Arabian Journal for Science and Engineering最新文献

{"title":"A Graph-Based Transformer Neural Network for Multi-Label ADR Prediction","authors":"Monika Yadav, Prachi Ahlawat, Vijendra Singh","doi":"10.1007/s13369-024-09342-6","DOIUrl":"https://doi.org/10.1007/s13369-024-09342-6","url":null,"abstract":"<p>Adverse drug reactions (ADRs) pose substantial health hazards and financial burdens on patients. Accurate prediction of these reactions has become crucial within the clinical domain to guarantee prompt intervention. Many techniques have been presented to predict ADRs based on the drug’s molecular structure. However, these techniques are limited to the transformation of a multi-label classification problem into multiple binary problems and the formation of distinct classifiers for individual drug reactions. Such techniques can be computationally expensive and time-consuming when dealing with a large no. of ADRs. Moreover, the multi-label classifier can learn associations between multiple related ADRs more effectively. Therefore, the objective of this research is the multi-label classification of adverse drug reactions by incorporating transformers-based graph neural networks (GNNs). This paper presents a new model called GTransfNN (graph-based transformer neural network) that leverages graphs with transformers to analyze the molecular structure of drugs. It aims to predict 27 ADR categories based on the system organ class. The proposed model introduces three key characteristics as its main components: First, it considers an attention mechanism that operates on the interconnectivity among neighboring nodes within the graph. Second, it incorporates edge features together with node features while calculating the attention weight for each node. Finally, it replaces layer normalization with batch normalization. The results indicate that the proposed model outperforms the other state-of-the-art models, such as neural fingerprint and Attentive_FP model, with notable increases of 10% and 18% in AUC, respectively. It achieves an AUC of 0.82 and an accuracy of 0.83 on the SIDER dataset. Similarly, it showcases steady performance enhancements on the ADRECS dataset, attaining an accuracy of 0.84 and an AUC of 0.82 by showcasing a 5%, 16%, and 25% increase in AUC as compared to iADRGSE, BERT_Smile, and Attentive_FP methods. These results show the model’s robustness and reliability across different datasets, thereby contributing to more effective drug safety assessments and health-care decision-making processes.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"1 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141882503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing Precision Agriculture: Enhanced Weed Detection Using the Optimized YOLOv8T Model","authors":"Shubham Sharma, Manu Vardhan","doi":"10.1007/s13369-024-09419-2","DOIUrl":"https://doi.org/10.1007/s13369-024-09419-2","url":null,"abstract":"<p>Precision agriculture relies on effective weed management for high yields and crop quality. Deep learning (DL)-based techniques show potential for providing effective solutions. However, their practicality is sometimes limited by insufficient datasets. Our research has utilized a comprehensive instance-level annotated weed dataset derived from existing agricultural imagery to address this critical gap. This dataset encompasses various weed and crop species, with images featuring detailed bounding box annotations to mark individual instances. This refinement facilitates the application of advanced DL models by providing more granular, real-world training data. Utilizing this dataset, we extensively evaluated the latest object detection models, focusing on the YOLO series, including YOLOv7, YOLOv8 variants, and our newly proposed YOLOv8T model. Our findings reveal that the YOLOv8T model surpasses its predecessors, achieving a mean average precision (mAP) of 82.5%. This notable improvement underscores the model’s enhanced capability to accurately distinguish between crop and weed species. Moreover, our study delves into the impact of data augmentation techniques to mitigate class imbalance within the dataset, further elevating the YOLOv8T’s performance metrics. These techniques improved the mAP results and showed how DL models, especially the YOLOv8T, can improve weed detection systems in the field. Through rigorous testing and analysis, our research confirms the viability of the YOLOv8T model as a cornerstone for developing automatic, efficient, and scalable weed detection systems.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"8 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141882651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Student Psychology-Based Optimization Tuned PIDA Controller for Improved Frequency Regulation of a Two-Area Microgrid","authors":"Sindhura Gupta, Susovan Mukhopadhyay, Ambarnath Banerji, Prasun Sanki, Sujit K. Biswas","doi":"10.1007/s13369-024-09346-2","DOIUrl":"https://doi.org/10.1007/s13369-024-09346-2","url":null,"abstract":"<p>This paper presents a student psychology-based optimization (SPBO) tuned proportional–integral derivative accelerator (PIDA) controller to address the frequency regulation issue of an interconnected microgrid system. The performance of the proposed control scheme is investigated under different load perturbations, and it is observed that the PIDA controller is effective for higher-order system configurations. Further, Bode plot-based stability margin analysis is presented to determine the EV gain parameter for ensuring optimal system performance. Available, research works consider lossless tie-line power model for the interconnected microgrid scenarios by neglecting the effect of the line reactance. In this regard, to replicate a practical microgrid scenario, an improved tie-line model is presented considering the effect of line resistance along with the line reactance. Furthermore, the performance of the proposed system configuration is validated under a 12-node radial distribution network. It is noteworthy to mention that the proposed control scheme shows improved responses in terms of peak over/under shoots, oscillations and settling time, when compared with the available control schemes. Therefore, the suggested controller presents significant improvement in the frequency as well as tie-line power oscillations. All the test scenarios are simulated and examined under the MATLAB 2016a environment.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"106 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141882487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Life-History Strategy Shifts in Withania somnifera (L.) Dunal (Winter Cherry) in the Face of Combined Environmental Stresses","authors":"Ummar Iqbal, Muhammad Usama Aslam, Muhammad Faisal Gul, Fahad Ur Rehman, Umar Farooq, Ali Daad, Ahmad Ali","doi":"10.1007/s13369-024-09367-x","DOIUrl":"https://doi.org/10.1007/s13369-024-09367-x","url":null,"abstract":"<p><i>Withania somnifera</i> (L.) Dunal. is a bushy evergreen plant that naturalizes dry and arid soils of subtropical regions across the world. It is widely recognized for therapeutic benefits and cultivated in rainfed areas for its drought tolerance. However, the purpose of the study is to investigate how <i>W. somnifera</i> adapts to different ecological conditions and the effects of these adaptations on the physio-biochemical properties of the plant. In this context, twelve populations of <i>W. somnifera</i> were collected from four diverse ecological ranges such as Cholistan desert (dryness ratio = 43.00–29.23, <i>P</i> = 101.4–149.2 mm), Thal desert (dryness ratio = 23.46–20.37, <i>P</i> = 185.9–213.1 mm), Rajanpur desert (Dryness ratio = 31.64–20.61, <i>P</i> = 137.8–211.6 mm) and Potohar Plateau (dryness ratio = 7.13–5.11, <i>P</i> = 611.5–850.4 mm) to explore the key anatomical and physiological modifications involved in ecological success of this species across heterogenic environmental conditions. Results showed that ionic contents, organic osmolytes, root and stem cellular area and trichome area substantially increased in Cholistan desert populations. We observed specific variations in Thal desert populations, including a higher shoot biomass and increased photosynthetic pigments, enlarged vascular bundles in stems and enlarged metaxylem and phloem areas in roots and leaves. Rajanpur desert populations were highly xeromorphic, with increased root biomass production, more leaves, thicker midribs and laminae, thicker epidermis and cortical region, sparse hairiness on leaf surfaces and deeply crypted stomata. Populations inhabiting the Potohar Plateau exhibited maximum plant height and shoot growth, large cortical cells in roots and leaves and numerous trichomes. Overall, these adaptive traits display <i>W. somnifera</i> resilience against environmental challenges, promising innovative applications in medicine and agriculture.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"1 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141882490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance Analysis of Embedding Methods for Deep Learning-Based Turkish Sentiment Analysis Models","authors":"Abdulfattah Ba Alawi, Ferhat Bozkurt","doi":"10.1007/s13369-024-09360-4","DOIUrl":"https://doi.org/10.1007/s13369-024-09360-4","url":null,"abstract":"<p>The complex syntactic structure of Turkish text makes sentiment analysis in natural language processing (NLP) a challenging task. Conventional sentiment analysis methods often fail to effectively identify attitudes in Turkish texts, creating an urgent need for more efficient approaches. To fill this need, our study investigates the effectiveness of embedding techniques including pre-trained Turkish models such as Word2Vec, GloVe, and FastText in addition to two character-level embedding methods, namely, character-integer embedding (CIE) and character one-hot encoding embedding (COE), in conjunction with deep learning models specifically long short-term memory (LSTM), convolution neural networks (CNNs), bidirectional LSTM (Bi-LSTM), and hybrid models, for Turkish short-texts sentiment analysis. DL-based models were investigated on two datasets (e.g., an original Twitter (X) dataset and an accessible hotel reviews dataset). In addition to providing an intensive performance analysis of different embedding strategies and assessing their efficacy in dealing with the linguistic intricacies of Turkish, this study proposed a previously unexplored method in Turkish text representation that relies on a character-level one-hot encoding technique. The obtained findings indicate positive progress using a novel approach utilizing a dual-pathway architecture for both character level and word level that constitutes a substantial contribution to the area of natural language processing (NLP), specifically in the context of complex morphological languages. By employing a hybrid strategy that combines character and word levels on Twitter (X) data, the LSTM model obtained an <i>F</i>1 score of <span>(0.835 pm 0.005)</span> concerning cross-validation while CNN-BiLSTM attained the highest <i>F</i>1 Score (0.8392) using holdout validation. This strategy consistently produced modest improvements across the second public dataset (hotel reviews dataset) by emerging as the runner-up embedding technique in effectiveness, surpassed only by FastText. Findings provide practical recommendations for practitioners on how to effectively use sentiment analysis to make informed decisions by introducing an extensive performance analysis of the use of embedding techniques and deep learning models for sentiment analysis in Turkish texts, which is crucial in the current age of data analysis.\u0000</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"1 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141868033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of Finite Element Simulation in Predicting Slab Cambers During the Width Sizing Process","authors":"Chungen Zong, Jiahan Bao, Weiwen Zhou","doi":"10.1007/s13369-024-09336-4","DOIUrl":"https://doi.org/10.1007/s13369-024-09336-4","url":null,"abstract":"<p>To investigate the effect of the equipment factors of the sizing press and the slab temperature on the camber of a slab, considering the elastic bending, flattening deformation, and torsion of multiple rollers with different characteristics, based on the Chaboche model, a finite element model was carefully constructed for an asymmetrical thermal sizing press, by comparing the field experimental data, and the proposed model with high prediction accuracy is verified. Under conditions of both uniform and non-uniform temperature distributions on both sides of the slab, the effects of misalignment of incoming slabs and misalignment of anvils on the camber are discussed and compared. Results indicate that the impacts on cambers can be prioritized in descending order: anvil horizontal tilt, slab centerline offset, slab horizontal tilt, and anvil centerline offset. Further research reveals that when the uneven temperature is coupled with these asymmetric factors, maintaining the influence value within 30 mm, and positioning the high-temperature side of the slab on the side opposing the tilt direction, while aligning the offsets of the slab and anvil in the same direction contributes to reducing the camber. Besides, by controlling the slab heating process and implementing related precision control measures for the sizing press, the cambers of the sizing slabs can be significantly reduced. Consequently, the camber qualification rate of rough-rolled intermediate billets routinely exceeds 80% each month, improving the overall quality of succeeding slabs.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"21 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141882563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"‍Mesoporous L-Phenylalanine-CuO as an Eco-Friendly and Efficient Nanocatalyst for 1,2,3-Triazoles Synthesis and Study of Their Antimicrobial Properties","authors":"Najmeh Ghaderi, Jalal Albadi, Heshmat Allah Samimi, Zahra Hemati, S. Saeid Saei Dehkordi, Maryam Majidian","doi":"10.1007/s13369-024-09403-w","DOIUrl":"https://doi.org/10.1007/s13369-024-09403-w","url":null,"abstract":"<p>A green mesoporous catalyst was prepared by copper immobilization onto L-phenylalanine (L-Phe), and it was studied using different analytical methods, including FT-IR, XRD, FE-SEM, EDX, BET, TGA, DSC, and ICP analysis. Using sodium azide, phenylacetylene, benzyl or alkyl halides, and a nanocatalyst, the CuAAC reaction has been effectively utilized to produce 1,2,3-triazoles with regioselective efficiency. The main advantages of the current approach are the easy recyclability of the catalyst, short reaction time, low cost, simple preparation, and high yield. Furthermore, the (L-Phe)-CuO showed antimicrobial properties.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"3 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141867917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Application of Partial Update Kalman Filter for Bilinear System Modelling","authors":"Lakshminarayana Janjanam, Suman Kumar Saha, Rajib Kar, C. R. S. Hanuman","doi":"10.1007/s13369-024-09313-x","DOIUrl":"https://doi.org/10.1007/s13369-024-09313-x","url":null,"abstract":"<p>Bilinear models are a special class of nonlinear models significant for nonlinear systems’ parameter estimation and control design. This study proposes a novel application of partial update Kalman filter (PUKF) where the PUKF profoundly enhances the accuracy of bilinear systems modelling. In the PUKF approach, only a subset of the parameter state vector is updated at each epoch, which could decrease the computational burden compared to the traditional Kalman filter. Moreover, this work uses a preaching optimisation algorithm (POA) to tune the PUKF parameters adaptively based on the estimation problem. The adequately adjusted adaptive PUKF provide good estimation results, stable filtering operation and quick convergence. A new objective function is formulated based on correlation functions and an error between the estimated and actual outputs. The new objective function significantly improved the quality of the solution. The sensitivity of POA on solution quality is analysed using various statistical parameters. The efficacy and correctness of the proposed algorithm are verified on a numerical plant and two real-time benchmark systems. The quantitative analysis based on the proposed scheme is examined with distinct standard metrics and robustness verified at different Gaussian noise variance levels. The accuracy, stability, and consistency of the proposed algorithm performance are verified through the Diebold–Mariano hypothesis test, results from several independent runs, and tenfold cross-validation tests. The simulation results manifest that the POA-assisted PUKF method is much more effective and better compared to other existing and employed benchmark metaheuristic techniques such as self-adaptive differential evolution, crow search algorithm, and POA methods.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"45 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141882558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Regional Chitosan and Melaleuca armillaris Essential Oil with Mesoporous Glass Particles for Enhancing Bioactive and Antibacterial Behaviour of Ti6Al4V Implants","authors":"Daniel Buldain, Florencia Diaz, Irem Unalan, Nora Mestorino, Aldo R. Boccaccini, Josefina Ballarre","doi":"10.1007/s13369-024-09414-7","DOIUrl":"https://doi.org/10.1007/s13369-024-09414-7","url":null,"abstract":"<p>Metal implants have long been studied and used for applications related to bone tissue engineering, thanks to their outstanding mechanical properties and appropriate biocompatibility. However, due to their lack of bioactivity, many implants struggle with osteointegration and attachment, and can be vulnerable to the development of infections. In this work, we have developed a composite coating via electrophoretic deposition which is both bioactive and antibacterial. We have loaded a combination of <i>Melaleuca armillaris</i> essential oil and gentamicin into mesoporous bioactive glass particles, and incorporated the nanoparticles into a chitosan solution electrophoretically deposited onto the titanium substrate. This coating significantly improves the antibacterial activity against both gram-positive and negative strains of bacteria compared to the bare substrate. The coating is biocompatible, as MG63 cells seeded on the coated materials exhibit their typical spindle-like morphology and can grow into a smooth layer on the surface after 7 days.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"80 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141882559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Short-term Power Load Forecasting Based on TCN-BiLSTM-Attention and Multi-feature Fusion","authors":"Yang Feng, Jiashan Zhu, Pengjin Qiu, Xiaoqi Zhang, Chunyan Shuai","doi":"10.1007/s13369-024-09351-5","DOIUrl":"https://doi.org/10.1007/s13369-024-09351-5","url":null,"abstract":"<p>Accurate power load forecasting provides reliable decision support for power system planning and operation, however, only using the load data for prediction is not enough, since it is influenced by electricity demand, electricity behavior, electricity prices, etc. Inspired by this, this paper proposes a hybrid model to promote the short-term power load forecasting performance by integrating such external factors and power load as multivariate time series. The proposed model, TCN-BiLSTM-Attention, combines two temporal convolutional network (TCN), two bidirectional long short-term memory (BiLSTM), and attention mechanism. Wherein, TCN uses parallel convolution kernels to extract temporal features from preprocessed each subsequence, and then BiLSTM further captures the long and short-term dependencies of these features. Further, the flatten and fully connection layer with Attention discovers the correlations between multivariate time series and improves the predictive performance by giving higher weights on the important information. The extensive experiment results show that TCN-BiLSTM-Attention is superior to the state-off-the- art, and the addition of multiple factors enables it to learn more useful information, and thus improving the prediction performance. All suggest that there is a strong correlation between the power load and external factors, and the proposed model can effectively obtain the long and short-term dependencies of single sequence and the correlations between multivariate time series, and this advantages makes it have excellent predictive performance and strong robustness in short-term load forecasting.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"34 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141868029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}