Comparative analysis of off-policy PPO algorithm and on-policy algorithm on the a) CSMAR and b) MorningStar datasets. by Cai Yuanqing (22513351)

Action potential of sample points in model 1. by Hang Zhao (143592)

Subjects: “…crayfish optimization algorithm…”

Action potential of sample points in model 2. by Hang Zhao (143592)

Subjects: “…crayfish optimization algorithm…”

Action potential of sample points in model 0. by Hang Zhao (143592)

Subjects: “…crayfish optimization algorithm…”

Schematic of the directed network flow entropy (DNFE) algorithm. by Xueqing Peng (10678527)

The actual training effect of four algorithms on original photo data (All images are original images taken by the author). by Xiaojun Wang (50332)

Subjects:

FastICA algorithm and feature point selection. by Huanyu Yang (6683780)

“…The sub-block selection algorithm sorts and filters sub-blocks based on the average pixel difference, reconstructing the input data to ensure accurate separation of melanin and hemoglobin. …”

Indexing of the serial synchrotron crystallography (SSX) diffraction images of the glucose isomerase (GI) processed using the MOSFLM, DirAx, and XGANDALF algorithms at various crys... by Ki Hyun Nam (5813819)

Subjects:

Proposed process model for sensor nodes. by Shayesteh Tabatabaei (12280016)

Subjects:

Proposing sequence genetic distances with our local greedy algorithm when genomic sampling data is unavailable. by Hannah Waddel (21520023)

The general processing diagram used to create OSSL. by José L. Safanelli (20552654)

Subjects:

Improved random forest algorithm. by Zhen Zhao (159931)

“…Subsequently, the feature factors corresponding to the model with the highest accuracy were selected as the optimal feature subsets and used in the model construction as input data. Additionally, considering the imbalanced in population spatial distribution, we used the K-means ++ clustering algorithm to cluster the optimal feature subset, and we used the bootstrap sampling method to extract the same amount of data from each cluster and fuse it with the training subset to build an improved random forest model. …”

K-means++ clustering algorithm. by Zhen Zhao (159931)

“…Subsequently, the feature factors corresponding to the model with the highest accuracy were selected as the optimal feature subsets and used in the model construction as input data. Additionally, considering the imbalanced in population spatial distribution, we used the K-means ++ clustering algorithm to cluster the optimal feature subset, and we used the bootstrap sampling method to extract the same amount of data from each cluster and fuse it with the training subset to build an improved random forest model. …”

Simulated solution and the original spectral data of the actual water sample. by Wang hongmei (22598690)

The accuracy of all employed learning algorithms. by Quan Shao (20148209)

A sample model illustrating the process. by Linxi Wang (3068649)

Subjects:

The process of creating the cluster-tree structure in the proposed method. by Shayesteh Tabatabaei (12280016)

Subjects:

Indexing of the serial synchrotron crystallography (SSX) diffraction images of the hen egg white lysozyme (HEWL) processed using the MOSFLM, DirAx, and XGANDALF algorithms at vario... by Ki Hyun Nam (5813819)

Subjects:

Ultrafast Hydrogen Detection System Using Vertical Thermal Conduction Structure and Neural Network Prediction Algorithm Based on Sensor Response Process by Ruilin Yang (151028)

“…Meanwhile, the model significantly enhanced the detection speed by enabling hydrogen concentration prediction using only the initial 40 data points (sampling frequency of 100 Hz) from the sensor response before the sensor completes the entire response process. …”

Ultrafast Hydrogen Detection System Using Vertical Thermal Conduction Structure and Neural Network Prediction Algorithm Based on Sensor Response Process by Ruilin Yang (151028)

“…Meanwhile, the model significantly enhanced the detection speed by enabling hydrogen concentration prediction using only the initial 40 data points (sampling frequency of 100 Hz) from the sensor response before the sensor completes the entire response process. …”