Cheng Pan

Cheng Pan

Auto-generated profile, based on publicly available information

Cheng Pan

The University of Hong Kong, Hong Kong, Hong Kong

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 May 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
CPCheng Pan
Cheng Pan
CZCong Zhang
Cong Zhang
ENEdith Ngai
Edith Ngai
JLJiangchuan Liu
Jiangchuan Liu
BLBo Li
Bo Li
The evolution of Internet of Things (IoT) is fostering the use of intelligent controls for energy conservation. Yet, the efficacy of these strategies is largely tied to diverse load forecasting algorithms. Given the significant contribution of heating, ventilation, and air-conditioning (HVAC) systems to global energy consumption, accurate forecasting of HVAC power usage is crucial for improving overall energy efficiency. However, real-world HVAC load forecasting, bolstered by various IoT devices, is complicated by multiple factors: data variability, power load fluctuations, electronic phenomena (e.g., zero drifts), and the increased time complexity and larger model sizes required to manage accumulating historical data. To address these challenges, we first present an in-depth measurement study on the characteristics of HVAC load at a minute scale based on the HVAC data collected in six locations. We propose HALO, a transformer-based framework specifically designed for forecasting HVAC load. HALO incorporates an adaptive data preprocessing stage and a local–global-scale transformer-based load forecasting stage, enabling precise forecasting of HVAC load and optimization of energy utilization. Evaluation based on real-world data traces from a prototype application demonstrates that the proposed framework significantly outperforms existing models.

16 May 2025 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
LZLei Zhang
Lei Zhang
PCPeng Chen
Peng Chen
CZCong Zhang
Cong Zhang
CPCheng Pan
Cheng Pan
TLTao Long
Tao Long
JLJiangchuan Liu
Jiangchuan Liu
Viewport prediction is the crucial task for adaptive 360-degree video streaming, as the bitrate control algorithms usually require the knowledge of the user's viewing portions of the frames. Various methods are studied and adopted for viewport prediction from less accurate statistic tools to highly calibrated deep neural networks. Conventionally, it is difficult to implement sophisticated deep learning methods on mobile devices, which have limited computation capability. In this work, we propose an advanced learning-based viewport prediction approach and carefully design it to minimize transmission and computation overhead for mobile terminals. To improve viewport prediction accuracy, we utilize both spatial information through a saliency prediction model and temporal information through a modified LSTM model. Different computations introduced by the neural network models are distributed across the network to keep the computation light on mobile devices. To better adapt to the content dynamics in live streaming, we employ the model-agnostic meta-learning (MAML) method for video saliency prediction. The learned saliency prediction model with optimized initialization via offline meta-training can be fast fine-tuned online using a few samples. We further discuss how to integrate this mobile-friendly viewport prediction (MFVP) approach into a typical 360-degree video live streaming system by formulating and solving the bitrate adaptation problem. Extensive experiment results demonstrate that our approach achieves real-time prediction for live video streaming and surpasses existing methods in prediction accuracy on mobile terminals, which, together with our bitrate adaptation algorithm, significantly improves the streaming QoE from various aspects. Compared to baseline methods, MFVP achieves a 4.7–28.7% improvement in accuracy and demonstrates faster adaptability to dynamic content changes, enabling rapid fine-tuning and adjustment. When integrated into a streaming system and paired with our adaptive bitrate allocation algorithm, MFVP enhances overall video quality by 5.6–12.9% and reduces quality fluctuations by 33.3–50.9%.

9 November 2022 in JMIR AI
Verified
Journal Article
Open access
CPCheng Pan
Cheng Pan
HLHao Luo
Hao Luo
GCGary Cheung
Gary Cheung
HZHuiquan Zhou
Huiquan Zhou
Reynold C.K. ChengReynold C.K. Cheng
Reynold C.K. Cheng
CWChuan Wu
Chuan Wu
Background: Machine learning techniques are starting to be used in various health care data sets to identify frail persons who may benefit from interventions. However, evidence about the performance of machine learning techniques compared to conventional regression is mixed. It is also unclear what methodological and database factors are associated with performance. Objective: This study aimed to compare the mortality prediction accuracy of various machine learning classifiers for identifying frail older adults in different scenarios. Methods: We used deidentified data collected from older adults (65 years of age and older) assessed with interRAI-Home Care instrument in New Zealand between January 1, 2012, and December 31, 2016. A total of 138 interRAI assessment items were used to predict 6-month and 12-month mortality, using 3 machine learning classifiers (random forest [RF], extreme gradient boosting [XGBoost], and multilayer perceptron [MLP]) and regularized logistic regression. We conducted a simulation study comparing the performance of machine learning models with logistic regression and interRAI Home Care Frailty Scale and examined the effects of sample sizes, the number of features, and train-test split ratios. Results: A total of 95,042 older adults (median age 82.66 years, IQR 77.92-88.76; n=37,462, 39.42% male) receiving home care were analyzed. The average area under the curve (AUC) and sensitivities of 6-month mortality prediction showed that machine learning classifiers did not outperform regularized logistic regressions. In terms of AUC, regularized logistic regression had better performance than XGBoost, MLP, and RF when the number of features was ≤80 and the sample size ≤16,000; MLP outperformed regularized logistic regression in terms of sensitivities when the number of features was ≥40 and the sample size ≥4000. Conversely, RF and XGBoost demonstrated higher specificities than regularized logistic regression in all scenarios. Conclusions: The study revealed that machine learning models exhibited significant variation in prediction performance when evaluated using different metrics. Regularized logistic regression was an effective model for identifying frail older adults receiving home care, as indicated by the AUC, particularly when the number of features and sample sizes were not excessively large. Conversely, MLP displayed superior sensitivity, while RF exhibited superior specificity when the number of features and sample sizes were large.

9 November 2022 in JMIR Preprints
Verified
Preprint
Open access
CPCheng Pan
Cheng Pan
HLHao Luo
Hao Luo
GCGary Cheung
Gary Cheung
HZHuiquan Zhou
Huiquan Zhou
Reynold C.K. ChengReynold C.K. Cheng
Reynold C.K. Cheng
CWChuan Wu
Chuan Wu
BACKGROUND Machine learning techniques are starting to be used in various health care data sets to identify frail persons who may benefit from interventions. However, evidence about the performance of machine learning techniques compared to conventional regression is mixed. It is also unclear what methodological and database factors are associated with performance. OBJECTIVE This study aimed to compare the mortality prediction accuracy of various machine learning classifiers for identifying frail older adults in different scenarios. METHODS We used deidentified data collected from older adults (65 years of age and older) assessed with interRAI-Home Care instrument in New Zealand between January 1, 2012, and December 31, 2016. A total of 138 interRAI assessment items were used to predict 6-month and 12-month mortality, using 3 machine learning classifiers (random forest [RF], extreme gradient boosting [XGBoost], and multilayer perceptron [MLP]) and regularized logistic regression. We conducted a simulation study comparing the performance of machine learning models with logistic regression and interRAI Home Care Frailty Scale and examined the effects of sample sizes, the number of features, and train-test split ratios. RESULTS A total of 95,042 older adults (median age 82.66 years, IQR 77.92-88.76; n=37,462, 39.42% male) receiving home care were analyzed. The average area under the curve (AUC) and sensitivities of 6-month mortality prediction showed that machine learning classifiers did not outperform regularized logistic regressions. In terms of AUC, regularized logistic regression had better performance than XGBoost, MLP, and RF when the number of features was ≤80 and the sample size ≤16,000; MLP outperformed regularized logistic regression in terms of sensitivities when the number of features was ≥40 and the sample size ≥4000. Conversely, RF and XGBoost demonstrated higher specificities than regularized logistic regression in all scenarios. CONCLUSIONS The study revealed that machine learning models exhibited significant variation in prediction performance when evaluated using different metrics. Regularized logistic regression was an effective model for identifying frail older adults receiving home care, as indicated by the AUC, particularly when the number of features and sample sizes were not excessively large. Conversely, MLP displayed superior sensitivity, while RF exhibited superior specificity when the number of features and sample sizes were large.

4 April 2026
Verified
Conference Paper
Open access
CPCheng Pan
Cheng Pan
YLYuying Li
Yuying Li
CZCong Zhang
Cong Zhang
ENEdith Ngai
Edith Ngai
JLJiangchuan Liu
Jiangchuan Liu
BLBaochun Li
Baochun Li
Multimodal large language models (MLLMs) are increasingly integrated into video conferencing, but mostly for speech-centric tasks such as transcription and summarization. Conferencing adaptation remains dominated by signal-driven congestion control that reacts to bandwidth changes without understanding why certain moments or streams will soon become quality-critical. This separation wastes predictive structure in conversation: text often reveals impending role shifts and interaction-mode transitions—for example, taking the floor or initiating screen sharing—seconds before the corresponding media and bandwidth demands materialize. We present Intent-aware Video conferencing Adaptation (IVA), a cross-modal control framework that converts text-derived intent cues into proactive bitrate orchestration. IVA extracts activity, control, and intent semantics from live streams, maps them to per-stream priority weights via a gated-bias model, and solves constrained bitrate allocation to maximize semantic QoE under uplink/downlink and latency limits. IVA learns this semantics-to-priority mapping with reinforcement learning over trace-driven simulations. Experiments with real-world network traces and emulated conferencing scenarios show that IVA improves QoE over signal-only ABR baselines and a semantic-aware conferencing baseline, while preserving low end-to-end latency and stabilizing quality around intent-triggered transitions.

14 November 2026
Verified
Conference Paper
Open access
HFHao Fang
Hao Fang
MZMiao Zhang
Miao Zhang
HZHaoyuan Zhao
Haoyuan Zhao
LCLong Chen
Long Chen
YCYi Ching Chou
Yi Ching Chou
JLJiangchuan Liu
Jiangchuan Liu