Markup Language Research Articles

Pre-Publication Data Linking in Taxonomy and Biodiversity: The ARPHA and Metotaxa-Metostem Publishing Systems

The traditional way of publishing in PDF makes it difficult to retrospectively convert the legacy literature into data. This presentation will discuss pre-publication tagging as an alternative solution for publishing FAIR (Findable, Accessible, Interoperable, Resuable) biodiversity data. The Metotaxa-Metostem workflow Тhe MetoTaxa project aims to create a new digital production chain for the European Journal of Taxonomy, which enables the pre-publication semantic structuring of text, automatic tagging and semantic enrichment (annotation). The system is based on a single-source publishing model, where the development of an XML file enables technical editors to automatically enrich text and produce multiple digital outputs. This makes it possible to structure generic or domain-specific sections of articles (e.g., Introduction; Material and methods; Taxon names or Мaterial examined). Thanks to the GoldenGate API developed by Plazi, the Text Encoding Intiative (TEI) XML source file is automatically annotated with JATS TaxPub tags: taxon names are labeled and each authorship can be checked via Catalogue of Life, each element of the material examined is parsed thanks to the preformatting of the text (Chester et al. 2019). Also, each bibliographic reference is parsed into Journal Article Tag Suite (JATS) elements (author names, title, journal, etc.), which automatically links references to their in-text citations. Pre-publication tagging will be carried out by the technical editors and then checked by the authors before publication, and will be sent to databases such as Global Biodiversity Information Facility (GBIF) or Biodiversity Literature Repository (BLR) as soon as the article is published. We will also briefly present MetoStem, which offers a technical solution for the digital transformation of monographs, and particularly floras. The tools and methods developed by this project will enable advanced publication of interoperable structured text and data. ARPHA Publishing Platform Launched in 2010 by Pensoft, ARPHA (Penev et al. 2010) is the first ever scholarly publishing platform to support pre-publication semantic tags and enhancements to entities (e.g., taxon treatments, taxon names, sequences) in the JATS TaxPub XML format developed by Plazi, which are then embedded into the HTML version of the article. Having proved advantageous for biodiversity scientists, Pensoft’s pre-publication tagging workflow has since been adopted by over 30 biodiversity journals hosted on ARPHA. The second development stage of ARPHA was marked by the launch of ARPHA Writing Tool (AWT)*1 and Biodiversity Data Journal in 2013. AWT supports import of Darwin Core structured data from GBIF, Barcode of Life Data Systems (BOLD) and Integrated Digitized Biocollections (iDigBio) directly into manuscripts. These are also exported automatically as published material citations to GBIF. AWT also provides several other unique tools encompassed within the ARPHA-BioDiv toolbox (Penev et al. 2017). Currently, AWT is being redeveloped into a standalone, freely accessible installation (AWT 2.0), based on a micro-service architecture. It enables new semantic enhancements during the authoring process, which can be confirmed by the authors before manuscript submission. Such enhancements include the in-text citations context by CiTO ontology; automated tagging of taxon names and linking to their identifiers in authoritative sources; annotator tool; nanopublication module; automated search and import of references; treatment citation module; export/import to/from JATS TaxPub; and internal communication tool for contributors.

A pathway model of glucose-stimulated insulin secretion in the pancreatic β-cell.

The pancreas plays a critical role in maintaining glucose homeostasis through the secretion of hormones from the islets of Langerhans. Glucose-stimulated insulin secretion (GSIS) by the pancreatic β-cell is the main mechanism for reducing elevated plasma glucose. Here we present a systematic modeling workflow for the development of kinetic pathway models using the Systems Biology Markup Language (SBML). Steps include retrieval of information from databases, curation of experimental and clinical data for model calibration and validation, integration of heterogeneous data including absolute and relative measurements, unit normalization, data normalization, and model annotation. An important factor was the reproducibility and exchangeability of the model, which allowed the use of various existing tools. The workflow was applied to construct a novel data-driven kinetic model of GSIS in the pancreatic β-cell based on experimental and clinical data from 39 studies spanning 50 years of pancreatic, islet, and β-cell research in humans, rats, mice, and cell lines. The model consists of detailed glycolysis and phenomenological equations for insulin secretion coupled to cellular energy state, ATP dynamics and (ATP/ADP ratio). Key findings of our work are that in GSIS there is a glucose-dependent increase in almost all intermediates of glycolysis. This increase in glycolytic metabolites is accompanied by an increase in energy metabolites, especially ATP and NADH. One of the few decreasing metabolites is ADP, which, in combination with the increase in ATP, results in a large increase in ATP/ADP ratios in the β-cell with increasing glucose. Insulin secretion is dependent on ATP/ADP, resulting in glucose-stimulated insulin secretion. The observed glucose-dependent increase in glycolytic intermediates and the resulting change in ATP/ADP ratios and insulin secretion is a robust phenomenon observed across data sets, experimental systems and species. Model predictions of the glucose-dependent response of glycolytic intermediates and biphasic insulin secretion are in good agreement with experimental measurements. Our model predicts that factors affecting ATP consumption, ATP formation, hexokinase, phosphofructokinase, and ATP/ADP-dependent insulin secretion have a major effect on GSIS. In conclusion, we have developed and applied a systematic modeling workflow for pathway models that allowed us to gain insight into key mechanisms in GSIS in the pancreatic β-cell.

Complementarity-Aware Space Learning for Video-Text Retrieval

In general, videos are powerful at recording physical patterns ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g</i> ., spatial layout) while texts are great at describing abstract symbols ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g</i> ., emotion). When video and text are used in multi-modal tasks, they are claimed to be complementary and their distinct information is crucial. However, when it comes to cross-modal tasks ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g</i> ., retrieval), existing works usually use their common part in the form of common space learning while their distinct information is abandoned. In this paper, we argue that distinct information is also beneficial for cross-modal retrieval. To address this problem, we propose a divide-and-conquer learning approach, namely Complementarity-aware Space Learning (CSL), by recasting this challenge into learning of two spaces ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., latent and symbolic spaces) to simultaneously explore their common and distinct information by considering multi-modal complementary character. Specifically, we first propose to learn a symbolic space from video with a memory-based video encoder and a symbolic generator. In contrast, we also introduce learning a latent space from text with a text encoder and a memory-based latent feature selector. Finally, we propose a complementarity-aware loss by integrating two spaces to facilitate video-text retrieval tasks. Extensive experiments show that our approach outperforms existing state-of-the-art methods by 5.1%, 2.1% and 0.9% of R@10 for text-to-video retrieval on three benchmarks, respectively. Ablation study also verifies that the distinct information from video and text improves the retrieval performance. Trained models and source code have been released at https://github.com/NovaMind-Z/CSL.

Application research on table structure recognition and information extraction in sci-tech academic journals based on visual studio tools for Office technology

The premise of intelligent table processing in Word is to extract the table structure and text information. By using visual studio tools for Office (VSTO) to obtain the extensible markup language (XML) information of the table, the structural relationship of the table and the text format of each cell can be further recognized. Compared with Visual Basic for Applications (VBA) technology, VSTO technology is slower in handling Word, but it has better extensibility and efficiency than VBA. VSTO technology can effectively recognize the structure of the table and extract information, providing possibilities for subsequent intelligent processing.

Evaluation of a Legally Binding Smart-Contract Language for Blockchain Applications

Blockchain governs inter-organizational business processes and enables decentralized autonomous organizations (DAO) with governance capabilities via smart contracts (SC). Due to the programmer&amp;rsquo;s lack of prior knowledge of the contract domain, SCs are ambiguous and error-prone. Several works, i.e., SPESC, Symboleo, and SmaCoNat, exist to support the legally-binding SCs. The aforementioned SCLs present intriguing approaches to building legally-binding SCs but either lack domain completeness, or are intended for non-collaborative business processes. In our previous work, we address the above-mentioned shortcomings of the XML-based smart-legal-contract markup language (SLCML), in which blockchain developers focus on the contractual workflow rather than the syntax specifics. However, SLCML, as a blockchain-independent formal specification language, is not evaluated to determine its applicability, usefulness, and usability for establishing legally-binding SCs for workflow enactment services (WES) to automate and streamline the business processes within connected organizations. In accordance with this, we formally implement the SLCML and propose evaluation approaches, such as running case and lab experiments, to demonstrate the SLCML&amp;rsquo;s generality and applicability for developing legally-binding SCs. Overall, the results of this work ascertain the applicability, usefulness, and usability of the proposed SLCML for establishing legally-binding SCs for WES.

A Cancelable Biometric System Based on Deep Style Transfer and Symmetry Check for Double-Phase User Authentication

In recent times, there has been a noticeable increase in the application of human biometrics for user authentication in various domains, such as online banking. However, the use of biometric systems poses security risks and the potential for misuse, primarily due to the storage of original templates in databases. To tackle this issue, the concept of cancelable biometrics has emerged as a reliable method utilizing one-way encryption. Several algorithms have been developed to implement cancelable biometrics, incorporating visual representations of single or multiple biometrics. This research proposes a cancelable biometric system that utilizes deep learning techniques to generate two encrypted modalities, namely text and image, using facial and fingerprint biometrics acquired from a smartphone. The system consists of two main stages: a visual encoder and a text encoder. The visual encoder converts the fingerprint style into a facial representation, creating a cancelable template to ensure the potential for cancelation. The resulting visual template is then processed by the text encoder, which employs hashing techniques to generate a corresponding text template. User authentication is automatically verified by utilizing the generated templates through Siamese networks.

An AI-based universal phantom analysis method based on XML-SVG wireframes with novel functional object identifiers

Objective. Quality assurance (QA) testing must be performed at regular intervals to ensure that medical devices are operating within designed specifications. Numerous QA phantoms and software packages have been developed to facilitate measurements of machine performance. However, due to the hard-coded nature of geometric phantom definition in analysis software, users are typically limited to the use of a small subset of compatible QA phantoms. In this work, we present a novel AI-based universal Phantom (UniPhan) algorithm that is not phantom specific and can be easily adapted to any pre-existing image-based QA phantom. Approach. Extensible Markup Language Scalable Vector Graphics (XML-SVG) was modified to include several new tags describing the function of embedded phantom objects for use in QA analysis. Functional tags include contrast and density plugs, spatial linearity markers, resolution bars and edges, uniformity regions, and light-radiation field coincidence areas. Machine learning was used to develop an image classification model for automatic phantom type detection. After AI phantom identification, UniPhan imported the corresponding XML-SVG wireframe, registered it to the image taken during the QA process, performed analysis on the functional tags, and exported results for comparison to expected device specifications. Analysis results were compared to those generated by manual image analysis. Main results. XML-SVG wireframes were generated for several commercial phantoms including ones specific to CT, CBCT, kV planar imaging, and MV imaging. Several functional objects were developed and assigned to the graphical elements of the phantoms. The AI classification model was tested for training and validation accuracy and loss, along with phantom type prediction accuracy and speed. The results reported training and validation accuracies of 99%, phantom type prediction confidence scores of around 100%, and prediction speeds of around 0.1 s. Compared to manual image analysis, Uniphan results were consistent across all metrics including contrast-to-noise ratio, modulation-transfer function, HU accuracy, and uniformity. Significance. The UniPhan method can identify phantom type and use its corresponding wireframe to perform QA analysis. As these wireframes can be generated in a variety of ways this represents an accessible automated method of analyzing image-based QA phantoms that is flexible in scope and implementation.

LFR-GAN: Local Feature Refinement based Generative Adversarial Network for Text-to-Image Generation

Text-to-image generation aims to generate images from text descriptions. Its main challenge lies in two aspects: (1) Semantic consistency, i.e., the generated images should be semantically consistent with the input text; and (2) Visual reality, i.e., the generated images should look like real images. To ensure text-image consistency, existing works mainly learn to establish the cross-modal representations via a text encoder and image encoder. However, due to the limited representation capability of the fixed-length embeddings and the flexibility of the free-form text descriptions, the learned text-to-image model is incapable of maintaining the semantic consistency between image local regions and fine-grained descriptions. As a result, the generated images sometimes miss some fine-grained attributes of the generated object, such as the color or shape of a part of the object. To address this issue, this paper proposes a Local Feature Refinement Based Generative Adversarial Network (LFR-GAN) , which first divides the text into some independent fine-grained attributes and generates an initial image, then refines the image details based on these attributes. The main contributions are three-fold: (1) An attribute modeling approach is proposed to model the fine-grained text descriptions by mapping them into representations of independent attributes, which provides more fine-grained details for image generation. (2) A local feature refinement approach is proposed to enable the generated image to form a complete reflection of the fine-grained attributes contained in the text description. (3) A multi-stage generation approach is proposed to realize the fine-grained manipulation of complex images progressively, which aims to improve the performance of the refinement and generate photo-realistic images. Extensive experiments on the CUB and Oxford102 datasets show the effectiveness of our LFR-GAN approach in both text-to-image generation and text-guided image manipulation tasks. Our LFR-GAN approach shows superior performance compared to the state-of-the-art methods. The codes will be released at https://github.com/PKU-ICST-MIPL/LFR-GAN_TOMM2023 .

Adaptation as Process: A Genetic Edition of Andrew Davies’ Middlemarch (BBC/WGBH, 1994)

Abstract This article reports on an interdisciplinary project to produce the first genetic edition of a television adaptation, drawing on the papers of screenwriter Andrew Davies who adapted George Eliot’s Middlemarch for the BBC in 1994. Combining methodologies from digital humanities, television history, and archival theory and practice, the digital resource places Xtensible Mark-up Language versions of Eliot’s novel and Davies’ scripts at the centre of an intertextual framework which enables close cross-referencing. Supported by primary sources derived from thorough production history research, the genetic edition opens up a potentially productive approach to adaptation which foregrounds the creative practice of the screenwriter at the heart of the collaborative process of producing television adaptations of classic novels. Following an outline of the case history, the project and the resource, the article then illustrates some preliminary findings based on new editorial commentary. It concludes that this genetic edition will not only be of interest to Eliot scholars, television historians, and adaptations studies, but might have potential beyond the academy in the development of resources for education and heritage sites.

CityGML in the Integration of BIM and the GIS: Challenges and Opportunities

CityGML (City Geography Markup Language) is the most investigated standard in the integration of building information modeling (BIM) and the geographic information system (GIS), and it is essential for digital twin and smart city applications. The new CityGML 3.0 has been released for a while, but it is still not clear whether its new features bring new challenges or opportunities to this research topic. Therefore, the aim of this study is to understand the state of the art of CityGML in BIM/GIS integration and to investigate the potential influence of CityGML3.0 on BIM/GIS integration. To achieve this aim, this study used a systematic literature review approach. In total, 136 papers from Web of Science (WoS) and Scopus were collected, reviewed, and analyzed. The main findings of this review are as follows: (1) There are several challenging problems in the IFC-to-CityGML conversion, including LoD (Level of Detail) mapping, solid-to-surface conversion, and semantic mapping. (2) The ‘space’ concept and the new LoD concept in CityGML 3.0 can bring new opportunities to LoD mapping and solid-to-surface conversion. (3) The Versioning module and the Dynamizer module can add dynamic semantics to the CityGML. (4) Graph techniques and scan-to-BIM offer new perspectives for facilitating the use of CityGML in BIM/GIS integration. These findings can further facilitate theoretical studies on BIM/GIS integration.

Trends in computerized provider order entry: 20-year bibliometric overview.

Drug-related problems (DRPs) can lead to serious health issues and have significant economic impacts on healthcare systems. One solution to address this issue is the use of computerized physician order entry systems (CPOE), which can help prevent DRPs by reducing the risk of medication errors. The purpose of this study is to provide an analysis on scientific production of the past 20 years in order to describe trends in academic publishing on CPOE and to identify the major topics as well as the predominant actors (journals, countries) involved in this field. A PubMed search was carried out to extract articles related to computerized provider order entry during the period January 1st 2003- December 31st 2022 using a specific query. Data were downloaded from PubMed in Extensible Markup Language (XML) and were processed through a dedicated parser. A total of 2,946 articles were retrieved among 623 journals. One third of these articles were published in eight journals. Publications grew strongly from 2002 to 2006, with a dip in 2008 followed by an increase again in 2009. After 2009, there follows a decreasing until 2022.The most producing countries are the USA with 51.39% of the publication over the period by France (3.80%), and Canada (3.77%). About disciplines, the top 3 is: "medical informatics" (21.62% of articles), "pharmacy" (19.04%), and "pediatrics" (6.56%). This study provides an overview of publication trends related to CPOE, which exhibited a significant increase in the first decade of the 21st century followed by a decline after 2009. Possible reasons for this decline include the emergence of digital health tools beyond CPOE, as well as healthcare professionals experiencing alert fatigue of the current system. Future research should focus on analyzing publication trends in the field of medical informatics and decision-making tools to identify other areas of interest that may have surpassed the development of CPOE.

On Isotropy of Multimodal Embeddings

Embeddings, i.e., vector representations of objects, such as texts, images, or graphs, play a key role in deep learning methodologies nowadays. Prior research has shown the importance of analyzing the isotropy of textual embeddings for transformer-based text encoders, such as the BERT model. Anisotropic word embeddings do not use the entire space, instead concentrating on a narrow cone in such a pretrained vector space, negatively affecting the performance of applications, such as textual semantic similarity. Transforming a vector space to optimize isotropy has been shown to be beneficial for improving performance in text processing tasks. This paper is the first comprehensive investigation of the distribution of multimodal embeddings using the example of OpenAI’s CLIP pretrained model. We aimed to deepen the understanding of the embedding space of multimodal embeddings, which has previously been unexplored in this respect, and study the impact on various end tasks. Our initial efforts were focused on measuring the alignment of image and text embedding distributions, with an emphasis on their isotropic properties. In addition, we evaluated several gradient-free approaches to enhance these properties, establishing their efficiency in improving the isotropy/alignment of the embeddings and, in certain cases, the zero-shot classification accuracy. Significantly, our analysis revealed that both CLIP and BERT models yielded embeddings situated within a cone immediately after initialization and preceding training. However, they were mostly isotropic in the local sense. We further extended our investigation to the structure of multilingual CLIP text embeddings, confirming that the observed characteristics were language-independent. By computing the few-shot classification accuracy and point-cloud metrics, we provide evidence of a strong correlation among multilingual embeddings. Embeddings transformation using the methods described in this article makes it easier to visualize embeddings. At the same time, multiple experiments that we conducted showed that, in regard to the transformed embeddings, the downstream tasks performance does not drop substantially (and sometimes is even improved). This means that one could obtain an easily visualizable embedding space, without substantially losing the quality of downstream tasks.

HydroLang Markup Language: Community-driven web components for hydrological analyses

Abstract We introduce HydroLang Markup Language (HL-ML), a programming interface that uses a markup language to perform environmental analyses using the hydrological and environmental framework HydroLang. The software acts as a self-contained interface that uses HTML tags powered by the web component specification to generate simple hydrological computations that enable data analysis, visualization, and manipulation via semantically driven instructions. It enables hydrological researchers and professionals to use markup language to retrieve, analyze, visualize, and map data with basic programming skills. The components' adaptability enables users to run analytical routines that perform simple and complex analyses on the client side. We present the implementation details of the approach, the use of custom elements in web technologies and academia, and share sample usages to demonstrate the simplicity of use of the human-readable and computer-executable framework.

Spatial-Semantic Collaborative Graph Network for Textbook Question Answering

Textbook Question Answering (TQA) task requires answering questions by reasoning based on both the given diagrams and text context. There are mainly two challenges for the task. First, the diagrams are different from the natural images. Similar shapes or color blocks may express different semantics and there is also a large intra-topic variation for diagrams. Hence, the characteristics of visual semantic ambiguity and variable visual appearance make the diagram understanding more challenging. Second, for the text, the specific education domain with terminologies exists a great gap with the general domain. Therefore, it is difficult to represent the text semantics effectively using a text encoder pretrained in the general domain. In this paper, we propose a Spatial-Semantic Collaborative Graph Network (SSCGN) for TQA task, which can help enhance the diagram and text understanding and facilitate multimodal reasoning. Specifically, the Spatial-guided Semantic Enhancing (SSE) module fully exploits the spatial and semantic relationships between visual objects and OCR tokens to collaboratively enhance the diagram semantic understanding. Moreover, based on the semantically enhanced region representations of the SSE module, the Fine-grained Spatial-Aware Graph Network (FSA-GN) can help obtain richer relation-aware region representations for joint reasoning by capturing more fine-grained spatial relationships. We further propose multiple self-supervised auxiliary tasks to enhance the initial diagram and text semantic representations by pretraining the diagram encoder and text encoder. Extensive experiments and ablation studies are conducted to validate the effectiveness of SSCGN.

Enabling efficient business process mining using flatten sequential structure model

The volume of extensible markup language (XML) format documents is increasing every day due to the development of internet and the use of XML format in business process log file. Storing business process log data in XML format is preferable due to the ability of extensible and storing data irrespective of how it will be represented. However, mining XML format data poses challenges due to its complex data structure and dimensions. This paper proposes a method to convert XML format document into a structured format without ignoring the structural information. Converting semi-structured business process log data into structured format will allow more data mining techniques and statistical test be conducted and extract information from the business process log data. The experiment in this study performs t-test on a set of synthetic data and a set of real-world data to prove that information in business process log can be extracted through normal statistical test. Empirical results show that statistical analysis can be conducted on business process log data especially in XML format after flatten sequential structure model (FSSM) is used.

PN2Maude: An automatic tool to generate Maude specification for Petri net models

Currently, Model-Driven Engineering (MDE) plays a key role in the software development process as it aims to handle their increasing complexity and focuses on the automatic generation of code and/or specifications from system models. This paper presents a very useful tool for the automatic generation of Maude specifications from both Petri net PNML (Petri Net Markup Language) descriptions or incidence matrices. At the end of this paper, a simple but complete Petri net example will be presented to demonstrate the usefulness of the developed tool.

Improving End-to-End Speech Translation by Leveraging Auxiliary Speech and Text Data

We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language text). Thus, the speech translation model can learn from both unlabeled and labeled data, especially when the source-language text data is abundant. Beyond this, we present a denoising method to build a robust text encoder that can deal with both normal and noisy text data. Our system sets new state-of-the-arts on the MuST-C En-De, En-Fr, and LibriSpeech En-Fr tasks.

Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval

Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully exploring the multi-modal information of videos, or simply fuse multi-modal features in a brute force manner without explicit guidance. In this paper, we integrate multi-modal information in an explicit manner by tagging, and use the tags as the anchors for better video-text alignment. Various pretrained experts are utilized for extracting the information of multiple modalities, including object, person, motion, audio, etc. To take full advantage of these information, we propose the TABLE (TAgging Before aLignmEnt) network, which consists of a visual encoder, a tag encoder, a text encoder, and a tag-guiding cross-modal encoder for jointly encoding multi-frame visual features and multi-modal tags information. Furthermore, to strengthen the interaction between video and text, we build a joint cross-modal encoder with the triplet input of [vision, tag, text] and perform two additional supervised tasks, Video Text Matching (VTM) and Masked Language Modeling (MLM). Extensive experimental results demonstrate that the TABLE model is capable of achieving State-Of-The-Art (SOTA) performance on various video-text retrieval benchmarks, including MSR-VTT, MSVD, LSMDC and DiDeMo.

CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels

Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are indexes, lacking concrete text descriptions. Therefore, it remains to be determined how such models could be applied to these tasks. This paper first finds out that simply fine-tuning the visual model initialized by the image encoder in CLIP, has already obtained competitive performances in various ReID tasks. Then we propose a two-stage strategy to facilitate a better visual representation. The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID and give them to the text encoder to form ambiguous descriptions. In the first training stage, image and text encoders from CLIP keep fixed, and only the text tokens are optimized from scratch by the contrastive loss computed within a batch. In the second stage, the ID-specific text tokens and their encoder become static, providing constraints for fine-tuning the image encoder. With the help of the designed loss in the downstream task, the image encoder is able to represent data as vectors in the feature embedding accurately. The effectiveness of the proposed strategy is validated on several datasets for the person or vehicle ReID tasks. Code is available at https://github.com/Syliz517/CLIP-ReID.

Design and Validation of a Low-Cost Mobile EEG-Based Brain-Computer Interface.

Objective: We designed and validated a wireless, low-cost, easy-to-use, mobile, dry-electrode headset for scalp electroencephalography (EEG) recordings for closed-loop brain-computer (BCI) interface and internet-of-things (IoT) applications. Approach: The EEG-based BCI headset was designed from commercial off-the-shelf (COTS) components using a multi-pronged approach that balanced interoperability, cost, portability, usability, form factor, reliability, and closed-loop operation. Main Results: The adjustable headset was designed to accommodate 90% of the population. A patent-pending self-positioning dry electrode bracket allowed for vertical self-positioning while parting the user's hair to ensure contact of the electrode with the scalp. In the current prototype, five EEG electrodes were incorporated in the electrode bracket spanning the sensorimotor cortices bilaterally, and three skin sensors were included to measure eye movement and blinks. An inertial measurement unit (IMU) provides monitoring of head movements. The EEG amplifier operates with 24-bit resolution up to 500 Hz sampling frequency and can communicate with other devices using 802.11 b/g/n WiFi. It has high signal-to-noise ratio (SNR) and common-mode rejection ratio (CMRR) (121 dB and 110 dB, respectively) and low input noise. In closed-loop BCI mode, the system can operate at 40 Hz, including real-time adaptive noise cancellation and 512 MB of processor memory. It supports LabVIEW as a backend coding language and JavaScript (JS), Cascading Style Sheets (CSS), and HyperText Markup Language (HTML) as front-end coding languages and includes training and optimization of support vector machine (SVM) neural classifiers. Extensive bench testing supports the technical specifications and human-subject pilot testing of a closed-loop BCI application to support upper-limb rehabilitation and provides proof-of-concept validation for the device's use at both the clinic and at home. Significance: The usability, interoperability, portability, reliability, and programmability of the proposed wireless closed-loop BCI system provides a low-cost solution for BCI and neurorehabilitation research and IoT applications.