A wave delay neural network for solving label-constrained shortest route query on time-varying communication networks.

The focus of the research is on the label-constrained time-varying shortest route query problem on time-varying communication networks. To the best of our knowledge, research on this issue is still relatively limited, and similar studies have the drawbacks of low solution accuracy and slow computational speed. In this study, a wave delay neural network (WDNN) framework and corresponding algorithms is proposed to effectively solve the label-constrained time-varying shortest routing query problem. This framework accurately simulates the time-varying characteristics of the network without any training requirements. WDNN adopts a new type of wave neuron, which is independently designed and all neurons are parallelly computed on WDNN. This algorithm determines the shortest route based on the waves received by the destination neuron (node). Furthermore, the time complexity and correctness of the proposed algorithm were analyzed in detail in this study, and the performance of the algorithm was analyzed in depth by comparing it with existing algorithms on randomly generated and real networks. The research results indicate that the proposed algorithm outperforms current existing algorithms in terms of response speed and computational accuracy.

Harnessing PubMed User Query Logs for Post Hoc Explanations of Recommended Similar Articles.

Searching for a related article based on a reference article is an integral part of scientific research. PubMed, like many academic search engines, has a "similar articles" feature that recommends articles relevant to the current article viewed by a user. Explaining recommended items can be of great utility to users, particularly in the literature search process. With more than a million biomedical papers being published each year, explaining the recommended similar articles would facilitate researchers and clinicians in searching for related articles. Nonetheless, the majority of current literature recommendation systems lack explanations for their suggestions. We employ a post hoc approach to explaining recommendations by identifying relevant tokens in the titles of similar articles. Our major contribution is building PubCLogs by repurposing 5.6 million pairs of coclicked articles from PubMed's user query logs. Using our PubCLogs dataset, we train the Highlight Similar Article Title (HSAT), a transformer-based model designed to select the most relevant parts of the title of a similar article, based on the title and abstract of a seed article. HSAT demonstrates strong performance in our empirical evaluations, achieving an F1 score of 91.72 percent on the PubCLogs test set, considerably outperforming several baselines including BM25 (70.62), MPNet (67.11), MedCPT (62.22), GPT-3.5 (46.00), and GPT-4 (64.89). Additional evaluations on a separate, manually annotated test set further verifies HSAT's performance. Moreover, participants of our user study indicate a preference for HSAT, due to its superior balance between conciseness and comprehensiveness. Our study suggests that repurposing user query logs of academic search engines can be a promising way to train state-of-the-art models for explaining literature recommendation.

Improved object detection method for unmanned driving based on Transformers.

The object detection method serves as the core technology within the unmanned driving perception module, extensively employed for detecting vehicles, pedestrians, traffic signs, and various objects. However, existing object detection methods still encounter three challenges in intricate unmanned driving scenarios: unsatisfactory performance in multi-scale object detection, inadequate accuracy in detecting small objects, and occurrences of false positives and missed detections in densely occluded environments. Therefore, this study proposes an improved object detection method for unmanned driving, leveraging Transformer architecture to address these challenges. First, a multi-scale Transformer feature extraction method integrated with channel attention is used to enhance the network's capability in extracting features across different scales. Second, a training method incorporating Query Denoising with Gaussian decay was employed to enhance the network's proficiency in learning representations of small objects. Third, a hybrid matching method combining Optimal Transport and Hungarian algorithms was used to facilitate the matching process between predicted and actual values, thereby enriching the network with more informative positive sample features. Experimental evaluations conducted on datasets including KITTI demonstrate that the proposed method achieves 3% higher mean Average Precision (mAP) than that of the existing methodologies.

GBDT Method Integrating Feature-Enhancement and Active-Learning Strategies-Sea Ice Thickness Inversion in Beaufort Sea.

Sea ice, as an important component of the Earth's ecosystem, has a profound impact on global climate and human activities due to its thickness. Therefore, the inversion of sea ice thickness has important research significance. Due to environmental and equipment-related limitations, the number of samples available for remote sensing inversion is currently insufficient. At high spatial resolutions, remote sensing data contain limited information and noise interference, which seriously affect the accuracy of sea ice thickness inversion. In response to the above issues, we conducted experiments using ice draft data from the Beaufort Sea and designed an improved GBDT method that integrates feature-enhancement and active-learning strategies (IFEAL-GBDT). In this method, the incident angle and time series are used to perform spatiotemporal correction of the data, reducing both temporal and spatial impacts. Meanwhile, based on the original polarization information, effective multi-attribute features are generated to expand the information content and improve the separability of sea ice with different thicknesses. Taking into account the growth cycle and age of sea ice, attributes were added for month and seawater temperature. In addition, we studied an active learning strategy based on the maximum standard deviation to select more informative and representative samples and improve the model's generalization ability. The improved GBDT model was used for training and prediction, offering advantages in dealing with nonlinear, high-dimensional data, and data noise problems, further expanding the effectiveness of feature-enhancement and active-learning strategies. Compared with other methods, the method proposed in this paper achieves the best inversion accuracy, with an average absolute error of 8 cm and a root mean square error of 13.7 cm for IFEAL-GBDT and a correlation coefficient of 0.912. This research proves the effectiveness of our method, which is suitable for the high-precision inversion of sea ice thickness determined using Sentinel-1 data.

User-centric design of a 3D search interface for protein-ligand complexes.

In this work, we present the frontend of GeoMine and showcase its application, focusing on the new features of its latest version. GeoMine is a search engine for ligand-bound and predicted empty binding sites in the Protein Data Bank. In addition to its basic text-based search functionalities, GeoMine offers a geometric query type for searching binding sites with a specific relative spatial arrangement of chemical features such as heavy atoms and intermolecular interactions. In contrast to a text search that requires simple and easy-to-formulate user input, a 3D input is more complex, and its specification can be challenging for users. GeoMine's new version aims to address this issue from the graphical user interface perspective by introducing an additional visualization concept and a new query template type. In its latest version, GeoMine extends its query-building capabilities primarily through input formulation in 2D. The 2D editor is fully synchronized with GeoMine's 3D editor and provides the same functionality. It enables template-free query generation and template-based query selection directly in 2D pose diagrams. In addition, the query generation with the 3D editor now supports predicted empty binding sites for AlphaFold structures as query templates. GeoMine is freely accessible on the ProteinsPlus web server ( https://proteins.plus ).

Studying Plant Specialized Metabolites Using Computational Metabolomics Strategies.

Plant specialized metabolites have diversified vastly over the course of plant evolution, and they are considered key players in complex interactions between plants and their environment. The chemical diversity of these metabolites has been widely explored and utilized in agriculture and crop enhancement, the food industry, and drug development, among other areas. However, the immensity of the plant metabolome can make its exploration challenging. Here we describe a protocol for exploring plant specialized metabolites that combines high-resolution mass spectrometry and computational metabolomics strategies, including molecular networking, identification of structural motifs, as well as prediction of chemical structures and metabolite classes.

On the relevance of query definition in the performance of 3D ligand-based virtual screening.

Ligand-based virtual screening (LBVS) methods are widely used to explore the vast chemical space in the search of novel compounds resorting to a variety of properties encoded in 1D, 2D or 3D descriptors. The success of 3D-LBVS is affected by the overlay of molecular pairs, thus making selection of the template compound, search of accessible conformational space and choice of the query conformation to be potential factors that modulate the successful retrieval of actives. This study examines the impact of adopting different choices for the query conformation of the template, paying also attention to the influence exerted by the structural similarity between templates and actives. The analysis is performed using PharmScreen, a 3D LBVS tool that relies on similarity measurements of the hydrophobic/philic pattern of molecules, and Phase Shape, which is based on the alignment of atom triplets followed by refinement of the volume overlap. The study is performed for the original DUD-E+ database and a Morgan Fingerprint filtered version (denoted DUD-E+-Diverse; available in https://github.com/Pharmacelera/Query-models-to-3DLBVS ), which was prepared to minimize the 2D resemblance between template and actives. Although in most cases the query conformation exhibits a mild influence on the overall performance, a critical analysis is made to disclose factors, such as the content of structural features between template and actives and the induction of conformational strain in the template, that underlie the drastic impact of the query definition in the recovery of actives for certain targets. The findings of this research also provide valuable guidance for assisting the selection of the query definition in 3D LBVS campaigns.

A Survey of Techniques for Discovering, Using, and Paying for Third-Party IoT Sensors.

The Internet of Things (IoT) includes billions of sensors and actuators (which we refer to as IoT devices) that harvest data from the physical world and send it via the Internet to IoT applications to provide smart IoT services and products. Deploying, managing, and maintaining IoT devices for the exclusive use of an individual IoT application is inefficient and involves significant costs and effort that often outweigh the benefits. On the other hand, enabling large numbers of IoT applications to share available third-party IoT devices, which are deployed and maintained independently by a variety of IoT device providers, reduces IoT application development costs, time, and effort. To achieve a positive cost/benefit ratio, there is a need to support the sharing of third-party IoT devices globally by providing effective IoT device discovery, use, and pay between IoT applications and third-party IoT devices. A solution for global IoT device sharing must be the following: (1) scalable to support a vast number of third-party IoT devices, (2) interoperable to deal with the heterogeneity of IoT devices and their data, and (3) IoT-owned, i.e., not owned by a specific individual or organization. This paper surveys existing techniques that support discovering, using, and paying for third-party IoT devices. To ensure that this survey is comprehensive, this paper presents our methodology, which is inspired by Systematic Literature Network Analysis (SLNA), combining the Systematic Literature Review (SLR) methodology with Citation Network Analysis (CNA). Finally, this paper outlines the research gaps and directions for novel research to realize global IoT device sharing.

BacteSign: Building a Findable, Accessible, Interoperable, and Reusable (FAIR) Database for Universal Bacterial Identification.

With the increasing incidence of diverse global bacterial outbreaks, it is important to build an immutable decentralized database that can capture regional changes in bacterial resistance with time. Herein, we investigate the use of a rapid 3D printed µbiochamber with a laser-ablated interdigitated electrode developed for biofilm analysis of Pseudomonas aeruginosa, Acinetobacter baumannii and Bacillus subtilis using electrochemical biological impedance spectroscopy (EBIS) across a 48 h spectrum, along with novel ladder-based minimum inhibitory concentration (MIC) stencil tests against oxytetracycline, kanamycin, penicillin G and streptomycin. Furthermore, in this investigation, a search query database has been built demonstrating the deterministic nature of the bacterial strains with real and imaginary impedance, phase, and capacitance, showing increased bacterial specification selectivity in the 9772.37 Hz range.

LollipopE: Bi-centered lollipop embedding for complex logic query on knowledge graph.

Answering complex First-Order Logic (FOL) query plays a vital role in multi-hop knowledge graph (KG) reasoning. Geometric methods have emerged as a promising category of approaches in this context. However, existing best-performing geometric query embedding (QE) model is still up against three-fold potential problems: (i) underutilization of embedding space, (ii) overreliance on angle information, (iii) uncaptured hierarchy structure. To bridge the gap, we propose a lollipop-like bi-centered query embedding method named LollipopE. To fully utilize embedding space, LollipopE employs learnable centroid positions to represent multiple entities distributed along the same axis. To address the potential overreliance on angular metrics, we design an angular-based and centroid-based metric. This involves calculating both an angular distance and a centroid-based geodesic distance, which empowers the model to make more informed selections of relevant answers from a wider perspective. To effectively capture the hierarchical relationships among entities within the KG, we incorporate dynamic moduli, which allows for the representation of the hierarchical structure among entities. Extensive experiments demonstrate that LollipopE surpasses the state-of-the-art geometric methods. Especially, on more hierarchical datasets, LollipopE achieves the most significant improvement.

REDCapDM: An R package with a set of data management tools for a REDCap project.

BACKGROUND: Research Electronic Data CAPture (REDCap) is a web application for creating and managing online surveys and databases. Clinical data management is an essential process before performing any statistical analysis to ensure the quality and reliability of study information. Processing REDCap data in R can be complex and often benefits from automation. While there are several R packages available for specific tasks, none offer an expansive approach to data management. RESULTS: The REDCapDM is an R package for accessing and managing REDCap data. It imports data from REDCap to R using either an API connection or the files in R format exported directly from REDCap. It has several functions for data processing and transformation, and it helps to generate and manage queries to clarify or resolve discrepancies found in the data. CONCLUSION: The REDCapDM package is a valuable tool for data scientists and clinical data managers who use REDCap and R. It assists in tasks such as importing, processing, and quality-checking data from their research studies.

A phrase-based questionnaire-answering approach for automatic initial frailty assessment based on clinical notes.

Frailty stands out as a particularly challenging multidimensional geriatric syndrome in the elderly population, often resulting in diminished quality of life and heightened mortality risk. Negative consequences encompass a heightened likelihood of hospitalization and institutionalization, as well as suboptimal post-hospitalization outcomes and elevated mortality rates. Using a questionnaire-based approach for assessing frailty has been shown to be an effective method for early diagnosis of frailty. Nonetheless, the majority of current frailty assessment tools necessitate in-person consultations. This poses a significant challenge for elderly patients residing in rural areas, who often encounter difficulties in accessing healthcare compared to their urban or suburban counterparts. Additionally, elderly patients face an elevated risk of contracting diseases as a result of frequent hospital visits, given that many of them are immunocompromised. An automated initial frailty assessment approach can help mitigate the challenges mentioned above and conserve clinical resources by circumventing the need for extensive manual assessments. The primary aim of this paper is to introduce an automatic initial frailty assessment method. This method efficiently identifies individuals who may necessitate further frailty evaluation by automatically extracting relevant information from a patient's clinical notes and using it to complete the Tillburg Frailty Indicator (TFI) questionnaire. The introduced phrase-based query expansion technique is designed to identify the most pertinent phrases related to the frailty assessment questionnaire using Unified Medical Language System (UMLS) ontology and incorporates information from clinical notes to enhance its accuracy. Additionally, a method for retrieving pertinent clinical notes to automatically facilitate the frailty assessment process based on the identified phrases was also proposed. The proposed approaches are evaluated using a dataset containing a collection of clinical notes from elderly patients, assessing their effectiveness in terms of automating frailty assessment and question-answering tasks. This research underscores the significance of incorporating phrases as features in the automated frailty assessment process using clinical notes. The research empowers clinicians to conduct automatic frailty assessments utilizing medical data, thereby reducing the need for frequent hospital visits and in-patient consultations. This becomes particularly valuable during unusual or unexpected situations, such as the COVID-19 pandemic, where minimizing in-person interactions is crucial.

Hierarchical matching and reasoning for multi-query image retrieval.

As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the semantically relevant image given multiple region-specific text queries. Existing works mainly focus on a single-level similarity between image regions and text queries, which neglect the hierarchical guidance of multi-level similarities and result in incomplete alignments. Besides, the high-level semantic correlations that intrinsically connect different region-query pairs are rarely considered. To address above limitations, we propose a novel Hierarchical Matching and Reasoning Network (HMRN) for MQIR. It disentangles MQIR into three hierarchical semantic representations, which is responsible to capture fine-grained local details, contextual global scopes, and high-level inherent correlations. HMRN consists of two modules: Scalar-based Matching (SM) module and Vector-based Reasoning (VR) module. Specifically, the SM module characterizes the multi-level alignment similarity, which consists of a fine-grained local-level similarity and a context-aware global-level similarity. Afterwards, the VR module is developed to excavate the potential semantic correlations among multiple region-query pairs, which further explores the high-level reasoning similarity. Finally, these three-level similarities are aggregated into a joint similarity space to form the ultimate similarity. Extensive experiments on the benchmark dataset demonstrate that our HMRN substantially surpasses the current state-of-the-art methods. For instance, compared with the existing best method Drill-down, the metric R@1 in the last round is improved by 23.4%. Our source codes will be released at https://github.com/LZH-053/HMRN.

The Utility of AI in Writing a Scientific Review Article on the Impacts of COVID-19 on Musculoskeletal Health.

PURPOSE OF REVIEW: There were two primary purposes to our reviews. First, to provide an update to the scientific community about the impacts of COVID-19 on musculoskeletal health. Second, was to determine the value of using a large language model, ChatGPT 4.0, in the process of writing a scientific review article. To accomplish these objectives, we originally set out to write three review articles on the topic using different methods to produce the initial drafts of the review articles. The first review article was written in the traditional manner by humans, the second was to be written exclusively using ChatGPT (AI-only or AIO), and the third approach was to input the outline and references selected by humans from approach 1 into ChatGPT, using the AI to assist in completing the writing (AI-assisted or AIA). All review articles were extensively fact-checked and edited by all co-authors leading to the final drafts of the manuscripts, which were significantly different from the initial drafts. RECENT FINDINGS: Unfortunately, during this process, it became clear that approach 2 was not feasible for a very recent topic like COVID-19 as at the time, ChatGPT 4.0 had a cutoff date of September 2021 and all articles published after this date had to be provided to ChatGPT, making approaches 2 and 3 virtually identical. Therefore, only two approaches and two review articles were written (human and AI-assisted). Here we found that the human-only approach took less time to complete than the AI-assisted approach. This was largely due to the number of hours required to fact-check and edit the AI-assisted manuscript. Of note, the AI-assisted approach resulted in inaccurate attributions of references (about 20%) and had a higher similarity index suggesting an increased risk of plagiarism. The main aim of this project was to determine whether the use of AI could improve the process of writing a scientific review article. Based on our experience, with the current state of technology, it would not be advised to solely use AI to write a scientific review article, especially on a recent topic.

A query-response causal analysis of reaction events in biochemical reaction networks.

The stochastic kinetics of biochemical reaction networks is described by a chemical master equation (CME) and the underlying laws of mass action. Assuming network-free simulations of the rule-based models of biochemical reaction networks (BRNs), this paper departs from the usual analysis of network dynamics as the time-dependent distributions of chemical species counts, and instead considers statistically evaluating the sequences of reaction events generated from the stochastic simulations. The reaction event-time series can be used for reaction clustering, identifying rare events, and recognizing the periods of increased or steady-state activity. However, the main aim of this paper is to device an effective method for identifying causally and anti-causally related sub-sequences of reaction events using their empirical probabilities. This allows discovering some of the causal dynamics of BRNs as well as uncovering their short-term deterministic behaviors. In particular, it is proposed that the reaction sub-sequences that are conditionally nearly certain or nearly uncertain can be considered as being causally related. Moreover, since the time-ordering of reaction events is locally irrelevant, the reaction sub-sequences can be transformed into the reaction sets or multi-sets. The distance metrics can be then used to define the equivalences among the reaction events. The proposed method for identifying the causally related reaction sub-sequences has been implemented as a computationally efficient query-response mechanism. The method was evaluated for five models of genetic networks in seven defined numerical experiments. The models were simulated in BioNetGen using the open-source network-free simulator NFsim. This simulator had to be modified first to allow recording the traces of reaction events, and it is available in the Github repository, ploskot/nfsim_1.20. The generated event time-series were analyzed with Python and Matlab scripts. The whole process of data generation, analysis and visualization has been nearly fully automated using shell scripts. This demonstrates the opportunities for substantially increasing the research productivity by creating automated data generation and processing pipelines.

Sketch-based semantic retrieval of medical images.

The volume of medical images stored in hospitals is rapidly increasing; however, the utilization of these accumulated medical images remains limited. Existing content-based medical image retrieval (CBMIR) systems typically require example images, leading to practical limitations, such as the lack of customizable, fine-grained image retrieval, the inability to search without example images, and difficulty in retrieving rare cases. In this paper, we introduce a sketch-based medical image retrieval (SBMIR) system that enables users to find images of interest without the need for example images. The key concept is feature decomposition of medical images, which allows the entire feature of a medical image to be decomposed into and reconstructed from normal and abnormal features. Building on this concept, our SBMIR system provides an easy-to-use two-step graphical user interface: users first select a template image to specify a normal feature and then draw a semantic sketch of the disease on the template image to represent an abnormal feature. The system integrates both types of input to construct a query vector and retrieves reference images. For evaluation, ten healthcare professionals participated in a user test using two datasets. Consequently, our SBMIR system enabled users to overcome previous challenges, including image retrieval based on fine-grained image characteristics, image retrieval without example images, and image retrieval for rare cases. Our SBMIR system provides on-demand, customizable medical image retrieval, thereby expanding the utility of medical image databases.

Simulating doctors' thinking logic for chest X-ray report generation via Transformer-based Semantic Query learning.

Medical report generation can be treated as a process of doctors' observing, understanding, and describing images from different perspectives. Following this process, this paper innovatively proposes a Transformer-based Semantic Query learning paradigm (TranSQ). Briefly, this paradigm is to learn an intention embedding set and make a semantic query to the visual features, generate intent-compliant sentence candidates, and form a coherent report. We apply a bipartite matching mechanism during training to realize the dynamic correspondence between the intention embeddings and the sentences to induct medical concepts into the observation intentions. Experimental results on two major radiology reporting datasets (i.e., IU X-ray and MIMIC-CXR) demonstrate that our model outperforms state-of-the-art models regarding generation effectiveness and clinical efficacy. In addition, comprehensive ablation experiments fully validate the TranSQ model's innovation and interpretation. The code is available at https://github.com/zjukongming/TranSQ.

Multi-objective genetic programming strategies for topic-based search with a focus on diversity and global recall.

Topic-based search systems retrieve items by contextualizing the information seeking process on a topic of interest to the user. A key issue in topic-based search of text resources is how to automatically generate multiple queries that reflect the topic of interest in such a way that precision, recall, and diversity are achieved. The problem of generating topic-based queries can be effectively addressed by Multi-Objective Evolutionary Algorithms, which have shown promising results. However, two common problems with such an approach are loss of diversity and low global recall when combining results from multiple queries. This work proposes a family of Multi-Objective Genetic Programming strategies based on objective functions that attempt to maximize precision and recall while minimizing the similarity among the retrieved results. To this end, we define three novel objective functions based on result set similarity and on the information theoretic notion of entropy. Extensive experiments allow us to conclude that while the proposed strategies significantly improve precision after a few generations, only some of them are able to maintain or improve global recall. A comparative analysis against previous strategies based on Multi-Objective Evolutionary Algorithms, indicates that the proposed approach is superior in terms of precision and global recall. Furthermore, when compared to query-term-selection methods based on existing state-of-the-art term-weighting schemes, the presented Multi-Objective Genetic Programming strategies demonstrate significantly higher levels of precision, recall, and F1-score, while maintaining competitive global recall. Finally, we identify the strengths and limitations of the strategies and conclude that the choice of objectives to be maximized or minimized should be guided by the application at hand.

Identification of new small molecule allosteric SHP2 inhibitor through pharmacophore-based virtual screening, molecular docking, molecular dynamics simulation studies, synthesis and in vitro evaluation.

Src homology-2 (SH2) domain-containing phosphatase-2 (SHP2) is the first identified protooncogene and is a promising target for developing small molecule inhibitors as cancer chemotherapeutic agents. Pharmacophore-based virtual screening (PBVS) is a pharmacoinformatics methodology that employs physicochemical knowhow of the chemical space into the dynamic environs of computational technology to extract virtual molecular hits that are precise and promising for a drug target. In the current study, PBVS has been applied on EnamineTM Advanced Collection of 551,907 molecules by using a pharmacophore model developed upon SHP099 by Molecular Operating Environment (MOE) software to identify potential small molecule allosteric SHP2 inhibitors. Obtained 37 hits were further filtered through DruLiTo software for drug-likeness and PAINS remover which yielded 35 hits. These were subjected to molecular docking studies against the tunnel allosteric site of SHP2 (PDB ID: 5EHR) to screen them according to their binding affinity for the enzyme. Top 5 molecules having highest binding affinity for 5EHR were passed through an ADMET prediction screening and the top 2 hits (ligands 111675 and 546656) with the most favourable ADMET profile were taken for post screening molecular docking and MD simulation studies. From the protein-ligand interaction pattern, conformational stability and energy parameters, ligand 111675 (SHP2 Ki = 0.118 µM) resulted as the most active molecule. Further, the synthesis and in vitro evaluation of the lead compound 111675 unveiled its potent inhibitory activity (IC50 = 0.878 ± 0.008 µM) against SHP2.Communicated by Ramaswamy H. Sarma.

Spatiotemporal retrieval and feature analysis of air pollution episodes.

Air pollution has inevitably come along with the economic development of human society. How to balance economic growth with a sustainable environment has been a global concern. The ambient PM2.5 (particulate matter with aerodynamic diameter ≤ 2.5 µm) is particularly life-threatening because these tiny aerosols could be inhaled into the human respiration system and cause millions of premature deaths every year. The focus of most relevant research has been placed on apportionment of pollutants and the forecast of PM2.5 concentration measures. However, the spatiotemporal variations of pollution regions and their relationships to local factors are not much contemplated in the literature. These local factors include, at least, land terrain, meteorological conditions and anthropogenic activities. In this paper, we propose an interactive analysis platform for spatiotemporal retrieval and feature analysis of air pollution episodes. A domain expert can interact with the platform by specifying the episode analysis intention considering various local factors to reach the analysis goals. The analysis platform consists of two main components. The first component offers a query-by-sketch function where the domain expert can search similar pollution episodes by sketching the spatial relationship between the pollution regions and the land objects. The second component helps the domain expert choose a retrieved episode to conduct spatiotemporal feature analysis in a time span. The integrated platform automatically searches the episodes most resembling the domain expert's original sketch and detects when and where the episode emerges and diminishes. These functions are helpful for domain experts to infer insights into how local factors result in particular pollution episodes.