Ordering Points To Identify The Clustering Structure Research Articles

APPLICATION OF CLUSTERING METHODS FOR DETECTING NETWORK THREATS

The objective of this article is to explore the possibilities of identifying network attacks using cluster analysis methods. Density-based spatial clustering of applications with noise (DBSCAN) and the ordering points to identify the clustering structure (OPTICS) algorithm have been implemented on data representing a simulated network. The findings reveal the most effective algorithmic combinations for distinguishing between regular connections and data associated with network intrusions.

Ship collision avoidance decision-making research in coastal waters considering uncertainty of target ships

Ship collision avoidance has always been a concern and it is crucial for achieving safe navigation of ships at sea. There are many studies on ship collision avoidance in open water, but less attention on coastal waters considering the uncertainty of target ships due to the complexity of the environment and traffic flow. In this paper, collision avoidance decision-making research in coastal waters considering the uncertainty of target ships was proposed. Firstly, accurate ship trajectories are obtained by preprocessing the raw Automatic Identification System (AIS) data. Subsequently, the processed trajectories are clustered using the Ordering Points to Identify the Clustering Structure (OPTICS) algorithm and Hausdorff distance, acquiring a dataset for trajectory prediction of target ships. Then, a mixed Gaussian model is utilized to calculate the prior probability distribution of the prediction model, thus establishing a trajectory prediction model that considers the uncertainty of the target ship. Finally, ship maneuverability is simulated using the Mathematical Model Group (MMG) and Proportion Integration Differentiation (PID) models, and a collision avoidance decision-making model for ships is constructed. The proposed algorithm has been tested and verified in a case study. The results show that the approach effectively predicts the trajectory of the target ship and facilitates informed collision avoidance decision-making.

A comprehensive evaluation of OPTICS, GMM and K-means clustering methodologies for geochemical anomaly detection connected with sample catchment basins

The process of data-driven clustering to uncover geochemical anomalies linked to sample catchment basins (SCBs) includes a comprehensive framework to discern areas exhibiting unique geochemical attributes within a specified study area. The Ordering Points to Identify the Clustering Structure (OPTICS) method can serve as a robust methodology for detecting geochemical anomalies in SCBs. This is attributed to its capacity to effectively manage varying cluster densities, adaptively identify cluster numbers, exhibit resilience to noise, and display minimum sensitivity to parameters. A comparison was conducted in this research between the outcomes of the OPTICS clustering algorithm and two traditional clustering techniques, namely the Gaussian Mixture Model (GMM) and K-means clustering. In the following, the Expectation-Maximization (EM) technique is employed to train the GMM for clustering. Moreover, the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) as two validate statistical metrics implemented to ascertain the optimal number of components (clusters) belong to the GMM. It should be noted that the effectiveness of the clustering algorithms was further assessed using the Calinski-Harabasz (CH) index and the success-rate curves. OPTICS, a density-based clustering approach, was confirmed to be more effective than K-means and GMM for identifying MVT PbZn anomalies in Varcheh district, western Iran. Furthermore, the specified anomalies show a geo-spatial correspondence with the geological facts, and it has been observed that strong anomalies are more discoverable in close proximity to MVT PbZn occurrences. This work suggests a novel anomaly detection approach based on OPTICS, which exhibits superior performance and data-modeling efficiency. The main emphasis is on effectively distinguishing geochemical anomalies from sample data originating from populations with uncertain distributions.

A Density-Based Multilevel Terrain-Adaptive Noise Removal Method for ICESat-2 Photon-Counting Data.

The photon point clouds collected by the high-sensitivity single-photon detector on the Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) are utilized in various applications. However, the discretely distributed noise among the signal photons greatly increases the difficulty of signal extraction, especially the edge noise adjacent to signals. To detect signal photons from vegetation coverage areas at different slopes, this paper proposes a density-based multilevel terrain-adaptive noise removal method (MTANR) that identifies noise in a coarse-to-fine strategy based on the distribution of noise photons and is evaluated with high-precision airborne LiDAR data. First, the histogram-based successive denoising method was used as a coarse denoising process to remove distant noise and part of the sparse noise, thereby increasing the fault tolerance of the subsequent steps. Second, a rotatable ellipse that adaptively corrects the direction and shape based on the slope was utilized to search for the optimal filtering direction (OFD). Based on the direction, sparse noise removal was accomplished robustly using the Otsu's method in conjunction with the ordering points to identify the clustering structure (OPTICS) and provide a nearly noise-free environment for edge searching. Finally, the edge noise was removed by near-ground edge searching, and the signal photons were better preserved by the surface lines. The proposed MTANR was validated in four typical experimental areas: two in Baishan, China, and two in Taranaki, New Zealand. A comparison was made with three other representative methods, namely differential, regressive, and Gaussian adaptive nearest neighbor (DRAGANN), used in ATL08 products, local distance statistics (LDS), and horizontal ellipse-based OPTICS. The results demonstrated that the values of the F1 score for the signal photon identification achieved by the proposed MTANR were 0.9762, 0.9857, 0.9839, and 0.9534, respectively, which were higher than those of the other methods mentioned above. In addition, the qualitative and quantitative results demonstrated that MTANR outperformed in scenes with steep slopes, abrupt terrain changes, and uneven vegetation coverage.

A new transfer entropy approach based on information granulation and clustering for root cause analysis

In complex industrial facilities, a fault may generate in a unit and easily propagate to other units, resulting in degraded performance of process operations and deteriorating the situation. Therefore, it is of great importance to trace the propagation of faults and locate the root causes. The non-parametric causality inference technique known as Transfer Entropy (TE) is successful in identifying cause–effect relations for both nonlinear and linear processes. Even though, TE has two drawbacks limiting its practical use in real industries: (1) It requires the studied process be stationary whereas the presence of faults may lead to nonstationary changes; (2) The computational complexity of TE is high while the real application could be sensitive to the computational cost. Motivated by these issues, this paper proposes a new transfer entropy approach based on the information granulation and clustering to identify the root causes of faults. The contributions of the proposed approach are twofold: (1) the Information Granulation based Transfer Entropy (IGTE) and Information Granulation based Direct Transfer Entropy (IGDTE) are proposed to infer causal and direct causal relations; (2) an Ordering Points To Identify the Clustering Structure (OPTICS) clustering based Probability Density Function (PDF) estimator is designed to estimate joint/conditional probabilities based on the information granule. Two case studies are used to illustrate the effectiveness of the proposed approach.

Research on Multilevel Filtering Algorithm Used for Denoising Strong and Weak Beams of Daytime Photon Cloud Data with High Background Noise

The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) is equipped with the Advanced Topographic Laser Altimeter System (ATLAS), which can achieve high-precision ground detection. However, due to its low pulse energy and high sensitivity, it is also affected by noise when obtaining data. Therefore, data denoising is critical to the subsequent processing and application. In this study, a multilevel filtering algorithm is proposed to denoise the daytime photon cloud data with high background noise. Firstly, the Random Sample Consensus (RANSAC) algorithm is used to roughly denoise the daytime photon cloud data with high background noise, and a signal point cloud buffer is established to remove most of the noise points. Subsequently, the horizontal continuity parameter is calculated based on the photon cloud data following the rough denoising process. Based on this parameter, the shape and size of the search domain of the results of the subsequent fine denoising algorithm are adaptively improved. Finally, three filtering directions (a horizontal direction, an intra-group unified direction, and an adaptive direction for each photon) are proposed, and a hybrid algorithm combining the Ordering Points to Identify the Clustering Structure (OPTICS) density clustering algorithm and the Relative Neighboring Relationship K-nearest neighbors-based noise removal (RNR−KNNB) algorithm is employed to accurately denoise the photon cloud data in the three filtering directions. Furthermore, the RANSAC algorithm based on a sliding overlap window is used to remove outliers for the weak beam fine denoising photon cloud data. The results indicate that, for the strong beams, the denoising accuracy of the multilevel filtering algorithm in the three filtering directions is comparable (Rs ≥ 0.96, F ≥ 0.67), and they are all better than that of the ATL08 algorithm (Rs/Rn/p/F = 0.85/0.67/0.52/0.65). For weak beams, the denoising accuracy of the multilevel filtering algorithm in the horizontal direction and the intra-group unified direction is similar (Rs = 0.92, F = 0.69), and it is superior to the denoising results in the adaptive direction of each photon and the ATL08 algorithm (Rs/Rn/p/F = 0.94/0.84/0.51/0.65, 0.88/0.87/0.55/0.67, respectively). For strong and weak beams, the p-value and F-value of the denoising results of multilevel filtering algorithms in three different filtering directions increase with the increase of SNR value. It is demonstrated that SNR is an important factor affecting the denoising results of algorithms. The multilevel filtering algorithm proposed in the study can effectively achieve precise denoising of daytime photon cloud data with high background noise, and the three different filtering directions have different effects on the denoising results of strong and weak beam photon cloud data. This can provide technical and methodological guidance for subsequent photon cloud data filtering processing.

APPLICATION OF MULTISTAGE CLUSTERING FOR MAPPING ECONOMIC POTENTIAL IN EAST JAVA PROVINCE

This study aims to map the economic potential in East Java Province based on GRDP according to business field category. Multistage clustering is a method developed for outlier data and datasets with large variance. Multistage clustering is a combination of Ordering Points to Identify the Clustering Structure (OPTICS) and K-Means. The first stage was grouped using OPTICS. The outlier data resulting from the clustering stage is used as a dataset in the second stage using K-Means. The performance of this method is compared with several other methods, namely: K-Means, DBSCAN – K-Means, Agglomerative, Fuzzy C-Means (FCM), Possibilistic C-Means (PCM), and Fuzzy Possibilistic C-Means (FPCM) based on the characteristics of the Silhouette score and Davies-Bouldin score. Multistage clustering was chosen as the best method with a Silhouette score of 0.442 and Davies-Bouldin score of 0.388. With the Elbow method and the two metrics, the optimum number of clusters is 8 clusters. The results of this mapping method, the City of Surabaya forms a separate cluster which has the highest economic potential in 15 categories of business fields. Next Gresik, Pasuruan, Sidoarjo, and Probolinggo have the second highest economic potential with 10 categories of business fields ranking in the top 3.

Unsupervised Spectral Analysis of Bio-Dyed Textile Samples

Article Unsupervised Spectral Analysis of Bio-Dyed Textile Samples Zong-Yue Li 1,*, Joni Hyttinen 1, Riikka Räisänen 2, Xiao-Zhi Gao 1, and Markku Hauta-Kasari 1 1 School of Computing, Faculty of Science, Forestry and Technology, University of Eastern Finland, Joensuu, 80101, Kuopio, 70211, Finland 2 Department of Education, Faculty of Educational Sciences, University of Helsinki, Helsinki, 00014 , Finland * Correspondence: winstonli711@gmail.com     Received: 12 March 2023 Accepted: 23 March 2023   Abstract: Natural compounds such as biological colorants (biocolorants) have long been employed as crucial ingredients for dying textile in the textile industry. As one part of the BioColour Consortium project, our goal is to take advantage of machine learning (in cluster analysis) to discover possible clusters of bio-dyed textile in the absence of ground truth labels or other knowledge of expert domains. Specifically, we use unsupervised learning methods of agglomerative clustering, fuzzy c-means, ordering points to identify the clustering structure (OPTICS) and self-organizing maps (SOMs), resulting in an investigation that combines data visualization and cluster analysis. In summary, we apply some selected data mining methods to 1) discover hidden clusters emerging among products that are colored with biocolorant (specifically bio-dyed textile samples), and 2) show the potentials of clustering techniques in the case study.

VizOPTICS: Getting insights into OPTICS via interactive visual analysis

Ordering points to identify the clustering structure (OPTICS) is a density-based clustering algorithm that allows the exploration of the cluster structure in the dataset by outputting an ordered queue called cluster ordering. However, this nonexplicit output makes it greatly more difficult for practitioners to identify cluster patterns and obtain high-quality clusters. In this paper, we firstly investigate OPTICS in depth and identify the challenges facing users of OPTICS for cluster analysis through a pilot user study. Then, integrating human intelligence deeply with the machine intelligence of OPTICS, a visual analytics approach, VizOPTICS, is proposed to support practitioners in understanding and applying OPTICS to extract meaningful clustering results. It includes an ordered lattice plot for observing the generation process of cluster ordering, a density scatter plot for analyzing the cluster structure in datasets, and a dynamic reachability plot for optimizing clustering results, and also provides several interaction modes, such as selecting and highlighting, to help users analyze the cluster formation and algorithm operation processes interactively. Finally, we assess our approach through four case studies and a user evaluation study. The results demonstrate the effectiveness and efficiency of the system.

A noise removal algorithm based on adaptive elevation difference thresholding for ICESat-2 photon-counting data

Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) has shown great potential for near-shore bathymetry. Unavoidably, the photon data acquired has a lot of noise. In order to remove noise more accurately, a photon denoising algorithm based on adaptive elevation difference thresholding (AEDTA) is proposed under the assumption that the terrain is continuously changing. The algorithm uses a Gaussian function obtained by fitting an elevation histogram to ICESat-2 data for the extraction of underwater photons. Repeatedly count the elevation difference histogram of underwater photons and adaptively determine the threshold. And the final denoised underwater signal photons are obtained. Compared with the conventional clustering method of ordering points to identify the clustering structure (OPTICS), our algorithm achieves better photon detection results for underwater topography for different densities of ICESat-2 data and has the advantage of parameter adaption without human intervention. ICESat-2 data from Ganquan Island, Dongdao Island and Oahu Island were selected for testing, and the ICESat-2 bathymetry results calculated by the algorithm were compared with in situ bathymetry data to assess the reliability and accuracy of the proposed denoising algorithm. The results show that the MAE of the bathymetry results calculated using the ICESat-2 signal photon data extracted by the method ranged from 0.54 to 1.57 m and the RMSE ranged from 0.64 to 1.74 m in different seas. The algorithm can provide high quality denoised data for bathymetric mapping around coastal areas and islands. Meanwhile, the AEDTA algorithm also has a good denoising effect on terrestrial photons, and the effect of cloud shading on the Gaussian fit analysis of ICESat-2 data cannot be ignored.

A novel deep learning-based forecasting model optimized by heuristic algorithm for energy management of microgrid

Recently, the integration of renewable energy sources (RESs) in microgrids (MGs) has risen significantly owing to extensive promotion of decarbonization and green energy. However, despite the environmental–economic benefits, RESs are intermittent, and increasing penetration of RESs into MG poses operation challenges in handling uncertainties. In this paper, a novel deep learning-based forecasting model is proposed for MG operation considering uncertainties of RESs, load, and day-ahead price (DAP). To handle the intrinsic uncertainties of MGs, a long short-term memory (LSTM) network is employed and a method for increasing prediction accuracy of the LSTM model based on a genetic algorithm–adaptive weight particle swarm optimization (GA-AWPSO) combination along with a global attention mechanism (GAM) is proposed. Herein, the hyperparameters of the LSTM model are optimized by the GA-AWPSO algorithm, and GAM is added to mine important features from input datasets to improve forecasting performance. To handle uncertainties through the demand side, A DM-CIDR program is developed for providing optimal incentive rate strategies to participants, as different customers exhibit diverse attitudes toward remunerated incentives. In this program, ordering points to identify the clustering structure (OPTICS) and k-nearest neighbor algorithms (k-NN) are used for clustering and classification, respectively, to determine reasonable incentive rates for customers according to their bid/offer data. A simulation was implemented on historical PJM datasets, the results of which revealed the performance and superiority of the proposed approach in handling uncertainties.

Complete outlier detection and classification framework for WSNs based on OPTICS

Wireless Sensor Networks (WSNs) consist of multi-functional sensors with limited resources that collect information in various applications (medical, manufacturing, militarily, etc.). However, data gathered by sensors are susceptible to outliers, which need to be detected and classified into errors and events using outlier detection and classification methods. This paper proposes a centralised outlier detection and classification approach for WSNs, which can distinguish between errors due to a faulty sensor and those due to an event. Also, it considers the spatial–temporal correlation between neighbouring sensor nodes and sensors’ data values. Our approach, titled OPTICS-K, combines the benefits of the Ordering Points To Identify the Clustering Structure (OPTICS) algorithm for clustering, the Inter-Cluster Distance (ICD) method and the K-Nearest Neighbours (KNN) algorithm for outlier detection. Furthermore, OPTICS-K uses a new method based on Kriging interpolation to classify the outliers. For evaluation, we conduct a comparison study between OPTICS-K and two works from the literature and thus for the multivariate data case. Simulation results with both synthetic and real-life datasets show that the OPTICS-K outperforms the studied techniques in terms of several metrics like Detection Rate (DR), False Alarm Rate (FAR), Accuracy rate (ACC), F1_score and Area Under the Curve (AUC).

Instar Determination for the Tomato Leafminer Tuta absoluta (Lepidoptera: Gelechiidae) Using the Density-Based OPTICS Clustering Algorithm.

The tomato leafminer Tuta absoluta (Meyrick) is one of the most harmful pests of solanaceous crops. Its larval morphological characteristics are similar, making the distinguishing between different larval instars difficult. Accurate identification of T. absoluta instars is necessary either for population outbreak forecasting, or developing successful control programs. Although a clustering algorithm can be used to determine the number of larval instars, little is known regarding the use of density-based ordering points to identify the clustering structure (OPTICS) and determine the number of larvae. In this study, larval instars of 240 T. absoluta individuals were determined by the density-based OPTICS clustering method, based on mandible width, and head capsule width and length. To verify the feasibility of the OPTICS clustering method, we compared it with the density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm, Gaussian mixture models, and k-means. Additionally, the instars determined by the clustering methods were verified using the Brooks–Dyar rule, Crosby rule, and linear regression model. The instars determined by the OPTICS clustering method were equal to those determined by the other types of clustering algorithms, and the instar results were consistent with the Brooks–Dyar rule, Crosby rule, frequency analysis, and logarithmic regression model. These results indicated that the OPTICS clustering method is robust for determining insect larva instar phase. Moreover, it was found that three morphological indices of T. absoluta can be used for determining instars of this pest in the field, which may provide important information for the management of T. absoluta populations.

Characterising reasons for reversals of COVID-19 vaccination hesitancy among Japanese people: One-year follow-up survey

BackgroundVaccine hesitancy is a global public health threat. We present unique data that characterises those who experienced reversals of COVID-19 vaccination hesitancy in Japan.MethodsWe administered a questionnaire on vaccination intention among 30053 Japanese adults aged 20 years or older before the COVID-19 vaccination was available to the general population (first survey) and conducted a follow-up survey on vaccination status one year later in February 2022 (second survey). Those who responded in the first survey that they did not intend to be vaccinated or were unsure and then responded in the second survey that they were vaccinated or intend to be vaccinated were asked about the reasons for their change of heart. Based on previous literature and expert opinion, 31 reasons for changing vaccination intention were compiled and respondents were asked to choose which among them applied to themselves, with multiple responses possible. Based on the results of those responses, each individual was then clustered using the Uniform Manifold Approximation and Projection (UMAP) dimensionality reduction technique and Ordering Points To Identify the Clustering Structure (OPTICS) algorithm. We then identified unique characteristics among each of the sub-populations (clusters).FindingsIn the second survey we received 19195 responses (response rate 63.9%), of which 8077 responded ‘no’ or ‘not sure’ in the first survey regarding their intention to be vaccinated. Of these, 5861 responded having received or intending to receive the vaccine (72.6%). We detected six and five sub-populations (clusters) among the ‘no’ group and ‘not sure’ group, respectively. The clusters were characterized by perceived benefits of vaccination, including the COVID-19 vaccine, awareness of the COVID-19 vaccination status of those close to them, recognition of the social significance of COVID-19 vaccination for the spread of infection, and dispelled concerns about short-term adverse reactions and the safety of the COVID-19 vaccine. Work and personal relationship reasons were also found to be a unique overarching reason for vaccination changes of heart only among those who did not intend to vaccinate.InterpretationThose who changed their intention to accept COVID-19 vaccination as well as their unique characteristics as detailed in this study will be important entry points when discussing how to promote vaccination to those who are hesitant to vaccinate in the future.FundingThe present work was supported in part by a grant from the Kanagawa Prefectural Government of Japan and by AIST government subsidies.

Differential privacy preserving dynamic data release scheme based on Jensen-Shannon divergence

Health monitoring data or the data about infectious diseases such as COVID-19 may need to be constantly updated and dynamically released, but they may contain user's sensitive information. Thus, how to preserve the user's privacy before their release is critically important yet challenging. Differential Privacy (DP) is well-known to provide effective privacy protection, and thus the dynamic DP preserving data release was designed to publish a histogram to meet DP guarantee. Unfortunately, this scheme may result in high cumulative errors and lower the data availability. To address this problem, in this paper, we apply Jensen-Shannon (JS) divergence to design the OPTICS (Ordering Points To Identify The Clustering Structure) scheme. It uses JS divergence to measure the difference between the updated data set at the current release time and private data set at the previous release time. By comparing the difference with a threshold, only when the difference is greater than the threshold, can we apply OPTICS to publish DP protected data sets. Our experimental results show that the absolute errors and average relative errors are significantly lower than those existing works.

Discovery of new drug indications for COVID-19: A drug repurposing approach.

MotivationThe outbreak of coronavirus health issues caused by COVID-19(SARS-CoV-2) creates a global threat to public health. Therefore, there is a need for effective remedial measures using existing and approved therapies with proven safety measures has several advantages. Dexamethasone (Pubchem ID: CID0000005743), baricitinib(Pubchem ID: CID44205240), remdesivir (PubchemID: CID121304016) are three generic drugs that have demonstrated in-vitro high antiviral activity against SARS-CoV-2. The present study aims to widen the search and explore the anti-SARS-CoV-2 properties of these potential drugs while looking for new drug indications with optimised benefits via in-silico research.MethodHere, we designed a unique drug-similarity model to repurpose existing drugs against SARS-CoV-2, using the anti-Covid properties of dexamethasone, baricitinib, and remdesivir as references. Known chemical-chemical interactions of reference drugs help extract interactive compounds withimprovedanti-SARS-CoV-2 properties. Here, we calculated the likelihood of these drug compounds treating SARS-CoV-2 related symptoms using chemical-protein interactions between the interactive compounds of the reference drugs and SARS-CoV-2 target genes. In particular, we adopted a two-tier clustering approach to generate a drug similarity model for the final selection of potential anti-SARS-CoV-2 drug molecules. Tier-1 clustering was based on t-Distributed Stochastic Neighbor Embedding (t-SNE) and aimed to filter and discard outlier drugs. The tier-2 analysis incorporated two cluster analyses performed in parallel using Ordering Points To Identify the Clustering Structure (OPTICS) and Hierarchical Agglomerative Clustering (HAC). As a result, itidentified clusters of drugs with similar actions. In addition, we carried out a docking study for in-silico validation of top candidate drugs.ResultOur drug similarity model highlighted ten drugs, including reference drugs that can act as potential therapeutics against SARS-CoV-2. The docking results suggested that doxorubicin showed the least binding energy compared to reference drugs. Their practical utility as anti-SARS-CoV-2 drugs, either individually or in combination, warrants further investigation.

Federated Learning Based on OPTICS Clustering Optimization

Federated learning (FL) has emerged for solving the problem of data fragmentation and isolation in machine learning based on privacy protection. Each client node uploads the trained model parameter information to the central server based on the local training data, and the central server aggregates the parameter information to achieve the purpose of common training. In the real environment, the distribution of data among nodes is often inconsistent. By analyzing the influence of independent identically distributed data (non-IID) on the accuracy of FL, it is shown that the accuracy of the model obtained by the traditional FL method is low. Therefore, we proposed the diversified sampling strategies to simulate the non-IID data situation and came up with the OPTICS (ordering points to identify the clustering structure)-based clustering optimization federated learning method (OCFL), which solves the problem that the learning accuracy is reduced when the data of different nodes are non-IID in FL. Experiments indicate that OCFL greatly improves the model accuracy and training speed compared with the traditional FL algorithm.

Visual Analysis of Vessel Behaviour Based on Trajectory Data: A Case Study of the Yangtze River Estuary

The widespread of shipborne Automatic Identification System (AIS) equipment will continue to produce a large amount of spatiotemporal trajectory data. In order to explore and understand the hidden behaviour patterns in the data, an interactive visual analysis method combining multiple views is proposed. The method mainly includes four parts: using a trajectory compression algorithm that takes into account the vessel motion characteristics to preprocess the vessel trajectory data; displaying and replaying vessel trajectories based on Electronic Chart System (ECS), and proposing a detection algorithm for vessel stay points based on the principle of spatiotemporal density to semantically label vessel trajectories; using the Fast Dynamic Time Warping (FastDTW) similarity measurement algorithm and the Ordering Points to Identify the Clustering Structure (OPTICS) clustering algorithm to cluster vessel trajectories to show the differences and similarities between vessel traffic flows; and showing the distribution of vessels and the variation trend of vessel density based on the vessel heatmap. Based on the AIS data of the Yangtze River Estuary, three cases are used to prove the usefulness and effectiveness of the system in vessel behaviour analysis.

A Data-Driven Customer-Search Modeling With the Consideration of Traffic Environment.

In order to explore the determinants of vacant taxi drivers' customer-search behavior, this paper intends to calibrate a time-dependent Multinomial Logit (MNL) model by mining over 1.6 billion GPS records from about 8,400 taxis in Shanghai, China. First, based on the ordering points to identify the clustering structure (OPTICS) algorithm, the downtown area of Shanghai city is divided into 47 hotspots to identify the hot areas of customer delivery and searching. Then, by investigating a typical search delivery process of a vacant taxi, five candidate factors that may affect the customer-search behavior are summarized and defined. Using the maximum likelihood method, the significant factors are finally found. The results reveal that the relative passenger demand, the regional likelihood of pick-ups as well as the expected rate of return are the most significant factors influencing customer-search behavior. Although the impact of traffic situation (i.e., the en-route delay and traffic condition of the target hotspot) is not particularly significant, service providers and policymakers should still take full advantage of it to schedule taxi service and mitigate the traffic congestion caused by the circulation of vacant taxis. Besides, this paper also shows that the customer-search behavior of a vacant taxi driver varies with the time of day. Findings in this paper are expected to provide comprehensive insights about factors that should be considered in the future operation pattern of a taxi service system where human driver taxis and self-driving taxis are mixed.

Exploring Unsupervised Machine Learning Classification Methods for Physiological Stress Detection.

Over the past decade, there has been a significant development in wearable health technologies for diagnosis and monitoring, including application to stress monitoring. Most of the wearable stress monitoring systems are built on a supervised learning classification algorithm. These systems rely on the collection of sensor and reference data during the development phase. One of the most challenging tasks in physiological or pathological stress monitoring is the labeling of the physiological signals collected during an experiment. Commonly, different types of self-reporting questionnaires are used to label the perceived stress instances. These questionnaires only capture stress levels at a specific point in time. Moreover, self-reporting is subjective and prone to inaccuracies. This paper explores the potential feasibility of unsupervised learning clustering classifiers such as Affinity Propagation, Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH), K-mean, Mini-Batch K-mean, Mean Shift, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Ordering Points To Identify the Clustering Structure (OPTICS) for implementation in stress monitoring wearable devices. Traditional supervised machine learning (linear, ensembles, trees, and neighboring models) classifiers require hand-crafted features and labels while on the other hand, the unsupervised classifier does not require any labels of perceived stress levels and performs classification based on clustering algorithms. The classification results of unsupervised machine learning classifiers are found comparable to supervised machine learning classifiers on two publicly available datasets. The analysis and results of this comparative study demonstrate the potential of unsupervised learning for the development of non-invasive, continuous, and robust detection and monitoring of physiological and pathological stress.