Schematic diagram of 3D velocity collision cone. by Pengxiang Sun (8189247)

“…This paper proposes a dynamic path planning method based on the reciprocal velocity obstacles algorithm, enabling micro-UAVs to safely and efficiently accomplish flight tasks in complex environments. …”

Initial environment for multi-dynamic obstacles. by Pengxiang Sun (8189247)

“…This paper proposes a dynamic path planning method based on the reciprocal velocity obstacles algorithm, enabling micro-UAVs to safely and efficiently accomplish flight tasks in complex environments. …”

Confusion matrix of CIC-IDS2017 dataset. by Mahbub E. Sobhani (22278967)

“…<div><p>Imbalanced intrusion classification is a complex and challenging task as there are few number of instances/intrusions generally considered as minority instances/intrusions in the imbalanced intrusion datasets. …”

Confusion matrix of NSL-KDD dataset. by Mahbub E. Sobhani (22278967)

“…<div><p>Imbalanced intrusion classification is a complex and challenging task as there are few number of instances/intrusions generally considered as minority instances/intrusions in the imbalanced intrusion datasets. …”

Confusion matrix of CSE-CIC-IDS2018 dataset. by Mahbub E. Sobhani (22278967)

“…<div><p>Imbalanced intrusion classification is a complex and challenging task as there are few number of instances/intrusions generally considered as minority instances/intrusions in the imbalanced intrusion datasets. …”

Confusion matrix of UNSW-NB15 dataset. by Mahbub E. Sobhani (22278967)

“…<div><p>Imbalanced intrusion classification is a complex and challenging task as there are few number of instances/intrusions generally considered as minority instances/intrusions in the imbalanced intrusion datasets. …”

Confusion matrix of CIC-DDoS2019 dataset. by Mahbub E. Sobhani (22278967)

“…<div><p>Imbalanced intrusion classification is a complex and challenging task as there are few number of instances/intrusions generally considered as minority instances/intrusions in the imbalanced intrusion datasets. …”

Proposed model training parameters. by M. Amudha (20390830)

“…Firstly, an Elephant Herding Optimization (EHO) algorithm selects pertinent features for classification tasks. …”

Input image and extracted features maps. by M. Amudha (20390830)

“…Firstly, an Elephant Herding Optimization (EHO) algorithm selects pertinent features for classification tasks. …”

Layer wise structure complexity reduction. by M. Amudha (20390830)

“…Firstly, an Elephant Herding Optimization (EHO) algorithm selects pertinent features for classification tasks. …”

Accuracy change vs. ELM layers pruning rate. by M. Amudha (20390830)

“…Firstly, an Elephant Herding Optimization (EHO) algorithm selects pertinent features for classification tasks. …”

Characteristic and limitations of existing work. by M. Amudha (20390830)

“…Firstly, an Elephant Herding Optimization (EHO) algorithm selects pertinent features for classification tasks. …”

Working procedure of ELM classifier network. by M. Amudha (20390830)

“…Firstly, an Elephant Herding Optimization (EHO) algorithm selects pertinent features for classification tasks. …”

Proposed CNN (EHO+HOBS-ELM) architecture. by M. Amudha (20390830)

“…Firstly, an Elephant Herding Optimization (EHO) algorithm selects pertinent features for classification tasks. …”

Methodological flowchart outlining the study’s workflow. by Ezekiel Ahn (6697256)

An overview of DDGWizard. by Mingkai Wang (9650918)

“…B: Collect data from the VariBench [<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013783#pcbi.1013783.ref043" target="_blank">43</a>] database, conduct feature enrichment to the collected data using the feature calculation pipeline to obtain the DDGWizard dataset, and then split it into training and test sets for subsequent ML tasks. C: Perform feature selection based on the RFE (recursive feature elimination) algorithm, followed by a further analysis of feature importance. …”

gcPCA v4 correctly identifies hippocampal replay in neurophysiological data without prior knowledge of replay content. by Eliezyer Fermino de Oliveira (20691761)

“…The automatic <i>α</i> selection algorithm from cPCA returns various <i>α</i> values depending on the number of cPCs requested (parameter <i>k</i>). …”

BOPIM: Bayesian Optimization for Influence Maximization on Temporal Networks by Eric Yanchenko (3266514)

“…In this work, we propose <math><mrow>BOPIM</mrow></math>, a Bayesian Optimization (BO) algorithm for IM on temporal networks. The IM task is well-suited for a BO solution due to its expensive and complicated objective function. …”

Example of CPE URI version 2.3. by Ke Zhang (115386)

“…Lastly, we propose a high-confidence text selection method and an improved self-training algorithm that incorporates a teacher-student model and weight update constraints, for exploring the true labels of low-confidence text using a model trained on high-confidence text, thereby reducing the noise in the distant annotation data. …”

Ablation experiment results (in %). by Ke Zhang (115386)

“…Lastly, we propose a high-confidence text selection method and an improved self-training algorithm that incorporates a teacher-student model and weight update constraints, for exploring the true labels of low-confidence text using a model trained on high-confidence text, thereby reducing the noise in the distant annotation data. …”