Learn Model Parameters Research Articles

Masking and Homomorphic Encryption-Combined Secure Aggregation for Privacy-Preserving Federated Learning

Secure aggregation of local learning model parameters is crucial for achieving privacy-preserving federated learning. This paper presents a novel and practical aggregation method that effectively combines the advantages of masking-based aggregation with those of homomorphic encryption-based techniques. Each node conceals its local parameters using a randomly selected mask, independently chosen, thereby eliminating the need for additional computations to generate or exchange mask values with other nodes. Instead, each node homomorphically encrypts its random mask using its own encryption key. During each federated learning round, nodes send their masked parameters and the homomorphically encrypted mask to the federated learning server. The server then aggregates these updates in an encrypted state, directly calculating the average of actual local parameters across all nodes without the necessity to decrypt the aggregated result separately. To facilitate this, we introduce a new multi-key homomorphic encryption technique tailored for secure aggregation in federated learning environments. Each node uses a different encryption key to encrypt its mask value. Importantly, the ciphertext of each mask includes a partial decryption component from the node, allowing the collective sum of encrypted masks to be automatically decrypted once all are aggregated. Consequently, the server computes the average of the actual local parameters by simply subtracting the decrypted total sum of mask values from the cumulative sum of the masked local parameters. Our approach effectively eliminates the need for interactions between nodes and the server for mask generation and sharing, while addressing the limitation of a single key homomorphic encryption. Moreover, the proposed aggregation process completes the global model update in just two interactions (in the absence of dropouts), significantly simplifying the aggregation procedure. Utilizing the CKKS (Cheon-Kim-Kim-Song) homomorphic encryption scheme, our method ensures efficient aggregation without compromising security or accuracy. We demonstrate the accuracy and efficiency of the proposed method through varied experiments on MNIST data.

Machine Learning–Finite Element Mesh Optimization-Based Modeling and Prediction of Excavation-Induced Shield Tunnel Ground Settlement

Ground settlement prediction for shield construction is highly important and challenging. This study introduces a machine learning algorithm combined with finite element numerical simulation, i.e., machine learning–finite element mesh optimization. For surface subsidence prediction, 16 combination models of ANN, KNN, RF and SVR were optimized by PSO, GA, BT and BO, involving raw data preprocessing, principal component analysis, hyperparameter selection and prediction accuracy evaluation. A subway shield tunneling project was analyzed, in which the meshes of finite element numerical models were discretized into different sizes from 1.0[Formula: see text]m to 2.0[Formula: see text]m. In total, 360 sets of data points were extracted from the simulation results, including stress, strain, shield jacking force, internal friction angle, cohesion force, and settlement, of which 252 data points were used as the input parameters of machine learning model. Analysis of average error rate of finite element–machine learning coupling models showed that the finite element model had the highest accuracy of settlement prediction when the mesh size of the finite element model was 1.4[Formula: see text]m, and the GA-SVR model had the highest accuracy and generalization ability in ground settlement prediction. This study highlights the uniqueness of machine learning–finite element mesh optimization model in application.

Real-Time prediction of pool fire burning rates under complex heat transfer effects influenced by ullage height: A comparative study of BPNN and SVR

This research utilizes machine learning methods to forecast the complex, non-linear thermal phenomena, along with heat transfer mechanisms, that influence the burning rate of pool fires, especially with changes in ullage height. Experiments involving pool fires were systematically designed and carried out, incorporating different diameters and ullage heights. Heptane was used as the representative alkane fuels. A dataset containing more than 70,000 sets of data was created as a training dataset for training the Backpropagation Neural Network (BPNN) and Support Vector Regression (SVR) models. During the optimization of machine learning model parameters, this study is based on Particle Swarm Optimization (PSO) with the principle of intelligent optimization to efficiently and accurately screen and optimize the key parameters of the model. The combustion duration, pool dimensions, and non-dimensional ullage height were input into a machine-learning model to predict the burning rate. By comparing against experimental data, the model was found to be able to predict the dynamic evolution of the burning rate of the pool fire in a real-time manner. The SVR model demonstrates greater predictive accuracy in comparison to the BPNN model, and the relative prediction error remains within ± 20 %, which fully proves its effectiveness and generalization ability in the prediction of pool fire burning rate. The insights gained will offer substantial scientific backing for enhanced fire monitoring systems, while highlighting the capability of advanced machine learning methodologies to predict the intricate, real-time thermal dynamics and heat transfer characteristics of burning liquid fuels.

Few-shot SAR target classification via meta-learning with hybrid models

Currently, in Synthetic Aperture Radar Automatic Target Recognition (SAR ATR), few-shot methods can save cost and resources while enhancing adaptability. However, due to the limitations of SAR imaging environments and observation conditions, obtaining a large amount of high-value target data is challenging, leading to a severe shortage of datasets. This paper proposes the use of an Adaptive Dynamic Weight Hybrid Model (ADW-HM) meta-learning framework to address the problem of poor recognition accuracy for unknown classes caused by sample constraints. By dynamically weighting and learning model parameters independently, the framework dynamically integrates model results to improve recognition accuracy for unknown classes. Experiments conducted on the TASK-MSTAR and OpenSARShip datasets demonstrate that the ADW-HM framework can obtain more comprehensive and integrated feature representations, reduce overfitting, and enhance generalization capability for unknown classes. The accuracy is improved in both 1-shot and 5-shot scenarios, indicating that ADW-HM is feasible for addressing few-shot problems.

Data-driven fire modeling: Learning first arrival times and model parameters with neural networks

Data-driven techniques are increasingly being applied to complement physics-based models in fire science. However, the lack of sufficiently large datasets continues to hinder the application of certain machine learning techniques. In this paper, we use simulated data to investigate the ability of neural networks to parameterize dynamics in fire science. In particular, we investigate neural networks that map five key parameters in fire spread to the first arrival time, and the corresponding inverse problem. By using simulated data, we are able to characterize the error, the required dataset size, and the convergence properties of these neural networks. For the inverse problem, we quantify the network’s sensitivity in estimating each of the key parameters. The findings demonstrate the potential of machine learning in fire science, highlight the challenges associated with limited dataset sizes, and quantify the sensitivity of neural networks to estimate key parameters governing fire spread dynamics.

Entomopathogenic nematode detection and counting model developed based on A-star algorithm

Entomopathogenic nematodes are soil-dwelling living organisms widely employed in the biological control of agricultural insect pests, serving as a significant alternative to pesticides. In laboratory procedures, the counting process remains the most common, labor-intensive, time-consuming, and approximate aspect of studies related to entomopathogenic nematodes. In this context, a novel method has been proposed for the detection and quantification of Steinernema feltiae isolate using computer vision on microscope images. The proposed method involves two primary algorithmic steps: framing and isolation. Compared to YOLO-V5m, YOLO-V7m, and YOLO-V8m, the A-star-based developed network demonstrates significantly improved detection accuracy compared to other networks. The novel method is particularly effective in facilitating the detection of overlapping nematodes. The developed algorithm excludes processes that increase space and time complexity, such as the weight document, which contains the learned parameters of the deep learning model, model integration, and prediction time, resulting in more efficient operation. The results indicate the feasibility of the proposed method for detecting and counting entomopathogenic nematodes.

Dopamine and Norepinephrine Differentially Mediate the Exploration-Exploitation Tradeoff.

Dopamine (DA) and norepinephrine (NE) have been repeatedly implicated in neuropsychiatric vulnerability, in part via their roles in mediating the decision-making processes. Although two neuromodulators share a synthesis pathway and are coactivated under states of arousal, they engage in distinct circuits and modulatory roles. However, the specific role of each neuromodulator in decision-making, in particular the exploration-exploitation tradeoff, remains unclear. Revealing how each neuromodulator contributes to exploration-exploitation tradeoff is important in guiding mechanistic hypotheses emerging from computational psychiatric approaches. To understand the differences and overlaps of the roles of these two catecholamine systems in regulating exploration, a direct comparison using the same dynamic decision-making task is needed. Here, we ran male and female mice in a restless two-armed bandit task, which encourages both exploration and exploitation. We systemically administered a nonselective DA antagonist (flupenthixol), a nonselective DA agonist (apomorphine), a NE beta-receptor antagonist (propranolol), and a NE beta-receptor agonist (isoproterenol) and examined changes in exploration within subjects across sessions. We found a bidirectional modulatory effect of dopamine on exploration. Increasing dopamine activity decreased exploration and decreasing dopamine activity increased exploration. The modulatory effect of beta-noradrenergic receptor activity on exploration was mediated by sex. Reinforcement learning model parameters suggested that dopamine modulation affected exploration via decision noise and norepinephrine modulation affected exploration via sensitivity to outcome. Together, these findings suggested that the mechanisms that govern the exploration-exploitation transition are sensitive to changes in both catecholamine functions and revealed differential roles for NE and DA in mediating exploration.

Augmenting Knowledge for Individual NVR Prediction in Different Spatial and Temporal Cross-Building Environments

Natural ventilation is a critical method for reducing energy consumption for heating, cooling, and ventilating buildings. Recent research has focused on utilizing environmental IoT data from both inside and outside buildings for NVR prediction based on a deep learning model. To design an accurate NVR prediction model while considering individual building environments, various knowledge-sharing methods can be applied, such as transfer learning and ensemble models for cross-building prediction. However, the characteristics of learning data and model parameters should be considered when applying transfer learning and ensemble models to predict NVR with different spatial and temporal domains. In this paper, we propose a way to design an NVR prediction model for a cross-building environment by normalizing the training data, selecting transfer learning layers that are well-suited to the data environment, and augmenting NVR knowledge via ensemble methods. Based on the experimental results, we confirm that the proposed knowledge-sharing deep learning approach, while considering the normalizing of training data, the selecting transfer learning layers, and augmenting the NVR knowledge approach, can improve the accuracy up to 11.8% in the two different offices and seasons.

Deep Learning-Based Vascular Aging Prediction From Retinal Fundus Images.

The purpose of this study was to establish and validate a deep learning model to screen vascular aging using retinal fundus images. Although vascular aging is considered a novel cardiovascular risk factor, the assessment methods are currently limited and often only available in developed regions. We used 8865 retinal fundus images and clinical parameters of 4376 patients from two independent datasets for training a deep learning algorithm. The gold standard for vascular aging was defined as a pulse wave velocity ≥1400 cm/s. The probability of the presence of vascular aging was defined as deep learning retinal vascular aging score, the Reti-aging score. We compared the performance of the deep learning model and clinical parameters by calculating the area under the receiver operating characteristics curve (AUC). We recruited clinical specialists, including ophthalmologists and geriatricians, to assess vascular aging in patients using retinal fundus images, aiming to compare the diagnostic performance between deep learning models and clinical specialists. Finally, the potential of Reti-aging score for identifying new-onset hypertension (NH) and new-onset carotid artery plaque (NCP) in the subsequent three years was examined. The Reti-aging score model achieved an AUC of 0.826 (95% confidence interval [CI] = 0.793-0.855) and 0.779 (95% CI = 0.765-0.794) in the internal and external dataset. It showed better performance in predicting vascular aging compared with the prediction with clinical parameters. The average accuracy of ophthalmologists (66.3%) was lower than that of the Reti-aging score model, whereas geriatricians were unable to make predictions based on retinal fundus images. The Reti-aging score was associated with the risk of NH and NCP (P < 0.05). The Reti-aging score model might serve as a novel method to predict vascular aging through analysis of retinal fundus images. Reti-aging score provides a novel indicator to predict new-onset cardiovascular diseases. Given the robust performance of our model, it provides a new and reliable method for screening vascular aging, especially in undeveloped areas.

Estimation of water quality in Korattur Lake, Chennai, India, using Bayesian optimization and machine learning

Assessing water quality becomes imperative to facilitate informed decision-making concerning the availability and accessibility of water resources in Korattur Lake, Chennai, India, which has been adversely affected by human actions. Although numerous state-of-the-art studies have made significant advancements in water quality classification, conventional methods for training machine learning model parameters still require substantial human and material resources. Hence, this study employs stochastic gradient descent (SGD), adaptive boosting (AdaBoosting), Perceptron, and artificial neural network algorithms to classify water quality categories as these well-established methods, combined with Bayesian optimization for hyperparameter tuning, provide a robust framework to demonstrate significant performance enhancements in water quality classification. The input features for model training from 2010 to 2019 comprise water parameters such as pH, phosphate, total dissolved solids (TDS), turbidity, nitrate, iron, chlorides, sodium, and chemical oxygen demand (COD). Bayesian optimization is employed to dynamically tune the hyperparameters of different machine learning algorithms and select the optimal algorithms with the best performance. Comparing the performance of different algorithms, AdaBoosting exhibits the highest performance in water quality level classification, as indicated by its superior accuracy (100%), precision (100%), recall (100%), and F1 score (100%). The top four important factors for water quality level classification are COD (0.684), phosphate (0.119), iron (0.112), and TDS (0.084). Additionally, variations or changes in phosphate levels are likely to coincide with similar variations in TDS levels.

Research on internal leakage detection of the ball valves based on stacking ensemble learning

Abstract Natural gas is an important clean energy source that is mainly transported through pipelines. The ball valve is a crucial piece of control equipment for the pipeline transportation system for natural gas, and the failure of internal leakage of the ball valve will seriously affect the natural gas transmission and increase the risk of sudden safety accidents. In response to the problems of the limitations of a single machine learning model in the traditional ball valve internal leakage rate prediction methods and failure to qualitatively analyze unilateral and bilateral internal leakage recognition of ball valve, a study of ball valve internal leakage detection based on Stacking ensemble learning is proposed. A total of 15 time and frequency domain feature parameters were obtained by feature extraction of 125 and 96 sets of raw acoustic emission signals from the ball valve; the parameters of a single machine learning model were adjusted by Bayesian optimization grid search. An internal leakage rate prediction model and an internal leakage recognition model are constructed, and the proposed model is compared and analyzed with a single model through a field ball valve internal leakage test. The results indicate that the Stacking ensemble learning model outperforms each single machine learning model in terms of SMAPE (17.2583), RMSE (1.1009), and MAE (0.9375) for internal leakage rate prediction. The Stacking ensemble learning model outperformed the single machine learning model in terms of accuracy (1), recall (1), precision (1), FAR(0), and F1-score (1) for internal leakage recognition. Stacking ensemble learning significantly enhances the model's ability to detect internal ball valve leaks.&amp;#xD;

Improving few-shot named entity recognition via Semantics induced Optimal Transport

Named entity recognition (NER) is to identify and categorize entities in unstructured text, which serves as a fundamental task for a variety of natural language processing (NLP) applications. In particular, emerging few-shot NER methods aim to learn model parameters well with few samples and have received considerable attention. The dominant few-shot NER methods usually employ pre-trained language models (PLMs) as their basic architecture and fine-tune model parameters with few NER samples. Since the sample size is small and there are a large number of parameters in PLMs, fine-tuning may result in the parameters of PLMs being highly biased. To address this issue, this study introduces the semantic distribution distance constraints to optimize the fine-tuning process of few-shot NER models and develops a framework named Semantic Constraints on few-shot Named Entity Recognition (SCNER). Specifically, the framework formulates the general knowledge transfer of PLMs as an optimal transport procedure with a semantic prior. And, a Semantics-induced Optimal Transport (SOT) regularizer is developed to utilize the importance and similarities of tokens within sentences. SOT builds the semantic distribution of the sentence and defines the transport costs between tokens to achieve the token-level optimal transport procedures. Finally, SOT is employed as a regularization term of few-shot NER to introduce the semantic distribution distance constraint for effectively transferring general knowledge from PLMs. The experiments on four public datasets demonstrate that the proposed method significantly improves the performance of NER models in both few-shot and fully supervised scenarios. SCNER is a common framework that can be applied to a variety of models without adding additional learning parameters, and can be used to enhance the generalization ability and adaptability of various few-shot NER models.

Quantifying uncertainty in graph neural network explanations.

In recent years, analyzing the explanation for the prediction of Graph Neural Networks (GNNs) has attracted increasing attention. Despite this progress, most existing methods do not adequately consider the inherent uncertainties stemming from the randomness of model parameters and graph data, which may lead to overconfidence and misguiding explanations. However, it is challenging for most of GNN explanation methods to quantify these uncertainties since they obtain the prediction explanation in a post-hoc and model-agnostic manner without considering the randomness of graph data and model parameters. To address the above problems, this paper proposes a novel uncertainty quantification framework for GNN explanations. For mitigating the randomness of graph data in the explanation, our framework accounts for two distinct data uncertainties, allowing for a direct assessment of the uncertainty in GNN explanations. For mitigating the randomness of learned model parameters, our method learns the parameter distribution directly from the data, obviating the need for assumptions about specific distributions. Moreover, the explanation uncertainty within model parameters is also quantified based on the learned parameter distributions. This holistic approach can integrate with any post-hoc GNN explanation methods. Empirical results from our study show that our proposed method sets a new standard for GNN explanation performance across diverse real-world graph benchmarks.

Recognition of Plastic Film in Terrain-Fragmented Areas Based on Drone Visible Light Images

In order to meet the growing demand for food and achieve food security development goals, contemporary agriculture increasingly depends on plastic coverings such as agricultural plastic films. The remote sensing-based identification of these plastic films has gradually become a necessary tool for agricultural production management and soil pollution prevention. Addressing the challenges posed by the complex terrain and fragmented land parcels in karst mountainous regions, as well as the frequent presence of cloudy and foggy weather conditions, the extraction efficacy of mulching films is compromised. This study utilized a DJI Mavic 2 Pro UAV to capture visible light images in an area with complex terrain features such as peaks and valleys. A plastic film sample dataset was constructed, and the U-Net deep learning model parameters integrated into ArcGIS Pro were continuously modified and optimized to achieve precise plastic film identification. The results are as follows: (1) Sample quantity significantly affects recognition performance. When the sample size is 800, the accuracy of plastic film extraction notably improves, with area accuracy reaching 91%, a patch quantity accuracy of 96.38%, and an IOU and F1-score of 85.89% and 94.20%, respectively, compared to the precision achieved with a sample size of 300; (2) Different learning rates, batch sizes, and iteration numbers have a certain impact on the training effectiveness of the U-Net model. The most suitable model parameters improved the training effectiveness, with the highest training accuracy achieved at a learning rate of 0.001, a batch size of 10, and 25 iterations; (3) Comparative experiments with the Support Vector Machine (SVM) model validate the suitability of U-Net model parameters and sample datasets for precise identification in rugged terrains with fragmented spatial distribution, particularly in karst mountainous regions. This underscores the applicability of the U-Net model in recognizing plastic film coverings in karst mountainous regions, offering valuable insights for agricultural environmental health assessment and green planting management in farmlands.

Bolstering stochastic gradient descent with model building

Stochastic gradient descent method and its variants constitute the core optimization algorithms that achieve good convergence rates for solving machine learning problems. These rates are obtained especially when these algorithms are fine-tuned for the application at hand. Although this tuning process can require large computational costs, recent work has shown that these costs can be reduced by line search methods that iteratively adjust the step length. We propose an alternative approach to stochastic line search by using a new algorithm based on forward step model building. This model building step incorporates second-order information that allows adjusting not only the step length but also the search direction. Noting that deep learning model parameters come in groups (layers of tensors), our method builds its model and calculates a new step for each parameter group. This novel diagonalization approach makes the selected step lengths adaptive. We provide convergence rate analysis, and experimentally show that the proposed algorithm achieves faster convergence and better generalization in well-known test problems. More precisely, SMB requires less tuning, and shows comparable performance to other adaptive methods.

Causal Reinforcement Learning for Knowledge Graph Reasoning

Knowledge graph reasoning can deduce new facts and relationships, which is an important research direction of knowledge graphs. Most of the existing methods are based on end-to-end reasoning which cannot effectively use the knowledge graph, so consequently the performance of the method still needs to be improved. Therefore, we combine causal inference with reinforcement learning and propose a new framework for knowledge graph reasoning. By combining the counterfactual method in causal inference, our method can obtain more information as prior knowledge and integrate it into the control strategy in the reinforcement model. The proposed method mainly includes the steps of relationship importance identification, reinforcement learning framework design, policy network design, and the training and testing of the causal reinforcement learning model. Specifically, a prior knowledge table is first constructed to indicate which relationship is more important for the problem to be queried; secondly, designing state space, optimization, action space, state transition and reward, respectively, is undertaken; then, the standard value is set and compared with the weight value of each candidate edge, and an action strategy is selected according to the comparison result through prior knowledge or neural network; finally, the parameters of the reinforcement learning model are determined through training and testing. We used four datasets to compare our method to the baseline method and conducted ablation experiments. On dataset NELL-995 and FB15k-237, the experimental results show that the MAP scores of our method are 87.8 and 45.2, and the optimal performance is achieved.

Asynchronous Robust Aggregation Method with Privacy Protection for IoV Federated Learning

Due to the wide connection range and open communication environment of internet of vehicle (IoV) devices, they are susceptible to Byzantine attacks and privacy inference attacks, resulting in security and privacy issues in IoV federated learning. Therefore, there is an urgent need to study IoV federated learning methods with privacy protection. However, the heterogeneity and resource limitations of IoV devices pose significant challenges to the aggregation of federated learning model parameters. Therefore, this paper proposes an asynchronous robust aggregation method with privacy protection for federated learning in IoVs. Firstly, we design an asynchronous grouping robust aggregation algorithm based on delay perception, combines intra-group truth estimation with inter-group delay aggregation, and alleviates the impact of stragglers and Byzantine attackers. Then, we design a communication-efficient and security enhanced aggregation protocol based on homomorphic encryption, to achieve asynchronous group robust aggregation while protecting data privacy and reducing communication overhead. Finally, the simulation results indicate that the proposed scheme could achieve a maximum improvement of 41.6% in model accuracy compared to the baseline, which effectively enhances the training efficiency of the model while providing resistance to Byzantine attacks and privacy inference attacks.

Learning the Optimal Representation Dimension for Restricted Boltzmann Machines

Hyperparameters refer to a set of parameters of a machine learning model that are fixed and not adjusted during training. A fundamental problem in this context is hyperparameter tuning which refers to the problem of identifying the best values for a set of model hyperparameters for a given task. In particular, model performance strongly depends on the choice of hyperparameters, and the right choice often determines the difference between average and stateof- the-art performance. This becomes especially important in models with many hyperparameters, as is common in deep learning models (DL) and automated machine learning (AutoML). However, finding the best set of hyperparameters for a model faced with a given task is very difficult in general, given the large state space and the high computational cost of assessing the quality of a given set of hyperparameters.

Epileptic seizure detection using machine learning on electroencephalogram data

It is estimated that more than 1% of people in the US have epilepsy, a life-threatening neurological disease characterized by recurrent, unprovoked seizures, due to abnormal electrical activity in the brain. The diagnostic process for epilepsy is very extensive and results in many misdiagnoses. We hypothesized that the implementation of machine learning, specifically utilizing Support Vector Machine (SVM), on preprocessed electroencephalogram (EEG) data would lead to improved accuracy in detecting epileptic seizures. Our study explored the application of machine learning in epileptic seizure detection using EEG data and aimed to improve the accuracy while limiting false positives. The study utilized a preprocessed EEG dataset and evaluated five machine learning models—Logistic Regression, K Nearest Neighbors (kNN), Random Forest, Neural Network, and SVM. We optimized model performance using hyperparameter tuning, the process of optimizing the parameters of a machine learning model to improve its performance, with a particular emphasis on recall. Results reveal that the SVM model outperforms others, achieving an accuracy of 96.77%, precision of 94.27%, and recall of 88.87%. We concluded by underscoring the need for further research to enhance model metrics, encompassing diverse datasets, alternative preprocessing techniques, and addressing privacy issues. This work contributes to advancing epilepsy diagnosis through machine learning applications, with implications for future developments in healthcare.

An outlier removal method based on PCA-DBSCAN for blood-SERS data analysis.

Surface-enhanced Raman spectroscopy (SERS) has shown promising potential in cancer screening. In practical applications, Raman spectra are often affected by deviations from the spectrometer, changes in measurement environments, and anomalies in spectrum characteristic peak intensities due to improper sample storage. Previous research has overlooked the presence of outliers in categorical data, leading to significant impacts on model learning outcomes. In this study, we propose a novel method, called Principal Component Analysis and Density Based Spatial Clustering of Applications with Noise (PCA-DBSCAN) to effectively remove outliers. This method employs dimensionality reduction and spectral data clustering to identify and remove outliers. The PCA-DBSCAN method introduces adjustable parameters (Eps and MinPts) to control the clustering effect. The effectiveness of the proposed PCA-DBSCAN method is verified through modeling on outlier-removed datasets. Further refinement of the machine learning model and PCA-DBSCAN parameters resulted in the best cancer screening model, achieving 97.41% macro-average recall and 97.74% macro-average F1-score. This paper introduces a new outlier removal method that significantly improves the performance of the SERS cancer screening model. Moreover, the proposed method serves as inspiration for outlier detection in other fields, such as biomedical research, environmental monitoring, manufacturing, quality control, and hazard prediction.