Search

Automated scoring systems have been revolutionized by natural language processing, enabling the evaluation of students' diverse answers across various academic disciplines. However, this presents a challenge as students' responses may vary significantly in terms of length, structure, and content. To tackle this challenge, this research introduces a novel automated model for short answer grading. The proposed model uses pretrained "transformer" models, specifically T5, in conjunction with a BI-LSTM architecture which is effective in processing sequential data by considering the past and future context. This research evaluated several preprocessing techniques and different hyperparameters to identify the most efficient architecture. Experiments were conducted using a standard benchmark dataset named the North Texas Dataset. This research achieved a state-of-the-art correlation value of 92.5 percent. The proposed model's accuracy has significant implications for education as it has the potential to save educators considerable time and effort, while providing a reliable and fair evaluation for students, ultimately leading to improved learning outcomes. [ABSTRACT FROM AUTHOR]

Building automation (BA) strives to control interconnected physical devices by using software management systems on which end-users can personalize their environmental preferences. In large buildings, among the leading causes of IoT apps conflict are the shareable locations/devices amongst residents and the diversity of their preferences. Addressing such conflicts and ensuring the safety of residents are vital requirements in building automation systems. Consequently, the potential of IoT safety and correctness frameworks relies on supporting conflict detection. This paper provides a model for detecting and resolving IoT automation conflicts. These conflicts can result from shareable locations or devices. The proposed model is evaluated using a benchmark dataset and refined scenarios collected from competitor-related works (80+ IoT apps with 117+ rules). The proposed model surpasses state-of-the-art models by covering more conflicts (joint behavior conflict); moreover, it does not require events’ chain between IoT apps like other models, one more advantage is that the proposed model uses a filtering process in conflict detection which leads to small detection run-time. Thereby, our proposed model can maximize the correctness and safety of building automation systems. [ABSTRACT FROM AUTHOR]

Real-time three-dimensional (3D) reconstruction has been widely explored in several domains in motion capture, robot navigation, augmented reality, and autonomous driving. It is considered one of the most efficient solutions to overcome several problems, such as occlusion and collision in computer vision and computer graphics. This process is computationally intensive and it considers a bottleneck for real-time realistic interaction applications which need a quick response to achieve action in real-time. The Monocular 3D model reconstruction (M3DMR) is considered one of the possible solutions to build an accurate 3D reconstruction in a dynamic environment. However, the proposed framework needs a high computational power to create a single frame. Graphics processors unit (GPU) architecture is used to improve the computational time of M3DMR. This study discussed how to maximize the benefits of using GPU resources by using several optimization techniques that enable GPU architecture to achieve the best possible performance for the M3DMR. Different multicore heterogeneous systems are used to evaluate the performance of the proposed framework. Experimental results confirm that our parallel implementation of 3D Model Reconstruction of Monocular Video Frames is valid for different GPU architectures. The proposed parallel implementation can execute 28 FBS compared with the serial version that executes one frame in 30 min. [ABSTRACT FROM AUTHOR]

Clustering of biological datasets proved to reveal a lot of significant insights into the medical and biological research. It is an important step towards drug design, vaccine discovery, disease diagnosis, and more. The current trend in biological and medical research is to combine more than one dataset, referred to as multi-omics, related to a specific problem, then perform the clustering or the analysis. The insights we gain for a particular biological problem or disease are double using multi-omics rather than using one dataset. It is like investigating a problem from many dimensions rather than using one dimension. On the other hand, the difficulty of clustering is increased. Another tricky problem in data clustering is determining the best number of clusters used by a clustering algorithm. Due to the big success of metaheuristics in solving the automatic clustering problems, we propose in this paper a new hybrid method that utilizes two powerful metaheuristics algorithms, the Binary Differential Evolution and Marine Predators Algorithm, to perform automatic clustering on multi-omics datasets. Our proposal's performance is investigated upon eight multi-omics datasets from TCGA, and it is compared with four recent and powerful metaheuristics. The used performance metrics are clustering quality and execution time. The experimental results show that the proposed algorithm not only outperformed its competitors in terms of clustering quality, it also only needed a third of the execution time that of its fastest competitor. Moreover, the statistical analysis shows that the obtained results are statistically significant. Accordingly, the proposed method can be considered as an efficient clustering method for multi-omics datasets. [ABSTRACT FROM AUTHOR]

The automatic diagnosis of breast cancer is an important medical problem. This paper hybridizes metaphors from cells membranes and intercommunication between compartments with clonal selection principle together with fuzzy logic to produce a fuzzy rule system in order to be used in diagnosis. The fuzzy-membrane-immune algorithm suggested were implemented and tested on the Wisconsin breast cancer diagnosis (WBCD) problem. The developed solution scheme is compared with five previous works based on neural networks and genetic algorithms. The algorithm surpasses all of them. There are two motivations for using fuzzy rules with the membrane-immune algorithm in the underline problem. The first is attaining high classification performance. The second is the possibility of attributing a confidence measure (degree of benignity or malignancy) to the output diagnosis, beside the simplicity of the diagnosis system, which means that the system is human interpretable. [ABSTRACT FROM AUTHOR]

In this paper a membrane-immune algorithm is proposed, which is inspired from the structure of living cells and the vertebrate immune system. The algorithm is used to solve one of the most famous combinatorial NP-complete problems, namely the Multiple Zero/One Knapsack Problem. Various heuristics, like genetic algorithms, have been devised to solve this class of combinatorial problems. The proposed algorithm is compared with two genetic based algorithms and overcame both of them. The algorithm is evaluated on nine benchmarks test problems and surpassed both of the genetic based algorithms in six problems, equaled with one of them in two problems and lost in one problem, which indicates that our algorithm surpasses in general genetic algorithms. We claim that the proposed algorithm is very useful in solving similar combinatorial NP-complete problems. [ABSTRACT FROM AUTHOR]

Membrane Computing is an emergent and promising branch of Natural Computing. Designing P systems is heavy constitutes a difficult problem. The candidate has often had an idea about the problem solution form. On the other hand, finding the exact and precise configurations and rules is a hard task, especially if there is no tool used to help in the designing process. The clonal selection algorithm, which is inspired from the vertebrate immune system, is introduced here to help in designing a P system that performs a specific task. This paper illustrates the use of the clonal selection algorithm with adaptive mutation in P systems design and compares it with genetic algorithms previously used to achieve the same purpose. Experimental results show that clonal selection algorithm surpasses genetic algorithms with a great difference. [ABSTRACT FROM AUTHOR]