Comparison of deconvolution and optimization algorithms on a batch of data. by Ali-Kemal Aydin (10968731)

“…Both experimental data have been resampled at 50ms and used to compute a set of TFs (in orange) either with direct deconvolution approaches (Fourier or Toeplitz methods, middle-upper panel TFs) or with 1-Γ function optimization performed by 3 different algorithms (middle-lower panel TFs). …”

Path comparison before and after smoothing. by Zhenggang Wang (1753657)

Subjects: “…target gravitational function…”

Comparison before and after path pruning. by Zhenggang Wang (1753657)

Subjects: “…target gravitational function…”

Baseline characteristics of recipients’ comparison before and after data match by the unsupervised machine learning algorithm. by Mahmoudreza Moein (22127153)

Feature selection algorithm. by Mahmoud Zeydabadinezhad (12289570)

Subjects:

The variation process of various loss functions before and after model improvement. by Zhenwei Li (834360)

The structure of genetic algorithm (GA). by Ali Akbar Moosavi (17769033)

“…First, physico-chemical inputs as bulk density (BD), initial water content (W_i), saturated water content (W_s), mean weight diameter (MWD), and geometric mean diameter (GMD) of aggregates, pH, electrical conductivity (EC), and calcium carbonate equivalent (CCE) were measured. Then, radial basis functions (RBFNNs), multilayer perceptron (MLPNNs), hybrid genetic algorithm (GA-NNs), and particle swarm optimization (PSO-NNs) neural networks were utilized to develop PTFs and compared their accuracy with the traditional regression model (MLR) using statistical indices. …”

Flowchart of system algorithm. by Syed Zahurul Islam (9635163)

Algorithm of the brightness scale calibration experiment. by Krzysztof Petelczyc (3954203)

“…<p>In the algorithm, the following variables were used: “I” denotes the current luminous intensity of the reference diode, “inc” denotes the current difference between reference and target diode luminous intensity; “cnt” is the current number of performed trials, while “correct” is a counter of correct answers in cnt trials, both of them are counted separately for every settings of I and inc. …”

Parameters of the genetic algorithm. by Jian Ma (170138)

Explained variance ration of the PCA algorithm. by Abeer Aljohani (18497914)

Subjects:

Accelerated MPC Algorithms and Augmented System Design for Legged Robots by John Ndegwa Nganga (21088838)

“…The approach is powered by a newly introduced algorithm, named the modified Recursive Newton Euler Algorithm~(mRNEA), which is inspired by classical RNEA, and computes the dynamics information pre-multiplied with a fixed vector. …”

Pseudo-code of MWOA algorithm. by Yi-Qiang Xia (20161326)

“…Moreover, the Wilcoxon rank sum test is used to verify the effectiveness of the proposed algorithm. …”

One iteration of the NSGA-II algorithm. by Erick Axel Padilla-García (16839233)

Optimization results of different algorithms. by Haijian Wang (746739)

“…Subsequently, the constraint conditions and objective functions were determined. Moreover, the multi-objective genetic algorithm optimized the structural block brake design. …”

Associative memory paradigm used to train the feature decoders. by Sam Hall-McMaster (10343795)

Subjects:

PSO algorithms flowchart. by Mohammed F. Elnaggar (18297954)

Features selected by optimization algorithms. by Afnan M. Alhassan (18349378)

“…After the image has been pre-processed, it is segmented using the Thresholding Level set approach. …”

Description of unimodal benchmark functions. by Yi-Qiang Xia (20161326)

“…Moreover, the Wilcoxon rank sum test is used to verify the effectiveness of the proposed algorithm. …”

Description of multimodal benchmark functions. by Yi-Qiang Xia (20161326)

“…Moreover, the Wilcoxon rank sum test is used to verify the effectiveness of the proposed algorithm. …”