Abstract Machine learning (ML) has been extensively applied in various disciplines. However, not much attention paid to data heterogeneity databases and number of samples used train ML models hydrology. In this study, we addressed these issues their impacts on the accuracy reliability estimation saturated hydraulic conductivity, K s . We selected 17,990 soil from USKSAT database created random subsets N = 2,000, 4,000, 6,000, 8,000, 10,000, 12,000, 14,000, 16,000, 17,990, 80% which were for...

Generating coherent and comprehensive responses remains a significant challenge Question-Answering (QA) systems when working with short answers especially for low-resourced languages like Farsi. We present novel approach to expand these into complete, fluent responses, addressing the critical issue of limited Farsi resources models. Our methodology employs two-stage process: first, we develop dataset using rule-based techniques on text, followed by BERT-based ranking system ensure fluency...

Long sessions of computer use introduce physical and mental health risks, particularly for programmers intensive users. Breathing exercises can improve focus, reduce stress, overall well-being. However, existing tools such practices are often app-based, requiring users to leave their workspace. In this technical report, we Nafas, a command-line interface (CLI) application designed specifically users, enabling them perform breathing directly within the terminal. Nafas offers structured...

Long sessions of computer use introduce physical and mental health risks, particularly for programmers intensive users. Breathing exercises can improve focus, reduce stress, overall well-being. However, existing tools such practices are often app-based, requiring users to leave their workspace. In this technical report, we _Nafas_, a command-line interface (CLI) application designed specifically users, enabling them perform breathing directly within the terminal. _Nafas_ offers structured...

PyMilo is an open-source Python package that addresses the limitations of existing Machine Learning (ML) model storage formats by providing a transparent, reliable, and safe method for exporting deploying trained models. Current formats, such as pickle other binary have significant problems, reliability, safety, transparency issues. In contrast, serializes ML models in transparent non-executable format, enabling straightforward exchange, while also facilitating deserialization deployment...

The rise of large language models (LLMs) has transformed numerous natural processing (NLP) tasks, yet their performance in low and mid-resource languages, such as Farsi, still lags behind resource-rich languages like English. To address this gap, we introduce Naab, the largest publicly available, cleaned, ready-to-use Farsi textual corpus. Naab consists 130GB data, comprising over 250 million paragraphs 15 billion words. Named after word ناب (meaning "pure" or "high-grade"), corpus is openly...

<p>Dataset includes Direct Borohydride Fuel Cell (DBFC) impedance and polarization test in anode with Pd/C, Pt/C Pd decorated Ni–Co/rGO catalysts. In fact, different concentration of Sodium (SBH), applied voltages various catalysts loading explanation experimental details electrochemical analysis are considered data. Voltage, power density resistance DBFC change as a function weight percent SBH (%), voltage amount catalyst that evaluated by curves using appropriate equivalent circuit...

Dataset includes Direct Borohydride Fuel Cell (DBFC) impedance and polarization test in anode with Pd/C, Pt/C Pd decorated Ni–Co/rGO catalysts. In fact, different concentration of Sodium (SBH), applied voltages various catalysts loading explanation experimental details electrochemical analysis are considered data. Voltage, power density resistance DBFC change as a function weight percent SBH (%), voltage amount catalyst that evaluated by curves using appropriate equivalent circuit fuel cell....

Sayed Hesam Alavian, Ali Satvaty, Sadra Sabouri, Ehsaneddin Asgari, Hossein Sameti. Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering. 2022.

Huge corpora of textual data are always known to be a crucial need for training deep models such as transformer-based ones. This issue is emerging more in lower resource languages - like Farsi. We propose naab, the biggest cleaned and ready-to-use open-source corpus It contains about 130GB data, 250 million paragraphs, 15 billion words. The project name derived from Farsi word NAAB K which means pure high grade. also provide raw version called naab-raw an easy-to-use preprocessor that can...