Search

Faults recovery has recently emerged as an important aspect of web service composition (WSC) testing, as it aims to minimize the impact of faults on system functionality through restoring the system's operation after a fault has occurred. However, most of the existing recommendation systems (RSs) tend to recommend frequently used services, which lack diversity and face inaccuracies due to incomplete or biased historical data. In addition, the focus of the existing RSs is on proposing fault handling models rather than recommending the best recovery strategy for handling faults, with most being code-based, thus not suitable for WSCs. Accordingly, due to the opaque nature of WSCs with hidden source code, model-based recovery methods are preferred. In this paper, the Fault Recovery Strategies RS for WSCs (F2RS-WSC) is proposed to recommend the best recovery strategy for handling emerging faults in the WSCs paradigm. The proposed system is a model-based system that recommends the best strategy for recovering faulty paths generated from service dependency graphs (SDGs) based on the faults' types, severity levels, faults' location, as well as the time at which faults may occur. The experimental results show that the time consumed by F2RS-WSC to recommend the optimum recovery strategy represents less than 3% of the SDG parsing time and 4% of the path validation time. In addition, its superior performance assures its accuracy and efficiency. Thus, it achieves accuracy levels between 70% and 88 % among multiple datasets. Moreover, its average precision, recall and f-measure values are 0.85,0.81 and 0.86 respectively. [ABSTRACT FROM AUTHOR]

Exploring and understanding the mechanisms of the complex cellular arrangements' orchestration by gene activity in multicellular organisms has great impact on the advancement of life sciences research. Spatial transcriptomics has been enabled by novel technological breakthroughs in next-generation sequencing- and imaging-based techniques to systematically measure the gene expression levels throughout the tissue, and accordingly, increase our capabilities to draw better biological insights in developmental biology and neuroscience as well as to better understand the cellular composition and landscapes of many complex diseases such as cancer. Such large-scale data made possible population wide genomic sequencing opens the door to answering many unanswered biological questions using exploratory data analysis. In this paper we deliver a review of the different exploratory data analysis aspects of spatial transcriptomic data in order to test different hypotheses using various experimental designs that utilize and compare different genetic or environmental conditions as well as different points in time. Finally, spatial transcriptomics can be integrated with multiple other omics data in order to provide much broader and deeper insights into the cellular composition and organization. [ABSTRACT FROM AUTHOR]

Recently with the high implementation of numerous Internet of Things (IoT) based systems, it becomes a crucial need to have an effective data prediction approach for IoT data analysis that copes with sustainable smart city services. Nevertheless, IoT data add many data perspectives to consider, which complicate the data prediction process. This poses the urge for advanced data fusion methods that would preserve IoT data while ensuring data prediction accuracy, reliability, and robustness. Although different data prediction approaches have been presented for IoT applications, but maintaining IoT data characteristics is still a challenge. This paper presents our proposed approach the domain-independent Data Fusion for Data Prediction (DFDP) that consists of: (1) data fusion, which maintains IoT data massive size, faults, spatiotemporality, and freshness by employing a data input-data output fusion approach, and (2) data prediction, which utilizes the K-Nearest Neighbor data prediction technique on the fused data. DFDP is validated using IoT data from different smart cities datasets. The experiments examine the effective performance of DFDP that reaches 91.8% accuracy level. [ABSTRACT FROM AUTHOR]

Automated Driving Systems (ADS) and Advanced Driving Assistance Systems (ADAS) are widely investigated for developing safe and intelligent transportation systems. A common module in both systems is road objects monitoring, in which the semantic segmentation for road scene understanding has encountered lots of challenges. Due to the rapid evolution in technologies applied in vision-based systems in many fields, diverse techniques and algorithms have emerged to tackle such limitations, as invariant-illumination conditions, shadows, false positives, misdetections, weather conditions, real time processing and occlusions. A comparative study is conducted in this paper for vehicle detection and tracking methods applied on images and streams produced from monocular cameras and sensors in ADAS and ADS in terms of the aforementioned problems, the used dataset, along with the extracted features and the associated evaluation criteria. The study deduces the limitations of the current state-of-art techniques in such particular systems and highlights the main directions that can be ado ted for future research and investigations. [ABSTRACT FROM AUTHOR]

Many studies have addressed e-learning, aiming to create a platform for the learning process that completes the traditional classroom work and maximizes the effectiveness of learning outcomes. Gamifying personalized adaptable educational systems have been recently considered to keep the learners motivated and positively progressing in a flow state. However, the current models remain inadequate, providing limited resources for comprehensive learning analytics. In this paper, a theoritical learning preferences adaptation model is proposed based on the Personalized Adaptive Gamified E-learning (PAGE) model. The PAGE model supports blended learning by enforcing the engagement of the traditional learning process's parties, where effective learning analytics can be sustained to continuously improve the quality of the learning experience. The overall model has been evaluated for its validity through a survey from different perspectives. The overall mean value of the evaluation is 2.77 out of 3. Thus, the evaluation outcomes for the adaptation, gamification, and learning experience of the PAGE model ensure a promising vision for advancements in the learning processes and analytics. [ABSTRACT FROM AUTHOR]