Sequential Detection Research Articles

Using Vision Transformers for Spatial-Context-Aware Rain and Road Surface Condition Detection on Freeways

Inclement weather conditions, particularly heavy rain and the consequent wet road surface, have an unfavorable effect on driving conditions, traffic infrastructure, and operational plans. To mitigate the potentially detrimental ramifications of turbulent weather, it must be continuously monitored in real time and with high geospatial granularity. Traditionally, road weather conditions are monitored using weather forecasts or Roadside Weather Information Systems (RWIS). However, these methods are either ill-equipped or too expensive to provide the required fine-grained observations. Alternatively, roadside traffic CCTV cameras are ubiquitously deployed on US freeways and can serve as inexpensive sensors to surveil weather. In this paper, a novel vision-based methodology is proposed to detect rain and road surface conditions from roadside traffic cameras. Vision Transformers were utilized for image-based classification. They demonstrated superior results compared to convolution-based approaches. Furthermore, the geographical distribution of roadside cameras was leveraged to add spatial context awareness to the detection model. A Spatial Self-Attention network was proposed to model the relationship between the detection results of adjacent images as a sequence-to-sequence detection task. The results indicate that the addition of the sequential detection module improved the accuracy of the stand-alone Vision Transformer as measured by the F1-score. The boost in performance enhanced the F1-scores of the stand-alone Vision Transformer by 5.61% and 5.97% for the rain and road surface condition detection tasks, respectively, raising the total F1-score to 96.71% and 98.07%.

Lysosome-Targeting Fluorescence Sensor for Sequential Detection and Imaging of Cu2+ and Homocysteine in Living Cells.

A conjugated polymer-based fluorescence sensor, namely, PTNPy, was constructed on the basis of a polythiophene scaffold coupled with dimethylpyridylamine (DPA) groups in side chains for the consecutive detection and quantification of Cu2+ and Hcy in a perfect aqueous medium. A dramatic fluorescence quenching of PTNPy by the addition of Cu2+ was observed in Tris–HCl buffer solution (2 mM, pH 7.4), demonstrating a quick (<1 min) and highly selective response to Cu2+ with a low limit of detection of 6.79 nM. Subsequently, the Cu2+-quenched fluorescence of PTNPy can be completely recovered by homocysteine (Hcy), showing excellent selectivity to Hcy over other competitive species such as cysteine and glutathione. Thanks to the low cytotoxicity and lysosomal targeting ability of PTNPy, it was further applied as an optical sensor for the sequential imaging of Cu2+ and Hcy in HeLa cells. More importantly, Hcy concentration was linearly related to the fluorescence intensity of PTNPy in living cells, demonstrating huge potential for real-time monitoring the fluctuation of Hcy levels in living cells.

CHEF induced fluorometric sensing of Al3+ and picric acid with bioimaging in human peripheral blood mononuclear cell

Herein we report a quinoline modified oxacalixarene architecture (HQOC) that shows chelation enhanced turn-on fluorescence response toward Al3+. The presence of hard carbonyl oxygen and quinoline nitrogen plays an important role in switching-on the system through coordinating with hard Al3+ ions. The photophysical of the probe HQOC toward aluminium were thoroughly investigated using various techniques including UV–vis spectroscopy, fluorescence and NMR spectroscopy. The sequential detection of Al3+ and picric acid is immensely significant in evaluating its presence in the human ecosystem. HQOC allowed the specific recognition and quantification of Al3+ and picric acid with the detection limits of 24.60 nM and 34.28 nM. The Density Functional Theory (DFT) calculations further provide insight into the mechanistic aspects and electronic transitions involved during sensing. Additionally, we extended the work toward several bio-analytical applications. The cytotoxicity of the synthesized complex was screened against Peripheral Blood Mononuclear Cells (PBMC) by MTT assay and subsequently cell imaging, DNA cleavage activity was also explored for amenable therapeutic needs.

EP11.01-014 Optimizing Targetable Gene Screening by Sequential Multi-platform Detection Applied to Driver-negative mNSCLC Patients Detected by DNA-NGS

Screening for targetable gene alteration is critical for patients with metastatic non-small cell lung cancer (mNSCLC) and is now mainly detected by next-generation sequencing (NGS) of DNA. For the patients without driver alteration, we estimated the value of additional sequential multi-traditional platform in the identification of targetable gene alteration in mNSCLC with limited tissue biopsy sample.

Colorimetric probe for sequential chemosensing of mercury(II) and cyanide ions in aqueous media, based on a benzoxadiazole-pyrazolin-5-one glycoconjugate with INHIBIT logic gate response

A new and efficient water-soluble probe L for the sequential detection of Hg2+ and CN− ions has been developed by the condensation of benzoxadiazole and glycoconjugated pyrazoline-5-one. The resulting probe has a water solubility of 45 g/L at room temperature and interacts selectively with Hg2+ ions in water over other cations by changing its color from yellow to red and forming the [L/Hg2+: 2:1] complex. On the other hand, the formed complex [L/Hg2+: 2:1] reacts selectively with CN− anions in an aqueous solution. This reaction is accompanied by a blue shift in wavelength from 545 nm to 472 nm with a color change from red to yellow visible to the naked eye. These reversible and repeatable colorimetric responses of probe L towards Hg2+ and CN− ions can be represented as a molecular logic gate 'IMPLICATION', where Hg2+ and CN− ions are considered as inputs and the absorbance at 472 nm as output. The detection limit for Hg2+ and CN− ions was found to be 2.31 ppb and 4.34 ppb, respectively. From a practical point of view, probe L was used to prepare a test strip based on filter paper treated with L. The resulting test strip selectively changes color after the sequential addition of Hg2+ and CN− ions in water at pH7. These high performances in terms of selectivity and sensitivity allow the probe L to be used for the sequential detection of Hg2+ and CN− ions in aqueous media.

Sequential change-point detection for skew normal distribution

In this article, we propose a modified max-cumulative sum (CUSUM) procedure for detecting changes in parameters of skew normal distribution. The corresponding false alarms frequency and the postchange detection delay are investigated. Asymptotic behaviors of detection delay and theoretical optimality of the detection procedure have been established. Simulations have been conducted to show the performance of the proposed method and compare it to the other existing methods including CUSUM. Real data are given to illustrate the detection procedure.

Colorimetric and fluorescent probe based on coumarin/ thiophene derivative for sequential detection of mercury(II) and cyanide ions in an aqueous medium

A novel colorimetric and fluorescent coumarin hydrazone probe L was prepared by condensing 7-(diethylamino)-coumarin–3-carbaldehyde and (thiophen-2-ylmethyl) hydrazine. Absorbance and emission titrations show that probe L detects Hg2+ rather than other interfering cations. The colorimetric change from yellow to red and the decrease in fluorescence intensity after the addition of Hg2+ cations to probe L are perfectly visible to the naked eye. It could be related to intramolecular charge transfer and d-d transitions of the metal cations. The binding stoichiometry of the probe L to the Hg2+ cation was found to be 1:1, which was confirmed by Job plot and mass spectrum analysis. The resulting complex L.Hg2+ is preferentially fluorescent and presents a distinct blueshift in its absorbance spectrum only with CN− anions, which is caused by the release of the probe L and the production of the Hg(CN)2 complex. The LOD of Hg2+ and CN− were found to be 5.15 nM and 0.208 µM respectively. Therefore, probe L can be employed to detect and quantify Hg2+ and CN− in real solutions.

A red-emitting Europium(III) complex as a luminescent probe with large Stokes shift for the sequential determination of Cu2+ and biothiols in real samples

In this work, a novel Eu3+-DTPA-bis(AMC) complex with red luminescence was designed and synthesized for sequential detection of Cu2+ and biothiols (Cys/Hcy/GSH) based on the displacement strategy with the good selectivity, high sensitivity, and large Stokes shift (288 nm). The possible detection mechanism was verified by UV–vis, the high-resolution mass spectrometry, and the fluorescence decay curve. The experimental parameters, including the solution pH, the incubation time, the concentration ratio of Eu3+-DTPA-bis(AMC) to Cu2+ and biothiols concentration, were optimized. Under the optimal conditions, it shows a good linear relationship between the concentration (0–10 μM) of Cu2+ and the fluorescence intensity of Eu3+-DTPA-bis(AMC), with a low detection limit of 0.065 μM. The linear range and the limit of detection of the Eu3+-DTPA-bis(AMC)/Cu2+ system for Cys/Hcy/GSH were 2.5–22.5/5–45/5–50 μM and 0.11/0.07/0.05 μM, respectively. Surprisingly, the high or low concentration of Eu3+-DTPA-bis(AMC)/Cu2+ can significantly affect the selectivity of the sensing system to biothiols (Cys/GSH/Hcy). When the concentration of the Eu3+-DTPA-bis(AMC)/Cu2+ system is 10.0 μΜ, it could recognize biothiols (Cys/GSH/Hcy) from other substances, but when the concentration is as low as 3.3 μM, it could further specifically distinguished Cys from Hcy/GSH. Owing to the high anti-interference characteristics, accuracy and specificity, the sensing system was well applied to the cascade detection of Cu2+ in actual environmental samples and Cys in biological and food samples, including FBS, urine, milk, beverage, fresh juice with the satisfactory recoveries from 96.20 to 106.80 %.

Sequential verb metaphor detection with linguistic theories

Metaphor plays an indispensable role in human life. Although sequence tagging models took advantage of linguistic theories of metaphor identification, the usage of metaphor in common words is not considered, when choosing the literal meaning of the target verbs. We present a novel approach to express the literal meaning subtly, combining the common usage and the inherent visualizability properties of words, termed GloVe embedding and visual embedding. Meanwhile, we import position information of the target verbs to gain the contextual meaning more accurately. Both two DNN models use these embeddings as inputs in this paper, which are inspired by two human metaphor identification procedures augmented with contextualized word representations (ELMo embedding). By testing on two public datasets, the results show improvement over previous state-of-the-art approaches. In addition, we also verify the universality of the approach by testing the examples that the target words were adjectives, adverbs, and nouns, and the results show the approach is applicable to the above three parts of speech.

Synthesis of epiminocyclohepta[b]pyrazolo[4,3-e]pyridines from tropinone: Fluorescent “Turn on–off” chemosensors for the sequential detection of Al3+, Cd2+ and Pb2+ in nanomolar concentration

The syntheses of hitherto unreported epiminocyclohepta[b]pyrazolo[4,3-e]pyridines have been achieved through a microwave-assisted two-component domino strategy. These bicyclic heterocycles exhibited weak fluorescence under UV in 1:1 dioxane:water mixture. From the metal interference studies it has been observed that addition of Al3+ selectively induced a four-fold increase in the fluorescence intensity of these compounds through chelation-enhanced fluorescence. The regenerative nature of these probes has been evidenced by the successive addition of EDTA and Al3+. Further it has been demonstrated that upon sequential addition of Al3+ followed by either Cd2+ or Pb2+ led to fluorescence “turn on-off” of the epiminocyclohepta[b]pyrazolo[4,3-e]pyridine probes.

A turn-on fluorescent sensor for Cd2+ and sequential detection of S2− using the quinolimide scaffold

A novel quinolimide derivative (BNAL), bearing the amide-DPA receptor at position 9 of the heterocyclic ring, was synthesized for sequential detection of Cd2+ and S2−. BNAL could discriminate Cd2+ from Zn2+, showing the turn-on response upon interaction with Cd2+. After adding S2−, the fluorescence of the BNAL-Cd2+ solution was reverted through the displacement strategy. The limits of detection (LODs) of BNAL for Cd2+ and the BNAL-Cd2+ complex for S2− were found to be 17.9 nM and 1.51 μM, respectively. Finally, cell imaging experiments showed BNAL could be successfully employed for sequentially imaging Cd2+ and S2− via the off-on-off behavior in yeast cells.

Carrageenan-derived sulfur, nitrogen co-doped carbon dots for sequential detection of Ag+ and Lime Sulfur with “on-off-on” pattern

Heteroatom doped carbon dots have great potential in sensing field because of their good optical properties, high selectivity and sensitivity to targets. Herein, sulfur and nitrogen co-doped carbon dots (SNCDs) was synthesized by one-step hydrothermal reaction of κ-carrageenan and glutathione. The surface of the prepared SNCDs was modified by active groups, which not only enhance the optical properties, but also improve the analytical detection performance. Then, SNCDs, as a high-efficient “on-off-on” fluorescent sensor, was fabricated for sequence determination of Ag+ and Lime Sulfur (LS). Furthermore, it performed good selectivity and sensitivity to Ag+ and LS even with the interference of other metal ions or pesticides. The linear detection range of Ag+ and LS by SNCDs was 0–100 µM and 0–1 mg/L, and the detection limit was 0.124 µM and 50 µg/L, respectively. More importantly, it has been successfully used in the detection of actual water samples with recovery rates of 98.6~107.1%. In addition, a portable, reusable and highly absorbent fluorescent resin ball was constructed to enrich the application of SNCDs.

Automated detection of gunshots in tropical forests using convolutional neural networks

Unsustainable hunting is one of the leading drivers of global biodiversity loss, yet very few direct measures exist due to the difficulty in monitoring this cryptic activity. Where guns are commonly used for hunting, such as in the tropical forests of the Americas and Africa, acoustic detection can potentially provide a solution to this monitoring challenge. The emergence of low cost autonomous recording units (ARUs) brings into reach the ability to monitor hunting pressure over wide spatial and temporal scales. However, ARUs produce immense amounts of data, and long term and large-scale monitoring is not possible without efficient automated sound classification techniques. We tested the effectiveness of a sequential two-stage detection pipeline for detecting gunshots from acoustic data collected in the tropical forests of Belize. The pipeline involved an on-board detection algorithm which was developed and tested in a prior study, followed by a spectrogram based convolutional neural network (CNN), which was developed in this manuscript. As gunshots are rare events, we focussed on developing a classification pipeline that maximises recall at the cost of increased false positives, with the aim of using the classifier to assist human annotation of files. We trained the CNN on annotated data collected across two study sites in Belize, comprising 597 gunshots and 28,195 background sounds. Predictions from the annotated validation dataset comprising 150 gunshots and 7044 background sounds collected from the same sites yielded a recall of 0.95 and precision of 0.85. The combined recall of the two-step pipeline was estimated at 0.80. We subsequently applied the CNN to an un-annotated dataset of over 160,000 files collected in a spatially distinct study site to test for generalisability and precision under a more realistic monitoring scenario. Our model was able to generalise to this dataset, and classified gunshots with 0.57 precision and estimated 80% recall, producing a substantially more manageable dataset for human verification. Using a classifier-guided listening approach such as ours can make wide scale monitoring of threats such as hunting a feasible option for conservation management.

Zero-Bias Deep-Learning-Enabled Quickest Abnormal Event Detection in IoT

Abnormal event detection with the lowest latency is an indispensable function for safety-critical systems, such as cyber defense systems. However, as systems become increasingly complicated, conventional sequential event detection methods become less effective, especially when we need to define indicator metrics from complicated data manually. Although deep neural networks (DNNs) have been used to handle heterogeneous data, the theoretic assurability and explainability are still insufficient. This article provides a holistic framework for the quickest and sequential detection of abnormalities and time-dependent abnormal events. We explore the latent space characteristics of zero-bias neural networks considering the classification boundaries and abnormalities. We then provide a novel method to convert zero-bias DNN classifiers into performance-assured binary abnormality detectors. Finally, we provide a sequential quickest detection (QD) scheme that provides the theoretically assured lowest abnormal event detection delay under false alarm constraints using the converted abnormality detector. We verify the effectiveness of the framework using real massive signal records in aviation communication systems and simulation. Codes and data are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/pcwhy/AbnormalityDetectionInZbDNN</uri> .

A benzoxazole-based smart molecule for relay detection of zinc and phosphate ions and its implication towards molecular logic gate constructions

A benzoxazole-based fluorescent chemosensor (OPMP) has been designed, synthesized, and characterized by various analytical techniques. The as-prepared OPMP is employed for the cascade detection of Zn2+ and PO43- ions, respectively, based on the ‘off–on-off’ photoluminescence mechanism in 30% (v/v) water-DMSO mixture. A significant fluorescence enhancement of OPMP at 495 nm is observed due to chelation-enhanced fluorescence upon binding with Zn2+ ions. A visual bluish-green color could be seen under 365 nm UV light irradiation, which is also well supported by the color chromaticity diagram. The fluorescence of the Zn2+chelated OPMP complex is quenched in the presence of PO43- ions. The sensitivity of OPMP and Zn2+chelated OPMP complex towards detection of Zn2+ and PO43- ions can be possible down to 38 nM and 48 nM, respectively. Such as dual ions detection system with outstanding reversibility and reproducibility led us to consider our OPMP as a feasible candidate for the construction of molecular logic circuits, molecular keypad locks, and set-reset memorized molecular devices. Further, an OPMP staining paper strips-based test kit has been fabricated and demonstrated for the sequential detection of Zn2+ and PO43- ions, respectively.

A new 7-(diethylamino)coumarin and 4-(diethylamino)phenol appended unsymmetrical thiocarbohydrazone: Detection of moisture in organic solvent and sequential fluorimetric detection of Cu2+ ions and cysteine

A novel 7-(diethylamino)coumarin and 4-(diethylamino)phenol appended unsymmetrical thiocarbohydrazone (2) was designed and synthesized successfully. The probe 2 forms an interesting three dimensional hydrogen bonded network results in an interesting supramolecular network. The compound, 2 showed fluorometric and colorimetric response towards fluoride anion via deprotonation process due to the presence of phenolic –OH and –NH groups. The anionic species 2-F− was successfully employed for the detection of moisture in organic solvents through the reprotonation process. The moisture detection features of 2-F− were explored by using UV–vis and emission experiments in DMF solvent and the corresponding mechanism was effectively confirmed by 1H NMR spectral analysis. Moreover, the synthesized probe 2 exhibits highly selective and sensitive detection for Cu2+ ions. Furthermore, the 2-Cu2+ ensemble might be used as a highly selective sensor for Cys in the presence of other amino acids without any interference. Further, the potential reversible sensing feature of Cu2+ and Cys by 2 were recognized to develop the INHIBIT logic gate function and on-site detection of Cu2+ ions and Cys by a paper strip applications.

Sequential common rate decrease detection, isolation, and estimation in multiple Poisson processes

ABSTRACT We consider the detection of a common change when M independent Poisson processes are monitored simultaneously where only a portion of the processes have rate decrease after the change time. In contrast to the detection of rate increase (Wu and Wu (2022)), the individual CUSUM and Shiryayev–Roberts (S–R) processes need to be calculated continuously in parallel. A combined CUSUM-SR procedure is proposed by using the sum of S–R processes as the detection process for a common change and after the detection, the M individual CUSUM processes are used to isolate the changed panels with FDR control. The medians of change time estimates from the individual CUSUM or S–R processes from the isolated changed panels are then used to estimate the common change time. Coal mining disaster data in USA are used for illustration.

A holistic sequential fault detection and diagnostics framework for multiple zone variable air volume air handling unit systems.

A holistic fault detection and diagnostics (FDD) method should explicitly consider the dependencies between faults at the system- and zone-level to isolate the root cause. A system-level fault can trigger false alarms at the zone-level, while concealing the presence of a zone-level fault. However, most FDD methods have focused on a single component/equipment without considering the importance of the interactions between zone- and system-level devices. This paper proposes a holistic hierarchical framework for FDD, combining the process of detection and diagnosis of controls hardware and sequencing logic faults affecting the actuators at the system- and zone-level. The proposed framework follows a holistic sequential procedure to diagnose faults and suppress false alarms in this order: hard faults in air handling units (AHUs), hard faults in variable air volume (VAV) zones, sequencing logic faults in AHUs, and sequencing logic faults in VAV zones. The detection of faults is performed by visualizing the discrepancies between the expected and measured operational behaviour of AHUs and VAV boxes. Examples demonstrating the framework are provided with data from 10 different VAV AHU systems.Practical application: This paper provides a sequential hierarchical FDD framework to address two main issues in VAV AHU systems: detectability and significance. Regarding detectability, the framework prioritizes hard faults over sequencing logic faults to avoid false positives and false negatives; about significance, system-level faults are prioritized over zone-level faults to triage high-impact faults in the system. The detection of faults is performed via visualizing the biases from the expected behaviour of AHU and VAV characteristics to provide an envisioning interpretation for the experts in facilities management in commercial buildings to find the root cause of the fault and fix them on-site.

A Multiple-Target Simultaneous Detection Method for Immunosorbent Assay and Immunospot Assay.

Enzyme-linked immunosorbent assay (ELISA) is one of the most common methods in biological studies, and enzyme-linked immunospot (ELISpot) is a method to measure specific cell numbers by detecting protein secretion at a single-cell level. However, these two current methods can only detect one signal at one time and the sensitivity is not high enough to test low-concentration samples, which are major shortcomings in systematically analyzing the samples of interest. Herein, we demonstrated fluorescence-based oligo-linked immunosorbent assay (FOLISA) and fluorescence-based oligo-linked immunospot (FOLISPOT), which utilized DNA-barcoded antibodies to provide a highly multiplexed method with signal amplification. Signal amplification and simultaneous multiple-target detection were achieved by DNA complementary pairing and modular orthogonal DNA concatemers. By comparing FOLISA with traditional ELISA and comparing FOLISPOT with traditional ELISPOT, we found that the detection sensitivities of FOLISA and FOLISPOT are much higher than those of traditional ELISA and ELISPOT. The detection limit of ELISA is around 3 pg/mL, and the detection limit of FOLISA is below 0.06 pg/mL. FOLISPOT can detect more spots than ELISPOT and can detect targets that are undetectable for ELISPOT. Furthermore, FOLISA and FOLISPOT allowed sequential detection of multiple targets by using a single dye or multiple dyes in one round and sequential detection in multiple rounds. Thus, FOLISA and FOLISPOT enabled simultaneous detection of a large number of targets, significantly improved the detection sensitivity, and overcame the shortcomings of ELISA and ELISPOT. Overall, FOLISA and FOLISPOT presented effective and general platforms for rapid and multiplexed detection of antigens or antibodies with high sensitivity, either in laboratory tests or potentially in clinic tests.

Bayesian Filtering for Dynamic Anomaly Detection and Tracking

This article presents a Bayesian approach for sequential detection of anomalies in the motion of a target and joint tracking. The anomaly is modeled as a binary (on/off) switching unknown control input that goes into action (begins to exist, or “switches on”) thereby modifying the object dynamics; and by ceasing its activity (becoming nonexistent, or “switching off”) returns the dynamics to nominal. The developed Bayesian framework brings together random finite set (RFS) theory to represent the switching nature of the anomaly, and optimal joint input and state estimation to sequentially update a hybrid state that incorporates a random vector for the kinematic state and a Bernoulli RFS for the unknown control input. In addition, a closed-form solution, the Gaussian-mixture hybrid Bernoulli filter (GM-HBF), has been developed to provide a customized solution for dynamic anomaly detection in the maritime domain characterized by linear Gaussian target dynamics. Based on the Ornstein–Uhlenbeck dynamic model for vessels, where the evolution of the object velocity is governed by a piecewise mean-reverting stochastic process, the anomaly can be represented by a change in the long-run mean velocity (i.e., the unknown control input) from the nominal condition that forces the vessel to deviate from its standard route. We demonstrate the effectiveness of the proposed GM-HBF in both simulated and real-world maritime surveillance applications and test its performance in the face of false measurements, detection uncertainty, and sensor data gaps.