Jinkun Chen

Jinkun Chen

Auto-generated profile, based on publicly available information

Jinkun Chen

Faculty of Computer Science Dalhousie University Halifax Canada

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications

4 November 2024 in SoftwareX
Verified
Journal Article
Open access
Gabriel SpadonGabriel Spadon
Gabriel Spadon
JKJAY KUMAR
JAY KUMAR
JCJinkun Chen
Jinkun Chen
MSMatthew Smith
Matthew Smith
CHCasey Hilliard
Casey Hilliard
RPRonald Pelot
Ronald Pelot

31 July 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
RWRongkun Wang
Rongkun Wang
LSLiming Song
Liming Song
JCJiaqi Cheng
Jiaqi Cheng
YHYihui Huang
Yihui Huang
JKJinkun Ke
Jinkun Ke
To address the challenges associated with pinpointing single and double switch open-circuit (OC) faults in conventional fault diagnosis strategies for T-type three-level inverters, a method for fault diagnosing based on energy feature extraction of intrinsic mode function (IMF) of voltage is proposed in this paper. Firstly, to mitigate modal aliasing and noise interference, the output voltage signal of the inverter is decomposed using the complete ensemble empirical mode decomposition (CEEMD) to extract IMF components. Subsequently, the short-term energy value of the selected IMF components is calculated by segmenting the decomposition results. By establishing a criterion for extracting fault features, the local variations in IMF short-term energy values at different fault locations are distinguished. Based on this criterion, a fault feature vector is constructed, enabling a diagnostic method for OC faults relying on the IMF components’ short-term energy values. Experimental results show that the fault diagnosis method proposed in this article can reliably achieve the diagnosis of single and double switch open-circuit faults in the T-type inverter. The proposed method does not require complex modeling, and has strong robustness and high accuracy compared to other types of diagnostic methods.


11 July 2024 in arXiv
Verified
Preprint
Open access
PDF file
Gabriel SpadonGabriel Spadon
Gabriel Spadon
JKJay Kumar
Jay Kumar
JCJinkun Chen
Jinkun Chen
MSMatthew Smith
Matthew Smith
CHCasey Hilliard
Casey Hilliard
RPRonald Pelot
Ronald Pelot
Efficiently handling Automatic Identification System (AIS) data is vital for enhancing maritime safety and navigation, yet is hindered by the system's high volume and error-prone datasets. This paper introduces the Automatic Identification System Database (AISdb), a novel tool designed to address the challenges of processing and analyzing AIS data. AISdb is a comprehensive, open-source platform that enables the integration of AIS data with environmental datasets, thus enriching analyses of vessel movements and their environmental impacts. By facilitating AIS data collection, cleaning, and spatio-temporal querying, AISdb significantly advances AIS data research. Utilizing AIS data from various sources, AISdb demonstrates improved handling and analysis of vessel information, contributing to enhancing maritime safety, security, and environmental sustainability efforts.

2 February 2026 in arXiv
Verified
Preprint
Open access
PDF file
JCJinkun Chen
Jinkun Chen
FCFengxiang Cheng
Fengxiang Cheng
SHSijia Han
Sijia Han
VKVlado Keselj
Vlado Keselj
Reasoning failures in large language models (LLMs) are typically measured only at the end of a generation, yet many failures manifest as a process-level breakdown: the model "loses the thread" mid-reasoning. We study whether such breakdowns are detectable from inference-time observables available in standard APIs (token log probabilities), without any training or fine-tuning. We define a simple instability signal that combines consecutive-step distributional shift (JSD) and uncertainty (entropy), summarize each trace by its peak instability strength, and show that this signal reliably predicts failure. Across GSM8K and HotpotQA, instability strength predicts wrong answers with above-chance AUC and yields monotonic bucket-level accuracy decline at scale across model sizes. Crucially, we show that instability is not uniformly harmful: early instability can reflect subsequent stabilization and a correct final answer (\emph{corrective instability}), whereas late instability is more often followed by failure (\emph{destructive instability}), even at comparable peak magnitudes, indicating that recoverability depends not only on how strongly the distribution changes but also on when such changes occur relative to the remaining decoding horizon. The method is model-agnostic, training-free, and reproducible, and is presented as a diagnostic lens rather than a corrective or control mechanism.