HCI.TOPHCI, made easy

arrow_backBack to questions View categoryarrow_forward

Sensing, Recognition, and Prediction Methods / Predictive Modeling, Behavior Inference, and Trend Estimation Methods

IoT devices cannot efficiently process heterogeneous data and large-scale model training, limiting federated learning applications.

lightbulbPractical problemPredictive Modeling, Behavior Inference, and Trend Estimation Methods

IoT devices cannot efficiently process heterogeneous data and large-scale model training, limiting federated learning applications.

UbiComp '23Inclusive Data Representation in Federated Learning: A Novel Approach Integrating Textual and Visual Prompt

Similar questions

lightbulbPractical problemPredictive Modeling, Behavior Inference, and Trend Estimation Methods

When users converse with digital characters, systems struggle to accurately understand context, resulting in stilted interaction.

CUI '24Multimodal Dialog Act Classification for Conversations With Digital Characters

lightbulbPractical problemPredictive Modeling, Behavior Inference, and Trend Estimation Methods

Existing liquid identification technologies are costly, inaccurate, and poorly suited to everyday use.

UbiComp '24LiquImager: Fine-grained Liquid Identification and Container Imaging System with COTS WiFi Devices

lightbulbPractical problemPredictive Modeling, Behavior Inference, and Trend Estimation Methods

Users struggle to obtain precise, personalized real-time stress monitoring in practice.

UbiComp '24Unraveling Temporal Dependencies in Stress: Insights from Self-Reported Stress Data

lightbulbPractical problemPredictive Modeling, Behavior Inference, and Trend Estimation Methods

When slow devices participate in federated learning, training latency is high and personalized accuracy is poor.

UbiComp '24EchoPFL: Asynchronous Personalized Federated Learning on Mobile Devices with On-Demand Staleness Control

lightbulbPractical problemPredictive Modeling, Behavior Inference, and Trend Estimation Methods

Users have high churn rates in weight-loss apps, preventing health goals from being achieved.

CHI '24Predicting early user churn in a public digital weight loss intervention

lightbulbPractical problemPredictive Modeling, Behavior Inference, and Trend Estimation Methods

Data centers face high power consumption and unstable power supply costs, making energy savings difficult.

UbiComp '23LSTM Based Short-Term Data Center Electrical Consumption Forecasting

Related papers

LiquImager: Fine-grained Liquid Identification and Container Imaging System with COTS WiFi Devices

Fei Shang, Panlong Yang, Dawei Yan

EchoPFL: Asynchronous Personalized Federated Learning on Mobile Devices with On-Demand Staleness Control

Xiaochen Li, Sicong Liu, Zimu Zhou

Predicting early user churn in a public digital weight loss intervention

Robert Jakob, Nils Lepper, Elgar Fleisch

Amortized Inference with User Simulations

Hee-Seung Moon, Antti Oulasvirta, Byungjoo Lee

Tisane: Authoring Statistical Models via Formal Reasoning from Conceptual and Data Relationships

Eunice Jun, Audrey Seo, Jeffrey Heer

Speeding up Inference with User Simulators through Policy Modulation

Hee-Seung Moon, Seungwon Do, Wonjae Kim

Modeling Touch Point Distribution with Rotational Dual Gaussian Model

Yan Ma, Shumin Zhai, IV Ramakrishnan