Showing papers by "Tallha Akram published in 2020"

A multilevel features selection framework for skin lesion classification

Abstract: Melanoma is considered to be one of the deadliest skin cancer types, whose occurring frequency elevated in the last few years; its earlier diagnosis, however, significantly increases the chances of patients’ survival. In the quest for the same, a few computer based methods, capable of diagnosing the skin lesion at initial stages, have been recently proposed. Despite some success, however, margin exists, due to which the machine learning community still considers this an outstanding research challenge. In this work, we come up with a novel framework for skin lesion classification, which integrates deep features information to generate most discriminant feature vector, with an advantage of preserving the original feature space. We utilize recent deep models for feature extraction, and by taking advantage of transfer learning. Initially, the dermoscopic images are segmented, and the lesion region is extracted, which is later subjected to retrain the selected deep models to generate fused feature vectors. In the second phase, a framework for most discriminant feature selection and dimensionality reduction is proposed, entropy-controlled neighborhood component analysis (ECNCA). This hierarchical framework optimizes fused features by selecting the principle components and extricating the redundant and irrelevant data. The effectiveness of our design is validated on four benchmark dermoscopic datasets; PH2, ISIC MSK, ISIC UDA, and ISBI-2017. To authenticate the proposed method, a fair comparison with the existing techniques is also provided. The simulation results clearly show that the proposed design is accurate enough to categorize the skin lesion with 98.8%, 99.2% and 97.1% and 95.9% accuracy with the selected classifiers on all four datasets, and by utilizing less than 3% features.

Phonocardiogram Signal Processing for Automatic Diagnosis of Congenital Heart Disorders through Fusion of Temporal and Cepstral Features.

Abstract: Congenital heart disease (CHD) is a heart disorder associated with the devastating indications that result in increased mortality, increased morbidity, increased healthcare expenditure, and decreased quality of life. Ventricular Septal Defects (VSDs) and Arterial Septal Defects (ASDs) are the most common types of CHD. CHDs can be controlled before reaching a serious phase with an early diagnosis. The phonocardiogram (PCG) or heart sound auscultation is a simple and non-invasive technique that may reveal obvious variations of different CHDs. Diagnosis based on heart sounds is difficult and requires a high level of medical training and skills due to human hearing limitations and the non-stationary nature of PCGs. An automated computer-aided system may boost the diagnostic objectivity and consistency of PCG signals in the detection of CHDs. The objective of this research was to assess the effects of various pattern recognition modalities for the design of an automated system that effectively differentiates normal, ASD, and VSD categories using short term PCG time series. The proposed model in this study adopts three-stage processing: pre-processing, feature extraction, and classification. Empirical mode decomposition (EMD) was used to denoise the raw PCG signals acquired from subjects. One-dimensional local ternary patterns (1D-LTPs) and Mel-frequency cepstral coefficients (MFCCs) were extracted from the denoised PCG signal for precise representation of data from different classes. In the final stage, the fused feature vector of 1D-LTPs and MFCCs was fed to the support vector machine (SVM) classifier using 10-fold cross-validation. The PCG signals were acquired from the subjects admitted to local hospitals and classified by applying various experiments. The proposed methodology achieves a mean accuracy of 95.24% in classifying ASD, VSD, and normal subjects. The proposed model can be put into practice and serve as a second opinion for cardiologists by providing more objective and faster interpretations of PCG signals.

An automated system for cucumber leaf diseased spot detection and classification using improved saliency method and deep features selection

Abstract: In the agriculture farming business, weeds, pests, and other plant diseases are the major reason for monetary misfortunes around the globe. It is an imperative factor, as it causes a significant diminution in both quality and capacity of crop growing. Therefore, detection and taxonomy of various plants diseases are crucial, and it demands utmost attention. However, this loss can be minimized by detecting crops diseases at their earlier stages. In this article, we are primarily focusing on a cucumber leaf diseases detection and classification method, which is comprised of five stages including image enhancement, infected spots segmentation, deep features extraction, feature selection, and finally classification. Image enhancement is performed as a pre-processing step, which efficiently improves the local contrast and makes infected regions more visible, which is later segmented with a novel Sharif saliency-based (SHSB) method. The segmentation results are further improved by fusing active contour segmentation and proposed saliency method. This step is much important for correct and useful feature extraction. In this work, pre-trained models- VGG-19 & VGG-M are utilized for features extraction and later select the most prominent features based on three selected parameters - local entropy, local standard deviation, and local interquartile range method. These refined features are finally fed to multi-class support vector machine for diseases identification. To prove the authenticity of the proposed algorithm, five cucumber leaf diseases are considered and classified to achieve classification accuracy of 98.08% in 10.52 seconds. Additionally, the proposed method is also compared with the recent techniques so as to prove its authenticity.

An integrated framework of skin lesion detection and recognition through saliency method and optimal deep neural network features selection

Abstract: Malignant melanoma, not belongs to a common type of skin cancers but most serious because of its growth—affecting large number of people worldwide. Recent studies proclaimed that risk factors can be substantially reduced by making it almost treatable, if detected at its early stages. This timely detection and classification demand an automated system, though procedure is quite complex. In this article, a novel strategy is adopted, which not only diagnoses the skin cancer but also assigns a proper class label. The proposed technique is principally built on saliency valuation and the selection of most discriminant deep features selection. The lesion contrast is being enhanced using proposed Gaussian method, followed by color space transformation from RGB to HSV. The new color space facilitates the saliency map construction process, utilizing inner and outer disjoint windows, by making the foreground and background maximally differentiable. From the segmented images, deep features are extracted by utilizing inception CNN model on two basic output layers. These extracted set of features are later fused using proposed decision-controlled parallel fusion method, prior to feature selection using proposed window distance-controlled entropy features selection method. The most discriminant features are later subjected to classification step. To demonstrate the efficiency of the proposed methods, three freely available datasets are utilized such as PH2, ISBI 2016, and ISBI 2017 with achieve accuracy is 97.74%, 96.1%, and 97%, respectively. Simulation results clearly reveal the improved performance of proposed method on all three datasets compared to existing methods.

Human action recognition: a framework of statistical weighted segmentation and rank correlation-based selection

Abstract: Human action recognition from a video sequence has received much attention lately in the field of computer vision due to its range of applications in surveillance, healthcare, smart homes, tele-immersion, to name but a few. However, it is still facing several challenges such as human variations, occlusion, change in illumination, complex background. In this article, we consider the problems related to multiple human detection and classification using novel statistical weighted segmentation and rank correlation-based feature selection approach. Initially, preprocessing is performed on a set of frames to remove existing noise and to make the foreground maximal differentiable compared to the background. A novel weighted segmentation method is also introduced for human extraction prior to feature extraction. Ternary features are exploited including color, shape, and texture, which are later combined using serial-based features fusion method. To avoid redundancy, rank correlation-based feature selection technique is employed, which acts as a feature optimizer and leads to improved classification accuracy. The proposed method is validated on six datasets including Weizmann, KTH, Muhavi, WVU, UCF sports, and MSR action and validated based on seven performance measures. A fair comparison with existing work is also provided which proves the significance of proposed compared to other techniques.

Fruits diseases classification: exploiting a hierarchical framework for deep features fusion and selection

Abstract: In agriculture farming business, plant diseases are one of the reasons for the financial deficits around the globe. It is the fundamental factor, as it causes significant abatement in both capacity and quality of the growing crops. In plants, fruits are amongst the major sources of nutrients, however, there exists a wide range of diseases which adversely affect both quality and production of the fruits. To overcome such predicament, computer vision (CV) based methods are introduced. These methods are quite effective, which not only detect the diseases/infections at the early stages but also assign them a label. In this article, we propose a deep convolutional neural network-based method for the diseases classification of different fruits’ leaves. Initially, the deep features are extracted by utilizing pre-trained deep models including VGG-s and AlexNet, which are later fine-tuned by employing a concept of transfer learning. A multi-level fusion methodology is also proposed, prior to the selection step, based on an entropy-controlled threshold value - calculated by averaging the selected features. The resultant final feature vector is later fed into a host classifier, multi-SVM. Five different diseases are considered for experiments including apple black rot, apple scab, apple rust, cherry powdery mildew, and peach bacterial spots, which are collected from a plant village dataset. Classification results clearly reveal the improved performance of proposed method in terms of sensitivity (97.6%), accuracy (97.8%), precision (97.6%), and G-measure (97.6%).

Multicriteria UAV Base Stations Placement for Disaster Management

Abstract: In disaster situations, collapse of local communication infrastructure is a major issue due to destruction of buildings, antennas, power sources, and to name a few. Drones, as flying base stations, are a promising solution to restore essential communication services in emergency situations. The contribution of this article is twofold: First, an efficient computer vision technique is proposed to identify areas with high density of low mobility or stationary users. This is done using a multistep process, which includes image acquisition, classification, and crowd density estimation. Next, an accurate mathematical model is presented for joint optimization of drone base stations placement and user assignment. The goal here is to maximize the number of serviced users with minimum number of drones, while satisfying practical network constraints. An optimal solution to such a biobjective optimization problem has complexity exponential to the network size. Furthermore, a low complexity heuristic is proposed to solve the optimization problem. Complexity analysis of the proposed solution is then carried out. Simulation results for a number of practical network scenarios demonstrate that the proposed solution achieves a performance comparable to the optimal solution.

Improved strategy for human action recognition; experiencing a cascaded design

Abstract: Human motion analysis has received a lot of attention in the computer vision community during the last few years. This research domain is supported by a wide spectrum of applications including video surveillance, patient monitoring systems, and pedestrian detection, to name a few. In this study, an improved cascaded design for human motion analysis is presented; it consolidates four phases: (i) acquisition and preprocessing, (ii) frame segmentation, (iii) features extraction and dimensionality reduction, and (iv) classification. The implemented architecture takes advantage of CIE-Lab and National Television System Committee colour spaces, and also performs contrast stretching using the proposed red–green–blue* colour space enhancement technique. A parallel design utilising attention-based motion estimation and segmentation module is also proposed in order to avoid the detection of false moving regions. In addition to these contributions, the proposed feature selection technique called entropy controlled principal components with weights minimisation, further improves the classification accuracy. The authors claims are supported with a comparison between six state-of-the-art classifiers tested on five standard benchmark data sets including Weizmann, KTH, UIUC, Muhavi, and WVU, where the results reveal an improved correct classification rate of 96.55, 99.50, 99.40, 100, and 100%, respectively.

Veins Depth Estimation Using Diffused Reflectance Parameter

Abstract: In order to perform the standard Intravenous (IV) catheterization, subcutaneous veins must be localized. It is a difficult task, especially in the cases when veins are hard to localize. The factors which affect the veins localization process are the physiological characteristics of patients, mainly darker skin tone, scars, hair, dehydration and low blood pressure. With the help of Near Infrared imaging, subcutaneous veins can be envisioned. This is due to the higher absorption of NIR light energy by Hemoglobin (Hb) found in the veins. Besides a superficial view, the veins depth information is also important in order to avoid their rupture by piercing through the walls during IV catheterization process. Diffused reflectance, measured with a camera sensor, can be used for the depth estimation of blood vessels. In this paper, a method to measure the depth of veins using diffused reflectance parameter, is presented. The well-known Monte Carlo model of light propagation in human tissues is used for the mathematical representation. A four-layered skin model is presented with varying vessel depths to describe the diffused reflectance of light while propagating inside skin tissues. The results are validated with Monte Carlo simulations for light propagation in layered medium. A sensitivity analysis of proposed method is also performed with a 5% alteration in the optical parameters of skin due to the change in operating conditions. The results showed a marginal error of maximum value 6.23% in vessel depth estimation using the standard optical parameters, 1.6% for −5% and 10.74% for +5% change in optical parameters.