{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:25:27Z","timestamp":1720743927545},"reference-count":17,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T00:00:00Z","timestamp":1720656000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The Prince Sultan University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Pashtu is one of the most widely spoken languages in south-east Asia. Pashtu Numerics recognition poses challenges due to its cursive nature. Despite this, employing a machine learning-based optical character recognition (OCR) model can be an effective way to tackle this issue. The main aim of the study is to propose an optimized machine learning model which can efficiently identify Pashtu numerics from 0\u20139. The methodology includes data organizing into different directories each representing labels. After that, the data is preprocessed <jats:italic>i.e.<\/jats:italic>, images are resized to 32\u00a0\u00d7\u00a032 images, then they are normalized by dividing their pixel value by 255, and the data is reshaped for model input. The dataset was split in the ratio of 80:20. After this, optimized hyperparameters were selected for LSTM and CNN models with the help of trial-and-error technique. Models were evaluated by accuracy and loss graphs, classification report, and confusion matrix. The results indicate that the proposed LSTM model slightly outperforms the proposed CNN model with a macro-average of precision: 0.9877, recall: 0.9876, F1 score: 0.9876. Both models demonstrate remarkable performance in accurately recognizing Pashtu numerics, achieving an accuracy level of nearly 98%. Notably, the LSTM model exhibits a marginal advantage over the CNN model in this regard.<\/jats:p>","DOI":"10.7717\/peerj-cs.2124","type":"journal-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T07:23:09Z","timestamp":1720682589000},"page":"e2124","source":"Crossref","is-referenced-by-count":0,"title":["Recognition of inscribed cursive Pashtu numeral through optimized deep learning"],"prefix":"10.7717","volume":"10","author":[{"given":"Sibtain","family":"Syed","sequence":"first","affiliation":[{"name":"Department of IT & CS, Pak-Austria Fachhochschule Institute of Applied Sciences and Technology,  Haripur, KP, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khalil","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, School of Engineering and Digital Sciences, Nazarbayev University,  Astana, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maqbool","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of IT & CS, Pak-Austria Fachhochschule Institute of Applied Sciences and Technology,  Haripur, KP, Pakistan"},{"name":"PAF-IAST, Sino-Pak Center for Artificial Intelligence (SPCAI), Haripur, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rehan Ullah","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulrahman","family":"Aloraini","sequence":"additional","affiliation":[{"name":"Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"issue":"1","key":"10.7717\/peerj-cs.2124\/ref-1","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.idm.2021.12.005","article-title":"The efficacy of deep learning based LSTM model in forecasting the outbreak of contagious diseases","volume":"7","author":"Absar","year":"2022","journal-title":"Infectious Disease Modelling"},{"key":"10.7717\/peerj-cs.2124\/ref-2","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1109\/ICDAR.2015.7333931","article-title":"Scale and rotation invariant OCR for Pashto cursive script using MDLSTM network","author":"Ahmad","year":"2015"},{"key":"10.7717\/peerj-cs.2124\/ref-3","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/978-3-319-32213-1_18","article-title":"Balinese character recognition using bidirectional LSTM classifier","volume-title":"Advances in machine learning and signal processing. Lecture notes in electrical engineering","volume":"387","author":"Ahmed","year":"2016"},{"key":"10.7717\/peerj-cs.2124\/ref-4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICAPAI49758.2021.9462055","article-title":"Predicting remaining fatigue life of topside piping using deep learning","author":"Chatterjee","year":"2021"},{"key":"10.7717\/peerj-cs.2124\/ref-5","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.1.3896.7842","article-title":"Analytical review of preprocessing techniques for offline handwritten character recognition","author":"Gaurav Kumar","year":"2013"},{"key":"10.7717\/peerj-cs.2124\/ref-6","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/CICN.2015.73","article-title":"Eastern Arabic numerals: a stand out from other Jargons","author":"Gautam","year":"2015"},{"issue":"6789","key":"10.7717\/peerj-cs.2124\/ref-7","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1038\/35016072","article-title":"Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit","volume":"405","author":"Hahnloser","year":"2000","journal-title":"Nature"},{"issue":"1","key":"10.7717\/peerj-cs.2124\/ref-8","doi-asserted-by":"publisher","first-page":"5979","DOI":"10.1038\/s41598-022-09954-8","article-title":"On evaluation metrics for medical applications of artificial intelligence","volume":"12","author":"Hicks","year":"2022","journal-title":"Scientific Reports"},{"key":"10.7717\/peerj-cs.2124\/ref-9","doi-asserted-by":"publisher","DOI":"10.17632\/ZBYC7SGP63.2","article-title":"Pashtu language digits dataset (PLDD)","author":"Khan","year":"2022"},{"issue":"2014","key":"10.7717\/peerj-cs.2124\/ref-10","first-page":"257","article-title":"Impact of data normalization on stock index forecasting","volume":"6","author":"Nayak","year":"2013","journal-title":"International Journal of Computer Information Systems and Industrial Management Applications"},{"issue":"11","key":"10.7717\/peerj-cs.2124\/ref-11","doi-asserted-by":"publisher","first-page":"753","DOI":"10.26438\/ijcse\/v6i11.753758","article-title":"A literature review on handwritten character recognition based on artificial neural network","volume":"6","author":"Singh","year":"2018","journal-title":"Ijcse"},{"key":"10.7717\/peerj-cs.2124\/ref-12","doi-asserted-by":"publisher","first-page":"128644","DOI":"10.1109\/ACCESS.2023.3331652","article-title":"Split-second cryptocurrency forecast using prognostic deep learning algorithms: data curation by deephaven","volume":"11","author":"Syed","year":"2023","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.2124\/ref-13","doi-asserted-by":"publisher","DOI":"10.54938\/ijemdcsai.2023.02.1.239","article-title":"Intracranial tumor detection using magnetic resonance imaging and deep learning","volume":"2","author":"Syed","year":"2023","journal-title":"IJEMD-CSAI"},{"issue":"6","key":"10.7717\/peerj-cs.2124\/ref-14","doi-asserted-by":"publisher","first-page":"1343","DOI":"10.2166\/wpt.2023.081","article-title":"Application of coupling machine learning techniques and linear Bias scaling for optimizing 10-daily flow simulations, Swat River Basin","volume":"18","author":"Syed","year":"2023","journal-title":"Water Practice & Technology"},{"issue":"3","key":"10.7717\/peerj-cs.2124\/ref-15","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/computation11030052","article-title":"Theoretical understanding of convolutional neural network: concepts, architectures, applications, future directions","volume":"11","author":"Taye","year":"2023","journal-title":"Computation"},{"key":"10.7717\/peerj-cs.2124\/ref-16","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1109\/ICDAR.2013.212","article-title":"Offline printed Urdu Nastaleeq script recognition with bidirectional LSTM networks","author":"Ul-Hasan","year":"2013"},{"key":"10.7717\/peerj-cs.2124\/ref-17","doi-asserted-by":"publisher","DOI":"10.5281\/ZENODO.1071948","article-title":"Recognition-based segmentation in persian character recognition","author":"Zand","year":"2008","journal-title":"Zenodo"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-2124.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2124.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2124.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2124.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T07:23:31Z","timestamp":1720682611000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-2124"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,11]]},"references-count":17,"alternative-id":["10.7717\/peerj-cs.2124"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.2124","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,11]]},"article-number":"e2124"}}