Time-frequency analysis of speech signal using Chirplet transform for automatic diagnosis of Parkinson's disease.

Parkinson's disease (PD) is the second most prevalent neurodegenerative disorder in the world after Alzheimer's disease. Early diagnosing PD is challenging as it evolved slowly, and its symptoms eventuate gradually. Recent studies have demonstrated that changes in speech may be utilized as an excellent biomarker for the early diagnosis of PD. In this study, we have proposed a Chirplet transform (CT) based novel approach for diagnosing PD using speech signals. We employed CT to get the time-frequency matrix (TFM) of each speech recording, and we extracted time-frequency based entropy (TFE) features from the TFM. The statistical analysis demonstrates that the TFE features reflect the changes in speech that occurs in the speech due to PD, hence can be used for classifying the PD and healthy control (HC) individuals. The effectiveness of the proposed framework is validated using the vowels and words from the PC-GITA database. The genetic algorithm is utilized to select the optimum features subset, while a support vector machine (SVM), decision tree (DT), K-Nearest Neighbor (KNN), and Naïve Bayes (NB) classifiers are employed for classification. The TFE features outperform the breathiness and Mel frequency cepstral coefficients (MFCC) features. The SVM classifier is most effective compared to other machine-learning classifiers. The highest classification accuracy rates of 98% and 99% are achieved using the vowel /a/ and word /atleta/, respectively. The results reveal that the proposed CT-based entropy features effectively diagnose PD using the speech of a person.

Effectiveness of repeated mutagenesis of sesame crosses for enhancing polygenic variability in F2M2 generation.

The value of combining hybridization and mutagenesis in sesame was examined to determine if treating hybrid sesame plant material with mutagens generated greater genetic variability in four key productivity traits than either the separate hybridization or mutation of plant material. In a randomized block design with three replications, six F2M2 varieties, three F2varieties, and three parental varieties were assessed at Odisha University of Agriculture and Technology, Bhubaneswar, Odisha, India. The plant characteristics height, number of seed capsules per plant, and seed yield per plant had greater variability in the F2M2 generation than their respective controls (F2), however, the number of primary branches per plant varied less than in the control population. The chances for trait selection to be operative were high for all the characteristics examined except the number of primary branches per plant, as indicated by heritability estimates. Increases in the mean and variability of the characteristics examined indicted a greater incidence of beneficial mutations and the breakdown of undesirable linkages with increased recombination. At both phenotypic and genotypic levels strong positive correlations between both primary branch number and capsule number with seed yield suggest that these traits are important for indirect improvement in sesame seed yield. As a result of the association analysis, sesame seed yield and its component traits improved significantly, which may be attributed to the independent polygenic mutations and enlarged recombination of the polygenes controlling the examined characteristics. Compared to the corresponding control treatment or to one cycle of mutagenic treatment, two cycles of mutagenic treatment resulted in increased variability, higher transgressive segregates, PTS mean and average transgression for sesame seed yield. These findings highlight the value of implementing two EMS treatment cycles to generate improved sesame lines. Furthermore, the extra variability created through hybridization may have potential in subsequent breeding research and improved seed yield segregants may be further advanced to develop ever-superior sesame varieties.

Significance of voiced and unvoiced speech segments for the detection of common cold.

This work investigates the significance of the voiced and unvoiced region for detecting common cold from the speech signal. In literature, the entire speech signal is processed to detect the common cold and other diseases. This study uses a short-time energy-based approach to segment the voiced and unvoiced region of the speech signal. Then, frame-wise mel frequency cepstral coefficients (MFCC) features are extracted from the voiced and unvoiced segments of each speech utterance, and statistics (mean, variance, skewness, and kurtosis) are calculated to get the feature vector for each speech utterance. The support vector machine (SVM) is utilized to analyze the performance of features extracted from the voiced and unvoiced region. Result shows that the feature extracted from voiced segments, unvoiced segments, and complete active speech (CAS) gives almost similar results using the MFCC features and SVM classifier. Therefore, rather than processing the CAS, we can process the unvoiced speech segments, which have fewer frames compared to CAS and voiced regions of speech. The processing of solely unvoiced segments can reduce the time and computation complexity of a speech signal-based common cold detection system.