Empirical Risk Minimization

Langford, John; Zhang, Xinhua; Brown, Gavin; Bhattacharya, Indrajit; Getoor, Lise; Zeugmann, Thomas; Todorovski, Ljupčo; Ting, Kai Ming; Corne, David; Handl, Julia; Knowles, Joshua; García-Almanza, AlmaLilia; Centeno, Tonatiuh Peña; García-Almanza, Alma Lilia; Alexandrova-Kabadjova, Biliana; Martínez-Jaramillo, Serafín; Krawiec, Krzysztof; Kavka, Carlos; Sipper, Moshe; Igel, Christian; Husbands, Phil; Jin, Xin; Heskes, Tom; DeJong, Gerald; Lim, Shiau Hong; Kambhampati, Subbarao; Yoon, Sungwook

doi:10.1007/978-0-387-30164-8_251

Cited by 200 publications

(103 citation statements)

References 0 publications

Supporting

Mentioning

103

Contrasting

Order By: Relevance

“…In this part, we aim at studying different factors influencing the model performance: Data amount, different augmentation strategies (e.g., random shift, mixup (Zhang et al, 2018)), age correction technique (see Section 3.2) and regressor (e.g., Multi‐Layer Perceptron (MLP), SVR). Table 3 shows the comparison results.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Brain structure ages—A new biomarker for multi‐disease classification

Nguyen,

Clément,

Mansencal

et al. 2024

Human Brain Mapping

View full text Add to dashboard Cite

Age is an important variable to describe the expected brain's anatomy status across the normal aging trajectory. The deviation from that normative aging trajectory may provide some insights into neurological diseases. In neuroimaging, predicted brain age is widely used to analyze different diseases. However, using only the brain age gap information (i.e., the difference between the chronological age and the estimated age) can be not enough informative for disease classification problems. In this paper, we propose to extend the notion of global brain age by estimating brain structure ages using structural magnetic resonance imaging. To this end, an ensemble of deep learning models is first used to estimate a 3D aging map (i.e., voxel‐wise age estimation). Then, a 3D segmentation mask is used to obtain the final brain structure ages. This biomarker can be used in several situations. First, it enables to accurately estimate the brain age for the purpose of anomaly detection at the population level. In this situation, our approach outperforms several state‐of‐the‐art methods. Second, brain structure ages can be used to compute the deviation from the normal aging process of each brain structure. This feature can be used in a multi‐disease classification task for an accurate differential diagnosis at the subject level. Finally, the brain structure age deviations of individuals can be visualized, providing some insights about brain abnormality and helping clinicians in real medical contexts.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Finally, we employed different data augmentation techniques to alleviate the overfitting problem. Concretely, we randomly shifted a patch by

t\in \left\{-\mathrm{1,0,1}\right\}

voxel in each dimension (denoted as random shift technique) and then applyed mixup data augmentation (Zhang et al, 2018).…”

Section: Methodsmentioning

confidence: 99%

Brain structure ages—A new biomarker for multi‐disease classification

Nguyen,

Clément,

Mansencal

et al. 2024

Human Brain Mapping

View full text Add to dashboard Cite

show abstract

“…Overfitting is a major challenge in DL models that can degrade generalization performance. To minimize overfitting, various techniques can be employed, including data augmentation, 38 which transforms existing data in various ways, adversarial training, 39 which employs adversarial examples during the training process, and dropouts, 40 which prevent the model from over‐relying on certain neurons.…”

Section: Resultsmentioning

confidence: 99%

Geriatric depression and anxiety screening via deep learning using activity tracking and sleep data

Lee,

Kim,

Choi

2024

Int J Geriat Psychiatry

View full text Add to dashboard Cite

BackgroundGeriatric depression and anxiety have been identified as mood disorders commonly associated with the onset of dementia. Currently, the diagnosis of geriatric depression and anxiety relies on self‐reported assessments for primary screening purposes, which is uncomfortable for older adults and can be prone to misreporting. When a more precise diagnosis is needed, additional methods such as in‐depth interviews or functional magnetic resonance imaging are used. However, these methods can not only be time‐consuming and costly but also require systematic and cost‐effective approaches.ObjectiveThe main objective of this study was to investigate the feasibility of training an end‐to‐end deep learning (DL) model by directly inputting time‐series activity tracking and sleep data obtained from consumer‐grade wrist‐worn activity trackers to identify comorbid depression and anxiety.MethodsTo enhance accuracy, the input of the DL model consisted of step counts and sleep stages as time series data, along with minimal depression and anxiety assessment scores as non‐time‐series data. The basic structure of the DL model was designed to process mixed‐input data and perform multi‐label‐based classification for depression and anxiety. Various DL models, including the convolutional neural network (CNN) and long short‐term memory (LSTM), were applied to process the time‐series data, and model selection was conducted by comparing the performances of the hyperparameters.ResultsThis study achieved significant results in the multi‐label classification of depression and anxiety, with a Hamming loss score of 0.0946 in the Residual Network (ResNet), by applying a mixed‐input DL model based on activity tracking data. The comparison of hyper‐parameter performance and the development of various DL models, such as CNN, LSTM, and ResNet contributed to the optimization of time series data processing and achievement of meaningful results.ConclusionsThis study can be considered as the first to develop a mixed‐input DL model based on activity tracking data for the multi‐label identification of late‐life depression and anxiety. The findings of the study demonstrate the feasibility and potential of using consumer‐grade wrist‐worn activity trackers in conjunction with DL models to improve the identification of comorbid mental health conditions in older adults. The study also established a multi‐label classification framework for identifying the complex symptoms of depression and anxiety.

show abstract

“…MixUp [22] is a widely‐used augmentation technique that linearly combines two images at a randomly selected ratio. We applied MixUp to road / non‐road data to generate new

X_{R}

X_{C}

, and

X_{L}

according to randomly selected ratios of road data,

r_{R}

r_{C}

, and

r_{L}

, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…Several augmentation methods of fusing multiple data into a single training datum have been proposed [20–22]. Specifically, these techniques create a new single image via the combination of multiple images.…”

Section: Related Workmentioning

confidence: 99%

Assembling three one‐camera images for three‐camera intersection classification

Astrid,

Lee

2023

ETRI Journal

View full text Add to dashboard Cite

Determining whether an autonomous self‐driving agent is in the middle of an intersection can be extremely difficult when relying on visual input taken from a single camera. In such a problem setting, a wider range of views is essential, which drives us to use three cameras positioned in the front, left, and right of an agent for better intersection recognition. However, collecting adequate training data with three cameras poses several practical difficulties; hence, we propose using data collected from one camera to train a three‐camera model, which would enable us to more easily compile a variety of training data to endow our model with improved generalizability. In this work, we provide three separate fusion methods (feature, early, and late) of combining the information from three cameras. Extensive pedestrian‐view intersection classification experiments show that our feature fusion model provides an area under the curve and F1‐score of 82.00 and 46.48, respectively, which considerably outperforms contemporary three‐ and one‐camera models.

show abstract

Empirical Risk Minimization

Cited by 200 publications

References 0 publications

Brain structure ages—A new biomarker for multi‐disease classification

Brain structure ages—A new biomarker for multi‐disease classification

Geriatric depression and anxiety screening via deep learning using activity tracking and sleep data

Assembling three one‐camera images for three‐camera intersection classification

Contact Info

Product

Resources

About