Capsule shell from animal source (bovine or porcine gelatin) is a problem for the follower of different religions and vegetarian. In that case, vegetable capsule shell could be a solution. In this research, we proposed a simple and cost-effective technique for detection of gelatin in vegetable capsule shell and for classification of capsule shell by source, based on Chemometric techniques with FTIR spectroscopic data. Partial Least-Square Regression (PLSR) models were developed and their efficiencies were assessed with spectroscopic data of range of 4000-700 cm-1. PLSR shows very good prediction efficiency (R2= 98%) for both vegetable capsule shell and gelatin. In addition, Soft Independent Modeling by Class Analogy (SIMCA) classification method were developed and assessed with spectral data of capsule shells from vegetable and animal sources. Results prove that FTIR spectroscopy in combination with chemometric method can be used for the classification of capsule shell by source and quantification of gelatin in vegetable capsule shell to ensure their authenticity. Bangladesh J. Sci. Ind. Res. 57(2), 91-98, 2022

No abstract

No abstract

Deep Learning algorithms are often used as black box type learning and they are too complex to understand. The widespread usability of Deep Learning algorithms to solve various machine learning problems demands deep and transparent understanding of the internal representation as well as decision making. Moreover, the learning models, trained on sequential data, such as audio and video data, have intricate internal reasoning process due to their complex distribution of features. Thus, a visual simulator might be helpful to trace the internal decision making mechanisms in response to adversarial input data, and it would help to debug and design appropriate deep learning models. However, interpreting the internal reasoning of deep learning model is not well studied in the literature. In this work, we have developed a visual interactive web application, namely d-DeVIS, which helps to visualize the internal reasoning of the learning model which is trained on the audio data. The proposed system allows to perceive the behavior as well as to debug the model by interactively generating adversarial audio data point. The web application of d-DeVIS is available at ddevis.herokuapp.com.