Distant label quality evaluation (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. …”

The entire framework. 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. …”

Example of distant labels. 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. …”

Comparsion of NER 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. …”

Spatial firing patterns of prefrontal neurons are altered by dHPC or vHPC silencing in specific SWM phases. by Susanne S. Babl (21169261)

“…Yellow shaded area indicates the trials and task phase in which light was delivered. Gray indicates activity in light-off trials; darker colors indicate activity in light-on trials during the task phase in which light was delivered (light-on phase); light colors indicate activity in the phase where light was not delivered during light-on trials (light-off phase). …”

A comparative study of decision tree-based learners to classify the switching transient disturbances in real microgrid network by Sannistha Banerjee (20584510)

“…The significant features are selected according to the performance of the processed DWT. …”

Supplementary Materials for ‘PGAE-ICA: A simplified digital system for intellectual measurement-assessment in children and adolescents using cognitive testing and machine learning... by Runzhou Wang (5894849)

“…The results indicated that after excluding the time selection task, the remaining eleven cognitive tests effectively reflected the differences between individuals with normal and abnormal intelligence, with significant positive correlations to intelligence. …”

Models and Dataset by M RN (9866504)

“…Operating in a binary search space, TJO simulates intelligent and evasive movements of the prey to guide the population toward optimal solutions. The algorithm does not rely on predefined control parameters like crossover or mutation rates, which makes it lightweight and easy to implement for various feature selection and optimization tasks.…”

Table 1_Integrated transcriptomic and network analysis reveals candidate immune–metabolic biomarkers in children with the inattentive type of ADHD.xlsx by Qiaoyan Shao (22357861)

“…High-confidence biomarkers were selected via a multi-step pipeline combining protein-protein interaction (PPI) network analysis and machine learning feature selection (LASSO regression, Boruta algorithm). …”

Image 1_Integrated transcriptomic and network analysis reveals candidate immune–metabolic biomarkers in children with the inattentive type of ADHD.tif by Qiaoyan Shao (22357861)

“…High-confidence biomarkers were selected via a multi-step pipeline combining protein-protein interaction (PPI) network analysis and machine learning feature selection (LASSO regression, Boruta algorithm). …”

Table 2_Integrated transcriptomic and network analysis reveals candidate immune–metabolic biomarkers in children with the inattentive type of ADHD.xlsx by Qiaoyan Shao (22357861)

“…High-confidence biomarkers were selected via a multi-step pipeline combining protein-protein interaction (PPI) network analysis and machine learning feature selection (LASSO regression, Boruta algorithm). …”

Supplementary Material for: Utilizing Deep Learning to Identify Electron-Dense Deposits in Renal Biopsy Electron Microscopy Images by figshare admin karger (2628495)

“…The ResNet18 architecture was selected for our task. To evaluate the model's classification capability, we created a binary classification model to identify the presence of deposits in EM images. …”

Aluminum alloy industrial materials defect by Ying Han (20349093)

“…</p><h2>Description of the data and file structure</h2><p dir="ltr">This is a project based on the YOLOv8 enhanced algorithm for aluminum defect classification and detection tasks.…”

A decision support framework on simulation fidelity for transferable and autonomously optimised swarm behaviour by Reda Ghanem (22764156)

“…These insights are synthesised into a flowchart-based decision tool that guides simulator selection based on task complexity, platform dynamics, and performance objectives. …”

Pressure control techniques in freeze-drying by Geoff Smith (6064268)

“…The most common Pressure control techniques would be listed as follows:</p><ul><li>PID method</li><li>Fuzzy logic</li><li>Max pressure algorithms</li><li>Reinforcement learning</li><li>Adaptive control</li><li>Setpoint profile tracking (Bang-bang control)</li></ul><p dir="ltr">Pressure control systems have to perform a particular task in the target process considering some key functionalities like: system dynamism, control performance, stability, adaptability, accuracy, etc. …”

Video 1_TDE-3: an improved prior for optical flow computation in spiking neural networks.mp4 by Matthew Yedutenko (5142461)

“…Proposed in the literature bioinspired neuromorphic Time-Difference Encoder (TDE-2) combines event-based sensors and processors with spiking neural networks to provide real-time and energy-efficient motion detection through extracting temporal correlations between two points in space. However, on the algorithmic level, this design leads to a loss of direction-selectivity of individual TDEs in textured environments. …”

Data Sheet 1_TDE-3: an improved prior for optical flow computation in spiking neural networks.pdf by Matthew Yedutenko (5142461)

“…Proposed in the literature bioinspired neuromorphic Time-Difference Encoder (TDE-2) combines event-based sensors and processors with spiking neural networks to provide real-time and energy-efficient motion detection through extracting temporal correlations between two points in space. However, on the algorithmic level, this design leads to a loss of direction-selectivity of individual TDEs in textured environments. …”

Data from an Investigation of Music Analysis by the Application of Grammar-based Compressor by David Humphreys (19079318)

“…Performance on various tasks was evaluated from the model attributes (primarily model size, measured in symbols). …”

Table 1_A novel muscle network approach for objective assessment and profiling of bulbar involvement in ALS.docx by Panying Rong (2697181)

“…</p>Methods<p>A noninvasive electrophysiological technique—surface electromyography—was combined with graph network analysis to extract 48 features measuring the regulatory mechanisms, connectivity, integration, segregation, assortativity, and lateralization of the functional muscle network during a speech task. These features were clustered into 10 interpretable latent factors. …”

<b>Supporting data for "CT Radiomics and Deep Learning Auto-segmentation in Epithelial Ovarian Carcinoma Treatment Response and Prognosis Evaluation"</b> by Mengge He (11085414)

“…Eleven radiomics features were selected and Extra Trees(ET) classifier was built across 10-fold stratified cross validation (SCV). …”