Wyniki wyszukiwania - BazTech

1

Sign language interpreting - relationships between research in different areas - overview

Probierz Barbara, Kozak Jan, Piasecki Adam, Podlaszewska Angelika

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

213--223

EN

Translation from the national language into sign language is an extremely important area of research and practice, which aims to ensure communication between deaf or hard of hearing people and the hearing community. The article provides an overview of the most important research on sign language interpretation conducted in various research areas. The latest scientific and theoretical achievements were presented, which contribute to a better understanding of the subject of sign language translation and the improvement of the quality of translation services. Our main goal is to identify outstanding areas of interdisciplinary research related to sign language translation and to identify links between these studies conducted in different areas. The conclusions of the article aim to broaden the knowledge and awareness of sign language translation and to identify areas that require further research and development. The work is linked to a project related to the application of machine learning in increasing accessibility for deaf people.

2

Detecting type of hearing loss with different AI classification methods: a performance review

Kassjański Michał, Kulawiak Marcin, Przewoźny Tomasz, Tretiakow Dmitry, Kuryłowicz Jagoda, Molisz Andrzej, Koźmiński Krzysztof, Kwaśniewska Aleksandra, Mierzwińska-Dolny Paulina, Grono Miłosz

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

1017--1022

EN

Hearing is one of the most crucial senses for all humans. It allows people to hear and connect with the environment, the people they can meet and the knowledge they need to live their lives to the fullest. Hearing loss can have a detrimental impact on a person's quality of life in a variety of ways, ranging from fewer educational and job opportunities due to impaired communication to social withdrawal in severe situations. Early diagnosis and treatment can prevent most hearing loss. Pure tone audiometry, which measures air and bone conduction hearing thresholds at various frequencies, is widely used to assess hearing loss. A shortage of audiologists might delay diagnosis since they must analyze an audiogram, a graphic representation of pure tone audiometry test results, to determine hearing loss type and treatment. In the presented work, several AI-based models were used to classify audiograms into three types of hearing loss: mixed, conductive, and sensorineural. These models included Logistic Regression, Support Vector Machines, Stochastic Gradient Descent, Decision Trees, RandomForest, Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), Graph Neural Network (GNN), and Recurrent Neural Network (RNN). The models were trained using 4007 audiograms classified by experienced audiologists. The RNN architecture achieved the best classification performance, with an out-of-training accuracy of 94.46%. Further research will focus on increasing the dataset and enhancing the accuracy of RNN models.

3

Development of an AI-based audiogram classification method for patient referral

Kassjański Michał, Kulawiak Marcin, Przewoźny Tomasz

Annals of Computer Science and Information Systems

|

2022

|

Vol. 30

163--168

EN

Hearing loss is one of the most significant sensory disabilities. It can have various negative effects on a person's quality of life, ranging from impeded school and academic performance to total social isolation in severe cases. It is therefore vital that early symptoms of hearing loss are diagnosed quickly and accurately. Audiology tests are commonly performed with the use of tonal audiometry, which measures a patient's hearing threshold both in air and bone conduction at different frequencies. The graphic result of this test is represented on an audiogram, which is a diagram depicting the values of the patient's measured hearing thresholds. In the course of the presented work several different artificial neural network models, including MLP, CNN and RNN, have been developed and tested for classification of audiograms into two classes - normal and pathological represented hearing loss. The networks have been trained on a set of 2400 audiograms analysed and classified by professional audiologists. The best classification performance was achieved by the RNN architecture (represented by simple RNN, GRU and LSTM), with the highest out-of-training accuracy being 98% for LSTM. In clinical application, the developed classifier can significantly reduce the workload of audiology specialists by enabling the transfer of tasks related to analysis of hearing test results towards general practitioners. The proposed solution should also noticeably reduce the patient's average wait time between taking the hearing test and receiving a diagnosis. Further work will concentrate on automating the process of audiogram interpretation for the purpose of diagnosing different types of hearing loss.