An explainable machine learning approach for Alzheimer's disease classification.

The early diagnosis of Alzheimer's disease (AD) presents a significant challenge due to the subtle biomarker changes often overlooked. Machine learning (ML) models offer a promising tool for identifying individuals at risk of AD. However, current research tends to prioritize ML accuracy while neglecting the crucial aspect of model explainability. The diverse nature of AD data and the limited dataset size introduce additional challenges, primarily related to high dimensionality. In this study, we leveraged a dataset obtained from the National Alzheimer's Coordinating Center, comprising 169,408 records and 1024 features. After applying various steps to reduce the feature space. Notably, support vector machine (SVM) models trained on the selected features exhibited high performance when tested on an external dataset. SVM achieved a high F1 score of 98.9% for binary classification (distinguishing between NC and AD) and 90.7% for multiclass classification. Furthermore, SVM was able to predict AD progression over a 4-year period, with F1 scores reached 88% for binary task and 72.8% for multiclass task. To enhance model explainability, we employed two rule-extraction approaches: class rule mining and stable and interpretable rule set for classification model. These approaches generated human-understandable rules to assist domain experts in comprehending the key factors involved in AD development. We further validated these rules using SHAP and LIME models, underscoring the significance of factors such as MEMORY, JUDGMENT, COMMUN, and ORIENT in determining AD risk. Our experimental outcomes also shed light on the crucial role of the Clinical Dementia Rating tool in predicting AD.

A New Traffic Sign Recognition Technique Taking Shuffled Frog-Leaping Algorithm into Account.

Everyday humans use cars to move faster, and the world is a chaotic place, and a little distraction or a mistake could be the reason for an accident and bring people great pain. An assistance system that can distinguish and detect signs on the roads and brings the driver's attention to road signs and make them aware of their meaning could be beneficial. The most important part of the Traffic Sign Recognition System is the algorithm. In this paper, a new way toward Traffic Sign Recognition algorithm taking the advantages of Color Segmentation, support vector machines, and histograms of oriented gradients on the GTSRB dataset is proposed. The unsupervised shuffled frog-leaping algorithm is employed for segmenting the images. The results show remarkable improvements by using meta-heuristic algorithms.

Kinect-Based Rehabilitation Systems for Stroke Patients: A Scoping Review.

Method: This study was conducted according to Arksey and O'Malley's framework. To investigate the evidence on the effects of Kinect-based rehabilitation, a search was executed in five databases (Web of Science, PubMed, Cochrane Library, Scopus, and IEEE) from 2010 to 2020. Results: Thirty-three articles were finally selected by the inclusion criteria. Most of the studies had been conducted in the US (22%). In terms of the application of Kinect-based rehabilitation for stroke patients, most studies had focused on the rehabilitation of upper extremities (55%), followed by balance (27%). The majority of the studies had developed customized rehabilitation programs (36%) for the rehabilitation of stroke patients. Most of these studies had noted that the simultaneous use of Kinect-based rehabilitation and other physiotherapy methods has a more noticeable effect on performance improvement in patients. Conclusion: The simultaneous application of Kinect-based rehabilitation and other physiotherapy methods has a stronger effect on the performance improvement of stroke patients. Better effects can be achieved by designing Kinect-based rehabilitation programs tailored to the characteristics and abilities of stroke patients.

Virtual conference design: features and obstacles.

The Covid-19 pandemic has forced a change in the way people work, and the location that they work from. The impact has caused significant disruption to education, the work environment and how social interactions take place. Online user habits have also changed due to lockdown restrictions and virtual conferencing software has become a vital cog in team communication. In result, a spate in software solutions have emerged in order to support the challenges of remote learning and working. The conferencing software landscape is now a core communication solution for company-wide interaction, team discussions, screen sharing and face-to-face contact. Yet the number of existing platforms is diverse. In this article, a systematic literature review investigation on virtual conferencing is presented. As output from the analysis, 67 key features and 74 obstacles users experience when interacting with virtual conferencing technologies are identified from 60 related open-source journal articles from 5 digital library repositories.

Automatic detection of papilledema through fundus retinal images using deep learning.

Papilledema is a syndrome of the retina in which retinal optic nerve is inflated by elevation of intracranial pressure. The papilledema abnormalities such as retinal nerve fiber layer (RNFL) opacification may lead to blindness. These abnormalities could be seen through capturing of retinal images by means of fundus camera. This paper presents a deep learning-based automated system that detects and grades the papilledema through U-Net and Dense-Net architectures. The proposed approach has two main stages. First, optic disc and its surrounding area in fundus retinal image are localized and cropped for input to Dense-Net which classifies the optic disc as papilledema or normal. Second, consists of preprocessing of Dense-Net classified papilledema fundus image by Gabor filter. The preprocessed papilledema image is input to U-Net to achieve the segmented vascular network from which the vessel discontinuity index (VDI) and vessel discontinuity index to disc proximity (VDIP) are calculated for grading of papilledema. The VDI and VDIP are standard parameter to check the severity and grading of papilledema. The proposed system is evaluated on 60 papilledema and 40 normal fundus images taken from STARE dataset. The experimental results for classification of papilledema through Dense-Net are much better in terms of sensitivity 98.63%, specificity 97.83%, and accuracy 99.17%. Similarly, the grading results for mild and severe papilledema classification through U-Net are also much better in terms of sensitivity 99.82%, specificity 98.65%, and accuracy 99.89%. The deep learning-based automated detection and grading of papilledema for clinical purposes is first effort in state of art.

A Survey of Deep Learning for Lung Disease Detection on Medical Images: State-of-the-Art, Taxonomy, Issues and Future Directions.

The recent developments of deep learning support the identification and classification of lung diseases in medical images. Hence, numerous work on the detection of lung disease using deep learning can be found in the literature. This paper presents a survey of deep learning for lung disease detection in medical images. There has only been one survey paper published in the last five years regarding deep learning directed at lung diseases detection. However, their survey is lacking in the presentation of taxonomy and analysis of the trend of recent work. The objectives of this paper are to present a taxonomy of the state-of-the-art deep learning based lung disease detection systems, visualise the trends of recent work on the domain and identify the remaining issues and potential future directions in this domain. Ninety-eight articles published from 2016 to 2020 were considered in this survey. The taxonomy consists of seven attributes that are common in the surveyed articles: image types, features, data augmentation, types of deep learning algorithms, transfer learning, the ensemble of classifiers and types of lung diseases. The presented taxonomy could be used by other researchers to plan their research contributions and activities. The potential future direction suggested could further improve the efficiency and increase the number of deep learning aided lung disease detection applications.

Plasmodium life cycle stage classification based quantification of malaria parasitaemia in thin blood smears.

Visual inspection for the quantification of malaria parasitaemiain (MP) and classification of life cycle stage are hard and time taking. Even though, automated techniques for the quantification of MP and their classification are reported in the literature. However, either reported techniques are imperfect or cannot deal with special issues such as anemia and hemoglobinopathies due to clumps of red blood cells (RBCs). The focus of the current work is to examine the thin blood smear microscopic images stained with Giemsa by digital image processing techniques, grading MP on independent factors (RBCs morphology) and classification of its life cycle stage. For the classification of the life cycle of malaria parasite the k-nearest neighbor, Naïve Bayes and multi-class support vector machine are employed for classification based on histograms of oriented gradients and local binary pattern features. The proposed methodology is based on inductive technique, segment malaria parasites through the adaptive machine learning techniques. The quantification accuracy of RBCs is enhanced; RBCs clumps are split by analysis of concavity regions for focal points. Further, classification of infected and non-infected RBCs has been made to grade MP precisely. The training and testing of the proposed approach on benchmark dataset with respect to ground truth data, yield 96.75% MP sensitivity and 94.59% specificity. Additionally, the proposed approach addresses the process with independent factors (RBCs morphology). Finally, it is an economical solution for MP grading in immense testing.

Classification of acute lymphoblastic leukemia using deep learning.

Acute Leukemia is a life-threatening disease common both in children and adults that can lead to death if left untreated. Acute Lymphoblastic Leukemia (ALL) spreads out in children's bodies rapidly and takes the life within a few weeks. To diagnose ALL, the hematologists perform blood and bone marrow examination. Manual blood testing techniques that have been used since long time are often slow and come out with the less accurate diagnosis. This work improves the diagnosis of ALL with a computer-aided system, which yields accurate result by using image processing and deep learning techniques. This research proposed a method for the classification of ALL into its subtypes and reactive bone marrow (normal) in stained bone marrow images. A robust segmentation and deep learning techniques with the convolutional neural network are used to train the model on the bone marrow images to achieve accurate classification results. Experimental results thus obtained and compared with the results of other classifiers Naïve Bayesian, KNN, and SVM. Experimental results reveal that the proposed method achieved 97.78% accuracy. The obtained results exhibit that the proposed approach could be used as a tool to diagnose Acute Lymphoblastic Leukemia and its sub-types that will definitely assist pathologists.

Rouleaux red blood cells splitting in microscopic thin blood smear images via local maxima, circles drawing, and mapping with original RBCs.

Splitting the rouleaux RBCs from single RBCs and its further subdivision is a challenging area in computer-assisted diagnosis of blood. This phenomenon is applied in complete blood count, anemia, leukemia, and malaria tests. Several automated techniques are reported in the state of art for this task but face either under or over splitting problems. The current research presents a novel approach to split Rouleaux red blood cells (chains of RBCs) precisely, which are frequently observed in the thin blood smear images. Accordingly, this research address the rouleaux splitting problem in a realistic, efficient and automated way by considering the distance transform and local maxima of the rouleaux RBCs. Rouleaux RBCs are splitted by taking their local maxima as the centres to draw circles by mid-point circle algorithm. The resulting circles are further mapped with single RBC in Rouleaux to preserve its original shape. The results of the proposed approach on standard data set are presented and analyzed statistically by achieving an average recall of 0.059, an average precision of 0.067 and F-measure 0.063 are achieved through ground truth with visual inspection.

An expert botanical feature extraction technique based on phenetic features for identifying plant species.

In this paper, we present a new method to recognise the leaf type and identify plant species using phenetic parts of the leaf; lobes, apex and base detection. Most of the research in this area focuses on the popular features such as the shape, colour, vein, and texture, which consumes large amounts of computational processing and are not efficient, especially in the Acer database with a high complexity structure of the leaves. This paper is focused on phenetic parts of the leaf which increases accuracy. Detecting the local maxima and local minima are done based on Centroid Contour Distance for Every Boundary Point, using north and south region to recognise the apex and base. Digital morphology is used to measure the leaf shape and the leaf margin. Centroid Contour Gradient is presented to extract the curvature of leaf apex and base. We analyse 32 leaf images of tropical plants and evaluated with two different datasets, Flavia, and Acer. The best accuracy obtained is 94.76% and 82.6% respectively. Experimental results show the effectiveness of the proposed technique without considering the commonly used features with high computational cost.

Soft bilateral filtering volumetric shadows using cube shadow maps.

Volumetric shadows often increase the realism of rendered scenes in computer graphics. Typical volumetric shadows techniques do not provide a smooth transition effect in real-time with conservation on crispness of boundaries. This research presents a new technique for generating high quality volumetric shadows by sampling and interpolation. Contrary to conventional ray marching method, which requires extensive time, this proposed technique adopts downsampling in calculating ray marching. Furthermore, light scattering is computed in High Dynamic Range buffer to generate tone mapping. The bilateral interpolation is used along a view rays to smooth transition of volumetric shadows with respect to preserving-edges. In addition, this technique applied a cube shadow map to create multiple shadows. The contribution of this technique isreducing the number of sample points in evaluating light scattering and then introducing bilateral interpolation to improve volumetric shadows. This contribution is done by removing the inherent deficiencies significantly in shadow maps. This technique allows obtaining soft marvelous volumetric shadows, having a good performance and high quality, which show its potential for interactive applications.

Identification of metabolic pathways using pathfinding approaches: a systematic review.

Metabolic pathways have become increasingly available for various microorganisms. Such pathways have spurred the development of a wide array of computational tools, in particular, mathematical pathfinding approaches. This article can facilitate the understanding of computational analysis of metabolic pathways in genomics. Moreover, stoichiometric and pathfinding approaches in metabolic pathway analysis are discussed. Three major types of studies are elaborated: stoichiometric identification models, pathway-based graph analysis and pathfinding approaches in cellular metabolism. Furthermore, evaluation of the outcomes of the pathways with mathematical benchmarking metrics is provided. This review would lead to better comprehension of metabolism behaviors in living cells, in terms of computed pathfinding approaches.

LivePhantom: Retrieving Virtual World Light Data to Real Environments.

To achieve realistic Augmented Reality (AR), shadows play an important role in creating a 3D impression of a scene. Casting virtual shadows on real and virtual objects is one of the topics of research being conducted in this area. In this paper, we propose a new method for creating complex AR indoor scenes using real time depth detection to exert virtual shadows on virtual and real environments. A Kinect camera was used to produce a depth map for the physical scene mixing into a single real-time transparent tacit surface. Once this is created, the camera's position can be tracked from the reconstructed 3D scene. Real objects are represented by virtual object phantoms in the AR scene enabling users holding a webcam and a standard Kinect camera to capture and reconstruct environments simultaneously. The tracking capability of the algorithm is shown and the findings are assessed drawing upon qualitative and quantitative methods making comparisons with previous AR phantom generation applications. The results demonstrate the robustness of the technique for realistic indoor rendering in AR systems.

Realistic real-time outdoor rendering in augmented reality.

Realistic rendering techniques of outdoor Augmented Reality (AR) has been an attractive topic since the last two decades considering the sizeable amount of publications in computer graphics. Realistic virtual objects in outdoor rendering AR systems require sophisticated effects such as: shadows, daylight and interactions between sky colours and virtual as well as real objects. A few realistic rendering techniques have been designed to overcome this obstacle, most of which are related to non real-time rendering. However, the problem still remains, especially in outdoor rendering. This paper proposed a much newer, unique technique to achieve realistic real-time outdoor rendering, while taking into account the interaction between sky colours and objects in AR systems with respect to shadows in any specific location, date and time. This approach involves three main phases, which cover different outdoor AR rendering requirements. Firstly, sky colour was generated with respect to the position of the sun. Second step involves the shadow generation algorithm, Z-Partitioning: Gaussian and Fog Shadow Maps (Z-GaF Shadow Maps). Lastly, a technique to integrate sky colours and shadows through its effects on virtual objects in the AR system, is introduced. The experimental results reveal that the proposed technique has significantly improved the realism of real-time outdoor AR rendering, thus solving the problem of realistic AR systems.