The proposed modified methods of Cramer's rule consider the column vector as well as the coefficient matrix concurrently in the linear system. The modified methods can be applied since Cramer's rule is typically known for solving the linear systems in $WZ$ factorization to yield Z-matrix. Then, we presented our results to show that there is no tangible difference in performance time between Cramer's rule and the modified methods in the factorization from improved versions of MATLAB. Additionally, the Frobenius norm of the modified methods in the factorization is better than using Cramer's rule irrespective of the version of MATLAB used.
Knowledge graph (KG) publishes machine-readable representation of knowledge on the Web. Structured data in the knowledge graph is published using Resource Description Framework (RDF) where knowledge is represented as a triple (subject, predicate, object). Due to the presence of erroneous, outdated or conflicting data in the knowledge graph, the quality of facts cannot be guaranteed. Trustworthiness of facts in knowledge graph can be enhanced by the addition of metadata like the source of information, location and time of the fact occurrence. Since RDF does not support metadata for providing provenance and contextualization, an alternate method, RDF reification is employed by most of the knowledge graphs. RDF reification increases the magnitude of data as several statements are required to represent a single fact. Another limitation for applications that uses provenance data like in the medical domain and in cyber security is that not all facts in these knowledge graphs are annotated with provenance data. In this paper, we have provided an overview of prominent reification approaches together with the analysis of popular, general knowledge graphs Wikidata and YAGO4 with regard to the representation of provenance and context data. Wikidata employs qualifiers to include metadata to facts, while YAGO4 collects metadata from Wikidata qualifiers. However, facts in Wikidata and YAGO4 can be fetched without using reification to cater for applications that do not require metadata. To the best of our knowledge, this is the first paper that investigates the method and the extent of metadata covered by two prominent KGs, Wikidata and YAGO4.
Time series clustering is an important solution to various problems in numerous fields of research, including business, medical science, and finance. However, conventional clustering algorithms are not practical for time series data because they are essentially designed for static data. This impracticality results in poor clustering accuracy in several systems. In this paper, a new hybrid clustering algorithm is proposed based on the similarity in shape of time series data. Time series data are first grouped as subclusters based on similarity in time. The subclusters are then merged using the k-Medoids algorithm based on similarity in shape. This model has two contributions: (1) it is more accurate than other conventional and hybrid approaches and (2) it determines the similarity in shape among time series data with a low complexity. To evaluate the accuracy of the proposed model, the model is tested extensively using syntactic and real-world time series datasets.
In practice, the collected spectra are very often composes of complex overtone and many overlapping peaks which may lead to misinterpretation because of its significant nonlinear characteristics. Using linear solution might not be appropriate. In addition, with a high-dimension of dataset due to large number of observations and data points the classical multiple regressions will neglect to fit. These complexities commonly will impact to multicollinearity problem, furthermore the risk of contamination of multiple outliers and high leverage points also increases. To address these problems, a new method called Kernel Partial Diagnostic Robust Potential (KPDRGP) is introduced. The method allows the nonlinear solution which maps nonlinearly the original input
X
matrix into higher dimensional feature mapping with corresponds to the Reproducing Kernel Hilbert Spaces (RKHS). In dimensional reduction, the method replaces the dot products calculation of elements in the mapped data to a nonlinear function in the original input space. To prevent the contamination of the multiple outlier and high leverage points the robust procedure using Diagnostic Robust Generalized Potentials (DRGP) algorithm was used. The results verified that using the simulation and real data, the proposed KPDRGP method was superior to the methods in the class of non-kernel and some other robust methods with kernel solution.
Existing face recognition methods utilize particle swarm optimizer (PSO) and opposition based particle swarm optimizer (OPSO) to optimize the parameters of SVM. However, the utilization of random values in the velocity calculation decreases the performance of these techniques; that is, during the velocity computation, we normally use random values for the acceleration coefficients and this creates randomness in the solution. To address this problem, an adaptive acceleration particle swarm optimization (AAPSO) technique is proposed. To evaluate our proposed method, we employ both face and iris recognition based on AAPSO with SVM (AAPSO-SVM). In the face and iris recognition systems, performance is evaluated using two human face databases, YALE and CASIA, and the UBiris dataset. In this method, we initially perform feature extraction and then recognition on the extracted features. In the recognition process, the extracted features are used for SVM training and testing. During the training and testing, the SVM parameters are optimized with the AAPSO technique, and in AAPSO, the acceleration coefficients are computed using the particle fitness values. The parameters in SVM, which are optimized by AAPSO, perform efficiently for both face and iris recognition. A comparative analysis between our proposed AAPSO-SVM and the PSO-SVM technique is presented.
In human sperm motility analysis, sperm segmentation plays an important role to determine the location of multiple sperms. To ensure an improved segmentation result, the Laplacian of Gaussian filter is implemented as a kernel in a pre-processing step before applying the image segmentation process to automatically segment and detect human spermatozoa. This study proposes an intersecting cortical model (ICM), which was derived from several visual cortex models, to segment the sperm head region. However, the proposed method suffered from parameter selection; thus, the ICM network is optimised using particle swarm optimization where feature mutual information is introduced as the new fitness function. The final results showed that the proposed method is more accurate and robust than four state-of-the-art segmentation methods. The proposed method resulted in rates of 98.14%, 98.82%, 86.46% and 99.81% in accuracy, sensitivity, specificity and precision, respectively, after testing with 1200 sperms. The proposed algorithm is expected to be implemented in analysing sperm motility because of the robustness and capability of this algorithm.
Modification of the intensification and diversification approaches in the recently developed cuckoo search algorithm (CSA) is performed. The alteration involves the implementation of adaptive step size adjustment strategy, and thus enabling faster convergence to the global optimal solutions. The feasibility of the proposed algorithm is validated against benchmark optimization functions, where the obtained results demonstrate a marked improvement over the standard CSA, in all the cases.
Tuberculosis is a major global health problem that has been ranked as the second leading cause of death from an infectious disease worldwide, after the human immunodeficiency virus. Diagnosis based on cultured specimens is the reference standard; however, results take weeks to obtain. Slow and insensitive diagnostic methods hampered the global control of tuberculosis, and scientists are looking for early detection strategies, which remain the foundation of tuberculosis control. Consequently, there is a need to develop an expert system that helps medical professionals to accurately diagnose the disease. The objective of this study is to diagnose tuberculosis using a machine learning method. Artificial immune recognition system (AIRS) has been used successfully for diagnosing various diseases. However, little effort has been undertaken to improve its classification accuracy. In order to increase the classification accuracy, this study introduces a new hybrid system that incorporates real tournament selection mechanism into the AIRS. This mechanism is used to control the population size of the model and to overcome the existing selection pressure. Patient epacris reports obtained from the Pasteur laboratory in northern Iran were used as the benchmark data set. The sample consisted of 175 records, from which 114 (65 %) were positive for TB, and the remaining 61 (35 %) were negative. The classification performance was measured through tenfold cross-validation, root-mean-square error, sensitivity, and specificity. With an accuracy of 100 %, RMSE of 0, sensitivity of 100 %, and specificity of 100 %, the proposed method was able to successfully classify tuberculosis cases. In addition, the proposed method is comparable with top classifiers used in this research.
Loss of the ability to speak or hear exerts psychological and social impacts on the affected persons due to the lack of proper communication. Multiple and systematic scholarly interventions that vary according to context have been implemented to overcome disability-related difficulties. Sign language recognition (SLR) systems based on sensory gloves are significant innovations that aim to procure data on the shape or movement of the human hand. Innovative technology for this matter is mainly restricted and dispersed. The available trends and gaps should be explored in this research approach to provide valuable insights into technological environments. Thus, a review is conducted to create a coherent taxonomy to describe the latest research divided into four main categories: development, framework, other hand gesture recognition, and reviews and surveys. Then, we conduct analyses of the glove systems for SLR device characteristics, develop a roadmap for technology evolution, discuss its limitations, and provide valuable insights into technological environments. This will help researchers to understand the current options and gaps in this area, thus contributing to this line of research.
Sign language recognition presents significant challenges due to the intricate nature of hand gestures and the necessity to capture fine-grained details. In response to these challenges, a novel approach is proposed-Lightweight Attentive VGG16 with Random Forest (LAVRF) model. LAVRF introduces a refined adaptation of the VGG16 model integrated with attention modules, complemented by a Random Forest classifier. By streamlining the VGG16 architecture, the Lightweight Attentive VGG16 effectively manages complexity while incorporating attention mechanisms that dynamically concentrate on pertinent regions within input images, resulting in enhanced representation learning. Leveraging the Random Forest classifier provides notable benefits, including proficient handling of high-dimensional feature representations, reduction of variance and overfitting concerns, and resilience against noisy and incomplete data. Additionally, the model performance is further optimized through hyperparameter optimization, utilizing the Optuna in conjunction with hill climbing, which efficiently explores the hyperparameter space to discover optimal configurations. The proposed LAVRF model demonstrates outstanding accuracy on three datasets, achieving remarkable results of 99.98%, 99.90%, and 100% on the American Sign Language, American Sign Language with Digits, and NUS Hand Posture datasets, respectively.
This paper presents a CBIR system to investigate the use of image retrieval with an extracted texture from the image of a bin to detect the bin level. Various similarity distances like Euclidean, Bhattacharyya, Chi-squared, Cosine, and EMD are used with the CBIR system for calculating and comparing the distance between a query image and the images in a database to obtain the highest performance. In this study, the performance metrics is based on two quantitative evaluation criteria. The first one is the average retrieval rate based on the precision-recall graph and the second is the use of F1 measure which is the weighted harmonic mean of precision and recall. In case of feature extraction, texture is used as an image feature for bin level detection system. Various experiments are conducted with different features extraction techniques like Gabor wavelet filter, gray level co-occurrence matrix (GLCM), and gray level aura matrix (GLAM) to identify the level of the bin and its surrounding area. Intensive tests are conducted among 250bin images to assess the accuracy of the proposed feature extraction techniques. The average retrieval rate is used to evaluate the performance of the retrieval system. The result shows that, the EMD distance achieved high accuracy and provides better performance than the other distances.
Multi-feature methods are able to contribute to a more effective method compared to single-feature
methods since feature fusion methods will be able to close the gap that exists in the single-feature
methods. This paper presents a feature fusion method, which focuses on extracting colour and shape features for content-based image retrieval (CBIR). The colour feature is extracted based on the proposed Multi-resolution Joint Auto Correlograms (MJAC), while the shape information is obtained through the proposed Extended Generalised Ridgelet-Fourier (EGRF). These features are fused together through a proposed integrated scheme. The feature fusion method has been tested on the SIMPLIcity image database, where several retrieval measurements are utilised to compare the effectiveness of the proposed method with few other comparable methods. The retrieval results show that the proposed Integrated Colour-shape (ICS) descriptor has successfully obtained the best overall retrieval performance in all the retrieval measurements as compared to the benchmark methods, which include precision (53.50%), precision at 11 standard recall levels (52.48%), and rank (17.40).
Text localisation determines the location of the text in an image. This process
is performed prior to text recognition. Localising text on shop signage is
a challenging task since the images of the shop signage consist of complex
background, and the text occurs in various font types, sizes, and colours.
Two popular texture features that have been applied to localise text in
scene images are a histogram of oriented gradient (HOG) and speeded up
robust features (SURF). A comparative study is conducted in this paper
to determine which is better with support vector machine (SVM) classifier.
The performance of SVM is influenced by its kernel function and another
comparative study is conducted to identify the best kernel function. The
experiments have been conducted using primary data collected by the
authors. Results indicate that HOG with quadratic kernel function localises
text for shop signage better than SURF.
Over the last decade, design patterns have been used extensively to generate reusable solutions to frequently encountered problems in software engineering and object oriented programming. A design pattern is a repeatable software design solution that provides a template for solving various instances of a general problem.
This paper describes the acquisition setup and development of a new gait database, MMUGait. This database consists of 82 subjects walking under normal condition and 19 subjects walking with 11 covariate factors, which were captured under two views. This paper also proposes a multiview model-based gait recognition system with joint detection approach that performs well under different walking trajectories and covariate factors, which include self-occluded or external occluded silhouettes. In the proposed system, the process begins by enhancing the human silhouette to remove the artifacts. Next, the width and height of the body are obtained. Subsequently, the joint angular trajectories are determined once the body joints are automatically detected. Lastly, crotch height and step-size of the walking subject are determined. The extracted features are smoothened by Gaussian filter to eliminate the effect of outliers. The extracted features are normalized with linear scaling, which is followed by feature selection prior to the classification process. The classification experiments carried out on MMUGait database were benchmarked against the SOTON Small DB from University of Southampton. Results showed correct classification rate above 90% for all the databases. The proposed approach is found to outperform other approaches on SOTON Small DB in most cases.
This paper presents a novel features mining approach from documents that could not be mined via optical character recognition (OCR). By identifying the intimate relationship between the text and graphical components, the proposed technique pulls out the Start, End, and Exact values for each bar. Furthermore, the word 2-gram and Euclidean distance methods are used to accurately detect and determine plagiarism in bar charts.
Test collection is used to evaluate the information retrieval systems in laboratory-based evaluation experimentation. In a classic setting, generating relevance judgments involves human assessors and is a costly and time consuming task. Researchers and practitioners are still being challenged in performing reliable and low-cost evaluation of retrieval systems. Crowdsourcing as a novel method of data acquisition is broadly used in many research fields. It has been proven that crowdsourcing is an inexpensive and quick solution as well as a reliable alternative for creating relevance judgments. One of the crowdsourcing applications in IR is to judge relevancy of query document pair. In order to have a successful crowdsourcing experiment, the relevance judgment tasks should be designed precisely to emphasize quality control. This paper is intended to explore different factors that have an influence on the accuracy of relevance judgments accomplished by workers and how to intensify the reliability of judgments in crowdsourcing experiment.
When the amount of data and information is said to double in every 20 months or so, feature selection has become highly important and beneficial. Further improvements in feature selection will positively affect a wide array of applications in fields such as pattern recognition, machine learning, or signal processing. Bio-inspired method called Bat Algorithm hybridized with a Naive Bayes classifier has been presented in this work. The performance of the proposed feature selection algorithm was investigated using twelve benchmark datasets from different domains and was compared to three other well-known feature selection algorithms. Discussion focused on four perspectives: number of features, classification accuracy, stability, and feature generalization. The results showed that BANB significantly outperformed other algorithms in selecting lower number of features, hence removing irrelevant, redundant, or noisy features while maintaining the classification accuracy. BANB is also proven to be more stable than other methods and is capable of producing more general feature subsets.
This paper presents a new evolutionary approach called the hybrid evolutionary artificial neural network (HEANN) for simultaneously evolving an artificial neural networks (ANNs) topology and weights. Evolutionary algorithms (EAs) with strong global search capabilities are likely to provide the most promising region. However, they are less efficient in fine-tuning the search space locally. HEANN emphasizes the balancing of the global search and local search for the evolutionary process by adapting the mutation probability and the step size of the weight perturbation. This is distinguishable from most previous studies that incorporate EA to search for network topology and gradient learning for weight updating. Four benchmark functions were used to test the evolutionary framework of HEANN. In addition, HEANN was tested on seven classification benchmark problems from the UCI machine learning repository. Experimental results show the superior performance of HEANN in fine-tuning the network complexity within a small number of generations while preserving the generalization capability compared with other algorithms.
This paper presents a new approach to detect exudates and optic disc from color fundus images based on inverse surface thresholding. The strategy involves the applications of fuzzy c-means clustering, edge detection, otsu thresholding and inverse surface thresholding. The main advantage of the proposed approach is that it does not depend on manually selected parameters that are normally chosen to suit the tested databases. When applied to two sets of databases the proposed method outperforms a method based on watershed segmentation.