http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Md. Rashed-Al-Mahfuz,Mohammad Ali Moni,Pietro Lio’,Sheikh Mohammed Shariful Islam,Shlomo Berkovsky,Matloob Khushi,Julian M. W. Quinn 대한의용생체공학회 2021 Biomedical Engineering Letters (BMEL) Vol.11 No.2
Medical practitioners need to understand the critical features of ECG beats to diagnose and identify cardiovascular conditionsaccurately. This would be greatly facilitated by identifying the signifi cant features of frequency components in temporalECG wave-forms using computational methods. In this study, we have proposed a novel ECG beat classifi er based ona customized VGG16-based Convolution Neural Network (CNN) that uses the time-frequency representation of temporalECG, and a method to identify the contribution of interpretable ECG frequencies when classifying based on the SHapleyAdditive exPlanations (SHAP) values. We applied our model to the MIT-BIH arrhythmia dataset to classify the ECG beatsand to characterise of the beats frequencies. This model was evaluated with two advanced time-frequency analysis methods. Our results indicated that for 2-4 classes our proposed model achieves a classifi cation accuracy of 100% and for 5 classes itachieves a classifi cation accuracy of 99.90%. We have also tested the proposed model using premature ventricular contractionbeats from the American Heart Association (AHA) database and normal beats from Lobachevsky University Electrocardiographydatabase (LUDB) and obtained a classifi cation accuracy of 99.91% for the 5-classes case. In addition, SHAP valueincreased the interpretability of the ECG frequency features. Thus, this model could be applicable to the automation of thecardiovascular diagnosis system and could be used by clinicians.
Md. Tanvir Ahmad,Drishti Nandita,Tanvir Mohammad Maruf,Mohammad Hasanuzzaman Pabitra,Sabrina Islam Mony,Md. Shawkat Ali,Md. Sarwar Ahmed,Mohammad Shamsul Alam Bhuiyan 한국가금학회 2021 韓國家禽學會誌 Vol.48 No.2
This study investigated the morphological features, growth, and meat yield performance of Pekin (P), Nageswari (N), and their reciprocal F1 crossbreds (P♂×N♀ and N♂×P♀). A total of 301-day-old ducklings were reared in four different pens up to 20 weeks of age under intensive management conditions. Feeding and management practices were similar for all individuals throughout the experimental period. The morphology and plumage pattern of F1 crossbreds were similar to those of indigenous Nageswari ducks because of the dominant inheritance of the extended Black allele (E locus). Genotype had significant differences (P<0.05) among the four genotypes in morphometric measurements, except wing and shank length. Growth performance was highly significant among the four genotypes (P<0.001) from one-day to 12 weeks of age. The average live weights of P, N, P♂×N♀ and N♂×P♀ crossbred genotypes at 12 weeks of age were 2038.35±29.74, 1542.44±33.61, 1851.85±28.59 and 1691.08±27.80 g, respectively. Meat yield parameters varied significantly (P<0.05) among the different genotypes for all studied traits, except for liver and gizzard weight. Moreover, no significant differences (P>0.05) were observed between P and P♂×N♀ crossbred for important meat yield traits such as hot carcass weight, dressing%, back half weight, drumstick with thigh weight and breast meat weight. Remarkably, the P♂×N♀ crossbreed possesses 50% native inheritance, which contributes to better adaptation in a hot-humid environment. Our results revealed that the P♂×N♀ genotype could be suitable for higher meat production with better adaptability in the agro-climatic conditions of Bangladesh.