Junjie Zhao

Dr. Junjie Zhao

Central South University School of Resources and Safety Engineering

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 July 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
Diyuan LiDiyuan Li
Diyuan Li
JZJunjie Zhao
Junjie Zhao
JMJinyin Ma
Jinyin Ma
Experimental studies were carried out to analyze the impact of optimizers and learning rate on the performance of deep learning-based algorithms for rock thin-section image classification. A total of 2634 rock thin-section images including three rock types—metamorphic, sedimentary, and volcanic rocks—were acquired from an online open-source science data bank. Four CNNs using three different optimizer algorithms (Adam, SGD, RMSprop) under two learning-rate decay schedules (lambda and cosine decay modes) were trained and validated. Then, a systematic comparison was conducted based on the performance of the trained model. Precision, f1-scores, and confusion matrix were adopted as the evaluation indicators. Trials revealed that deep learning-based approaches for rock thin-section image classification were highly effective and stable. Meanwhile, the experimental results showed that the cosine learning-rate decay mode was the better option for learning-rate adjustment during the training process. In addition, the performance of the four neural networks was confirmed and ranked as VGG16, GoogLeNet, MobileNetV2, and ShuffleNetV2. In the last step, the influence of optimization algorithms was evaluated based on VGG16 and GoogLeNet, and the results demonstrated that the capabilities of the model using Adam and RMSprop optimizers were more robust than that of SGD. The experimental study in this paper provides important practical value for training a high-precision rock thin-section image classification model, which can also be transferred to other similar image classification tasks.

17 February 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Diyuan LiDiyuan Li
Diyuan Li
JZJunjie Zhao
Junjie Zhao
ZLZida Liu
Zida Liu
Rock lithology recognition plays a fundamental role in geological survey research, mineral resource exploration, mining engineering, etc. However, the objectivity of researchers, rock variable natures, and tedious experimental processes make it difficult to ensure the accurate and effective identification of rock lithology. Additionally, multitype hybrid rock lithology identification is challenging, and few studies on this issue are available. In this paper, a novel multitype hybrid rock lithology detection method was proposed based on convolutional neural network (CNN), and neural network model compression technology was adopted to guarantee the model inference efficiency. Four fundamental single class rock datasets: sandstone, shale, monzogranite, and tuff were collected. At the same time, multitype hybrid rock lithologies datasets were obtained based on data augmentation method. The proposed model was then trained on multitype hybrid rock lithologies datasets. Besides, for comparison purposes, the other three algorithms, were trained and evaluated. Experimental results revealed that our method exhibited the best performance in terms of precision, recall, and efficiency compared with the other three algorithms. Furthermore, the inference time of the proposed model is twice as fast as the other three methods. It only needs 11 milliseconds for single image detection, making it possible to be applied to the industry by transforming the algorithm to an embedded hardware device or Android platform.

26 June 2024 in Minerals
Verified
Journal Article
Open access
PDF file
JZJunjie Zhao
Junjie Zhao
Diyuan LiDiyuan Li
Diyuan Li
YYYisong Yu
Yisong Yu
Rock fragmentation is an important evaluation indicator for field blasting operations. This paper applies a deep learning-based method, the Segment Anything Model (SAM), to automatically segment rock fragments. To review the SAM’s segmentation performance, 83 images of rock fragment collected from the mine site were used as the test dataset. Pixel-level accuracy (PA), intersection over union (IOU), and dice coefficient (Dice) were employed to evaluate the model pixel-level segmentation performance. The results showed that the SAM exhibited excellent segmentation performance on the test data (PA = 94.5%, IOU = 94.4%, Dice = 95.4%). The coefficient of determination (R2) values for the 50% and 80% passing sizes (X50 and X80) were 0.970 and 0.991, respectively, which demonstrated that the SAM could achieve high precision measurement of rock fragmentation. Additionally, the effectiveness of the SAM was further evaluated by comparing it to commercial software, and the generalizability of the SAM was verified on two other datasets. The findings revealed that the SAM not only outperformed the Split-Desktop V 4.0 on the test dataset but also achieved comparable accuracy to previous studies on the two other datasets. The SAM could be regarded as a useful tool to provide fast and accurate feedback for field blasting.