Semantic Location Research Articles

Trajectory privacy protection method based on sensitive semantic location replacement

As Location-Based Services (LBSs) proliferate within the Social Internet of Vehicles (SIoVs), the collection and utilization of vehicle trajectories, which are rich in spatio-temporal and semantic informations, have intensified. Publishing these trajectories without adequate privacy safeguards significantly threatens user semantic trajectory privacy. Current methodologies for protecting semantic trajectory privacy do not adequately consider the similarity in query probability between sensitive and alternative semantic locations, thus undermining the efficacy of privacy protection. To address this critical gap, we introduces a novel trajectory privacy protection method based on sensitive semantic location replacement (SSLR), which strategically replaces sensitive semantic locations. This method consists of three key steps: first, semantically annotating trajectory sampling locations to identify sensitive semantic points; second, employing a unique double semicircular area to define replacement regions and selecting replacement Points of Interests (PoIs) that align in semantic attributes and query probabilities; third, reconstructing and publishing the modified trajectories. Our simulation results confirm that SSLR advances the state of the art by delivering superior performance in average recognition rate, geographic similarity, and semantic similarity compared to existing methods. Crucially, by incorporating considerations of query probability similarities, this paper not only enhances the effect of trajectory privacy protection but also preserves its utility. This dual enhancement represents a groundbreaking approach to trajectory privacy, with significant implications for advancing privacy strategies in LBSs within SIoVs.

APTrans: Transformer-Based Multilayer Semantic and Locational Feature Integration for Efficient Text Classification

Text classification is not only a prerequisite for natural language processing work, such as sentiment analysis and natural language reasoning, but is also of great significance for screening massive amounts of information in daily life. However, the performance of classification algorithms is always affected due to the diversity of language expressions, inaccurate semantic information, colloquial information, and many other problems. We identify three clues in this study, namely, core relevance information, semantic location associations, and the mining characteristics of deep and shallow networks for different information, to cope with these challenges. Two key insights about the text are revealed based on these three clues: key information relationship and word group inline relationship. We propose a novel attention feature fusion network, Attention Pyramid Transformer (APTrans), which is capable of learning the core semantic and location information from sentences using the above-mentioned two key insights. Specially, a hierarchical feature fusion module, Feature Fusion Connection (FFCon), is proposed to merge the semantic features of higher layers with positional features of lower layers. Thereafter, a Transformer-based XLNet network is used as the backbone to initially extract the long dependencies from statements. Comprehensive experiments show that APTrans can achieve leading results on the THUCNews Chinese dataset, AG News, and TREC-QA English dataset, outperforming most excellent pre-trained models. Furthermore, extended experiments are carried out on a self-built Chinese dataset theme analysis of teachers’ classroom corpus. We also provide visualization work, further proving that APTrans has good potential in text classification work.

CRMEFNet: A coupled refinement, multiscale exploration and fusion network for medical image segmentation

Accurate segmentation of target areas in medical images, such as lesions, is essential for disease diagnosis and clinical analysis. In recent years, deep learning methods have been intensively researched and have generated significant progress in medical image segmentation tasks. However, most of the existing methods have limitations in modeling multilevel feature representations and identification of complex textured pixels at contrasting boundaries. This paper proposes a novel coupled refinement and multiscale exploration and fusion network (CRMEFNet) for medical image segmentation, which explores in the optimization and fusion of multiscale features to address the abovementioned limitations. The CRMEFNet consists of three main innovations: a coupled refinement module (CRM), a multiscale exploration and fusion module (MEFM), and a cascaded progressive decoder (CPD). The CRM decouples features into low-frequency body features and high-frequency edge features, and performs targeted optimization of both to enhance intraclass uniformity and interclass differentiation of features. The MEFM performs a two-stage exploration and fusion of multiscale features using our proposed multiscale aggregation attention mechanism, which explores the differentiated information within the cross-level features, and enhances the contextual connections between the features, to achieves adaptive feature fusion. Compared to existing complex decoders, the CPD decoder (consisting of the CRM and MEFM) can perform fine-grained pixel recognition while retaining complete semantic location information. It also has a simple design and excellent performance. The experimental results from five medical image segmentation tasks, ten datasets and twelve comparison models demonstrate the state-of-the-art performance, interpretability, flexibility and versatility of our CRMEFNet.

SGO: Semantic Group Obfuscation for Location-Based Services in VANETS.

Location privacy is an important parameter to be addressed in the case of vehicular ad hoc networks. Each vehicle frequently communicates with location-based services to find the nearest location of interest. The location messages communicated with the location server may contain sensitive information like vehicle identity, location, direction, and other headings. A Location-Based Services (LBS) server is not a trusted entity; it can interact with an adversary, compromising the location information of vehicles on the road and providing a way for an adversary to extract the future location tracks of a target vehicle. The existing works consider two or three neighboring vehicles as a virtual shadow to conceal location information. However, they did not fully utilize the semantic location information and pseudonym-changing process, which reduces the privacy protection level. Moreover, a lot of dummy location messages are generated that increase overheads in the network. To address these issues, we propose a Semantic Group Obfuscation (SGO) technique that utilizes both location semantics as well as an efficient pseudonym-changing scheme. SGO creates groups of similar status vehicles on the road and selects random position coordinates for communication with the LBS server. It hides the actual location of a target vehicle in a vicinity. The simulation results verify that the proposed scheme SGO improves the anonymization and entropy of vehicles, and it reduces the location traceability and overheads in the network in terms of computation cost and communication cost. The cost of overhead is reduced by 55% to 65% compared with existing schemes. We also formally model and specify SGO using High-Level Petri Nets (HLPNs), which show the correctness and appropriateness of the scheme.

Determining user specific semantics of locations extracted from trajectory data

Knowledge about people's daily travel behavior is very relevant for transportation planning, but also for urban and regional planning in general. This information is typically collected through questionnaires or surveys. With the increasing availability of mobile devices capable of using Global Navigation Satellite Systems, it is possible to derive individual mobility behavior on a large scale and for a variety of different users. However, the challenge is to derive the relevant information from the mere GNSS trajectories; in this paper, the relevant information is semantic locations such as home, work place or leisure places. This paper presents an approach to first detect and cluster stop points as potential semantic locations of a user, which are then enriched with Points of Interest from OpenStreetMap and additional features, and finally a Viterbi optimization assigns the most probable semantics to these locations. Overall, this approach produces promising results for predicting user location semantics on a generalized level.

Implicit Markers of Old Belief in the Onomastics of Karelian Pomorye

This article draws on field materials collected by the Toponymic Expedition of Ural University, conducted in 2023–2024 in the Pomorye area of the Belomorsky District, Republic of Karelia. It examines collective nicknames such as oblivantsy (‘residents of the village of Sukhoye’) and lesovikibezmedniki (‘residents of villages and settlements in the south-eastern part of the Belomorsky region, including Endoguba, Vorenzha, Sumostrov, Pertozero, and Pulozero’). The study also explores phraseological units containing toponymic adjectives (e.g., face as / looking like hot Vyg copper, ‘about a flushed man’), and terms used for territorial groups with locative semantics that are similar to nicknames (e.g., poozery — pomory — lesoviki). Additionally, it includes various onomastic and appellative units, such as the names of sketes derived from lake names and the expression polumbrous hilozër, which features the quasi-katoikonym hilozër. The author interprets these linguistic elements as implicit markers of the Old Believers, who significantly influenced the historical and cultural landscape of the region. For example, the nickname oblivantsy is linked to the practice of dousing baptism practiced by the residents of Sukhoye, which the Old Believers viewed negatively. The phrase face like hot Vyg copper alludes to the tradition of crafting copper-cast icons among the Vyg Monastery inhabitants. The triad pomory — poozery — lesoviki is not only taxonomic (referring to the place of residence of the respective groups of people), but also reflects an evaluative opposition: the coastal inhabitants are economically and religiously contrasted with the Old Believers who retreated to the forests and lakes. Beyond reconstructing the semantics of these names, the author reveals the nominators’ perspectives embedded within them.

Периферийные глаголы в значении движения в хакасском языке: семантика и функционирование

The article analyses the functionality and semantics of the Khakass expressive verbs being on the periphery of the lexico-semantic group of movement. These verbs are common for native speakers’ everyday speech and acquire the meaning of movement when used in a particular context. Their semantics is complex, with emotional, evaluative and figurative elements intersecting and overlapping with each other. The meaning of movement can be acquired in different ways. Firstly, verbs with the meaning of behavior can combine with verbs of movement. Secondly, polysemous verbs can be combined with dependent lexemes of locative semantics. Lastly, onomatopoeic verbs in secondary lexical and semantic versions can be formed by adding the forced voice affix -t-. All these functionalsemantic and grammatical properties contribute to the transition to the category of expressives denoting the subject’s figurative movement. Almost all verbs expressing the subject’s movement in their secondary lexical and semantic versions originate from verbs with neutral semantics. The expressiveness in certain word-formation and combinational models is lexically motivated, with a significant focus on imagery. Despite being frequently used, many of these verbs are missing in lexicographical sources, and for those that are listed, no information on their seme of “movement” is provided. The situation is complicated by contextual ambiguity of expressive words. Given that the abundance of expressive vocabulary in everyday conversation indicates a reliable native language proficiency and guarantees the preservation and development of the Khakass language, further lexicographic projects should take into account all the semantic and expressive nuances.

The concept of "way" as a characteristic of the image of the hero in the novel by A. A. Fadeev "The Rout"

The subject of the study is the representation of the concept of the "way" in the novel by A. A. Fadeev "The Rout". The purpose of the work is to describe the representations of the concept of "way" as a real space in the novel and as a metaphor for the changes of its characters. The space category reflects the topographical features of the Far East, helping to trace the path of the detachment in the coordinates of space through the point of view of the protagonist. The spatial frame of the narrative is built with the help of specific subject words and toponyms, which mainly represent the remote countryside and the physical geography of the Far East. The attributes that form the natural space in the novel correspond to the negative emotional changes of the characters, revealing the inherent cruelty of the Civil War. When expressing this type of spatial relationship, it is the verb that plays the dominant role, which is based on the separation according to the static/dynamic manifestation of locative semantics, at the same time, verbs of displacement significantly surpass verbs of position. The following methods were used in the course of the study: the method of linguistic description, the method of contextual analysis, and the method of semantic analysis. The text space, as an important part of the content of the novel, depicts fragments of reality, and through the spatial concept of the "way" builds a general spatial picture of the world. The concept of "way" in a metaphorical sense is a subconcept of the concept of "Civil War", in accordance with this, the results of this work enrich the figurative zone of the concept of "Civil War". An analytical algorithm for the study of text space can be applied to the spatial analysis of similar works of art. The result of the study was the conclusion that the "way" is one of the central concepts of the novel. The concept of "way" has a negative connotation, suffering occurs in the process of the detachment's retreat. In addition, A. Fadeev includes spiritual trials in the path of the revolutionary hero, the character completes internal changes in the affirmation of socialist values in external crises and complex character relationships.

Типы пространственной семантики в модели фрейма «Киберпространство» (на материале медиатекстов на русском языке)

The aim of the study is to identify the cognitive models and language means used to express locative semantics in the ‘Cyberspace’ frame involving the texts of Russian-language media. The study is based on the hypothesis that global news stories concerning events in cyberspace often receive a specific framing in the Russian media discourse due to both socio-cultural singularity and the peculiarities of spatial semantics expression in the Russian language. The scientific novelty of the study is determined by the fact that cyberspace representation in the mass media in Russian has not previously been the object of linguistic research, although new lexical units describing phenomena from the cybertechnology industry are being actively included both in the media discourse and in the common Russian language and require a systematic description. As a result of the study, the process of adapting the global news frame in the Russian-language media has been described for the first time taking into account lexical and word-formation models and linguocultural aspects. It has been found that the semantics of cyberspace is actualised within the framework of three thematic clusters: real, associative-background and conceptual locations described using borrowed vocabulary, authorial neologisms, metaphorisation and homonymy.

Indoor Semantic Location Privacy Protection With Safe Reinforcement Learning

Indoor Semantic Location Privacy Protection With Safe Reinforcement Learning

Improving Next Location Recommendation Services With Spatial-Temporal Multi-Group Contrastive Learning

Next location recommendation services play a pivotal role in Location-Based Social Networks (LBSNs) due to their ability to provide personalized recommendations of attractive destinations, resulting in substantial benefits for both users and service providers. Recent research indicates that these services are influenced by both sequential and geographical factors. However, we argue that most of these services fail to fully exploit the latent multi-group knowledge of location semantics and user preferences, resulting in suboptimal performance. Therefore, we propose STMGCL, a novel spatial-temporal multi-group contrastive learning-based method to discover intrinsic multi-group information for improving next location recommendation services. Specifically, STMGCL designs Spatial Group Contrastive Learning (SGCL) to extract multiple group knowledge regarding location semantics. Additionally, it develops Temporal Group Contrastive Learning (TGCL) to explore multiple user preference group information through a self-attention based encoder. Finally, we leverage a multi-task learning strategy and a generalized Expectation Maximization (EM) algorithm to ensure that STMGCL is optimized end-to-end with guaranteed convergence. Extensive experiments conducted on four real-world datasets demonstrate the superior performance of STMGCL over baselines.

Towards applying image retrieval approach for finding semantic locations in autonomous vehicles

Towards applying image retrieval approach for finding semantic locations in autonomous vehicles

Attention-induced semantic and boundary interaction network for camouflaged object detection

The high intrinsic similarity between camouflaged objects and the background makes camouflaged object detection (COD) more challenging than traditional salient object detection (SOD). Existing deep-learning methods often fall into the following shortcomings: (1) When dealing with high-level features, it is difficult to fully and accurately extract semantic information, which is crucial for locating camouflaged targets. (2) The camouflaged targets identified by existing methods in complex scenes have rough boundaries and incomplete spatial information. (3) Existing methods cannot effectively exert the uniqueness and complementarity of multiple features when integrating multiple features. To this end, we propose an attention-induced semantic and boundary interaction network for accurately identifying camouflaged objects. Specifically, we propose a contrastive positioning module (CPM), which adopts a contrastive learning way to separate the camouflaged object from the background, thereby obtaining the exact location of the camouflaged target and retaining more semantic information. Then, we design a boundary exploration module (BEM), which can reduce background noise interference, focus on the structural details of camouflaged targets, and explore rich fine-grained spatial information. Finally, we propose an attention-induced interaction module (AIM) to fuse multivariate information (i.e., semantic location information, boundary information, and the side output information of the backbone), and multivariate information is complementarily fused under attention guidance to generate more powerful camouflaged target features. Extensive experiments show that the proposed method on the different backbones (i.e., ResNet-50, Res2Net-50, PVTv2-B2, EfficientNet-B1) produces state-of-the-art results on several camouflaged benchmarks. The code is available https://github.com/zhangqiao970914/ASBI.

IPatch: a remote adversarial patch

Applications such as autonomous vehicles and medical screening use deep learning models to localize and identify hundreds of objects in a single frame. In the past, it has been shown how an attacker can fool these models by placing an adversarial patch within a scene. However, these patches must be placed in the target location and do not explicitly alter the semantics elsewhere in the image. In this paper, we introduce a new type of adversarial patch which alters a model’s perception of an image’s semantics. These patches can be placed anywhere within an image to change the classification or semantics of locations far from the patch. We call this new class of adversarial examples ‘remote adversarial patches’ (RAP). We implement our own RAP called IPatch and perform an in-depth analysis on without pixel clipping on image segmentation RAP attacks using five state-of-the-art architectures with eight different encoders on the CamVid street view dataset. Moreover, we demonstrate that the attack can be extended to object recognition models with preliminary results on the popular YOLOv3 model. We found that the patch can change the classification of a remote target region with a success rate of up to 93% on average.

WiserVR: Semantic Communication Enabled Wireless Virtual Reality Delivery

Virtual reality (VR) over wireless is expected to be one of the killer applications in next-generation communication networks. Nevertheless, the huge data volume along with stringent requirements on latency and reliability under limited bandwidth resources makes untethered wireless VR delivery increasingly challenging. Such bottlenecks, therefore, motivate this work to seek the potential of using semantic communication, a new paradigm that promises to significantly ease the resource pressure, for efficient VR delivery. To this end, we propose a novel framework, namely WIreless SEmantic deliveRy for VR (WiserVR), for delivering consecutive 360{\deg} video frames to VR users. Specifically, deep learning-based multiple modules are well-devised for the transceiver in WiserVR to realize high-performance feature extraction and semantic recovery. Among them, we dedicatedly develop a concept of semantic location graph and leverage the joint-semantic-channel-coding method with knowledge sharing to not only substantially reduce communication latency, but also to guarantee adequate transmission reliability and resilience under various channel states. Moreover, implementation of WiserVR is presented, followed by corresponding initial simulations for performance evaluation compared with benchmarks. Finally, we discuss several open issues and offer feasible solutions to unlock the full potential of WiserVR.

PESO: A Seq2Seq-Based Vessel Trajectory Prediction Method with Parallel Encoders and Ship-Oriented Decoder

Vessel trajectory prediction supports navigation services and collision detection. To maintain safety and efficiency in maritime transportation, vessel trajectory prediction is always an important topic. By using automatic identification system (AIS) data and deep learning methods, the task of vessel trajectory prediction has made significant progress. However, this task is still full of challenges due to the complexity of historical information dependencies and the strong influence of spatial correlations. In this paper, we introduce a novel deep learning model, PESO, based on the structure of Seq2Seq, consisting of Parallel Encoders and a Ship-Oriented Decoder. The Parallel Encoders, including the Location Encoder and the Sailing Status Encoder are designed to integrate more information into feature representation. The Ship-Oriented Decoder is targeted to utilize the Semantic Location Vector (SLV) to guide the prediction, which better represents the spatial correlation of historical track points. In order to verify the efficiency and efficacy of PESO, we conducted comparative experiments with several baseline models. The experimental results demonstrate that PESO is superior to them both quantitatively and qualitatively.

Linguo-cognitive model analysis of low-format texts in educational discourse (in the course book “English Unlimited” Elementary)

The article deals with cognitive modeling of low-format texts from the course book “English Unlimited. Elementary”. The aim of the article is to reveal the dominant constituents of the linguo-cognitive model and to highlight their relevance to this very level of language learning (Elementary). The study shows that Participants, Setting and Scene and Act Sequence are the dominant components of the linguo-cognitive model in the texts. The constituent Participants is expressed by personal pronouns and proper nouns. The component Setting and Scene is represented by toponyms and nouns with locative semantics. Action verbs and stative verbs in present tenses are used to express the constituent Act Sequence. The importance of these constituents can be explained by the anthropocentric approach to educational material selection and to the learning process where the main purpose is to develop communicative competence of a student. These components of the linguo-cognitive model and their language representations show that the authors of the course book consider them the leading ones for developing language competence acquired at A2 level of language learning. It has been also found that linguistic representations of the objective-referential situations refer to the concept of National Identity in the educational discourse under analysis.

Semantic ontology enabled modeling, retrieval and inference for incomplete mobile trajectory data

Prevalence of vehicular terminals enables more and more mobile trajectory data to be collected. To promote the intelligent urban planning, traffic management and service in smart city applications, how to analyze and reasoning the inherent patterns in mobile trajectory has grabbed considerable research attentions from academia and industry. Current widely used popular methods are subject to the check-in dataset, and the pattern inference results greatly suffer from the sparsity and incompleteness in mobile trajectory data. To address this issue, a method of semantic ontology enabled modeling, retrieval and inference for incomplete mobile trajectory is investigated in this paper. To enhance the interpretability of mobile trajectory data, the latitude and longitude coordinates in spatio-temporal sequence are converted into semantic locations, and an ontology model with constraints then is constructed for vehicle movement through defining the corresponding semantic rules with the considerations of the location relationships both between road intersections and between vehicle movements. On the basis, by taking the constructed ontology model as the knowledge base and taking the semantic query results as the training set, an ontology based markov logic network is investigated for the mobile trajectory inference problem with incomplete data. Through comprehensive comparison and analysis, the experimental results achieved on real-world data finally have been shown to demonstrate the efficiency of the investigations, and verify the influence of weight configurations on the inference performance achieved by the proposed ontology based markov logic network.

EG-TransUNet: a transformer-based U-Net with enhanced and guided models for biomedical image segmentation

Although various methods based on convolutional neural networks have improved the performance of biomedical image segmentation to meet the precision requirements of medical imaging segmentation task, medical image segmentation methods based on deep learning still need to solve the following problems: (1) Difficulty in extracting the discriminative feature of the lesion region in medical images during the encoding process due to variable sizes and shapes; (2) difficulty in fusing spatial and semantic information of the lesion region effectively during the decoding process due to redundant information and the semantic gap. In this paper, we used the attention-based Transformer during the encoder and decoder stages to improve feature discrimination at the level of spatial detail and semantic location by its multihead-based self-attention. In conclusion, we propose an architecture called EG-TransUNet, including three modules improved by a transformer: progressive enhancement module, channel spatial attention, and semantic guidance attention. The proposed EG-TransUNet architecture allowed us to capture object variabilities with improved results on different biomedical datasets. EG-TransUNet outperformed other methods on two popular colonoscopy datasets (Kvasir-SEG and CVC-ClinicDB) by achieving 93.44% and 95.26% on mDice. Extensive experiments and visualization results demonstrate that our method advances the performance on five medical segmentation datasets with better generalization ability.

Towards a clinically-based common coordinate framework for the human gut cell atlas: the gut models

BackgroundThe Human Cell Atlas resource will deliver single cell transcriptome data spatially organised in terms of gross anatomy, tissue location and with images of cellular histology. This will enable the application of bioinformatics analysis, machine learning and data mining revealing an atlas of cell types, sub-types, varying states and ultimately cellular changes related to disease conditions. To further develop the understanding of specific pathological and histopathological phenotypes with their spatial relationships and dependencies, a more sophisticated spatial descriptive framework is required to enable integration and analysis in spatial terms.MethodsWe describe a conceptual coordinate model for the Gut Cell Atlas (small and large intestines). Here, we focus on a Gut Linear Model (1-dimensional representation based on the centreline of the gut) that represents the location semantics as typically used by clinicians and pathologists when describing location in the gut. This knowledge representation is based on a set of standardised gut anatomy ontology terms describing regions in situ, such as ileum or transverse colon, and landmarks, such as ileo-caecal valve or hepatic flexure, together with relative or absolute distance measures. We show how locations in the 1D model can be mapped to and from points and regions in both a 2D model and 3D models, such as a patient's CT scan where the gut has been segmented.ResultsThe outputs of this work include 1D, 2D and 3D models of the human gut, delivered through publicly accessible Json and image files. We also illustrate the mappings between models using a demonstrator tool that allows the user to explore the anatomical space of the gut. All data and software is fully open-source and available online.ConclusionsSmall and large intestines have a natural “gut coordinate” system best represented as a 1D centreline through the gut tube, reflecting functional differences. Such a 1D centreline model with landmarks, visualised using viewer software allows interoperable translation to both a 2D anatomogram model and multiple 3D models of the intestines. This permits users to accurately locate samples for data comparison.