Hadi Veisi

Accurately predicting Pump-as-Turbine (PAT) performance curves under variable-speed conditions remains a major challenge for water distribution networks, primarily because conventional empirical models rely heavily on the Best Efficiency Point (BEP) and fail to capture hydraulic behavior under dynamic operating regimes.From an artificial intelligence perspective, this study introduces the Neural Oblivious Decision Ensembles (NODE) architecture as a data-driven modeling framework for nonlinear hydraulic performance prediction. Fifteen NODE configurations were systematically evaluated to identify the optimal NL2–TL2–TD2 structure, demonstrating superior generalization capability and robustness under variable-speed conditions.From an engineering application perspective, the proposed model accurately predicts PAT performance curves without dependence on BEP and reliably estimates head and power across different flow rates and rotational speeds (revolutions per minute, RPM). Feature importance analysis shows that flow rate dominates power prediction, whereas rotational speed exerts a decisive nonlinear influence on head.Comparison with conventional empirical correlations confirms that the proposed approach significantly reduces prediction uncertainty under real operational conditions. The results provide a practical foundation for real-time intelligent control and optimization of energy recovery systems in water distribution networks.

Low-resource machine translation for Central Kurdish (ckb) remains challenging due to scarce parallel data, orthographic variation, and rich morphology. We introduce our Kurdish with English corpus, a 500,000-pair ckb–En parallel dataset, and an efficient Marian-based neural machine translation system tailored to ckb through transfer learning and language-aware preprocessing (normalization, diacritic/script handling, and morphology-aware subwording). Trained on our corpus and evaluated against strong baselines and widely used online translators (Google Translate, Microsoft Translator), our models deliver consistent improvements in both directions as measured by BLEU and chrF++ (with COMET corroboration), with notable gains on named entities and numerals. Beyond advancing Kurdish MT, the work offers a practical recipe for building effective systems in data-poor settings and underscores the value of targeted adaptation for typologically distinct languages. To support reproducibility and future research, we will release the corpus, evaluation scripts, and model checkpoints.

Aim: Patients diagnosed with irregular astigmatism often require specific methods of vision correction. Among these, the use of a rigid gas permeable (RGP) lens is considered one of the most effective treatment approaches. This study aims to propose a new automated method for accurate RGP lens base-curve detection. Methods: A multi-modal feature fusion approach was developed based on Pentacam images, incorporating image processing and machine learning techniques. Four types of features were extracted from the images and integrated through a serial feature fusion mechanism. The fused features were then evaluated using a multi-layered perceptron (MLP) network. Specifically, the features included: (1) middle-layer outputs of a convolutional autoencoder (CAE) applied to RGB map combinations; (2) ratios of colored areas in the front cornea map; (3) a feature vector from cornea front parameters; and (4) the radius of the reference sphere/ellipse in the front elevation map. Results: Evaluations were performed on a manually labeled dataset. The proposed method achieved a mean squared error (MSE) of 0.005 and a coefficient of determination of 0.79, demonstrating improved accuracy compared to existing techniques. Conclusions: The proposed multi-modal feature fusion technique provides a reliable and accurate solution for RGP lens base-curve detection. This approach reduces manual intervention in lens fitting and represents a significant step toward automated base-curve determination.

This paper enhances the study of sentiment analysis for the Central Kurdish language by integrating the Bidirectional Encoder Representations from Transformers (BERT) into Natural Language Processing techniques. Kurdish is a low-resourced language, having a high level of linguistic diversity with minimal computational resources, making sentiment analysis somewhat challenging. Earlier, this was done using a traditional word embedding model, such as Word2Vec, but with the emergence of new language models, specifically BERT, there is hope for improvements. The better word embedding capabilities of BERT lend to this study, aiding in the capturing of the nuanced semantic pool and the contextual intricacies of the language under study, the Kurdish language, thus setting a new benchmark for sentiment analysis in low-resource languages.

Human consumption patterns have a significant impact on the amount of available water. However, the human effect on water resources is perceived to have been poorly studied. For the effective management of water resources, social and hydrological components should be studied. To fill this gap, the aim of this study was to investigate the socio-hydrological system of the Gavshan Dam in western Iran. Therefore, the qualitative method and root cause analysis (RCA) were used to investigate the causes of the imbalance between water consumption and water resources. Root cause analysis was used to investigate the perceptions of 87 farmers and extension experts from Kermanshah province in Iran. Participants were chosen using the snowball technique and interviewed using a semistructured questionnaire. The results showed that the ineffective administrative structure was the most important and fundamental cause of water management inefficiency, accounting for 48.49% of the total inefficiency. Furthermore, the community sensitivity component (1.34%) indicated that the socio-hydrological system in the studied basin is not fully understood and that network users are not concerned about water crisis and environmental degradation. Poor yield, low income of farmers, reduction of cultivated area, social instability, and lack of secondary agricultural jobs are the main reasons for mismanagement of water resources. Conceptualizing water challenges based on the socio-hydrology revealed by this study can help designers focus on the fundamental causes, discover opportunities for policy, and implement sustainable water management strategies.

Patients diagnosed with irregular astigmatism require certain means of vision correction. In this regard, the use of a Rigid Gas Permeable (RGP) lens is among the most effective treatment methods. However, RGP lens base-curve detection is among the challenging issues. Current techniques have faced drawbacks in providing accuracy in detection. In this paper, a new method is defined based on multi-modal feature fusion on Pentacam images for automatic RGP lens base-curve detection using image processing and machine learning techniques. To this end, four types of features have been extracted from Pentacam images followed by a serial feature fusion mechanism. The fusion technique provides all possible combinatory views of these feature types to a Multi-Layered Perceptron (MLP) network to determine the base-curve. The first type of feature is obtained from the middle layer after passing the RGB combination of maps through a Convolutional Autoencoder (CAE) neural network. The second set is obtained by calculating the ratio of the area of the colored areas of the front cornea map. A feature vector is derived from the Cornea Front parameters as the third modality and the fourth feature vector is the radius of the reference sphere/ellipse of the front elevation map. Our evaluations on a manually labeled dataset show that the proposed technique provides an accurate detection rate with a 0.005 means square error (MSE) and a coefficient of determination of 0.79, superior to previous methods. This can be considered an effective step towards automatic base-curve determination, minimizing manual intervention in lens fitting.