KP-Rank: a semantic-based unsupervised approach for keyphrase extraction from text data

Automatic key concept identification from text is the main challenging task in information extraction, information retrieval, digital libraries, ontology learning, and text analysis. The main difficulty lies in the issues with the text data itself, such as noise in text, diversity, scale of data, context dependency and word sense ambiguity. To cope with this challenge, numerous supervised and unsupervised approaches have been devised. The existing topical clustering-based approaches for keyphrase extraction are domain dependent and overlooks semantic similarity between candidate features while extracting the topical phrases. In this paper, a semantic based unsupervised approach (KP-Rank) is proposed for keyphrase extraction. In the proposed approach, we exploited Latent Semantic Analysis (LSA) and clustering techniques and a novel frequency-based algorithm for candidate ranking is introduced which considers locality-based sentence, paragraph and section frequencies. To evaluate the performance of the proposed method, three benchmark datasets (i.e. Inspec, 500N-KPCrowed and SemEval-2010) from different domains are used. The experimental results show that overall, the KP-Rank achieved significant improvements over the existing approaches on the selected performance measures.

     

Type 2 Diabetes Risk Prediction Using Deep Convolutional Neural Network Based-Bayesian Optimization

Diabetes mellitus is a long-term condition characterized by hyperglycemia. It could lead to plenty of difficulties. According to rising morbidity in recent years, the world’s diabetic patients will exceed 642 million by 2040, implying that one out of every ten persons will be diabetic. There is no doubt that this startling figure requires immediate attention from industry and academia to promote innovation and growth in diabetes risk prediction to save individuals’ lives. Due to its rapid development, deep learning (DL) was used to predict numerous diseases. However, DL methods still suffer from their limited prediction performance due to the hyperparameters selection and parameters optimization. Therefore, the selection of hyper-parameters is critical in improving classification performance. This study presents Convolutional Neural Network (CNN) that has achieved remarkable results in many medical domains where the Bayesian optimization algorithm (BOA) has been employed for hyperparameters selection and parameters optimization. Two issues have been investigated and solved during the experiment to enhance the results. The first is the dataset class imbalance, which is solved using Synthetic Minority Oversampling Technique (SMOTE) technique. The second issue is the model's poor performance, which has been solved using the Bayesian optimization algorithm. The findings indicate that the Bayesian based-CNN model superbases all the state-of-the-art models in the literature with an accuracy of 89.36%, F1-score of 0.88.6, and Matthews Correlation Coefficient (MCC) of 0.88.6.     

Investigation of the effect of superheating on the performance of a refrigeration system using low temperature different refrigerant blends in porous media

A comparative experimental investigation on the effect of superheating of R‐22, R‐404A, R‐407C, and R‐422A as low‐temperature refrigerant blends on the performance of a vapor compression refrigeration system is conducted. Empty and porous evaporators with porosities of (40%, 43%, and 45%) are used during the tests, to predict good alternatives to the refrigerant R‐22, which has high ozone depletion potential and high global warming potential. Condensation, evaporation temperatures, degree of subcool are kept constants at 40°C, ?26°C, and 6°C (±0.5°C), respectively. The effect of superheating on the compressor discharge temperature, evaporating pressure drop, evaporating capacity, volumetric refrigeration capacity and coefficient of performance (COP) of these refrigerants has been analyzed. Refrigerants, R‐422A and R‐404A showed greater performances than that of R‐22. The percentages of increase in evaporation capacities of R‐407c, R‐22, R‐404A, and R‐422A are approximately 144%, 168%, 146.3%, and 161.5%, respectively, when changing the degrees of superheat from 6°C to 16°C and changing the porosity from empty evaporator to 40%. The percentages of increase in COP are approximately 319%, 320%, 312%, and 350%, respectively. The percentages of increase in evaporation capacities of R‐422A and R‐404A when compared with R‐22 under the same conditions are 18.6% and 8.8%, respectively, while the percentages of increase in COP when compared with R‐22 are 17% and 12%, respectively.     

Solution Synthesis of BiFeO3 Thin Films onto Silicon Substrates with Ferroelectric,Magnetic, and Optical Functionalities

Single‐BiFeO₃ perovskite films onto Pt‐coated silicon substrates have been fabricated by chemical solution deposition using a synthesis strategy based on the use of nonhazardous reagents. Different routes were tested to obtain precursors for the deposition of the films, inferring that bismuth (III) nitrate and iron (III) 2,4‐pentanedionate dissolved in acetic acid and 1,3‐propendiol led to the best solution. Ferroelectric, magnetic, and optical functionalities were demonstrated in these films, obtaining a high ferroelectric polarization at room temperature, ~67 μC × cm^?2, a dependence of the magnetization with the film thickness, 0.60 and 2.50 emu × g^?1 for the ~215 and ~42‐nm‐thick films, and a direct band gap in the visible range, E_g ~2.82 eV. These results support the interest of solution methods for the fabrication of BiFeO₃ thin films onto the silicon substrates required in microelectronic devices.