首页|Firat University Reports Findings in Robotics and Machine Learning (Multifeature Fusion Method with Metaheuristic Optimization for Automated Voice Pathology Det ection)
Firat University Reports Findings in Robotics and Machine Learning (Multifeature Fusion Method with Metaheuristic Optimization for Automated Voice Pathology Det ection)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Robotics and Machine L earning is the subject of a report. According to news reporting originating in E lazig, Turkey, by NewsRx journalists, research stated, “Voice pathologies occur due to various factors, such as malfunction of the vocal cords. Computerized aco ustic examinationbased vocal pathology detection is crucial for early diagnosis , efficient follow-up, and improving problematic speech.” The news reporters obtained a quote from the research from Firat University, “Di fferent acoustic measurements provide it. Executing this process requires expert monitoring and is not preferred by patients because it is time-consuming and co stly. This paper is aimed at detecting metaheuristic-based automatic voice patho logy. First, feature maps of 10 common diseases, including cordectomy, dysphonia , front lateral partial resection, contact pachyderma, laryngitis, lukoplakia, p ure breath, recurrent laryngeal paralysis, vocal fold polyp, and vox senilis, we re obtained from the Zero-Crossing Rate, Root-Mean-Square Energy, and Mel-freque ncy Cepstral Coefficients using a thousand voice signals from the Saarbruecken V oice Database dataset. Hybridizations of different features obtained from the vo ices of the same diseases using these three methods were used to increase the mo del’s performance. The Grey Wolf Optimizer (MELGWO) algorithm based on local sea rch, evolutionary operator, and concatenated feature maps derived from various a pproaches was employed to minimize the number of features, implement the models faster, and produce the best result. The fitness values of the metaheuristic alg orithms were then determined using supervised machine learning techniques such a s Support Vector Machine (SVM) and K-nearest neighbors. The F1 score, sensitivit y, specificity, accuracy, and other assessment criteria were compared with the e xperimental data.”
ElazigTurkeyEurasiaHealth and Medi cinePathologyRobotics and Machine Learning
NETL
NSTL
