Journal: Dialogues in Clinical Neuroscience

Article Title: Deep learning with ensemble-based hybrid AI model for bipolar and unipolar depression detection using demographic and behavioral based on time-series data

doi: 10.1080/19585969.2025.2524337

Figure Lengend Snippet: Proposed architecture of 1D CNN.

Article Snippet: We compared the following model configurations: Model A: XGBoost (structured data only) Model B: 1D CNN (actigraph data only) Model C: Hybrid Model (fusion of XGBoost and 1D CNN) Each model was evaluated across 5-fold stratified cross-validation, and the F1-score was used as the primary performance metric.

Techniques:

Journal: Applied sciences (Basel, Switzerland)

Article Title: Individualized Stress Mobile Sensing Using Self-Supervised Pre-Training

doi: 10.3390/app132112035

Figure Lengend Snippet: The 1D CNN architecture for the pretext task.

Article Snippet: They demonstrated that the 1D CNN model architecture can be successfully applied towards making predictions from biosignal data without manual feature engineering and feature selection [ ].

Techniques:

Journal: Applied sciences (Basel, Switzerland)

Article Title: Individualized Stress Mobile Sensing Using Self-Supervised Pre-Training

doi: 10.3390/app132112035

Figure Lengend Snippet: The 1D CNN architecture for fine-tuning the pre-trained network towards the downstream stress-prediction task.

Article Snippet: They demonstrated that the 1D CNN model architecture can be successfully applied towards making predictions from biosignal data without manual feature engineering and feature selection [ ].

Techniques:

Journal: International Journal of Environmental Research and Public Health

Article Title: Epileptic Seizures Detection Using Deep Learning Techniques: A Review

doi: 10.3390/ijerph18115780

Figure Lengend Snippet: Summary of related works done using 2D-CNNs.

Article Snippet: [ ] , 2D-CNN with 1D-CNN , 12 , Softmax , NA.

Techniques:

Journal: Journal of activity, sedentary and sleep behaviors

Article Title: Method for Activity Sleep Harmonization (MASH): a novel method for harmonizing data from two wearable devices to estimate 24-h sleep–wake cycles

doi: 10.1186/s44167-023-00017-5

Figure Lengend Snippet: Number of days in the sample, MASH model used, and sleep–wake interval size

Article Snippet: The AUC-ROC for both 1D CNN models developed for MASH (ActiGraph + Actiwatch or ActiGraph-only) were considered excellent ( ) with values of 0.991 and 0.983 for the ActiGraph + Actiwatch and ActiGraph-only models, respectively.

Techniques: