Voice recognition systems have become increasingly important in recent years due to the growing need for more efficient and intuitive human-machine interfaces. The use of Hybrid LSTM networks and deep learning has been very successful in improving speech detection systems. The aim of this paper is to develop a novel approach for the detection of voice pathologies using a hybrid deep learning model that combines the Bidirectional Long Short-Term Memory (BiLSTM) and the Convolutional Neural Network (CNN) architectures. The proposed model uses a combination of temporal and spectral features extracted from speech signals to detect the different types of voice pathologies. The performance of the proposed detection model is evaluated on a publicly available dataset of speech signals from individuals with various voice pathologies(MEEI database). The experimental results showed that the hybrid BiLSTM-CNN model outperforms several classifiers by achieving an accuracy of 98.86\%. The proposed model has the potential to assist health care professionals in the accurate diagnosis and treatment of voice pathologies, and improving the quality of life for affected individuals.

This paper is a brief guide aimed at evaluating the time complexity of metaheuristic algorithms both mathematically and empirically. Starting with the mathematical foundational principles of time complexity analysis, key notations and fundamental concepts necessary for computing the time efficiency of a metaheuristic are introduced. The paper then applies these principles on three well-known metaheuristics, i.e. differential evolution, harmony search and the firefly algorithm. A procedure for the empirical analysis of metaheuristics' time efficiency is then presented. The procedure is then used to empirically analyze the computational cost of the three aforementioned metaheuristics. The pros and cons of the two approaches, i.e. mathematical and empirical analysis, are discussed.

Outlier analysis has been widely studied and has produced many methods. However, there is still rare a method to detect outliers for dynamically streaming batch data (online learning). In the present research, a novel online algorithm to detect outliers in such dataset is proposed. Data points are proceeded by applying a modified recursive PCA to predict sequentially parameters of the model; eigenvalues and eigenvectors of the statistical detection model are recursively updated using approximate values by perturbation methods. More specifically, the recursive eigenstructure is obtained from the derivation of the covariance matrix using the first-order perturbation technique. The Mahalanobis distance is then used as an outlier score. Our algorithm performances are evaluated using some metrics, namely accuration, precision, recall, F1-score, AUC-PR, and the execution time. Results show that the proposed online outlier detection is computationally efficient in time and the algorithm's performance effectiveness is comparable to that of the offline outlier detection algorithm via classical PCA.

The emergence of immersive technologies presents unprecedented opportunities for both users and organizations. This paper explores the future of digital marketing as a new ecosystem wherein innovative marketing strategies enable organizations to communicate with their customer base in ways previously unattainable, reshaping traditional marketing concepts into novel and unimaginable actions. This study proposes an experiential marketing tourism and hospitality tours generation hybrid model. The model focuses on generating virtual tours based on 360° VR videos, specifically designed for hotel environments, their surroundings, and tourist zones. The immersive environment proposal includes the design of user interface prototypes and incorporates the automated division of 360° videos using convolutional neural networks. Subsequently, personalized tours are composed based on user profiles, utilizing a Case-Based Reasoning (CBR). Functionality tests for the video division and labeling component, as well as the composition of tours according to user profiles recommended by the CBR, yielded satisfactory results. The application of this system has the potential to positively influence reservation intentions and enhance brand image. Immersive experiences have the capability to trigger effects in affective, attitudinal/behavioral, and cognitive dimensions.

Examination is one of the common ways to evaluate the students’ cognitive levels in higher education institutions. Exam questions are labeled manually by educators in accordance with Bloom’s taxonomy cognitive domain. To ease the burden of the educators, several past research works have proposed the automated question classification based on Bloom’s taxonomy using the machine learning technique. Feature selection, feature extraction and term weighting are common ways to improve the accuracy of question classification. Commonly used term weighting method in the past work is unsupervised namely TF and TF-IDF. There are several variants of TF and TFIDF and the most optimal variant has yet to be identified in the context of question classification based on BT. Therefore, this paper aims to study the TF, TF-IDF and normalized TF-IDF variants and identify the optimal variant that can enhance the exam question classification accuracy. To investigate the variants two different classifiers were used, which are Support Vector Machine (SVM) and Naïve Bayes. The average accuracies achieved by TF-IDF and normalized TF-IDF variants using SVM classifier were 64.3% and 72.4% respectively, while using Naïve Bayes classifier the average accuracies for TF-IDF and normalized TF-IDF were 61.9% and 63.0% respectively. Generally, the normalized TF-IDF variants outperformed TF and TF-IDF variants in accuracy and F1-measure respectively. Further statistical analysis using t-test and Wilcoxon Signed also shows that the differences in accuracy between normalized TF-IDF and TF, TF-IDF are significant. The findings from this study show that the Normalized TF-IDF3 variant recorded the highest accuracy of 74.0% among normalized TF-IDF variants. Also, the differences in accuracy between Normalized TF-IDF3 and other normalized variants are generally significant, thus the optimal variant is Normalized TF-IDF3. Therefore, the normalized TF-IDF3 variant is important for benchmarking purposes, which can be used to compare with other term weighting techniques in future work.

The cooperation between mobile robots is one of the most important topics of interest to researchers, especially in the many areas in which it can be applied. Hunting a moving target with random behavior is an application that requires robust cooperation between several robots in the multi-robot system. This paper proposed a hybrid formation control for hunting a dynamic target which is based on wolves’ hunting behavior in order to search and capture the prey quickly and avoid its escape and Multi Agent Deep Deterministic Policy Gradient (MADDPG) to plan an optimal accessible path to the desired position. The validity and the effectiveness of the proposed formation control are demonstrated with simulation results.

One of the record killers in the world is lung disease. Lung disease denotes to many disorders affecting the lungs. These diseases can be identified through Chest X- Ray, Computed Tomography CT, Ultrasound tests. This study provides a systematic review on different types of Deep Learning (DL) designs, methods, techniques used by different researchers in diagnosing COVID-19, Pneumonia, Tuberculosis, Lung tumor, etc. In the present research study, a systematic review and analysis is carried by following PRISMA research methodology. For this study, more than 900 research articles are considered from various indexing sources such as Scopus and Web of Science. After several selection steps, finally a 40 quality research articles are included for detailed analysis. From this study, it is observed that majority of the research articles focused on DL techniques with Chest X-Ray images and few articles focused on CT scan images and very few have focused on Ultrasound images to identify the lung disease

In recent months and years, with more and more computers and computer systems becoming the target of cyberattacks. These attacks are gaining strength and the sophistication of the approach in terms of how to attack. Attackers and Defenders are increasingly using artificial intelligence methods to maximize the success of their actions. For a successful defence, we must be able to anticipate future threats that may come. For these reasons, our research group is engaged in creating experimental software with artificial intelligence to test the possibilities and capabilities of such malware in the event of its deployment. This software has not only malware capabilities but also antimalware and can be used on both sides. This article introduces the reader to the main principles of our design, which can serve as a future platform for cyber defence systems.

Aim: The aim of this research is to evaluate the factors that affect the adoption intention of AI and ML in the context of Jordan’s retail industry
 Method: For this research paper, primary data was collected with the help of surveying different retail companies that are operational in Jordan with a sample of 400 participants. The survey questionnaire was based on a Likert scale where five points ranging from strongly agree to strongly disagree were provided to the participants. Structural Equation Modelling (SEM) used to analyse the impact and significance of the different factors on the adoption of AI and ML in Jordanian retail sector.
 Results: It has been concluded from this research paper that communication, government regulations, market structure, and technological infrastructure are important factors that influence the adoption of AI and ML in the retail industry of Jordan. However, the results of this research have pointed out that managerial support and vendor relationship do not have a significant influence on the adoption of AI and ML.
 Limitations: The scope of the research is restricted to the context of the retail industry only. This research has been carried out in the context of Jordan thus it cannot be applied on to other geographical backgrounds. Due to the time and scope limitations, there are restricted factors considered in the framework.

This paper compares centrality indices usage within a heuristic method for a fast spread of alarm, or crucial information. Such indices can be used as a core part within more sophisticated optimisation methods, which should determine a graph parameter - burning number, defining, how fast can an alarm spread through all nodes. In this procedure at each time step a new chosen node is alarmed (i.e. burned) “from outside”, and already alarmed nodes at each time step then alarm their neighbours. The procedure ends, when all the nodes are alarmed (i.e. burned). The optimisation heuristic should choose such ordered sequence of nodes, which are to be alarmed “from outside”, that their number, equal the number of time steps (i.e. burning number) necessary to alarm the whole network, is minimised. The NP completeness of the problem necessitates a usage of heuristics. However, even the heuristics can be slower, reaching towards a global optimum, or faster, exchanging part of the quality for a time. This paper studies the usage of centrality indices in a simpler and faster heuristic. It should be useful e.g. for a mobile network of cars or drones, when an optimal solution cannot be computed in advance, or take too much CPU time, since the connections within the dynamic network might not exist any longer. A wide range of centrality indices was tested on selected networks, both real as well as artificially generated. While the performances of indices substantially differ for different types of networks, results show, which centrality indices work well across all tested networks.