arXiv subjects

Nicholas Tan Jerome

Publications and source records attributed to Nicholas Tan Jerome.

7 recordsLinked to original sources

arXiv2026

Six Dimensions of Benchmarking Time-Series Databases

Time-series databases (TSDBs) employ diverse storage architectures optimized for specific workload characteristics, leading to distinct performance profiles and bottlenecks that are often not apparent under conventional benchmarking approaches. System architects designing robust data backends must understand which storage engines are efficient for their particular pipelines and which exhibit the lowest risk of encountering future scalability constraints. This paper presents SciTSv2, a benchmarking framework that evaluates time-series databases across six workload dimensions: connection parallelism, batch ingestion, time-series regularity, multi-variate series, mixed workloads, and system metrics. We exploit SciTSv2 to systematically evaluate 4 TSDBs representing distinct storage engines: InfluxDB (Time-Structured Merge tree), TimescaleDB (based on relational databases), ClickHouse (columnar), and DataLayerTS (specialized in regular time-series). We show that each dimension surfaces architectural behavior that dedicated, single-axis benchmarks obscure, including regularity-dependent trade-offs, contention between concurrent reads and writes, and distinct CPU, I/O, and disk-bandwidth-bound bottlenecks. Paired with fine-grained system metrics, SciTSv2 gives architects a diagnostic tool for tracing performance outcomes back to their underlying architectural causes, supporting storage engine selections grounded in empirical, workload-specific evidence.

cs.DB↗

arXiv2026

The Remote Analog to Digital Conversion DAQ System for the TRISTAN Detector Upgrade

The TRISTAN detector is an upgrade to the KATRIN experiment to enable a differential measurement of the tritium $β$-decay spectrum to search for sterile neutrinos with keV masses. This entails performing precision electron spectroscopy with over one thousand silicon drift detector pixels, each responsible for recording incident electron rates of $10^5$ counts per second. A project specific data acquisition (DAQ) system is developed to meet the experimental challenges through a remote analog to digital conversion (RADC) design. In this work, the conceptual design of the RADC DAQ is presented along with the built system for operating the TRISTAN detector upgrade. The system includes flexible signal processing logic and data management that is optimized for the high-rate precision measurement.

physics.ins-det↗

arXiv2026

Optimizing Sensor Placement for Hydrogen Leak Detection in Enclosed Infrastructure: A Comparative Study Using CFD-informed Genetic Algorithm and DeepSets Neural Surrogate

Hydrogen infrastructure in enclosed environments, such as parking facilities for fuel cell vehicles, presents significant safety challenges due to hydrogen's low ignition energy and wide flammability range. Current monitoring systems are largely reactive, detecting leaks only after hazardous concentrations have formed. This study develops a computational framework for proactive sensor placement optimization by integrating computational fluid dynamics (CFD), genetic algorithm (GA) optimization, and a DeepSets neural surrogate. A CFD database of 180 scenarios was generated for a representative 50 m x 30 m x 3 m garage, covering multiple leak positions, rates (1-150 g/s), and ventilation conditions (ACH = 3-10 per hour). Sensor placement was optimized using a multi-objective GA and compared with uniform, random, and surrogate-assisted approaches. The GA achieved a detection rate of 96.1% within 60 s and reduced blind areas to 0.12%, corresponding to an approximately 5% improvement in composite fitness over a uniform baseline. The DeepSets surrogate reproduced near-optimal configurations with a fitness gap below 0.01 while reducing CFD evaluations by 89% and computational time by two orders of magnitude. Detection performance and spatial coverage remained comparable to the GA, demonstrating that surrogate-assisted optimization can retain solution quality while enabling rapid design iteration. Overall, the results show that CFD-informed optimization improves detection effectiveness and reduces sensor requirements compared to conventional layouts. The proposed framework supports scalable deployment and provides a foundation for integrating optimized sensor networks with digital twin systems for real-time monitoring and risk assessment.

cs.NE↗

arXiv2026

When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters

Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost. We provide the first systematic break-even analysis answering when this investment pays off. Across 30 benchmark datasets, we compare zero-shot and LoRA fine-tuned foundation models (Chronos, Moirai, Lag-Llama) against classical baselines (Naive, ETS, ARIMA, XGBoost) at six training set sizes from 2% to 100% of available data. Foundation models outperform classical methods at every evaluated training fraction on 15 of 30 datasets -- GPU deployment is unconditionally justified on these regardless of data volume. On 6 datasets, classical methods surpass zero-shot foundation models with as little as 2% of training data (21-2,768 samples); on the remaining 9, break-even ranges from 24 to 8,361 samples. One robust deployment rule requires no model training: if n_train < 700 and seasonality is non-negligible, use FM zero-shot and skip fine-tuning -- this resolves 10 of 30 deployment decisions immediately. Contrary to common practice, LoRA fine-tuning can actively degrade performance on short series. We operationalise these findings as a two-step decision framework -- compute dataset length and seasonality strength, run a brief 5-10% pilot only if needed -- enabling practitioners to make the FM-versus-classical decision before committing to full infrastructure. Four dataset features motivate mechanistic hypotheses for the remaining cases, though reliable automated prediction at this benchmark scale remains an open problem. Code, benchmark, and decision tools are available at https://github.com/nicolaisi/fm-breakeven.

cs.LG↗

arXiv2026

Forecasting Source Stability in Scientific Experiments using Temporal Learning Models: A Case Study from Tritium Monitoring

The Karlsruhe Tritium Neutrino Experiment (KATRIN) aims to measure the absolute neutrino mass with unprecedented sensitivity, requiring precise monitoring of the windowless gaseous tritium source, where tritium beta decay occurs. To track variations of the source activity, beta-induced X-ray spectroscopy provides real-time diagnostics. However, traditional drift detection methods struggle with the infrequent and transient nature of instability events in gaseous tritium. This study bridges the gap between state-of-the-art time-series forecasting models and real-world experimental applications by leveraging deep learning to predict the time to stability after instabilities. Unlike standard benchmarking approaches that emphasize algorithmic performance on fixed datasets, we apply forecasting models -- including LSTM, N-BEATS, TFT, NHITS, DLinear, NLinear, TSMixer, and Chronos-LLM -- to complex, large-scale experimental data. Our findings highlight two challenges: learning from sparse instability events and forecasting long time horizons (i.e., predicting hundreds of future points), both of which are ongoing challenges in time-series forecasting and remain active areas of research. This prediction task has direct experimental value by enabling better scheduling and maintenance planning. A reliable forecast of stability time allows for more efficient measurement and task management during stabilization periods. Through model selection, we identified N-BEATS as the top performer, excelling in accuracy and repeatability, demonstrating that deep learning can optimize large-scale physics experiments.

physics.ins-det↗

arXiv2024

BORA: A Personalized Data Display for Large-scale Experiments

Given the rapid improvement of the detectors at high-energy physics experiments, the need for real-time data monitoring systems has become imperative. The significance of these systems lies in their ability to display experiment status, steer software and hardware instrumentation, and provide alarms, thus enabling researchers to manage their experiments better. However, researchers typically build most data monitoring systems as standalone in-house solutions that cannot be reused for other experiments or future upgrades. We present BORA (personalized collaBORAtive data display), a lightweight browser-based monitoring system that supports diverse protocols and is built specifically for customizable visualization of complex data, which we standardize via video streaming. We show how absolute positioning layout and visual overlay background can address the diverse data display design requirements. Using the client-server architecture, we enable support for diverse communication protocols, with the server component responsible for parsing the incoming data. We integrate the Jupyter Notebook as part of our ecosystem to address the limitations of the web-based framework, providing a foundation to leverage scripting capabilities and integrate popular AI frameworks. Since video streaming is a core component of our framework, we evaluate viable approaches to streaming protocols like HLS, WebRTC, and MPEG-Websocket. The study explores the implications for our use case, highlighting its potential to transform data visualization and decision-making processes.

cs.HC↗

arXiv2023

Low-latency Visual Previews of Large Synchrotron Micro-CT Datasets

The unprecedented rate at which synchrotron radiation facilities are producing micro-computed (micro-CT) datasets has resulted in an overwhelming amount of data that scientists struggle to browse and interact with in real-time. Thousands of arthropods are scanned into micro-CT within the NOVA project, producing a large collection of gigabyte-sized datasets. In this work, we present methods to reduce the size of this data, scaling it from gigabytes to megabytes, enabling the micro-CT dataset to be delivered in real-time. In addition, arthropods can be identified by scientists even after implementing data reduction methodologies. Our initial step is to devise three distinct visual previews that comply with the best practices of data exploration. Subsequently, each visual preview warrants its own design consideration, thereby necessitating an individual data processing pipeline for each. We aim to present data reduction algorithms applied across the data processing pipelines. Particularly, we reduce size by using the multi-resolution slicemaps, the server-side rendering, and the histogram filtering approaches. In the evaluation, we examine the disparities of each method to identify the most favorable arrangement for our operation, which can then be adjusted for other experiments that have comparable necessities. Our demonstration proved that reducing the dataset size to the megabyte range is achievable without compromising the arthropod's geometry information.

cs.CV↗