An automated materials and processes identification tool for material informatics using deep learning approach.

This article reports a tool that enables Materials Informatics, termed as MatRec, via a deep learning approach. The tool captures data, makes appropriate domain suggestions, extracts various entities such as materials and processes, and helps to establish entity-value relationships. This tool uses keyword extraction, a document similarity index to suggest relevant documents, and a deep learning approach employing Bi-LSTM for entity extraction. For example, materials and processes for electrical charge storage under an electric double layer capacitor (EDLC) mechanism are demonstrated herewith. A knowledge graph approach finds and visualizes different latent knowledge sets from the processed information. The MatRec received an F1 score of 9̃6% for entity extraction, 8̃3% for material-value relationship extraction, and 8̃7% for process-value relationship extraction, respectively. The proposed MatRec could be extended to solve material selection issues for various applications and could be an excellent tool for academia and industry.

ReSTiNet: An Efficient Deep Learning Approach to Improve Human Detection Accuracy.

Human detection is an important task in computer vision. It is one of the most important tasks in global security and safety monitoring. In recent days, Deep Learning has improved human detection technology. Despite modern techniques, there are very few optimal techniques to construct networks with a small size, deep architecture, and fast training time while maintaining accuracy. ReSTiNet is a novel small convolutional neural network that overcomes the problems of network size, detection speed, and accuracy. The developed ReSTiNet contains fire modules by evaluating their number and position in the network to minimize the model parameters and network size. To improve the detection speed and accuracy of ReSTiNet, the residual block within the fire modules is carefully designed to increase the feature propagation and maximize the information flow in the network. The developed approach compresses the well-known Tiny-YOLO architecture while improving the following features: (i) small model size, (ii) faster detection speed, (iii) resolution of overfitting, and (iv) better performance than other compact networks such as SqueezeNet and MobileNet in terms of mAP on the Pascal VOC and MS COCO datasets. ReSTiNet is 10.7 MB, five times smaller than Tiny-YOLO. On Tesla k80, mAP is 27.3% for MS COCO and 63.74% for PASCAL VOC. The validation of the proposed ReSTiNet model has been done on INRIA person dataset using the Tesla K80.•All the necessary steps, algorithms, and mathematical formulas for building the net- work are provided.•The network is small in size but has a faster detection speed with high accuracy.

Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study.

Thyroid disease is the general concept for a medical problem that prevents one's thyroid from producing enough hormones. Thyroid disease can affect everyone-men, women, children, adolescents, and the elderly. Thyroid disorders are detected by blood tests, which are notoriously difficult to interpret due to the enormous amount of data necessary to forecast results. For this reason, this study compares eleven machine learning algorithms to determine which one produces the best accuracy for predicting thyroid risk accurately. This study utilizes the Sick-euthyroid dataset, acquired from the University of California, Irvine's machine learning repository, for this purpose. Since the target variable classes in this dataset are mostly one, the accuracy score does not accurately indicate the prediction outcome. Thus, the evaluation metric contains accuracy and recall ratings. Additionally, the F1-score produces a single value that balances the precision and recall when an uneven distribution class exists. Finally, the F1-score is utilized to evaluate the performance of the employed machine learning algorithms as it is one of the most effective output measurements for unbalanced classification problems. The experiment shows that the ANN Classifier with an F1-score of 0.957 outperforms the other nine algorithms in terms of accuracy.