Search

Complex assistive systems providing human behavior support independent of the age or abilities of users are broadly used in a variety of domains including automotive, production, aviation, or medicine. Current research lacks a common understanding of which architectural components are needed to create assistive systems that use models at runtime. Existing descriptions of architectural components are focused on particular domains, consider only some parts of an assistive system, or do not consider models at runtime. We have analyzed common functional requirements for such systems to be able to propose a set of reusable components, which have to be considered when creating assistive systems that use models. Such components constitute a reference architecture that we propose within this paper. To validate the proposed architecture, we have expressed the architectures of two assistive systems from different domains, namely assistance for elderly people and assistance for operators in smart manufacturing in terms of compliance with such architecture. The proposed reference architecture will facilitate the creation of future assistive systems. [ABSTRACT FROM AUTHOR]

This study introduces an innovative hybrid approach for personalized trip recommendations, aiming to enhance existing recommender systems by leveraging multidimensional data. Our proposed method integrates user preferences and diverse contextual factors to address challenges related to data sparsity effectively. To overcome this hurdle, our methodology employs a clustering approach, streamlining the extraction of Points of Interest (PoI) and reducing computational complexity. The framework comprises three key components: I) a unique strategy for context assessment, achieved by combining contextual information in vector form through the Term-Frequency-Inverse-Document-Frequency technique, II) the incorporation of tourist demographic information to alleviate the Cold Start problem, and III) the implementation of an asymmetric schema that elevates the traditional similarity paradigm. Moreover, our approach utilizes personalized PoIs in consecutive travel patterns, enabling the retrieval and ranking of an optimal list of potential routes. The experimental results based on Flickr and Yelp datasets reveal that the proposed method surpasses prior work on all three metrics, achieving a significant 8% increase in precision and an 11% increase in F-Score, thereby enhancing the quality metrics of personalized trip recommendations. [ABSTRACT FROM AUTHOR]

With the advancement of artificial intelligence, the home care environment for elderly users is becoming increasingly intelligent and systematic. The context aware human–computer interaction technology of sustainable aging-friendly smart homes can effectively identify user needs, enhance energy efficiency, and optimize resource utilization, thereby improving the convenience and sustainability of smart home care services. This paper reviews literature and analyzes cases to summarize the background and current state of context-aware interaction experience research in aging-friendly smart homes. Targeting solitary elderly users aged 60–74, the study involves field observations and user interviews to analyze their characteristics and needs, and to summarize the interaction design principles for aging-friendly smart homes. We explore processes for context-aware and methods for identifying user behaviors, emphasizing the integration of green, eco-friendly, and energy-saving principles in the design process. Focusing on the living experience and quality of life for elderly users living alone, this paper constructs a context-aware user experience model based on multimodal interaction technology. Using elderly falls as a case example, we design typical scenarios for aging-friendly smart homes from the perspectives of equipment layout and innovative hardware and software design. The goal is to optimize the home care experience for elderly users, providing theoretical and practical guidance for smart home services in an aging society. Ultimately, the study aims to develop safer, more convenient, and sustainable home care solutions. [ABSTRACT FROM AUTHOR]

Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion. However, the segmentation process only considers each pixel independently, and the expansion process is difficult to achieve a favorable accuracy-speed trade-off. In this paper, we propose a context-aware and boundary-guided network (CBN) to tackle these problems. In CBN, a basic text detector is first used to predict initial segmentation results. Then, we propose a context-aware module to enhance text kernel feature representations, which considers both global and local contexts. Finally, we introduce a boundary-guided module to expand enhanced text kernels adaptively with only the pixels on the contours, which not only obtains accurate text boundaries but also keeps high speed, especially on high-resolution output maps. In particular, with a lightweight backbone, the basic detector equipped with our proposed CBN achieves state-of-the-art results on several popular benchmarks, and our proposed CBN can be plugged into several segmentation-based methods. Code will be available on https://github.com/XiiZhao/cbn.pytorch. [ABSTRACT FROM AUTHOR]

Visual tracking has become widespread in swarm robots for intelligent video surveillance, navigation, and autonomous vehicles due to the development of machine learning algorithms. Discriminative correlation filter (DCF)-based trackers have gained increasing attention owing to their efficiency. This study proposes "context-aware environmental residual correlation filter tracking via deep convolution features (CAERDCF)" to enhance the performance of the tracker under ambiguous environmental changes. The objective is to address the challenges posed by intensive environment variations that confound DCF-based trackers, resulting in undesirable tracking drift. We present a selective spatial regularizer in the DCF to suppress boundary effects and use the target's context information to improve tracking performance. Specifically, a regularization term comprehends the environmental residual among video sequences, enhancing the filter's discrimination and robustness in unpredictable tracking conditions. Additionally, we propose an efficient method for acquiring environmental data using the current observation without additional computation. A multi-feature integration method is also introduced to enhance the target's presence by combining multiple metrics. We demonstrate the efficiency and feasibility of our proposed CAERDCF approach by comparing it with existing methods using the OTB2015, TempleColor128, UAV123, LASOT, and GOT10K benchmark datasets. Specifically, our method increased the precision score by 12.9% in OTB2015 and 16.1% in TempleColor128 compared to BACF. [ABSTRACT FROM AUTHOR]

Augmented reality provides users with immersive digital experiences by overlaying digital content on top of physical world and helps users better understand reality. In recent years, research on context awareness in augmented reality has received widespread attention. Augmented reality is closely related to its usage context, not only it is basic contextual information such as location information, light level, head posture, but also higher level contextual information such as geometric information, semantic information and eye movement information, these contextual information have impacts on user experience of augmented reality in various degrees. Based on recent advances in context awareness of augmented reality, this paper outlines the contextual factors of augmented reality, illustrates the context-aware processing flow in augmented reality, and analyzes the context-aware algorithms and latest applications related to geometry, semantics and eye movement contextual information in augmented reality. Finally, combined with the current status of augmented reality contextual awareness, it discusses the future development trends of augmented reality contextual awareness, so as to provide reference for future research. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This research aims to prove the effectiveness of a context-aware ubiquitous learning model through the case method and team-based projects in enhancing the knowledge construction skills of students regarding instructional media. In this analysis, a quasiexperimental posttest-only control group design was used, with the subjects comprising 62 students. These students were subsequently split into experimental and control groups of 32 and 30 participants, respectively. An interaction analysis model was also used as the data collection instrument to characterize learning behavior in knowledge construction. This was reflected in a questionnaire, with an independent ttest statistical analysis technique used to analyze the data. The results showed that the context-aware ubiquitous learning model based on the case method and team-based project was effective in improving the knowledge construction skills of students. In managing learning, lecturers were also advised to utilize educational strategies that were more oriented toward the students, such as active techniques including case techniques and team-based projects. [ABSTRACT FROM AUTHOR]

Environmental mapping and robot navigation are the basis for realizing robot automation in modern agricultural production. This study proposes a new autonomous mapping and navigation method for gardening scene robots. First, a new LiDAR slam-based semantic mapping algorithm is proposed to enable the robots to analyze structural information from point cloud images and generate roadmaps from them. Secondly, a general robot navigation framework is proposed to enable the robot to generate the shortest global path according to the road map, and consider the local terrain information to find the optimal local path to achieve safe and efficient trajectory tracking; this method is equipped in apple orchards. The LiDAR was evaluated on a differential drive robotic platform. Experimental results show that this method can effectively process orchard environmental information. Compared with vnf and pointnet++, the semantic information extraction efficiency and time are greatly improved. The map feature extraction time can be reduced to 0.1681 s, and its MIoU is 0.812. The resulting global path planning achieved a 100% success rate, with an average run time of 4ms. At the same time, the local path planning algorithm can effectively generate safe and smooth trajectories to execute the global path, with an average running time of 36 ms. [ABSTRACT FROM AUTHOR]

Modern vehicles are becoming more appealing to potential intruders due to two primary reasons. Firstly, they are now equipped with various connectivity features like WiFi, Bluetooth, and cellular connections, e.g., LTE and 5G, which expose them to external networks. Secondly, the growing complexity of on-board software increases the potential attack surface. In this article, we introduce CAHOOTv2, a context-sensitive intrusion detection system (IDS), aiming at enhancing the vehicle's security and protect against potential intrusions. CAHOOTv2 leverages the vehicle's sensors data, such as the amount of steering, the acceleration and brake inputs, to analyze driver habits and collect environmental information. To demonstrate the validity of the algorithm, we collected driving data from both an artificial intelligence (AI) and 39 humans. We include the AI driver to demonstrate that CAHOOTv2 is able to detect intrusions when the driver is both a human or an AI. The dataset is obtained using a modified version of the MetaDrive simulator, taking into account the presence of an intruder capable of performing the following types of intrusions: denial of service, replay, spoofing, additive and selective attacks. The sensors present in the vehicle are a numerical representation of the environment. The amount of steering, the acceleration and brake inputs given by the driver are based on the environmental situation. The intruder's input often contradicts the driver's wishes. CAHOOTv2 uses vehicle sensors to detect this contradiction. We perform several experiments that show the benefits of hyperparameter optimization. Indeed, we use a hyperparameter tuning paradigm to increase detection accuracy combining randomized and exhaustive search of hyperparameters. As a concluding remark, the results of CAHOOTv2 show great promise in detecting intrusions effectively. [ABSTRACT FROM AUTHOR]

The decentralized nature of blockchain enables data traceability, transparency, and immutability as complementary security features to the existing Internet of Things (IoT) systems. These Blockchain-based IoT (BIoT) systems aim to mitigate security risks such as malicious control, data leakage, and dishonesty often found in traditional cloud-based, vendor-specific IoT networks. As we steadily advance into the era of situation-aware IoT, the use of machine learning (ML) techniques has become essential for synthesizing situations based on sensory contexts. However, the challenge to integrate learning-based situation awareness with BIoT systems restricts the full potential of such integration. This is primarily due to the conflicts between the deterministic nature of smart contracts and the non-deterministic nature of machine learning, as well as the high costs of conducting machine learning on blockchain. To address the challenge, we propose a framework named Situ-Oracle. With the framework, a computation oracle of the blockchain ecosystem is leveraged to provide situation analysis as a service, based on Recurrent Neural Network (RNN)-based learning models tailored for the Situ model, and specifically designed smart contracts are deployed as intermediary communication channels between the IoT devices and the computation oracle. We used smart homes as a case study to demonstrate the framework design. Subsequently, system-wide evaluations were conducted over a physically constructed BIoT system. The results indicate that the proposed framework achieves better situation analysis accuracy (above 95%) and improves gas consumption as well as network throughput and latency when compared to baseline systems (on-chain learning or off-chain model verification). Overall, the paper presents a promising approach for improving situation analysis for BIoT systems, with potential applications in various domains such as smart homes, healthcare, and industrial automation. [ABSTRACT FROM AUTHOR]

The prevalence of mobile devices has significantly increased in recent years, becoming an integral part of our daily lives. This shift has created promising opportunities for mobile advertising, with industry leaders like Apple and Google already integrating it into their services. However, effective mobile advertising still grapples with challenges such as precise customer targeting and adaptability in an ever-changing landscape. To address these issues, we propose an innovative mobile advertising recommender system that employs "context-fitness" and "social referral" techniques. Experiments provide compelling evidence that context-aware information significantly enhances accuracy in predicting users' evolving needs. With our system, we can identify the most suitable ads for targeted users in a changing environment and enhance ad effectiveness by considering friends’ influence. [ABSTRACT FROM AUTHOR]

Chronic Obstructive Pulmonary Disease (COPD) poses a significant global healthcare challenge. It is a progressive lung disease that causes breathing difficulties and can significantly impact a person's quality of life. COPD is primarily caused by smoking, but other factors, such as air pollution and genetic predisposition, can also contribute to its development. This paper introduces a novel Context-Aware Framework for the Diagnosis and Personalized Management of COPD. We discuss the limitations of traditional COPD management, highlighting the importance of early detection and remote monitoring. Early detection and remote monitoring are crucial in managing COPD as they allow for timely interventions and better disease management. In this paper, we propose a framework based mostly on contextual data and other parameters of COPD as put forth by the World Health Organization (WHO) in the form of the International Classification of Functioning, Disability, and Health. Ontologies drive this architecture and incorporate dynamic contextual information from patient environments, user profiles, and sensor data. In addition to the various obvious data items like patient personal details (gender, contact, medical history) and COPD risks and symptoms, the COPD ontology also considers the details about the caregiver and healthcare professional. This is in addition to the contextual data processed separately using the Context Ontology. The ontology we constructed using Protégé serves as the framework for the structured representation and logical inference of contextual information. By harnessing dynamic contextual data, our ontology enables real-time decision-making tailored to individual patient requirements. It empowers healthcare professionals to make informed choices and deliver timely interventions, enhancing healthcare services by offering proactive care to detect early signs of health deterioration and suggest preventive measures. This approach improves patient experiences and optimizes resource allocation within the healthcare system. To uphold ethical standards and prioritize the needs of patients, we emphasize the significance of safeguarding data, obtaining informed permission, and recognizing data ownership. The ontologybased approach presented in this study offers a scalable and flexible framework that can be readily incorporated into existing healthcare systems, redefining the management of COPD in response to evolving demands. Security poses one of the biggest threats in context-based environments due to the different data formats acquired by the diverse sensors. Another essential consideration is confidentiality because the data in hand is sensitive patient information. [ABSTRACT FROM AUTHOR]

Research efforts focused on Smart Building (SB) development have concentrated on the automation of resources within intelligent environments towards an enhanced experience for occupants. The process converts everyday manual activities into automatic actions, such as turning on lights upon entering a room, activating air conditioning on hot days, and switching off a television when there are no viewers. This article addresses a case study on context-aware monitoring conducted at the Laboratory of Distributed Systems and Concurrent Programming (LaSDPC) of the University of São Paulo. The focus is on a Fog layer of the IoT operating closer to sensors and reducing communication delays. Concepts of context-aware systems, multi-agent systems, ontology, and MQTT protocol were considered for the implementation of the intelligent system on-site. The programming languages used were Java and Python, leveraging libraries and frameworks dedicated to such technologies. A scalable system that does not compromise computational resource use and maintains responsiveness with low data exchange latency is proposed and tests checked the intelligent behavior of the laboratory under specific conditions using temperature, luminosity, and presence of a person as parameters. [ABSTRACT FROM AUTHOR]

In an era where digital information is abundant, the role of recommender systems in navigating this vast landscape has become increasingly vital. This study proposes a novel deep learning-based approach integrating multi-context and multi-criteria data within a unified neural network framework. The model processes these dimensions concurrently, significantly improving the precision of personalized recommendations. Context-aware and multi-criteria recommender systems extend traditional two-dimensional user-item preference methods with context awareness and multiple criteria. In contrast to traditional methods, our approach intricately weaves together multi-context and multi-criteria data within its architecture. This concurrent processing enables sophisticated interactions between context and criteria, enhancing recommendation accuracy. While context-aware systems incorporate contextual information such as time and location when making recommendations, multi-criteria-based approaches offer a spectrum of evaluative criteria, enriching the user experience with more tailored and relevant suggestions. Although both approaches have advantages in producing more accurate and personalized referrals, context information and multi-criteria ratings have not been employed together for producing recommendations. Our research proposes a novel deep learning-based approach for the multi-context, multi-criteria recommender system to address this gap. In contrast to traditional approaches that process context-aware recommender systems and multi-criteria recommender systems separately, our deep learning model intricately weaves together multi-context and multi-criteria data within its architecture. This integration is not staged; both dimensions are concurrently processed through a unified neural network framework. The model facilitates a sophisticated interaction between context and criteria by embedding these elements into the core of the network’s multiple layers. This methodology enhances the system’s adaptability and significantly improves its precision in delivering personalized recommendations, leveraging the compounded effects of contextual and criteria-specific insights. The proposed model shows superior performance in predictive tasks, achieving the lowest Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) on the TripAdvisor and ITMRec datasets compared to other state-of-the-art recommendation techniques. Context-aware multi-criteria ratings data demonstrate the robustness and accuracy of the model.

Humans possess the remarkable capacity to comprehend narratives presented in text and subsequently conjure associated mental images through their imagination. This cognitive ability enhances their grasp of the content and augments their overall enjoyment. Consequently, the development of an automated system aimed at producing visually faithful images based on textual descriptions, often referred to as the text-to-image task, stands as a profoundly meaningful endeavor. For this reason, a variety of text-to-image generating artificial intelligences (AIs) have been devised until now. Nevertheless, the generative AIs introduced thus far encounter an issue wherein they struggle to uphold the coherence of input sentences, particularly when multiple sentences are provided. Within this paper, we present a remedy to this challenge through the application of prompt editing. Furthermore, our experimental results substantiate that our proposed solution more effectively preserves contextual coherence among the generated images in comparison to other preexisting generative artificial intelligence models. The experimental results demonstrate that the proposed scheme improves performance by at least 30 percent in terms of the similarity of the generated image and by 130 percent in terms of $ROUGE_{recall}$ .

Due to the limited availability of power defect data， most current defect detection methods are unable to accurately detect power system anomalies. To overcome this challenge， a few-shot image generation method is employed. Building upon the improved local-fusion generative adversarial network （LoFGAN）， a context-aware few-shot image generator is designed to enhance the defect detection network’s capability to extract detailed features. A regularization loss based on LC-divergence is introduced to optimize the training effectiveness of the image generation model on limited datasets. Experimental results reveal that the few-shot image generation method can generate effective and diverse defect data for power scenarios. The proposed model can address the issue of data unavailability in power defect scenarios.

This article proposes an architecture of an intelligent and autonomous recommendation system to be applied to any virtual learning environment, with the objective of efficiently recommending digital resources. The paper presents the architectural details of the intelligent and autonomous dimensions of the recommendation system. The paper describes a hybrid recommendation model that orchestrates and manages the available information and the specific recommendation needs, in order to determine the recommendation algorithms to be used. The hybrid model allows the integration of the approaches based on collaborative filter, content or knowledge. In the architecture, information is extracted from four sources: the context, the students, the course and the digital resources, identifying variables, such as individual learning styles, socioeconomic information, connection characteristics, location, etc. Tests were carried out for the creation of an academic course, in order to analyse the intelligent and autonomous capabilities of the architecture.

With the development of deep learning, synthetic aperture radar (SAR) ship detection and recognition based on deep learning have gained widespread application and advancement. However, there are still challenging issues, manifesting in two primary facets: firstly, the imaging mechanism of SAR results in significant noise interference, making it difficult to separate background noise from ship target features in complex backgrounds such as ports and urban areas; secondly, the heterogeneous scales of ship target features result in the susceptibility of smaller targets to information loss, rendering them elusive to detection. In this article, we propose a context-aware one-stage ship detection network that exhibits heightened sensitivity to scale variations and robust resistance to noise interference. Then we introduce a Local feature refinement module (LFRM), which utilizes multiple receptive fields of different sizes to extract localmulti-scale information, followed by a two-branch channel-wise attention approach to obtain local cross-channel interactions. To minimize the effect of a complex background on the target, we design the global context aggregation module (GCAM) to enhance the feature representation of the target and suppress the interference of noise by acquiring long-range dependencies. Finally, we validate the effectiveness of our method on three publicly available SAR ship detection datasets, SAR-Ship-Dataset, high-resolution SAR images dataset (HRSID), and SAR ship detection dataset (SSDD). The experimental results show that our method is more competitive, with AP50s of 96.3, 93.3, and 96.2% on the three publicly available datasets, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Zhejiang Electric Power is the property of Zhejiang Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This article proposes an architecture of an intelligent and autonomous recommendation system to be applied to any virtual learning environment, with the objective of efficiently recommending digital resources. The paper presents the architectural details of the intelligent and autonomous dimensions of the recommendation system. The paper describes a hybrid recommendation model that orchestrates and manages the available information and the specific recommendation needs, in order to determine the recommendation algorithms to be used. The hybrid model allows the integration of the approaches based on collaborative filter, content or knowledge. In the architecture, information is extracted from four sources: the context, the students, the course and the digital resources, identifying variables, such as individual learning styles, socioeconomic information, connection characteristics, location, etc. Tests were carried out for the creation of an academic course, in order to analyse the intelligent and autonomous capabilities of the architecture. [ABSTRACT FROM AUTHOR]

Knowledge graphs have been widely used in recent years to build recommendation systems. However, in related research, the main focus has been on improving recommendation algorithms, with less attention paid to the type of knowledge graph that is more conducive to knowledge recommendations. This paper addresses knowledge recommendation systems in the shipbuilding domain by constructing knowledge graphs in two ways and comparing their performance in knowledge recommendation. One type of knowledge graph is built based on classification tags of knowledge documents, characterized by its simplicity and sparsity; the other is constructed automatically using machine learning, linking knowledge documents together based on concepts and relationships extracted by the algorithm, featuring complexity and density. To recommend shipbuilding knowledge, a context-aware mechanism was employed, gathering information from the user's task environment and linking it to the knowledge graph. Then, using RippleNet, the system spreads the user's interests within the knowledge graph and infers the required knowledge documents. Experimental results show that the sparse knowledge graph achieved better recommendation results. We believe this is due to the human expert experience relied upon during the construction of the sparse knowledge graph, namely a knowledge classification system oriented towards knowledge applications. [ABSTRACT FROM AUTHOR]

Copyright of Acta Scientiarum Naturalium Universitatis Pekinensis is the property of Editorial Office of Acta Scientiarum Naturalium Universitatis Pekinensis and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Augmented Reality is a technique that allows users to overlap digital information with their physical world. The Augmented Reality (AR) displays have an exceptional characteristic from the Human–Computer Interaction (HCI) perspective. Due to its increasing popularity and application in diverse domains, increasing user-friendliness and AR usage are critical. Context-aware is one approach since an AR application can adapt to the user, environment, needs and enhance ergonomic principles and functionality. This paper proposes the Intelligent Contextaware Augmented Reality Model (ICAARM) for Human–Computer Interaction systems. This study explores and reduces interaction uncertainty by semantically modeling user-specific interaction with context, allowing personalised interaction. Sensory information is captured from an AR device to understand user interactions and context. These depictions carry semantics to Augmented Reality applications about the user's intention to interact with a specific device affordance. Thus, this study describes personalised gesture interaction in VR/AR applications for immersive/intelligent environments. [ABSTRACT FROM AUTHOR]

Graph convolutional networks (GCN) have attracted increasing attention in hyperspectral images (HSIs) classification because of its excellent capacities in modeling arbitrarily irregular data. The essential aim of GCN-based methods is obtaining a more reliable graph that accurately describes the similarity between graph nodes and makes its representation more discriminative. However, it is a challenging task to get a high-quality graph during the convolution process. In this paper, a novel spectral-spatial dynamic graph convolutional network (SSD-GCN) is proposed for HSIs classification, which not only can adaptively update graph according to the HSI content but also can generate the discriminative node features during the convolution process, by integrating the current spectral-spatial information of nodes and the graph embedding in the previous layers. Unlike the traditional GCN-based methods that directly convert the raw HSI into a graph in the preprocessing process, we further integrate the graph mapping into the network, to reduce the irrelevant information among spectral bands and facilitate node feature learning. In addition, an auxiliary local context-aware feature reconstruction is constructed to enhance the local representational capacities of the node features and alleviate over-smoothing. Extensive experiments compared with state-of-the-art methods on three HSIs datasets, including Pavia University, Salinas, and Kennedy Space Center, demonstrate the effectiveness and superiority of our proposed SSD-GCN method, even with small-sized training data. [ABSTRACT FROM AUTHOR]

National Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), China Retrieving out-of-reach objects is a crucial task in virtual reality (VR). One of the most commonly used approaches for this task is the gesture-based approach, which allows for bare-hand, eyes-free, and direct retrieval. However, previous work has primarily focused on assigned gesture design, neglecting the context. This can make it challenging to accurately retrieve an object from a large number of objects due to the one-to-one mapping metaphor, limitations of finger poses, and memory burdens. There is a general consensus that objects and contexts are related, which suggests that the object expected to be retrieved is related to the context, including the scene and the objects with which users interact. As such, we propose a commonsense knowledge-driven joint reasoning approach for object retrieval, where human grasping gestures and context are modeled using an And-Or graph (AOG). This approach enables users to accurately retrieve objects from a large number of candidate objects by using natural grasping gestures based on their experience of grasping physical objects. Experimental results demonstrate that our proposed approach improves retrieval accuracy. We also propose an object retrieval system based on the proposed approach. Two user studies show that our system enables efficient object retrieval in virtual environments (VEs). [ABSTRACT FROM AUTHOR]

Recommendation systems serve as a pivotal solution to address the increasing issue of information overload. While traditional recommendation algorithms have been grounded primarily on user-item interactions, the significance of a user's contextual information influencing decision-making has often been overlooked. Such neglect becomes more evident in the realm of systems integrating contextual mechanisms, which encounter pronounced data sparsity challenges. Existing studies in contextual recommendation systems tend to treat all contextual features uniformly as influencers of user decisions. Yet, a prevalent dilemma is the frequent absence of contextual data, leading to potential misallocations of contextual features. To mitigate these challenges, a novel deep learning-based recommendation system, termed the CAW-NeuMF Model, has been designed. Accompanying this model, a Context-aware Weighted high-order Tensor Factorization algorithm (CAWTF) has been introduced. This algorithm facilitates the calculation of correlations between user ratings in varied contexts, relying on the said context. Additionally, it ascertains the weight of context features grounded on the user ratings correlation. Such a process aids in isolating the most influential contextual features, thereby amplifying the efficiency of personalized recommendations. Empirical evaluations using the LDOS CoMoDa dataset revealed that the proposed model substantially enhances prediction score accuracy. Comparative analyses against alternative recommendation models further affirmed the superior efficacy of the introduced approach. [ABSTRACT FROM AUTHOR]

Visual tracking has become widespread in swarm robots for intelligent video surveillance, navigation, and autonomous vehicles due to the development of machine learning algorithms. Discriminative correlation filter (DCF)-based trackers have gained increasing attention owing to their efficiency. This study proposes “context-aware environmental residual correlation filter tracking via deep convolution features (CAERDCF)” to enhance the performance of the tracker under ambiguous environmental changes. The objective is to address the challenges posed by intensive environment variations that confound DCF-based trackers, resulting in undesirable tracking drift. We present a selective spatial regularizer in the DCF to suppress boundary effects and use the target’s context information to improve tracking performance. Specifically, a regularization term comprehends the environmental residual among video sequences, enhancing the filter’s discrimination and robustness in unpredictable tracking conditions. Additionally, we propose an efficient method for acquiring environmental data using the current observation without additional computation. A multi-feature integration method is also introduced to enhance the target’s presence by combining multiple metrics. We demonstrate the efficiency and feasibility of our proposed CAERDCF approach by comparing it with existing methods using the OTB2015, TempleColor128, UAV123, LASOT, and GOT10K benchmark datasets. Specifically, our method increased the precision score by 12.9% in OTB2015 and 16.1% in TempleColor128 compared to BACF.

Environmental mapping and robot navigation are the basis for realizing robot automation in modern agricultural production. This study proposes a new autonomous mapping and navigation method for gardening scene robots. First, a new LiDAR slam-based semantic mapping algorithm is proposed to enable the robots to analyze structural information from point cloud images and generate roadmaps from them. Secondly, a general robot navigation framework is proposed to enable the robot to generate the shortest global path according to the road map, and consider the local terrain information to find the optimal local path to achieve safe and efficient trajectory tracking; this method is equipped in apple orchards. The LiDAR was evaluated on a differential drive robotic platform. Experimental results show that this method can effectively process orchard environmental information. Compared with vnf and pointnet++, the semantic information extraction efficiency and time are greatly improved. The map feature extraction time can be reduced to 0.1681 s, and its MIoU is 0.812. The resulting global path planning achieved a 100% success rate, with an average run time of 4ms. At the same time, the local path planning algorithm can effectively generate safe and smooth trajectories to execute the global path, with an average running time of 36 ms.

Abstract With the increasing volume of news articles available on the internet, personalized news recommendations have become increasingly important for users to discover relevant and interesting news articles. However, traditional recommender systems often fail to capture the dynamic nature of users' preferences and the changing trends in news articles. To address this challenge, this paper proposes a context-aware personalized news recommendation system that incorporates contextual information to enhance the personalization of news recommendations. The approach involves collecting, extracting, exploring, cleaning, and processing a large dataset of news articles from 19 distinct internet news sources, totaling 22,657 English pieces. Four different recommender systems were built using different techniques, including content-based methods such as TF-IDF, Bag-of-Words, and Word2Vec, and a collaborative filtering system based on click behavior. To evaluate the effectiveness of our models, we used a combination of standard comparison metric, including precision and recall, and user feedback. To demonstrate the applicability of the model, a web interface was constructed, and we used RMSE and MAE to evaluate the performance of the collaborative filtering model. In addition, we conducted a comparative study to compare the accuracy of different algorithms with different baseline methods, including random and recency. The evaluation results showed that incorporating contextual information and collaborative filtering can significantly improve the personalization of news recommendations. The study suggests that the collaborative filtering model based on click behavior is the most effective approach, with a mean MAE of 0.0252 and a mean RMSE of 0.0364. The content-based models were also effective approaches for recommending news articles, outperforming the baseline approaches.

The traditional Colombian vallenato was declared Intangible Cultural Heritage of Humanity by UNESCO on 1 December 2015 with urgency for it to be safeguarded, which led the government of Colombia in the head of the Ministry of Culture and the vallenato music cluster to develop a safeguarding plan that contains different activities, among which stands out a platform for the management of vallenato through educational processes. In this sense, this document proposes an ontological model for the representation of vallenato as cultural heritage in a context-aware system called Vallenatic. The ontology was developed using the NeOn methodology, designed in the Protégé software, and has 15 concepts (Vallenata Songs, Artist, Devices, Persons, Environment, Cultural Managers, Interface, Location, MOOC, Learning Object, Profile, Preference, Net, Time Cultural, Event, Cultural_Sites). The model was evaluated by means of nine (9) situations described in natural language and SWRL; this language was used since it allows expressing OWL concepts in combination with RuleML. The proposed model can be used for other musical genres that have the recognition of cultural and intangible heritage, such as the Spanish flamenco, Argentine Tango, Mexican Mariachi music, Peruvian scissors dance, Brazilian capoeira, Dominican bachata, Jamaican reggae, among others.

Crowd monitoring for sports games is important to improve public safety, game experience, and venue management. Recent crowd-crushing incidents (e.g., the Kanjuruhan Stadium disaster) have caused 100+ deaths, calling for advancements in crowd-monitoring methods. Existing monitoring approaches include manual observation, wearables, video-, audio-, and WiFi-based sensing. However, few meet the practical needs due to their limitations in cost, privacy protection, and accuracy.

The existing dataset for visual dialog comprises multiple rounds of questions and a diverse range of image contents. However, it faces challenges in overcoming visual semantic limitations, particularly in obtaining sufficient context from visual and textual aspects of images. This paper proposes a new visual dialog dataset called Diverse History-Dialog (DS-Dialog) to address the visual semantic limitations faced by the existing dataset. DS-Dialog groups relevant histories based on their respective Microsoft Common Objects in Context (MSCOCO) image categories and consolidates them for each image. Specifically, each MSCOCO image category consists of top relevant histories extracted based on their semantic relationships between the original image caption and historical context. These relevant histories are consolidated for each image, and DS-Dialog enhances the current dataset by adding new context-aware relevant history to provide more visual semantic context for each image. The new dataset is generated through several stages, including image semantic feature extraction, keyphrase extraction, relevant question extraction, and relevant history dialog generation. The DS-Dialog dataset contains about 2.6 million question-answer pairs, where 1.3 million pairs correspond to existing VisDial’s question-answer pairs, and the remaining 1.3 million pairs include a maximum of 5 image features for each VisDial image, with each image comprising 10-round relevant question-answer pairs. Moreover, a novel adaptive relevant history selection is proposed to resolve missing visual semantic information for each image. DS-Dialog is used to benchmark the performance of previous visual dialog models and achieves better performance than previous models. Specifically, the proposed DSDialog model achieves an 8% higher mean reciprocal rank (MRR), 11% higher R@1%, 6% higher R@5%, 5% higher R@10%, and 8% higher normalized discounted cumulative gain (NDCG) compared to LF. DS-Dialog also achieves approximately 1 point improvement on R@k, mean, MRR, and NDCG compared to the original RVA, and 2 points improvement compared to LF and DualVD. These results demonstrates the importance of the relevant semantic historical context in enhancing the visual semantic relationship between textual and visual representations of the images and questions. [ABSTRACT FROM AUTHOR]

The traditional Colombian vallenato was declared Intangible Cultural Heritage of Humanity by UNESCO on 1 December 2015 with urgency for it to be safeguarded, which led the government of Colombia in the head of the Ministry of Culture and the vallenato music cluster to develop a safeguarding plan that contains different activities, among which stands out a platform for the management of vallenato through educational processes. In this sense, this document proposes an ontological model for the representation of vallenato as cultural heritage in a context-aware system called Vallenatic. The ontology was developed using the NeOn methodology, designed in the Protégé software, and has 15 concepts (Vallenata Songs, Artist, Devices, Persons, Environment, Cultural Managers, Interface, Location, MOOC, Learning Object, Profile, Preference, Net, Time Cultural, Event, Cultural_Sites). The model was evaluated by means of nine (9) situations described in natural language and SWRL; this language was used since it allows expressing OWL concepts in combination with RuleML. The proposed model can be used for other musical genres that have the recognition of cultural and intangible heritage, such as the Spanish flamenco, Argentine Tango, Mexican Mariachi music, Peruvian scissors dance, Brazilian capoeira, Dominican bachata, Jamaican reggae, among others. [ABSTRACT FROM AUTHOR]

This article proposes a context-aware course-planning model for pervasive learning environments. The model considers learners' preferences, including their learning styles, locations, activities, and devices. The model generates four-dimensional contexts based on these preferences, each dimension being a weighted vector of visual, aural, read/write, and kinesthetic (VARK) features. Using a content-based similarity algorithm, the model adapts the course content to each learner's context. The courses are created in a sequence of rings, each containing all possible learning materials (LMs) that have the same content in different formats. Each LM is represented by a vector with weights like those of the learners' context dimensions. The model generates all possible plans based on the predefined contexts of the learner, detects the learner's actual context, and adapts the content accordingly. The goal of the model is to enable learners to learn what they want, in the way they prefer, and to complete courses efficiently, at any time, place, and during any activity, in the appropriate format. [ABSTRACT FROM AUTHOR]

Integrating the Internet of Medical Things (IoMT) in the Hospital system has modified the traditional medical service from a reactive system based on hospitalization and diseases to a preventive and interoperable system based mainly on the interactive data flow between patients and health professionals. Medical data is collected and processed using medically connected objects (MCOs). According to gathered data, the new medical system should be able to sort patient states based on urgent and critical vital signs, and consequently, priorities are defined. In this paper, we focus on managing priority in hospital emergencies to adapt dynamic operations and interactions with different stakeholders according to the changes in their execution context. Indeed, based on data sensed from MCOs implemented in ambulances, emergency rooms might be prepared to receive injured persons like victims of road accidents or other incidents. Therefore, we design a context-aware monitoring framework for injured people based on gathered medical data to manage priorities. [ABSTRACT FROM AUTHOR]

Point-of-Interest (POI) recommender systems can effectively assist users to find their preferred POIs. Recent studies mainly focus on extracting users' dynamic context from their check-in behaviors and using attention mechanism to capture different influence of context information for predicting their real-time requirements. However, the existing methods mainly focus on learning the weights of different POI as well as their correlations in the check-in sequences. In addition, these methods still suffer from limited performance, especially when the interaction data are sparse. In this paper, we propose a C ontext- and C ategory-aware D ouble S elf-A ttention (CCDSA) model for POI recommendation to explore and capture users' contextual preferences in two different aspects collaboratively, including the fine-grained preference for POI in check-in behaviors and the coarse-grained preference for category. Specifically, we first design a double self-attention mechanism module to learn the users' preferences for both POI and category in specific context. Then we combine users' check-in behaviors with POIs' category information to alleviate data sparsity problem in context-aware recommendation. Finally, we leverage context and category information to perform personalized POI recommendation. In particular, we devise an improved version of CCDSA, i.e., CCDSA+, which further replaces the self-attention mechanism with the sparse self-attention mechanism for improving training efficiency. The experimental results on four real-world datasets, Foursquare-NY, Foursquare-TKY, Weeplaces-NY and Weeplaces-SF show that the proposed models, CCDSA and CCDSA+, outperform the baselines. [ABSTRACT FROM AUTHOR]

For oriented object detection, the existing CNN-based methods typically rely on a substantial and diverse dataset, which can be expensive to acquire and demonstrate limited capacity for generalization when faced with new categories that lack annotated samples. In this case, we propose MOCA-Net, a few-shot oriented object detection method with a multi-oriented enhancement branch and context-aware module, utilizing a limited number of annotated samples from novel categories for training. Especially, our method generates multi-oriented and multi-scale positive samples and then inputs them into an RPN and the detection head as a multi-oriented enhancement branch for enhancing the classification and regression capabilities of the detector. And by utilizing the context-aware module, the detector can effectively extract contextual information surrounding the object and incorporate it into RoI features in an adaptive manner, thereby improving its classification capability. As far as we know, our method is the first to attempt this in this field, and comparative experiments conducted on the public remote sensing dataset DOTA for oriented object detection showed that our method is effective. [ABSTRACT FROM AUTHOR]

Summary: Text classification is one of the most important tasks to extract information from the Internet and identifying the best text representation settings. With the increase of data volume on the world wide web, the significance of text classification increases. This situation requires huge human efforts to understand and classify the digital data available on the Internet. Text classification is classifying the number of text files into different classes. The data or text available on the Internet is in an unstructured form which increases the difficulty to understand and classify it for useful purposes. This paper proposes a context‐aware text classification system to improve text quality. We use a content‐aware recommendation system to extract the data from well‐known news databases. Text preprocessing techniques like tokenization, stemming, and stop words removal are studied in detail. Furthermore, unigram, bigram, and trigram attributes are also being tested. Attribute selection methods are also examined and their impact on the text classification results. To carry out a detailed investigation, 11 versions are created of each dataset to save the time in experimentation process and applied the different preprocessing techniques to understand the impact of each technique on classification results. The proposed system is compared with the existing approach to check the accuracy where the proposed system achieved better performance. [ABSTRACT FROM AUTHOR]