Estimating the semantic similarity between short texts plays an increasingly prominent role in many fields related to text mining and natural language processing applications, especially with the large increase in the volume of textual data that is produced daily. Traditional approaches for calculating the degree of similarity between two texts, based on the words they share, do not perform well with short texts because two similar texts may be written in different terms by employing synonyms. As a result, short texts should be semantically compared. In this paper, a semantic similarity measurement method between texts is presented which combines knowledge-based and corpus-based semantic information to build a semantic network that represents the relationship between the compared texts and extracts the degree of similarity between them. Representing a text as a semantic network is the best knowledge representation that comes close to the human mind's understanding of the texts, where the semantic network reflects the sentence's semantic, syntactical, and structural knowledge. The network representation is a visual representation of knowledge objects, their qualities, and their relationships. WordNet lexical database has been used as a knowledge-based source while the GloVe pre-trained word embedding vectors have been used as a corpus-based source. The proposed method was tested using three different datasets, DSCS, SICK, and MOHLER datasets. A good result has been obtained in terms of RMSE and MAE.
Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven class
... Show MoreIn this paper, a new equivalent lumped parameter model is proposed for describing the vibration of beams under the moving load effect. Also, an analytical formula for calculating such vibration for low-speed loads is presented. Furthermore, a MATLAB/Simulink model is introduced to give a simple and accurate solution that can be used to design beams subjected to any moving loads, i.e., loads of any magnitude and speed. In general, the proposed Simulink model can be used much easier than the alternative FEM software, which is usually used in designing such beams. The obtained results from the analytical formula and the proposed Simulink model were compared with those obtained from Ansys R19.0, and very good agreement has been shown. I
... Show MoreModern civilization increasingly relies on sustainable and eco-friendly data centers as the core hubs of intelligent computing. However, these data centers, while vital, also face heightened vulnerability to hacking due to their role as the convergence points of numerous network connection nodes. Recognizing and addressing this vulnerability, particularly within the confines of green data centers, is a pressing concern. This paper proposes a novel approach to mitigate this threat by leveraging swarm intelligence techniques to detect prospective and hidden compromised devices within the data center environment. The core objective is to ensure sustainable intelligent computing through a colony strategy. The research primarily focusses on the
... Show MoreThe complexity and variety of language included in policy and academic documents make the automatic classification of research papers based on the United Nations Sustainable Development Goals (SDGs) somewhat difficult. Using both pre-trained and contextual word embeddings to increase semantic understanding, this study presents a complete deep learning pipeline combining Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Network (CNN) architectures which aims primarily to improve the comprehensibility and accuracy of SDG text classification, thereby enabling more effective policy monitoring and research evaluation. Successful document representation via Global Vector (GloVe), Bidirectional Encoder Representations from Tra
... Show MoreThis paper present the fast and robust approach of English text encryption and decryption based on Pascal matrix. The technique of encryption the Arabic or English text or both and show the result when apply this method on plain text (original message) and how will form the intelligible plain text to be unintelligible plain text in order to secure information from unauthorized access and from steel information, an encryption scheme usually uses a pseudo-random enecryption key generated by an algorithm. All this done by using Pascal matrix. Encryption and decryption are done by using MATLAB as programming language and notepad ++to write the input text.This paper present the fast and robust approach of English text encryption and decryption b
... Show MoreThe construction industry in Iraq suffers from many problems, perhaps the most important of which is the delay in time and the increase in costs. Therefore, it was necessary to try to adopt a new methodology that would help in overcoming these problems. It was suggested to combine building information modeling with the agile management approach because this technique and methodology is modern and helps in reducing time and cost and improving quality. This paper aims to know the status of using Building Information Modeling (BIM) and Agile Project management (APM) in Iraq and to shed light on the merging of this integration, explaining the benefits, difficulties, and workflow practices, finding the most influencing factors on the tim
... Show MoreThe present study deals with the strategies used in the Arabic translations of the most popular genres of children’s literature; namely fairy tales and fables as an attempt to identify the best methods and strategies to be adopted in translating these genres to fulfill the ultimate purpose of enriching the children’s knowledge in addition to attracting their interest and arousing the joy sought for in every piece of literature.
The study sets off from three dominating trends: the first calls for the adoption of domestication strategy of translation as the most appropriate and effective strategy in translation for children. In the same line, the second opposes using the foreignization strategy, w
... Show More