No abstract

In computer vision, the convolutional neural network (CNN) is a very popular model used for emotion recognition. It has been successfully applied to detect various objects in digital images with remarkable accuracy. In this paper, we extracted learned features from a pre-trained CNN and evaluated different machine learning (ML) algorithms to perform classification. Our research looks at the impact of replacing the standard SoftMax classifier with other ML algorithms by applying them to the FC6, FC7, and FC8 layers of Deep Convolutional Neural Networks (DCNNs). Experiments were conducted on two well-known CNN architectures, AlexNet and VGG-16, using a dataset of masked facial expressions (MLF-W-FER dataset). The results of our experiments demonstrate that Support Vector Machine (SVM) and Ensemble classifiers outperform the SoftMax classifier on both AlexNet and VGG-16 architectures. These algorithms were able to achieve improved accuracy of between 7% and 9% on each layer, suggesting that replacing the classifier in each layer of a DCNN with SVM or ensemble classifiers can be an efficient method for enhancing image classification performance. Overall, our research demonstrates the potential for combining the strengths of CNNs and other machine learning (ML) algorithms to achieve better results in emotion recognition tasks. By extracting learned features from pre-trained CNNs and applying a variety of classifiers, we provide a framework for investigating alternative methods to improve the accuracy of image classification.

Background: People nowadays have developed a new passion of weightlifting. Weightlifting focuses on vigorous muscle development. But injuries are also common in weightlifting. This study aims to compare the injury rates among supervised and non-supervised weightlifters. Methods: A group of 138 weight lifters was divided into two groups i.e. who did training under supervision and the other who did training without any supervision. Injuries related to musculoskeletal system were identified using Nordic musculoskeletal questionnaire. Data was analyzed using SPSS. Chi square test was used to see the association of musculoskeletal pain among weightlifters with or without supervision. Results: Significant association found between musculoskeletal injuries and supervision. Injuries lesser in number among supervised weightlifters as compared to unsupervised weightlifters. Mean age of weight lifters under supervision and without supervision was 21.99 (SD 3.81) and 24.64 (SD 5.01) respectively. Mean workout days /week among weight lifters under supervision was almost same i.e. 5.67 (SD .63) and was 5.62 (SD .81). Out of 51 participants who work-out for 46-60 min, 30 were not under supervision while 31 weightlifters who work-out for 61-90 min were working out under supervision. Injury rate was more in the region of shoulder in both groups supervised and unsupervised groups while hip/thigh region was less involved in both supervised and unsupervised groups. Conclusion: Overall results showed significant association between musculoskeletal injuries and supervision. Injury rate was more among weightlifters who work without supervision as compared to those who work under supervision. Care should be taken and weight lifting and exercises must be performed under expert’s supervision.

High heeled shoes align the foot in planter flexion, modifying the relative orientation of the skeletal structures of ankle, metatarsal, and metatarsophalangeal joints, and alter the insertion angles of the foot and gliding joint muscles, therefore increasing the risk factor for ankle sprain. Objective: Study conducted to determine Risk Factors Causing Ankle Sprain among undergraduate female students. Methods: Cross-Sectional study was conducted among 500 female students (Between ages 18-26 years) at Sargodha Medical College and completed in 06 months (June 2019-December 2019). Non-probability convenient sampling technique was used to collect data and then entered to SPSS-25 for further statistical analysis. Result: Among 500 participants, Age 19.65±1.416 years. Mean height (m) 1.61±0.073, mean weight (kg) 57.37±10.4, Mean BMI was 22.02±3.6. Female experience ankle sprain (54%), not experienced ankle sprain (46%) Significant association found between Ankle Sprain and body mass index (BMI) as the P value was 0.014 which was <0.05. Female wearing high heel have 1.082 times greater chance of developing ankle sprain (OR 1.082). Female wearing high heel for long duration (4-6 hrs.) have 1.271 times greater chance of developing ankle sprain (OR 1.271), female wearing high heel (3-4 inches) have 1.072 times greater chance of developing ankle sprain (OR 1.072), female using Pencil heel have 1.281 times greater chance of developing ankle sprain (OR 1.281). Conclusion: Significant association found between Ankle Sprain and body mass index (BMI). Female wearing, high heel for long duration (4-6 hrs.), high heel (3-4 inches height), using Pencil heel have greater chance of developing ankle sprain.

High heeled shoes align the foot in planter flexion, modifying the relative orientation of the skeletal structures of ankle, metatarsal, and metatarsophalangeal joints, and alter the insertion angles of the foot and gliding joint muscles, therefore increasing the risk factor for ankle sprain. Objective: Study conducted to determine Risk Factors Causing Ankle Sprain among undergraduate female students. Methods: Cross-Sectional study was conducted among 500 female students (Between ages 18-26 years) at Sargodha Medical College and completed in 06 months (June 2019-December 2019). Non-probability convenient sampling technique was used to collect data and then entered to SPSS-25 for further statistical analysis. Result: Among 500 participants, Age 19.65±1.416 years. Mean height (m) 1.61±0.073, mean weight (kg) 57.37±10.4, Mean BMI was 22.02±3.6. Female experience ankle sprain (54%), not experienced ankle sprain (46%) Significant association found between Ankle Sprain and body mass index (BMI) as the P value was 0.014 which was <0.05. Female wearing high heel have 1.082 times greater chance of developing ankle sprain (OR 1.082). Female wearing high heel for long duration (4-6 hrs.) have 1.271 times greater chance of developing ankle sprain (OR 1.271), female wearing high heel (3-4 inches) have 1.072 times greater chance of developing ankle sprain (OR 1.072), female using Pencil heel have 1.281 times greater chance of developing ankle sprain (OR 1.281). Conclusion: Significant association found between Ankle Sprain and body mass index (BMI). Female wearing, high heel for long duration (4-6 hrs.), high heel (3-4 inches height), using Pencil heel have greater chance of developing ankle sprain.