Intelligent Mapping Research Articles

MapReader: a framework for learning a visual language model for map analysis

Intelligent map analysis is an important yet challenging topic. Recently, the development of large models, especially Visual Language Models (VLMs), has shown potential for intelligent image analysis. However, these models are primarily trained on natural images, which have intrinsic differences from maps. Consequently, there remains a gap in applying existing general-domain VLMs to map analysis. To address this issue, we propose a framework for developing a specialized VLM, called MapReader. To achieve this goal, a comprehensive data resource is collected using a strategy that combines self-instruct with expert refinement, including training data (MapTrain: 2,000 pairs of maps and descriptions) and evaluation data (MapEval: 250 maps and 500 map-related questions). Based on the training data, MapReader is fine-tuned on top of a general-domain VLM to learn to understand and describe map contents. The evaluation results on MapEval suggest that: (1) MapReader can accept map inputs and generate detailed descriptions of core geographic information, and it also possesses visual question-answering capabilities, showing potential for application in various map analysis scenarios, such as accessible map reading and robotic map usage; (2) The proposed data collection strategy is effective, and the collected dataset can serve as a benchmark to promote further map analysis research.

Enhancing Autonomous Vehicle Safety and Efficiency Through Intelligent Mapping and Recommendations

Enhancing Autonomous Vehicle Safety and Efficiency Through Intelligent Mapping and Recommendations

Task-to-Thread Mapping in OpenMP Using Fuzzy Decision Making

The performance of shared-resource multi-core hardware platforms in complex cyber-physical systems (CPSs), e.g., automotive industry, can be improved using task-based parallelism through OpenMP. However, most CPS require certain level of predictability, which challenges the efficient implementation of the task-to-thread mapping process. This exploratory work build on the fact that existing mapping methods mostly use elementary or heuristic algorithms, and the idea that artificial intelligence (AI) algorithms can be used to enhance the efficiency of such processes. Accordingly, this paper (1) evaluates the suitability of AI-based techniques in improving the performance of task-to-thread mapping in the OpenMP framework, and (2) proposes a hypothesis to perform an intelligent mapping using fuzzy logic for multi-queue schedulers to improve the predictability of the system.

MapGPT: an autonomous framework for mapping by integrating large language model and cartographic tools

ABSTRACT The mapping process generally involves intricate operations, such as symbol design, layout design, and text annotation, demanding a high level of professional expertise. The high requirement for map producers hinders the promotion and widespread adoption of mapping. Consequently, researchers are concentrating on techniques to automate and enhance the intelligence of the mapping process. For example, some studies attempt to train deep learning models for mapping, including methods like map style transfer. However, these approaches typically treat the entire map as a global input and generate a new map as output, lacking the flexibility to consider and control detailed elements within a map. Therefore, in this paper, we propose a large language model-based intelligent mapping framework, termed MapGPT, which can be used for mapping by considering the map as an integration of various map elements. Specifically, multiple professional mapping tools are designed in MapGPT, and each tool is designed to control a corresponding map element. With these tools, a large language model is used to first understand the demand of users based on mere natural language descriptions, and subsequently automatically invoke appropriate tools in sequence to generate a map. Furthermore, by utilizing a memory component to store interaction information, users can interact with MapGPT through conversation to adjust map elements such as color and position. In conclusion, MapGPT offers user-friendly mapping experience, showing potential to be a mapping assistant for professional map producers. A comprehensive demonstration of this framework is provided in a visual case study video, accessible at https://github.com/AGI-GIS/MapGPT.

Integration of Spatial and Co-Existence Relationships to Improve Administrative Region Target Detection in Map Images

Administrative regions are fundamental geographic elements on maps, thus making their detection in map images crucial to enhancing intelligent map interpretation. However, existing methods in this field primarily depend on the texture features within the images and do not account for the influence of spatial and co-existence relationships among different targets. In this study, taking the administrative regions of the Chinese Mainland, Taiwan, Tibet, and Henan as test targets, we employed the spatial and co-existence relationships of pairs of targets to improve target detection performance. Firstly, these four regions were detected using a simple Single-Target Cascading detection model based on RetinaNet. Subsequently, the detection results were adjusted with the spatial and co-existence relationships of each pair of targets. The adjusted outcomes demonstrate a significant increase in target detection accuracy, as well as precision (from 0.62 to 0.96) and F1 score (from 0.76 to 0.88), for the Chinese Mainland target. This study contributes to the advancement of intelligent map interpretation.

EXPERIENCE OF USING CLOUD SERVICES FOR TEAMWORK BETWEEN SUPERVISOR AND GRADUATE STUDENTS

Given the recent events in the world in general and in Ukraine in particular, in the context of the pandemic caused by the COVID-19 virus infection and the full-scale military invasion of Ukraine, they contributed to the transition of all activities of the educational process to online mode. However, working with postgraduate students still required online work, as practice shows that a significant number of postgraduate students work full-time, and it is very difficult to choose a time that suits both parties. Therefore, there is a problem of finding new opportunities and prospects for using digital technologies for teamwork between supervisors and their Ph.D. students. Based on their own experience, the authors propose to use the following Google Cloud services in the complex: Google Drive, Google Docs, Google Sheet, Google Slide, Google Form, Google Meet, and Google Calendar. The advantages of using such cloud services for the joint work of a supervisor and a postgraduate student are presented. In addition to the proposed Google services for high-quality collaboration, the authors substantiate the expediency of using intelligent maps. The possibilities of using intelligent maps in the work of a supervisor and a postgraduate student are presented. In addition, communication with postgraduate students and management of their activities play an important role in the work of a supervisor. For this type of work, we offer the Trello project management tool. The expedient and pedagogically balanced use of digital technologies in the joint work of supervisors and postgraduate students will help to improve the quality of postgraduate research and increase the productivity of postgraduate students' work on their research. It has been established that the professional development of supervisors working with graduate students still does not receive sufficient attention. The pilot program of advanced training of Ph.D. students' supervisors "Innovative Supervisor", which was implemented in May 2023, is presented.

СПОСОБЫ УПРОЩЕНИЯ НАПИСАНИЯ ТЕСТ-КЕЙСОВ

The main purpose of software testing is formulated, the main ways of correctly compiling test cases are described, and an example of creating an intelligent map in the XMind application is given

Multi-Institution Analysis Demonstrates that Augmented Intelligent Maps Improve Intra-Operative Safety During Physician Modified Endograft Repairs

Multi-Institution Analysis Demonstrates that Augmented Intelligent Maps Improve Intra-Operative Safety During Physician Modified Endograft Repairs

Hybrid architecture to support the intelligent mapping and redesign of organizational processes

The objective of this article was to develop and apply a Hybrid Architecture (HA) based on Business Process Management (BPM), Enterprise Architecture (EA) with TOGAF and Process Mining (PM) to support the intelligent mapping and redesign of organizational processes. The experiments were carried out in four phases: company selection, data selection, computational experiments and comparison of results. The comparison of the results showed that with the application of AH the mapping time was reduced by 60%, the number of people involved by 50% and a 20% reduction in the return time to the customer. The number of activities mapped with AH increased from 19 to 27, that is, 42% more than in the traditional method. It was concluded that AH contributed intelligence, agility and discovery of knowledge not perceptible with other methods to support intelligent mapping and redesign of organizational processes.

Intelligent mapping of geochemical anomalies: Adaptation of DBSCAN and mean-shift clustering approaches

Cluster analysis can be used to organize samples and generate ideas regarding the multivariate geochemistry of given dataset. Traditional clustering techniques have the drawbacks of high computational complexity and poor adaptability to big data. Hence, there has recently been much focus on creating better clustering algorithms. Although many clustering algorithms have been applied, and some produce notable clustering results, the performance efficiency of algorithms is often highly dependent on the values the user chooses for the parameters. Currently, density-based spatial clustering of applications with noise clustering (DBSCAN) is widely utilized in image processing, bioinformatics, and social network analysis owing to its ability to detect clusters of various shapes. Even though partitional clustering techniques may be effective when the number of clusters K is known in advance, they cannot implement non-convex clustering and rapidly return to a local optimum. This study proposes the concept of DBSCAN clustering for stream sediment geochemical data. In this respect, the geochemical data collected from Varcheh district, SW Iran, were processed using the clr transformation before applying DBSCAN. Then, PCA was used to minimize the dimension of variables and specify the mineralization-related elements. In the following, one of the PCs connected with mineralization (PC2) was chosen for further analysis. DBSCAB, Mean-shift and Fuzzy K-means algorithms were used to monitor the multi-element geochemical anomalies linked to MVT PbZn deposits in the study area. According to Davies-Bouldin and Silhouette as two validation metrics, it can be deduced that the three SCB models are advantageous, however, the model generated by DBSCAN is preferable to the model generated by Mean-shift and Fuzzy K-means.

Optimization of patient-specific stereo-EEG recording sensitivity.

Stereo-EEG is a minimally invasive technique used to localize the origin of epileptic activity (the epileptogenic zone) in patients with drug-resistant epilepsy. However, current stereo-EEG trajectory planning methods are agnostic to the spatial recording sensitivity of implanted electrodes. In this study, we used image-based patient-specific computational models to design optimized stereo-EEG electrode configurations. Patient-specific optimized electrode configurations exhibited substantially higher recording sensitivity than clinically implanted configurations, and this may lead to a more accurate delineation of the epileptogenic zone. The optimized configurations also achieved equally good or better recording sensitivity with fewer electrodes compared with clinically implanted configurations, and this may reduce the risk for complications, including intracranial haemorrhage. This approach improves localization of the epileptogenic zone by transforming the clinical use of stereo-EEG from a discrete ad hoc sampling to an intelligent mapping of the regions of interest.

A competitive intelligence acquisition framework for mining user perception from user generated content

Competitive intelligence is an important basis for companies in the process of developing competitive strategies. However, competitive intelligence acquisition methods such as surveys and expert ratings are not able to achieve rapid responses to user perceptions. In addition, the huge amount of unstructured user-generated content makes it more difficult to analyze user perceptions. In this paper, we propose a competitive intelligence mining framework for acquiring user perceptions from user-generated content. The framework covers multiple aspects of competitive intelligence acquisition, mining, analysis, and decision-making. A unified text processing model (WS-TCM) can automatically filter the content irrelevant to competitive intelligence and quickly extract fine-grained user perceptions of competitive attributes from the huge amount of user-generated content. In addition, the quantile-based intelligence mapping method (QB-IM) determines the competitive landscape of an enterprise based on fine-grained user perceptions and provides help for managers’ strategic decisions. In the case study, the method proposed in this paper has significantly improved compared with the baseline model in the stages of competitive intelligence identification, competitive attribute identification, and user perception identification. Especially, the accuracy improvement in identifying user dissatisfaction perception is more obvious. Meanwhile, our model shows strong robustness. In the competitive analysis stage, the results of the framework are consistent with those obtained by market analysts through surveys. This study provides a new approach to competitive intelligence research and fine-grained user perception mining, which improves the efficiency of competitive intelligence acquisition for companies while also improving the reliability, accuracy, and usefulness of competitive intelligence.

Indonesian language learning based on ecological intelligence: A case of Bengawan Solo Nature School

Ecological intelligence has a complex structure for improving education. Learning Indonesian needs to contain ecological intelligence. It aims to make students love, protect and preserve the environment. The purpose of this article is to analyze the way teachers carry out ecological intelligence mapping and assess the potential of advanced students at the Bengawan Solo Natural School. This research method is qualitative with a case study approach. Data and data sources were obtained from the results of document analysis, observation, and in-depth interviews with teachers and students. Test the validity of the data used in this study is the technique of data triangulation and source triangulation. The results of this study are that the teacher maps ecological intelligence by becoming a partner or co-parent in developing the potential that exists in students based on spiritual, intelligence, social-emotional, and physical and motor skills of students. The Bengawan Solo natural school has four types of assessment to measure the potential of students. The types of assessments are (1) moral assessments in the form of Al-Qur'an report cards; (2) leadership assessment in the form of narrative report cards; (3) cognitive and scientific assessments in the form of numerical report cards and portfolio reports; and (4) business assessment in the form of business reports. The Bengawan Solo Nature School does not only educate students to become great people in the future, but also has the character of loving nature and being useful to others.

Recognition and Semantic Information Extraction for Map Based on Deep Learning

Abstract. Geospatial information contained in maps plays an important role in geographic information data acquisition, map understanding, intelligent mapping and other applications. In terms of map recognition and geospatial information extraction from maps, traditional methods that heavily rely on human or human-computer interaction for semantic recognition can no longer meet the real-time needs. In this paper, we first analysed the composition and characteristics of maps, and then systematically illustrated the semantic understanding methods of map image recognition, target detection of geographic features and semantic segmentation of geographic features based on deep learning architecture, which is crucial to intelligent map recognition and mapping.

Desiderata for Intelligent Maps: A Multiperspective Compilation

Interactive digital maps are useful for illustrating and analyzing geographic data and are used for diverse purposes (e.g., wayfinding, data journalism, data analysis, and citizen engagement). This article discusses the requirements of intelligent maps from three perspectives: the literature, a user survey, and a reverse-brainstorming workshop. The ideas brought forth are relevant to researchers and designers of digital maps as they incorporate innovative features and strive for a good user experience.

EXPLORATION AND APPLICATION OF "1+2+3" TEACHING MODE USING VIRTUAL REALITY ENVIRONMENTS FOR GEOMATICS UNDERGRADUATE STUDENTS

Abstract. Since the beginning of this century, mapping and geographic information technology has been deeply integrated with virtual reality, artificial intelligence and other technologies, the mapping industry has entered the "intelligent mapping era", how to train innovative and practical mapping talents is urgent. The teaching team takes the cultivation of innovative and practical talents in surveying and mapping as the core goal, and focuses closely on the cultivation of students' innovation ability and large (complex) project implementation ability. Relying on Guangxi Spatial Information and Mapping Virtual Simulation Experimental Teaching Center and Southern Mapping Virtual Simulation Teaching Platform, the team carries out teaching reform and practice. The team proposes the training mode of "one goal, two synergy, three integration", which will use VR/AR, GIS and other technologies to teach major projects and scientific research achievements through virtual simulation, and adopt online + offline methods to enhance students' innovative practical ability. Through scientific assessment and incentive mechanism, students' initiative and enthusiasm will be improved, thus solving the problem of difficulty in cultivating students' innovation and practice ability. After years of reform and practice, students' innovation and practical ability have been improved significantly, and they have won dozens of awards such as the silver prize of "Internet+" national competition, the second prize of "Challenge Cup" national competition, and the national mapping skills competition. The teaching reform methods have been well promoted.

TransOrGAN: An Artificial Intelligence Mapping of Rat Transcriptomic Profiles between Organs, Ages, and Sexes.

Animal studies are required for the evaluation of candidate drugs to ensure patient and volunteer safety. Toxicogenomics is often applied in these studies to gain understanding of the underlying mechanisms of toxicity, which is usually focused on critical organs such as the liver or kidney in young male rats. There is a strong ethical reason to reduce, refine and replace animal use (the 3Rs), where the mapping of data between organs, sexes and ages could reduce the cost and time of drug development. Herein, we proposed a generative adversarial network (GAN)-based framework entitled TransOrGAN that allowed the molecular mapping of gene expression profiles in different rodent organ systems and across sex and age groups. We carried out a proof-of-concept study based on rat RNA-seq data from 288 samples in 9 different organs of both sexes and 4 developmental stages. First, we demonstrated that TransOrGAN could infer transcriptomic profiles between any 2 of the 9 organs studied, yielding an average cosine similarity of 0.984 between synthetic transcriptomic profiles and their corresponding real profiles. Second, we found that TransOrGAN could infer transcriptomic profiles observed in females from males, with an average cosine similarity of 0.984. Third, we found that TransOrGAN could infer transcriptomic profiles in juvenile, adult, and aged animals from adolescent animals with an average cosine similarity of 0.981, 0.983, and 0.989, respectively. Altogether, TransOrGAN is an innovative approach to infer transcriptomic profiles between ages, sexes, and organ systems, offering the opportunity to reduce animal usage and to provide an integrated assessment of toxicity in the whole organism irrespective of sex or age.

Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction

Mapping is a fundamental application of remote sensing images, and the accurate evaluation of remote sensing image information extraction using artificial intelligence is critical. However, the existing evaluation method, based on Intersection over Union (IoU), is limited in evaluating the extracted information’s boundary accuracy. It is insufficient for determining mapping accuracy. Furthermore, traditional remote sensing mapping methods struggle to match the inflection points encountered in artificial intelligence contour extraction. In order to address these issues, we propose the mean inflection point distance (MPD) as a new segmentation evaluation method. MPD can accurately calculate error values and solve the problem of multiple inflection points, which traditional remote sensing mapping cannot match. We tested three algorithms on the Vaihingen dataset: Mask R-CNN, Swin Transformer, and PointRend. The results show that MPD is highly sensitive to mapping accuracy, can calculate error values accurately, and is applicable for different scales of mapping accuracy while maintaining high visual consistency. This study helps to assess the accuracy of automatic mapping using remote sensing artificial intelligence.

2D-Localization Based on Tracking Antenna Using Artificial Intelligence Mapping (AIM) Approach

2D-Localization Based on Tracking Antenna Using Artificial Intelligence Mapping (AIM) Approach

���������� �������� ��������� �� ������� �����������ί �������������ί ������� �����˲��� ��ֲ������ί ����IJ� �������

The article deals with the use of the "Kropyva" software complex as an element of the prospective automated control system of the National Guard of Ukraine (NGU). Automated troop management systems significantly increase the effectiveness of the process of preparation and military decision-making through the use of accelerated analysis and generalization of information about enemy forces and assets, own forces, and terrain. In fact, instant simulation of various scenarios takes place, and artificial intelligence automatically deduces the most appropriate one in these conditions. Starting from 2018, individual elements of tactical-level information systems were used ? "Delta", "Kropyva", "Virazh-tablet", "GisArta" and others. For the tasks of NGU, the software "Kropyva" is of interest ? a actical link management system based on GIS for creating intelligent maps in combination with devices and instruments, for planning, calculations and orientation on the terrain. The analysis of the functional capabilities of the software complex in solving the tasks of the service and combat activity of the NGU was carried out. It is proposed to use the functionality of the software " Kropyva" when solving the tasks of orientation on the terrain, performing topogodetic calculations, plotting the tactical situation and exchanging this information between users, as well as managing the battle. Currently, there are several types of automated workplace that perform tasks according to their level ? the commander's automated workplace is stationary and the automated workplace is mobile. Recommended recommendations for the use of automated workplaces on the basis of the "Kropyva" in the performance of service-combat (combat) tasks by units and parts of the NGU. It is emphasized that the direct adjustment of the software "Kropyva" system and the corresponding automated workplace should be carried out only after other necessary measures for organizing management and establishing communication.