Yen-Jen Chang

Yen-Jen Chang

Auto-generated profile, based on publicly available information

Yen-Jen Chang

Department of Computer Science and Engineering, National Chung Hsing University, Taichung, Taiwan

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
22 March 2024 in Agriculture
Verified
Journal Article
Open access
PDF file
CCChe-Hao Chang
Che-Hao Chang
Jason LinJason Lin
Jason Lin
JCJia-Wei Chang
Jia-Wei Chang
YHYu-Shun Huang
Yu-Shun Huang
MLMing-Hsin Lai
Ming-Hsin Lai
YCYen-Jen Chang
Yen-Jen Chang
Recently, data-driven approaches have become the dominant solution for prediction problems in agricultural industries. Several deep learning models have been applied to crop yield prediction in smart farming. In this paper, we proposed an efficient hybrid deep learning model that coordinates the outcomes of a classification model and a regression model in deep learning via the shared layers to predict the rice crop yield. Three statistical analyses on the features, including Pearson correlation coefficients (PCC), Shapley additive explanations (SHAP), and recursive feature elimination with cross-validation (RFECV), are proposed to select the most relevant ones for the predictive goal to reduce the model training time. The data preprocessing normalizes the features of the collected data into specific ranges of values and then reformats them into a three-dimensional matrix. As a result, the root-mean-square error (RMSE) of the proposed model in rice yield prediction has achieved 344.56 and an R-squared of 0.64. The overall performance of the proposed model is better than the other deep learning models, such as the multi-parametric deep neural networks (MDNNs) (i.e., RMSE = 370.80, R-squared = 0.59) and the artificial neural networks (ANNs) (i.e., RMSE = 550.03, R-squared = 0.09). The proposed model has demonstrated significant improvement in the predictive results of distinguishing high yield from low yield with 90% accuracy and 94% F1 score.

14 June 2021 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
KTKun-Lin Tsai
Kun-Lin Tsai
YCYen-Jen Chang
Yen-Jen Chang
CWChien-Ho Wang
Chien-Ho Wang
CCCheng-Tse Chiang
Cheng-Tse Chiang
Approximate computing is an efficient approach for reducing computational costs. This method involves a trade-off between computational accuracy and the circuit's power consumption, delay, and area. However, the accuracy requirements may differ for different applications. In some situations, precise results are required. Therefore, this paper proposes an accuracy-configurable radix-4 adder (ACRA), which uses the power gating technique to turn on or turn off the partial logic gates of an adder element dynamically to compute accurate or approximate results. When the ACRA operates in the approximate mode, the partial sum of one adder element is modified to reduce the error distance between the approximate and accurate results. A comparison of the ACRA with two state-of-the-art accuracy-configurable adders indicated that the ACRA achieved the best trade-off between the power-delay product and computational accuracy. In addition, in the image processing experiment conducted in this study, under half-approximate computation, the peak signal-to-noise ratio of the ACRA was less than 1 dB and its structural similarity index measure was maintained above 0.99. These results are superior to those obtained for other accuracy-configurable adders.

7 March 2013 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
YCYen-Jen Chang
Yen-Jen Chang
KTKun-Lin Tsai
Kun-Lin Tsai
HTHsiang-Jen Tsai
Hsiang-Jen Tsai
Ternary content-addressable memory (TCAM) is a popular hardware device for fast routing lookup and an attractive solution for applications such as packet forwarding and classification. However, the high cost and power consumption are limiting its popularity and versatility. In this paper, a low leakage power TCAM architecture which uses two-side self power gating technique is proposed to reduce the leakage power dissipation of the mask SRAM cells. The TCAM mask cells are divided into several segments, and the mask bits of one segment are the same except for the boundary segment. In this design, the boundary segment is activated and the others are disabled so that the leakage power can be reduced. The experimental results show that average 26% leakage power can be reduced by using UMC 90 nm CMOS process with 1.0 V supply voltage when compared with the traditional TCAM architecture.

3 November 2023 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
YCYen-Jen Chang
Yen-Jen Chang
YWYi-Da Wu
Yi-Da Wu
YLYu-Lin Liao
Yu-Lin Liao
CWChien-Ho Wang
Chien-Ho Wang
YWYen-Ching Wu
Yen-Ching Wu

8 February 2023 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
YCYen-Jen Chang
Yen-Jen Chang
SCShih-Hsiang Chen
Shih-Hsiang Chen
The widely used Von Neumann architecture must move data between memory and the computation unit when performing operations, which causes a performance bottleneck. In-memory computing is an effective way to reduce the bottleneck; therefore, we design an in-memory Boolean computing architecture based on static random access memory (SRAM). We also propose a new multi-logic sense amplifier (MLSA) design, an improvement over conventional sense amplifiers that only perform a single logical operation, either NOR/OR or NAND/AND. Our design can generate multiple logical outputs, including OR/NOR, AND/NAND, and XOR/XNOR, with a lower compute delay, lower power consumption, and less transistor count. In the experimental results, the proposed MLSA design reduces the NAND, AND, and XNOR delay by 62%, 39%, and 30%, and it also decreases the static power consumption by 40% and dynamic power consumption in computing operations by 22% compared to the conventional sensing method.

14 March 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YCYen-Jen Chang
Yen-Jen Chang
MLMing-Hsin Lai
Ming-Hsin Lai
CWChien-Ho Wang
Chien-Ho Wang
YHYu-Shun Huang
Yu-Shun Huang
Jason LinJason Lin
Jason Lin
Because rice is the most important food crop, its yield prediction has a critical impact on the food policy and farmer income. In this paper, we propose a new yield prediction model for the rice, called target-aware yield prediction (TAYP) model that can effectively improve the accuracy of yield prediction. The proposed TAYP model is a LSTM-based network, in which we modify the loss function by introducing the target yield. Unlike the traditional loss function that is independent of the target yield, our design can make the prediction model sensitive to the target yield, such that the accuracy of yield prediction is increased. To test the TAYP model, we use a rice dataset from Taiwan Agricultural Research Institute, which consists of multispectral vegetation indexes collected by drones. The experimental results show that the TAYP model performs better than the related works on various evaluation criteria. Compared to the traditional LSTM model, TAYP model improves RMSE and R-squared by 6.1% and 13.0%, respectively, while increasing accuracy from 89% to 95%. Particularly, the Kappa value of TAYP is 0.82 that is almost perfect agreement with the real measurement. It is clear that the proposed TAYP model can make significant accuracy improvement to the rice yield prediction and has the potential to be a useful tool for improving agricultural productivity.