53 hasil
Menampilkan 1–20 · 0,18 detik · RSS
Measurement. Digitalization
ISSN 3050-6441 · Elsevier · 53 artikel di indeks
-
Artikel Jurnal
Cross-dataset zero-shot IoT attack detection using a hybrid CNN–BiLSTM + attention framework with explainable AI
The rapid proliferation of Internet of Things (IoT) devices has heightened network susceptibility to diverse cyber-attacks and volumetric threats. Conventional intrusion detection systems (IDS) often struggle to generalise across heterogeneous network environments due to unstandardised feature…
-
Artikel Jurnal
Experimental characterization of degradation propagation in an embedded virtualized mixed-criticality legal-metrology system
Industrial legal-metrology systems increasingly integrate Industry 4.0 functionalities such as telemetry, diagnostics, automation, cloud connectivity, and third-party software. In regulated metrological environments, this evolution creates the challenge of allowing auxiliary software to coexist…
-
Artikel Jurnal
ClinFormer: a hybrid deep learning framework combining 1D-CNN, bidirectional LSTM, and Transformer encoder for Alzheimer’s disease classification from structured clinical records
Alzheimer’s disease (AD) is a leading cause of disability in late life, yet gold-standard diagnostic procedures remain costly and inaccessible to most at-risk populations. Reliable digital screening pipelines built on routinely measured clinical variables could extend the reach of early detection…
-
Artikel Jurnal
SI-traceability and digitalization of clinical intraocular-pressure measurement: a scoping review of the calibration chain, reference standards, measurement uncertainty, and machine-readable traceability
Intraocular pressure governs the diagnosis and management of glaucoma, yet whether the clinical result is metrologically traceable to the International System of Units (SI) has not been mapped, and neither has the digital infrastructure that would carry such traceability to the clinic. This review…
-
Artikel Jurnal
Integrating artificial intelligence in shelf-life prediction and packaging design for sustainable food systems
Rising global populations and changing environmental conditions continually challenge the stability of food supply chains, making the reduction of food waste while maintaining product quality a critical priority. Traditional approaches to shelf-life prediction and supply chain management are often…
-
Artikel Jurnal
Towards trustworthy ai monitoring of roll-to-roll electrode coating: an evidence-centred digital measurement twin with uncertainty-aware sensor fusion
Industrial AI monitoring increasingly transforms high frequency plant data into process state estimates and quality predictions, yet many systems still treat sensor readings as exact, stable and equally reliable. This limits trustworthiness because plant measurements are affected by calibration…
-
Artikel Jurnal
AIDPCP: an adaptive intelligent data preprocessing and clustering pipeline for obesity prediction with explainable AI
Obesity is a chronic metabolic disease characterized by excessive or abnormal fat accumulation and influenced by demographic, dietary, behavioral, and lifestyle factors. Questionnaire-based obesity prediction remains challenging because these datasets contain mixed feature types, class imbalance…
-
Artikel Jurnal
Towards laboratory-wide digitalisation in mass metrology: Automated and interoperable digital calibration certificate generation
In an era of global digital transformation, metrology is evolving from conventional operator-based and document-based infrastructures toward automated, machine-readable and interoperable digital ecosystems. In this context, Digital Calibration Certificates (DCCs) have emerged as a key enabling…
-
Artikel Jurnal
Spectrally equivalent artificial reconstruction of a historical church bell as a characterized acoustic source for in-situ soundscape studies
Historical soundscapes are often difficult to investigate experimentally because the acoustic sources that once shaped them have been removed, replaced, damaged, or are no longer usable under controlled conditions. This study proposes a digital metrological procedure for constructing a synthetic…
-
Artikel Jurnal
Integrated GPR surveys and 3D modelling of the Sforza Castle’s underground network
The research on Castello Sforzesco in Milan developed an integrated 3D information model combining historical sources and contemporary survey technologies. A digital twin was structured through multiple Levels of Geometric Information (LOGI), organized by attributes and accuracy of the original…
-
Artikel Jurnal
A declared readout-map model for machine-actionable digital measurement reports: Cutoff-conditioned uncertainty propagation in surface-profile roughness reporting
Digital calibration certificates, digital SI representations, FAIR data principles, and semantic metrology support machine-readable measurement reporting, but the transformation from exposed data to reported quantities often remains implicit. This paper formulates that transformation as a declared…
-
Artikel Jurnal
Daily actual evapotranspiration estimation in dryland cropping systems using parsimonious machine learning frameworks
Daily field-scale estimation of actual evapotranspiration (ETₐ) in dryland agricultural systems remains challenging due to limited in situ observations, strong spatiotemporal variability in hydroclimatic forcing, and data constraints. This study develops a footprint-aware, data-driven framework for…
-
Artikel Jurnal
Uncertainty-awareness in explainable artificial intelligence (xAI) for sensor network metrology
Machine learning models are increasingly used in sensor network applications, but the influence of measurement uncertainty and data quality on model explainability remains insufficiently understood. In this work, we investigate how degradation of input data quality in the form of increasing…
-
Artikel Jurnal
A stochastic approach to criterion weighting in multi-criteria decision making: Entropy-based Monte Carlo modeling
Route selection for Unmanned Combat Aerial Vehicles (UCAVs) is of strategic importance due to its dynamism and uncertainty. This study addresses the weighting of criteria in the UCAV route planning process, methodologically advancing the findings of a previous. In the previous study, 54 criteria…
-
Artikel Jurnal
Deep learning-based crack detection and 3D reconstruction for cost-effective structural health monitoring
The resilience of civil infrastructures decreases the risk of collapse and guarantees the durability of structures under permanent loads. The maintenance, management, and inspection optimize and improve structural integrity and resilience, ensuring public safety and uninterrupted operation. Crack…
-
Artikel Jurnal
A novel weakly supervised 3D object real-time detection method on intelligent recognition of tunnel wall obstacles
Ensuring the safety and efficiency of tunnel-wall cleaning has become increasingly important in tunnel maintenance. Traditionally, tunnel-wall cleaning is mainly supervised by manual operators. However, excessive reliance on manual operation may lead to safety risks, unstable cleaning quality, and…
-
Artikel Jurnal
Wavelet-enhanced Haar framework for face detection with convolutional neural networks
The process of face detection in real-world scenarios is influenced by lighting conditions, background environment, and the possibility of classical techniques to produce false positives, whereas deep learning models require more computing power. This paper presents an integrated face detection…
-
Artikel Jurnal
Advanced dementia prediction and detection via hybrid convolutional neural networks on MRI data
Alzheimer's disease (AD) is a progressive neurodegenerative disorder affecting approximately 50 million individuals worldwide, characterised by cognitive decline and memory impairment. Early and accurate staging is critical for timely intervention and treatment planning. This study proposes a novel…
-
Artikel Jurnal
Partial shading effect on recent PV array configurations and mismatch loss mitigation techniques: An extensive review
A common and complicated problem, shading reduces output power significantly and creates many power peaks in characteristic curves, which impairs Photovoltaic (PV) system performance. These detrimental effects are connected to the PV array's configuration and the shading pattern, not just the…
-
Artikel Jurnal
Evaluating sensor-based supply chain systems for economic resilience: A decision-making approach
Modern supply chains face growing disruptions from climate events, geopolitical tensions, pandemics, and cyberattacks, exposing their vulnerability. Effective decision-making on sensor system investments is critical to enhance economic resilience. This study presents a structured framework for…