Subsea pipelines often bend upward due to vertical buckling or downward due to spanning and seabed settling. Typically, harsh environments and the difficulty of accessing underwater pipelines make the inspection and monitoring of subsea pipeline bends a challenging task. This paper demonstrates a low-cost, high-efficiency, and quasi-real-time method for detecting the vertical bends of subsea pipelines by using an in-pipe spherical detector (SD) with rolling features and a low blockage risk. When the SD rolls forward inside a bent pipeline, its rolling speed will change as it moves uphill and downhill, which can be indicated by the centripetal acceleration—the DC component of the recorded rolling acceleration signals. To achieve a high bend detection performance, the mass of the SD should be distributed in a centered disc area to make the SD capable of stably rolling around one of the sensitive axes of the accelerometer, and the accelerometer should be kept as far from the rotation axis as possible. It is experimentally demonstrated that a convex/concave DC component indicates that the pipe is bent downward/upward, and the bend detection resolution can reach 1 cm for a 12 m pipeline.

The globalization of the food supply chain presents complex challenges for safety assurance within a highly fragmented regulatory landscape. This review synthesizes the frameworks of eight influential jurisdictions—including the European Union (EU), the United States, China, and Codex Alimentarius—to evaluate how legal mandates function as regulatory drivers that guide the evolution of analytical chemistry. By examining legislation on Maximum Residue Limits (MRLs), positive list systems, and method validation guidelines (e.g., SANTE), we demonstrate that strict preventive controls have established chromatography coupled with tandem mass spectrometry (LC/GC-MS/MS) as the universal standard for multi-residue screening. We show that global regulatory fragmentation is not merely an administrative artifact, but is rooted in divergent toxicological philosophies and localized dietary exposure models. This regulatory heterogeneity requires analytical laboratories to adopt a posture of “defensive technological redundancy,” forcing them to continuously optimize targeted methods against the strictest global default limits (e.g., 0.01 mg/kg). We establish that this continuous methodological escalation for ultra-trace quantification has reached practical and operational limits. Consequently, we conclude that the future of food safety testing must transition from static target-list compliance toward adaptable, non-targeted chemical profiling using High-Resolution Mass Spectrometry (HRMS), enabling laboratories to proactively address emerging contaminants, food fraud, and the complexities of modern food matrices.

Mass spectrometry (MS) data present challenges for machine learning (ML) classification due to their high dimensionality, complex feature distributions, batch effects, and intensity discrepancies, often hindering model generalization and efficiency. To address these issues, this study introduces the Efficient Quick 1D Lite Convolutional Neural Network (CNN) Ensemble Classifier (EQLC-EC), integrating 1D convolutional networks with reshape layers and dual voting mechanisms for enhanced feature representation and classification performance. Validation was performed on five publicly available MS datasets, each featured in high-impact publications. EQLC-EC underwent comprehensive evaluation against classical machine learning (ML) models (e.g., support vector machine (SVM), random forest) and the leading deep learning methods reported in these studies. EQLC-EC demonstrated dataset-specific improvements, including enhanced classification accuracy (1–5% increase) and reduced standard deviation (1–10% reduction). Performance differences between soft and hard voting mechanisms were negligible (<1% variation in accuracy and standard deviation). EQLC-EC presents a powerful and efficient tool for MS data analysis with potential applications across metabolomics and proteomics.

Extracting key features for phenotype classification from high-dimensional and complex mass spectrometry (MS) data presents a significant challenge. Conventional data representation methods, such as traditional peak lists or grid-based imaging strategies, are often hampered by information loss and compromised signal integrity, thereby limiting the performance of downstream deep learning models. To address this issue, we propose a novel data representation framework named MSIMG. Inspired by object detection in computer vision, MSIMG introduces a data-driven, “density-peak-centric” patch selection strategy. This strategy employs density map estimation and non-maximum suppression algorithms to locate the centers of signal-dense regions, which serve as anchors for dynamic, content-aware patch extraction. This process transforms raw mass spectrometry data into a multi-channel image representation with higher information fidelity. Extensive experiments conducted on two public clinical mass spectrometry datasets demonstrate that MSIMG significantly outperforms both the traditional peak list method and the grid-based MetImage approach. This study confirms that the MSIMG framework, through its content-aware patch selection, provides a more information-dense and discriminative data representation paradigm for deep learning models. Our findings highlight the decisive impact of data representation on model performance and successfully demonstrate the immense potential of applying computer vision strategies to analytical chemistry data, paving the way for the development of more robust and precise clinical diagnostic models.

Mass spectrometry (MS) data presents challenges for machine learning (ML) classification due to its high dimensionality, complex feature distributions, batch effects, and intensity discrepancies, often hindering model generalization and efficiency. To address these issues, this study introduces the Efficient Quick 1D Lite CNN Ensemble Classifier (EQLC-EC), integrating 1D convolutional networks with reshape layers and dual voting mechanisms for enhanced feature representation and classification performance. Validation was performed on five publicly available MS datasets, each featured in high-impact publications. EQLC-EC underwent comprehensive evaluation against classical machine learning (ML) models (e.g., support vector machine [SVM], random forest) and the leading deep learning methods reported in these studies. EQLC-EC demonstrated dataset-specific improvements, including enhanced classification accuracy (1%-5% increase) and reduced standard deviation (1%-10% reduction). Performance differences between soft and hard voting mechanisms were negligible (<1% variation in accuracy and standard deviation). EQLC-EC presents a powerful and efficient tool for MS data analysis with potential applications across metabolomics and proteomics.

Artificial intelligence (AI) increasingly produces uncertainty outputs for sensing and measurement tasks, but the evidence supporting these outputs may not maintain a traceable correspondence with the relevant real-world conditions. This study conducted a structured 15-dimensional coding review of 566 studies, of which 556 formed stable dominant AI uncertainty claim units and entered the common analytic set. Each final code was linked to row-level audit evidence. The unidimensional distributions first showed breakpoint states with nonzero frequencies at the relevant nodes of the claim–condition–test–uncertainty-response chain, thereby confirming observable evidence discontinuities in the current corpus. The studies were then stratified using three sequential, non-compensatory evidence questions. Among the 556 studies, 347 (62.4%) were classified as Weak, 133 (23.9%) as Medium, and 76 (13.7%) as Strong. Descriptive cross-dimensional comparisons showed that specific OOD/drift risk or Error/quality estimation claims, Multiple uncertainty entry points, Multiple physical information types, and Sampling/ensemble approximation more often co-occurred with higher evidence traceability; Prediction reliability/confidence claims, a standalone Uncertainty proxy/score, and Latency/real-time inference constraints more often co-occurred with lower evidence traceability. This study summarizes the above evidence discontinuity as the physical fidelity gap (PFG), which refers to incomplete or unverifiable evidential links between AI uncertainty claims publicly reported in the literature and the relevant physical, measurement, or operational conditions. PFG provides a scope-bounded reference for locating links in the evidence chain that may need strengthening. The breakpoints observable in the current corpus indicate that the public evidence still has room for improvement in forming continuous, verifiable claim–condition–test–response correspondences; the tiered comparison indicates that subsequent work can strengthen the evidence chain by clarifying claim conditions, incorporating the relevant conditions into empirical testing, and reporting identifiable uncertainty responses and extended corroboration.