Evaluation model of teaching effectiveness of sports characteristic course based on intelligent fuzzy system

In order to improve the accuracy of the teaching effect evaluation, a teaching effect evaluation model based on the intelligent fuzzy system is designed. The evaluation index are selected based on the teaching situation of physical education courses, relevant national policy documents, subject textbooks, intelligent fuzzy system to modify the index system through expert interview, determine the weight coefficient of each index by hierarchical analysis method (AHP), and calculate the single layer and total ranking of the index matrix to realize the evaluation of physical education courses. The test results show that the fuzzy evaluation accuracy of the proposed model is above 95.63%, with high evaluation performance and strong utility.

Multi-Path Deep CNN with Residual Inception Network for Single Image Super-Resolution

Recent research on single-image super-resolution (SISR) using deep convolutional neural networks has made a breakthrough and achieved tremendous performance. Despite their significant progress, numerous convolutional neural networks (CNN) are limited in practical applications, owing to the requirement of the heavy computational cost of the model. This paper proposes a multi-path network for SISR, known as multi-path deep CNN with residual inception network for single image super-resolution. In detail, a residual/ResNet block with an Inception block supports the main framework of the entire network architecture. In addition, remove the batch normalization layer from the residual network (ResNet) block and max-pooling layer from the Inception block to further reduce the number of parameters to preventing the over-fitting problem during the training. Moreover, a conventional rectified linear unit (ReLU) is replaced with Leaky ReLU activation function to speed up the training process. Specifically, we propose a novel two upscale module, which adopts three paths to upscale the features by jointly using deconvolution and upsampling layers, instead of using single deconvolution layer or upsampling layer alone. The extensive experimental results on image super-resolution (SR) using five publicly available test datasets, which show that the proposed model not only attains the higher score of peak signal-to-noise ratio/structural similarity index matrix (PSNR/SSIM) but also enables faster and more efficient calculations against the existing image SR methods. For instance, we improved our method in terms of overall PSNR on the SET5 dataset with challenging upscale factor 8× as 1.88 dB over the baseline bicubic method and reduced computational cost in terms of number of parameters 62% by deeply-recursive convolutional neural network (DRCN) method.

Molecular Profiling of Chilli Germplasm By Using SSR Marker

The molecular characterization of chilli germplasm was done based on estimation of genetic diversity among the germplasm by using SSR markers. Forty chilli germplasms were analyzed using eight SSR primers. The SSR primers produced 30 SSR loci with an average value of 3.75 alleles per SSR locus. The similarity index matrix ranged from zero to 2.74. Polymorphic information content (PIC) of the SSR primers ranged from 0.543 to 0.735 with an average value of 0.658. The highest number (five) of allele was observed in primer CAMS-647, whereas the primers CAMS-864, CAMS-880 and CAMS-885 showed lowest number (three) of allele. The smallest allele was found in case of primer CAMS- 236 (176 bp), while the longest allele was detected for the primer CAMS- 864 (288 bp). Based on similarity matrix using the un-weighed Pair Group Method of Arithmetic Means (UPGMA) dendrogram, chilli germplasms were grouped into four main clusters. SSR markers showed genetic variability in the studied chilli germplasm. SAARC J. Agric., 19(1): 1-13 (2021)

Multi-task Pruning via Filter Index Sharing: A Many-Objective Optimization Approach

State-of-the-art deep neural network plays an increasingly important role in artificial intelligence, while the huge number of parameters in networks brings high memory cost and computational complexity. To solve this problem, filter pruning is widely used for neural network compression and acceleration. However, existing algorithms focus mainly on pruning single model, and few results are available to multi-task pruning that is capable of pruning multi-model and promoting the learning performance. By utilizing the filter sharing technique, this paper aimed to establish a multi-task pruning framework for simultaneously pruning and merging filters in multi-task networks. An optimization problem of selecting the important filters is solved by developing a many-objective optimization algorithm where three criteria are adopted as objectives for the many-objective optimization problem. With the purpose of keeping the network structure, an index matrix is introduced to regulate the information sharing during multi-task training. The proposed multi-task pruning algorithm is quite flexible that can be performed with either adaptive or pre-specified pruning rates. Extensive experiments are performed to verify the applicability and superiority of the proposed method on both single-task and multi-task pruning.

Sustainable Business Model Innovations in the Value Uncaptured Manufacturing Industry: Fitting Gains—Gain Creators

Increased manufacturing activity has an impact on environmental quality degradation. Waste generated from manufacturing activities is one of the causes. Previous studies have referred to this waste as value uncaptured. Minimizing value uncaptured is a solution to improve environmental quality. This study aims to reduce value uncaptured by converting it into value captured. This process requires a value proposition design approach because of its advantages. One of the advantages of this approach is that it can improve existing or future products/services. To do so, this research uses a case study of a furniture company. To implement a converting process, a sustainable business model is proposed to solve this problem. This business model combines several methods: value proposition design, house of value and the product sustainability index matrix. Recently, the existing value proposition problem-solving has been using the value proposition design method. This research proposed implementing a house of value to replace the fitting process. The questionnaire is developed to obtain various value uncaptured in the company. To the weight of the value uncaptured, this research utilized the pairwise comparison method. Then, the weights could represent the importance of jobs. Based on the highest weight of these jobs, the alternative gains would be selected. To provide the weight of the gain creators and value captured, the house of value method is developed. Referring to three pillars of sustainability, the value captured should be considered. This research proposed implementing a product sustainability index which in turn produces eco-friendly products. This study produces “eco-friendly products” as sustainability value captured. The sustainability business model could be an alternative policy to minimize the existence of value uncaptured.