Co-simulation architecture. by Honglei Pang (22693724)

“…To address the issue of maintaining vehicle stability during emergency braking on roads with low and non-uniform adhesion, this paper proposes an intelligent integrated longitudinal and lateral stability control algorithm based on the Proximal Policy Optimization (PPO) algorithm. …”

Overall framework diagram of the study. by Honglei Pang (22693724)

“…To address the issue of maintaining vehicle stability during emergency braking on roads with low and non-uniform adhesion, this paper proposes an intelligent integrated longitudinal and lateral stability control algorithm based on the Proximal Policy Optimization (PPO) algorithm. …”

Braking system model. by Honglei Pang (22693724)

“…To address the issue of maintaining vehicle stability during emergency braking on roads with low and non-uniform adhesion, this paper proposes an intelligent integrated longitudinal and lateral stability control algorithm based on the Proximal Policy Optimization (PPO) algorithm. …”

Vehicle parameters. by Honglei Pang (22693724)

“…To address the issue of maintaining vehicle stability during emergency braking on roads with low and non-uniform adhesion, this paper proposes an intelligent integrated longitudinal and lateral stability control algorithm based on the Proximal Policy Optimization (PPO) algorithm. …”

Data for revision version by Santanu Saha (18277927)

“…This study enhances the well-established min-max method based interactive fuzzy bi-objective optimization algorithm by incorporating the absolute difference function along with the trade-off ratio based autonomized optimization approach. …”

Schematic illustration of the multi-type biological network used in APDCA. by Yangsong He (13909371)

PSO-Optimized Electronic Load Controller with Intelligent Energy Recovery for Self-Excited Induction Generator Based Micro-Hydro Systems by MRINAL KANTI RAJAK (21838169)

“…The dataset includes: (1) <b>PSO configuration parameters</b> - complete algorithm setup with population size (N=20), adaptive inertia weights (0.9→0.4), time-varying cognitive/social coefficients (c1: 2.5→0.5, c2: 0.5→2.5), search space boundaries for all 10 optimization variables, and convergence criteria specifications; (2) <b>Multi-objective fitness function data</b> - detailed weight adaptation formulas, individual objective convergence statistics (voltage: 15.3 iter, frequency: 19.2 iter, THD: 12.8 iter, energy: 23.0 iter), and composite fitness evolution from 0.537 to 0.903 over 50 iterations; (3) <b>Particle dynamics tracking</b> - complete position and velocity trajectories for all 20 particles across optimization dimensions [Kpv, Kiv, Kdv, Kpf, Kif, Kdf, ma, θphase, fc, Ppump,ref], diversity evolution (100%→8%), and exploration/exploitation transition patterns; (4) <b>Real-time implementation metrics</b> - computational requirements (2.6 kB memory, 67% CPU utilization), execution timing (0.83 ms average, 1.2 ms worst-case), and synchronization protocols for 100 Hz optimization loops; and (5) <b>Validation datasets</b> - performance verification across six different load conditions, convergence statistics, and algorithm robustness testing results demonstrating consistent ±1.8% voltage regulation and ±0.9% frequency stability achievements, all provided in structured CSV/JSON formats with comprehensive documentation under CC-BY license.…”

Software: Learning zero-cost portfolio selection with pattern matching by Tim Gebbie (8064947)

“…The <i>match-learn</i> algorithm loops over two hyper-parameters indexed by k and ell. …”

Data Sheet 1_Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea).docx by Degninou Yehadji (3451511)

<b>D-Star-based Optimized Trajectory Planner for </b><b>Mobile Robots Operating in Dense </b><b>Environments</b> by Andrey Vukolov (19730578)

“…Test results of the algorithm are given for the dense industrial environment containing closed loops.…”

Hyperparameter and model configurations. by Hongtao Wang (570131)

“…The five interconnected modules constituting the architecture include (i) multi-source data collection using RESTful APIs; (ii) weighted preprocessing pipelines using tokenization, lemmatization, and normalization; (iii) Adam algorithm-optimized model training and cross-entropy loss minimization-based training; (iv) adaptive real-time processing using dynamic window segmentation; and (v) an ongoing refinement loop using continuous user inputs, triggered by a feedback mechanism. …”

Performance in best and worst case scenarios. by Hongtao Wang (570131)

“…The five interconnected modules constituting the architecture include (i) multi-source data collection using RESTful APIs; (ii) weighted preprocessing pipelines using tokenization, lemmatization, and normalization; (iii) Adam algorithm-optimized model training and cross-entropy loss minimization-based training; (iv) adaptive real-time processing using dynamic window segmentation; and (v) an ongoing refinement loop using continuous user inputs, triggered by a feedback mechanism. …”

Datasets and experimental settings. by Hongtao Wang (570131)

“…The five interconnected modules constituting the architecture include (i) multi-source data collection using RESTful APIs; (ii) weighted preprocessing pipelines using tokenization, lemmatization, and normalization; (iii) Adam algorithm-optimized model training and cross-entropy loss minimization-based training; (iv) adaptive real-time processing using dynamic window segmentation; and (v) an ongoing refinement loop using continuous user inputs, triggered by a feedback mechanism. …”

Response time by scenario (ms). by Hongtao Wang (570131)

“…The five interconnected modules constituting the architecture include (i) multi-source data collection using RESTful APIs; (ii) weighted preprocessing pipelines using tokenization, lemmatization, and normalization; (iii) Adam algorithm-optimized model training and cross-entropy loss minimization-based training; (iv) adaptive real-time processing using dynamic window segmentation; and (v) an ongoing refinement loop using continuous user inputs, triggered by a feedback mechanism. …”

Ablation study: Component contribution analysis. by Hongtao Wang (570131)

“…The five interconnected modules constituting the architecture include (i) multi-source data collection using RESTful APIs; (ii) weighted preprocessing pipelines using tokenization, lemmatization, and normalization; (iii) Adam algorithm-optimized model training and cross-entropy loss minimization-based training; (iv) adaptive real-time processing using dynamic window segmentation; and (v) an ongoing refinement loop using continuous user inputs, triggered by a feedback mechanism. …”

Reinforcement Learning-Based Hybrid Force/Position Control of Redundant Manipulators under Time Delays by Mojtaba Radan Kashani (20150034)

“…This paper introduces a semi-model-free framework, the Force/Position Reinforcement Learning Super-Twisting Algorithm (F/P-RL-STA), which avoids explicit space separation and reduces dependency on accurate models. …”

Numerical example of linearization formulation. by Panfei Li (22379086)

“…This paper introduces the Circular Assembly Line Balancing Problem with Task-Splitting (CALBP-TS), a novel NP-hard optimization challenge characterized by closed-loop topology, station revisitation, fixed-position machines, and collaborative task execution. …”

Summary of the literature review on ALBP/UALBP. by Panfei Li (22379086)

“…This paper introduces the Circular Assembly Line Balancing Problem with Task-Splitting (CALBP-TS), a novel NP-hard optimization challenge characterized by closed-loop topology, station revisitation, fixed-position machines, and collaborative task execution. …”

Image 2_AI-driven innovation in antibody-drug conjugate design.jpeg by Heather A. Noriega (21604514)

“…This review is organized into six sections: (1) the progression from traditional modeling approaches to AI-driven design of individual ADC components; (2) the application of deep learning (DL) to antibody structure prediction and identification of optimal conjugation sites; (3) the use of AI/ML models for forecasting pharmacokinetic properties and toxicity profiles; (4) emerging generative algorithms for antibody sequence diversification and affinity optimization; (5) case studies demonstrating the integration of computational tools with experimental pipelines, including systems that link in silico predictions to high-throughput validation; and (6) persistent challenges, including data sparsity, model interpretability, validation complexity, and regulatory considerations. …”

Image 1_AI-driven innovation in antibody-drug conjugate design.jpeg by Heather A. Noriega (21604514)

“…This review is organized into six sections: (1) the progression from traditional modeling approaches to AI-driven design of individual ADC components; (2) the application of deep learning (DL) to antibody structure prediction and identification of optimal conjugation sites; (3) the use of AI/ML models for forecasting pharmacokinetic properties and toxicity profiles; (4) emerging generative algorithms for antibody sequence diversification and affinity optimization; (5) case studies demonstrating the integration of computational tools with experimental pipelines, including systems that link in silico predictions to high-throughput validation; and (6) persistent challenges, including data sparsity, model interpretability, validation complexity, and regulatory considerations. …”