proposed. The built model correctly classifies hand gestures for keyboard typing based on the activity captured by an ordinary camera. Two models are initially developed for classifying video data and classifying time-series sequences of the skeleton data extracted from a video. The models use different strategies of classification and are built using lightweight architectures. The two models are the baseline models which are integrated to form a single multi-modal model with multiple inputs, i.e., video and time-series in-puts, to improve accuracy. The performances of the baseline models are then compared to the multimodal classifier. Since the multimodal classifier is based on the initial models, it naturally inherits the benefits of both baseline architectures and provides a higher testing accuracy of 100% compared to the accuracy of 85% and 75% for the baseline models respectively.Item Embargo Image Enhancement Preprocessing for Improving Visual Localization and Mapping(Springer, 2025-12-12) Fletcher, Piran; Taherkhani, Aboozar; Baisa, Nathanael L.We present an enhancement to the ORB-SLAM3 visual localization and mapping algorithm for mobile robots that helps the algorithm to work in conditions of low light or rapid movement. We tested the practicality of the algorithm when used on a low-cost mobile robot platform with limited computational power. We successfully showed that image enhancement can improve the consistency of results in feature extraction and matching. The percentage of matched points between keyframes in the static tests was improved by up to 95% in light conditions and 57% in dark conditions. The image enhancement algorithms improved path quality by 50% - 70% in the rotational tests, and by up to 50% in the zig-zag path following tests. Image enhancement as a pre-feature extraction step in the ORB-SLAM3 algorithm therefore shows promise as a method to improve localization in conditions of low light or rapid movement.Item Open Access PointCloud-At: Point Cloud Convolutional Neural Networks with Attention for 3D Data Processing(MDPI, 2024-10-05) Umar, Saidu; Taherkhani, AboozarThe rapid growth in technologies for 3D sensors has made point cloud data increasingly available in different applications such as autonomous driving, robotics, and virtual and augmented reali-ty. This raises a growing need for deep learning methods to process the data. Point clouds are dif-ficult to be used directly as inputs in several deep learning techniques. The difficulty is raised by the unstructured and unordered nature of the point cloud data. So, machine learning models built for images or videos cannot be used directly on point cloud data. Although the research in the field of point clouds has gained high attention and different methods have been developed over the decade, very few research works directly with point cloud data, and most of them con-vert the point cloud data into 2D images or voxels by performing some pre-processing that caus-es information loss. Methods that directly work on point clouds are in the early stage and this af-fects the performance and accuracy of the models. Advanced techniques in classical convolutional neural networks, such as the attention mechanism, need to be transferred to the methods directly working with point clouds. In this research, an attention mechanism is proposed to be added to deep convolutional neural networks that process point clouds directly. The attention module was proposed based on specific pooling operations which are designed to be applied directly to point clouds to extract vital information from the point clouds. Segmentation of the ShapeNet dataset was performed to evaluate the method. The mean intersection over union (mIoU) score of the proposed framework was increased after applying the attention method compared to a base state-of-the-art framework that does not have the attention mechanism.Item Open Access A review of learning in biologically plausible spiking neural networks(Elsevier, 2019-10-11) Taherkhani, Aboozar; Belatreche, Ammar; Li, Yuhua; Cosma, Georgina; Maguire, Liam P.; McGinnity, T.M.Artificial neural networks have been used as a powerful processing tool in various areas such as pattern recognition, control, robotics, and bioinformatics. Their wide applicability has encouraged researchers to improve artificial neural networks by investigating the biological brain. Neurological research has significantly progressed in recent years and continues to reveal new characteristics of biological neurons. New technologies can now capture temporal changes in the internal activity of the brain in more detail and help clarify the relationship between brain activity and the perception of a given stimulus. This new knowledge has led to a new type of artificial neural network, the Spiking Neural Network (SNN), that draws more faithfully on biological properties to provide higher processing abilities. A review of recent developments in learning of spiking neurons is presented in this paper. First the biological background of SNN learning algorithms is reviewed. The important elements of a learning algorithm such as the neuron model, synaptic plasticity, information encoding and SNN topologies are then presented. Then, a critical review of the state-of-the-art learning algorithms for SNNs using single and multiple spikes is presented. Additionally, deep spiking neural networks are reviewed, and challenges and opportunities in the SNN field are discussed.Item Embargo Segmenting breast ultrasound scans using a generative adversarial network embedding U-Net(Springer, 2024) Etinosa Enobun, Abraham; Henry Anakwenze, Uche; Taherkhani, Aboozar; Anastassi, Zacharias; Caraffini, Fabio; Hassan EshkikiBreast ultrasound imaging, due to its noninvasive nature and cost-effectiveness, has become an indispensable instrument in the early detection of breast cancer, highlighting the importance of early detection of lesions for timely intervention. In this study, we discuss possible problems deriving from using deep learning techniques on such images and propose novel solutions towards achieving a segmentation tool based on a generative adversarial network architecture. As a proof-of-concept, we build on existing methods to develop our system by modifying a U-Net known as Residual-Dilated-Attention-Gate with the addition of skip modules and dilated convolutional neural networks after the decoder stage. Compared with other state-of-the-art methods in established evaluation metrics, the results indicate that the proposed model achieves the highest accuracy of 98.11%, despite being trained on a limited number of epochs. However, it still requires further tuning and optimisation to enhance precision, ensuring that it is more balanced, robust, and thus competitive with the state-of-the-art.