No abstract

Supraspinatus tendon injury is a common clinical shoulder joint disease and is one of the most common causes of shoulder pain and dysfunction. Supraspinatus tendon injury will lead to articular cartilage injury and degeneration, then cause joint disease, seriously affect the quality of life of patients, and bring a huge burden to the family and society. This paper mainly studies and evaluates the application value of special signs of shoulder joint and indirect MR imaging in the diagnosis of supraspinatus tendon injury. Through a series of special examinations for the diagnosis of supraspinatus tendon injury in 90 patients, including zero degree abduction resistance test, arm drop test, Jobe test, Neer sign, and Hawkins sign, all patients in the study underwent indirect magnetic resonance imaging of the shoulder joint. Finally, arthroscopic examination results were used as the “gold standard” to evaluate and analyze the diagnosis. The results showed that among the special signs, the specificity of the falling-arm test was the highest (72.2%) in the diagnosis of full-thickness supraspinatus tendon injury. Hawkins sign had the highest sensitivity (84.0%). In the diagnosis of partial supraspinatus tendon injury, the specificity of the Jobe test was the highest, which was 66.6%. The Neer sign had the highest sensitivity of 50.0%. In the diagnosis of full-thickness supraspinatus tendon injury, there was no significant difference in sensitivity between indirect MRI and Hawkins sign, but the diagnostic specificity of indirect MRI was higher than that of special sign examination. In the diagnosis of partial supraspinatus tendon injury, the sensitivity and specificity of indirect MR imaging are higher than those of special sign examination.

This paper proposes a tempo feature extraction method based on the long-term modulation spectrum analysis. To transform the modulation spectrum to a condensed feature vector, the log-scale modulation frequency coefficients are introduced. This idea aims at averaging the modulation frequency energy via the constant-Q filter-banks. Further it is pointed out that the feature can be extracted directly from the perceptually compressed data of digital music archives. To verify the effectiveness of the feature and its utility to music applications, the feature vector is used in a music emotion classification system. The system consisting two layers of Adaboost classifiers. In the first layer the conventional timbre features are employed. Then by adding the tempo feature in the second layer, the classification precision is improved dramatically. By this way the discriminability of the classifier based on the given features can be exploited extremely. The system obtains high classification precision on a small corpus. It proves that the proposed feature is very effective and computationally efficient to characterize the tempo information of music.

No abstract

No abstract