Search results

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.

Online news websites provide huge amounts of timely news, bringing the challenge of recommending personalized news articles. Generative adversarial networks (GAN) based on collaborative filtering (CFGAN) can achieve effective recommendation quality. However, CFGAN ignores item contents, which contain more latent preference features than just user ratings. It is important to consider both ratings and item contents in making preference predictions. This study aims to improve news recommendation by proposing a GAN-based news recommendation model considering both ratings (implicit feedback) and the latent features of news content.

The collaborative topic modeling (CTM) can improve user preference prediction by combining matrix factorization (MF) with latent topics of item content derived from latent topic modeling. This study proposes a novel hybrid news recommendation model, Hybrid-CFGAN, which modifies the architecture of the CFGAN model with enhanced preference learning from the CTM. The proposed Hybrid-CFGAN model contains parallel neural networks – original rating-based preference learning and CTM-based preference learning, which consider both ratings and news content with user preferences derived from the CTM model. A tunable parameter is used to adjust the weights of the two preference learnings, while concatenating the preference outputs of the two parallel neural networks.

This study uses the dataset collected from an online news website, NiusNews, to conduct an experimental evaluation. The results show that the proposed Hybrid-CFGAN model can achieve better performance than the state-of-the-art GAN-based recommendation methods. The proposed novel Hybrid-CFGAN model can enhance existing GAN-based recommendation and increase the performance of preference predictions on textual content such as news articles.

As the existing CFGAN model does not consider content information and solely relies on history logs, it may not be effective in recommending news articles. Our proposed Hybrid-CFGAN model modified the architecture of the CFGAN generator by adding a parallel neural network to gain the relevant information from news content and user preferences derived from the CTM model. The novel idea of adjusting the preference learning from two parallel neural networks – original rating-based preference learning and CTM-based preference learning – contributes to improve the recommendation quality of the proposed model by considering both ratings and latent preferences derived from item contents. The proposed novel recommendation model can improve news recommendation, thereby increasing the commercial value of news media platforms.

There is limited research on the behavior of different categories of space tourists as identified by different types of space tourism. To address this deficiency, the purpose of this study is to examine what factors make consumers participate in orbital and/or suborbital space tourism, along with three dimensions of motivation, constraint and artificial intelligence. To achieve this study’s goals, a comprehensive research model was developed that included three dimensions of intrinsic and extrinsic motivation, intrapersonal and interpersonal constraint and awareness of and trust in artificial intelligence, in comparing orbital and suborbital space tourism groups.

A questionnaire was carried out with respondents who wanted to participate in orbital (n = 332) and suborbital (n = 332) space tourism in the future. Partial least squares-structural equation modeling, fuzzy-set qualitative comparative analysis, multi-group analysis and deep learning were used to understand potential space tourist behavior.

Extrinsic motivation has the greatest positive impact on behavioral intention, followed by awareness of and trust in artificial intelligence, while intrapersonal constraint strongly negatively affects behavioral intention. Surprisingly, interpersonal constraint is insignificant by partial least squares-structural equation modeling but is still one of sufficient causal configurations by fuzzy-set qualitative comparative analysis. Interestingly, the two types of space tourism have very distinct characteristics.

This study created a comprehensive integrated research model with three dimensions of motivation, constraint and artificial intelligence, along with potential orbital and suborbital space tourist groups, to identify future consumer behavior. Importantly, this study used multi-analysis methods using four different approaches to better shed light on potential orbital and suborbital space tourists.

对不同类型太空旅游所识别的不同类别太空游客行为的研究有限。 为了解决这一缺陷, 这项工作研究了哪些因素使消费者参与轨道和/或亚轨道太空旅游, 以及动机、约束和人工智能三个维度。 为了实现研究目标, 在比较轨道和亚轨道太空旅游群体时, 开发了一个综合研究模型, 包括内在和外在动机、内在和人际约束以及对人工智能的认识和信任三个维度。

对希望在未来参与轨道 (n = 332) 和亚轨道 (n = 332) 太空旅游的受访者进行了问卷调查。 利用偏最小二乘法 (PLS)-结构方程模型 (SEM)、模糊集定性比较分析 (fsQCA)、多组分析和深度学习来了解潜在的太空游客行为。

外在动机对行为意图的积极影响最大, 其次是对人工智能的认识和信任, 而内在约束对行为意图有强烈的负面影响。 令人惊讶的是, 人际约束对于 PLS-SEM 来说是微不足道的, 但对于 fsQCA 来说仍然是充分的因果配置之一。 有趣的是, 这两类太空旅游具有非常鲜明的特点。

这项工作创建了一个全面的综合研究模型, 具有动机、约束和人工智能三个维度, 以及潜在的轨道和亚轨道太空旅游群体, 以确定未来的消费者行为。 重要的是, 这项研究采用了多种分析方法, 使用四种不同的方法来更好地揭示潜在的轨道和亚轨道太空游客。

existe una investigación limitada sobre el comportamiento de las diferentes categorías de turistas espaciales identificados por diferentes tipos de turismo espacial. Para abordar esta deficiencia, este trabajo examina qué factores hacen que los consumidores participen en el turismo espacial orbital y/o suborbital, junto con tres dimensiones de motivación, restricción e inteligencia artificial. Para lograr los objetivos del estudio, se desarrolló un modelo de investigación integral que incluía tres dimensiones de motivación intrínseca y extrínseca, restricción intrapersonal e interpersonal, y conocimiento y confianza en la inteligencia artificial, al comparar grupos de turismo espacial orbital y suborbital.

se realizó un cuestionario con los encuestados que querían participar en el turismo espacial orbital (n = 332) y suborbital (n = 332) en el futuro. Se utilizaron modelos de ecuaciones estructurales (SEM) de mínimos cuadrados parciales (PLS), análisis comparativo cualitativo de conjuntos borrosos (fsQCA), análisis multigrupo y aprendizaje profundo para comprender el comportamiento potencial del turista espacial.

la motivación extrínseca tiene el mayor impacto positivo en la intención de comportamiento, seguida de la conciencia y la confianza en la inteligencia artificial, mientras que la restricción intrapersonal afecta negativamente la intención de comportamiento. Sorprendentemente, la restricción interpersonal es insignificante por PLS-SEM, pero sigue siendo una de las configuraciones causales suficientes por fsQCA. Curiosamente, los dos tipos de turismo espacial tienen características muy distintas.

este trabajo creó un modelo de investigación integral integral con tres dimensiones de motivación, restricción e inteligencia artificial, junto con posibles grupos de turistas espaciales orbitales y suborbitales para identificar el comportamiento futuro del consumidor. Es importante destacar que este estudio empleó métodos de análisis múltiple utilizando cuatro enfoques diferentes para arrojar mejor luz sobre los posibles turistas espaciales orbitales y suborbitales.

This research explores project manager (PM) behavior in their professional virtual communities (PVCs), using social identity theory as a theoretical foundation. The purpose is to examine the extent to which PMs seek information on key topics in the Project Management Body of Knowledge Guide (PMBoK).

A text data analytics methodology that uses quantitative and qualitative analysis techniques is followed. The research method reveals relationships in language-based data gathered from six project management forums and blogs.

Information related to all the PMBoK topics is sought in the project management virtual communities. People management topics account for a dominant portion of interactions. The findings enhance social identification theorizing for the PM role. From a practical standpoint, the findings shed light on focal areas for greater emphasis in PM PVCs.

Our people management finding constructively replicates existing findings via a large, global sample and strengthens calls for increased focus on people management matters in project management. As a result, we call for increased scholarly attention to people management in project management. Finally, we encourage pursuit of several research questions to enhance knowledge of PM information-seeking behavior.

The paper aims to empirically test a framework to predict the desire and intention to engage with an elective health-care procedure and implement a methodology to test the anticipated positive and negative emotions in hedonic adaptation to an elective procedure.

Two studies in USA and Australia (N = 1,200) confirmed the psychometric properties of the key constructs under the chemical peel condition. Two further studies in the USA and Australia (N = 1,100) explored the research question and hypotheses in the adapted model of goal-directed behaviour under the Botox condition. A survey was self-administered to online panels who had previously engaged in such elective procedures.

The findings highlighted the pragmatic implications for communication and activation strategies to safeguard consumer interests and retain their loyalty.

From the authors’ best understanding, neither a methodology nor a theoretical framework exists to explore hedonic adaptation to recurring engagement with elective health care. A methodology and theoretical framework will highlight the mood states and factors that predict desire and intention to engage. This can advance the research on hedonic adaptation and decision-making and offer pragmatic suggestions for communication and activation strategies to safeguard consumer interests and retain their loyalty.

This study examines the antecedents and dynamics of authoritarian leadership and extends the effects of managers' sleep quality to employee behavior.

On the basis of self-regulation theory, 513 unit day samples were analyzed using cross-level path analysis and a Monte Carlo simulation test.

Managers' sleep quality is positively related to authoritarian leadership and positive emotions play a mediating role. Authoritarian leadership is positively related to employees' counterproductive behavior. Managers' sleep quality affects employees' counterproductive behavior through managers' positive emotions and authoritarian leadership.

Individuals should learn to reduce stress and maintain a positive mood. Organizations should reduce employees' overtime work and work stress and find other ways to improve employees' sleep quality.

First, we considered authoritarian leadership to be dynamic and studied it on a daily basis. Second, we studied the antecedents of authoritarian leadership from the perspective of leaders' states (sleep quality and emotions). Third, we discussed the effect of managers' sleep quality on employee behavior.

This study aims to examine the influence of reward personalization on financing outcomes in the Industry 5.0 era, where reward-based crowdfunding meets the personalized needs of individuals.

The study utilizes a corpus of 218,822 crowdfunding projects and 1,276,786 reward options on Kickstarter to investigate the effect of reward personalization on investors’ willingness to participate in crowdfunding. The research draws on expectancy theory and employs quantitative and qualitative approaches to measure reward personalization. Quantitatively, the number of reward options is calculated by frequency; whereas text-mining techniques are implemented qualitatively to extract novelty, which serves as a proxy for innovation.

Findings indicate that reward personalization has an inverted U-shaped effect on investors’ willingness to participate, with investors in life-related projects having a stronger need for reward personalization than those interested in art-related projects. The pledge goal and reward text readability have an inverted U-shaped moderating effect on reward personalization from the perspective of reward expectations and reward instrumentality.

This study refines the application of expectancy theory to online financing, providing theoretical insight and practical guidance for crowdfunding platforms and financiers seeking to promote sustainable development through personalized innovation.

Despite the significance of knowledge sharing for competitive advantage in networked businesses like franchising systems, there is a lack of comprehensive understanding regarding the strategic value of knowledge sharing in the context of franchising. In particular, the specific contribution of information and communication technologies (ICTs) in facilitating interorganizational knowledge exchange among franchising members remains inadequately understood, particularly in emerging economies. Therefore, this study aims to explore the mechanisms involved in the knowledge-sharing process facilitated by a virtual learning environment (VLE) within franchising networks and examine the role of VLEs in facilitating knowledge.

This study uses a multiple-case study approach involving 24 franchisees and the franchisor within a Brazilian franchising network operating in the furniture market to examine the role played by a VLE.

The results of the study reveal that the introduction of a VLE has played a significant role in fostering enhancements in the knowledge-sharing process among the franchisor and franchisees in the network. Moreover, the results indicate that VLEs play a significant role in overcoming geographical obstacles, thereby enabling efficient knowledge sharing between franchisees and franchisors operating in extensive territorial contexts. Finally, findings indicate that intracommercial competition acts as a prominent barrier, leading to low levels of cooperation and knowledge-sharing intent among franchisees within the network.

This study contributes to the existing knowledge by enhancing the understanding of how ICTs can facilitate knowledge sharing in organizations operating within franchising systems. Furthermore, this paper advances the comprehension of the role of networking franchising configuration and governance in supporting organizational improvements. Additional actionable insights are provided.

Because of the various advantages of reinforcement learning (RL) mentioned above, this study uses RL to train unmanned aerial vehicles to perform two tasks: target search and cooperative obstacle avoidance.

This study draws inspiration from the recurrent state-space model and recurrent models (RPM) to propose a simpler yet highly effective model called the unmanned aerial vehicles prediction model (UAVPM). The main objective is to assist in training the UAV representation model with a recurrent neural network, using the soft actor-critic algorithm.

This study proposes a generalized actor-critic framework consisting of three modules: representation, policy and value. This architecture serves as the foundation for training UAVPM. This study proposes the UAVPM, which is designed to aid in training the recurrent representation using the transition model, reward recovery model and observation recovery model. Unlike traditional approaches reliant solely on reward signals, RPM incorporates temporal information. In addition, it allows the inclusion of extra knowledge or information from virtual training environments. This study designs UAV target search and UAV cooperative obstacle avoidance tasks. The algorithm outperforms baselines in these two environments.

It is important to note that UAVPM does not play a role in the inference phase. This means that the representation model and policy remain independent of UAVPM. Consequently, this study can introduce additional “cheating” information from virtual training environments to guide the UAV representation without concerns about its real-world existence. By leveraging historical information more effectively, this study enhances UAVs’ decision-making abilities, thus improving the performance of both tasks at hand.

This study seeks to provide a greater understanding of the variables that influence travellers’ intention to participate in social media, paying special attention to (1) the direct impact of perceived usefulness (PU) of social media and (2) the moderating impact of tourists’ altruism and self-interest.

The proposed conceptual model was empirically tested using an online questionnaire distributed to a sample of 394 tourists visiting a World Heritage city.

The findings show that perceived social media usefulness has a significant effect on users’ intention to share experiences. Additionally, self-interest appears to moderate the relationship between perceived social media usefulness and users’ sharing intention, but the results do not support the moderating effect of altruism.

Despite scholars’ growing interest in social networks as sources of tourist information, little is known about the aspects that encourage users’ participation in these platforms. This paper offers key contributions to the relevant literature in this field and offers compelling recommendations for tour operators' management of social networks.

本研究擬讓我們更清楚了解驅使旅行人士參與社交媒體上的交流活動的變數;為求達至這研究目的，研究人員特別對以下兩方面加以注意和研究：(一) 、旅行人士對社交媒體的感知效用所帶來的直接影響;(二) 、旅行人士的利他主義，以及其對個人利益的考慮所帶來的緩和影響。

研究人員對其提出之概念模型進行實證測試，方法乃透過收集一個包含394名曾參觀世界遺產城市的旅行人士的樣本所回應的網上問卷數據，並進行數據分析。

研究結果顯示，旅行人士若覺得社交媒體是有用的話，則他們會更願意在那裡分享旅行經歷;而且，他們對自己個人利益的考慮，似會緩和他們對社交媒體的感知效用與其分享經歷的願意程度之間的關係;唯研究結果沒有證實利他主義會帶來緩和的影響。

雖然學者對社交網絡作為提供資訊的來源感到興趣，而且這興趣不斷增加，但我們對促進旅行人士參與社交網絡平台活動之因素的了解仍然淺薄，就此而言，本研究於有關的文獻提供了重要的貢獻;研究亦為旅遊經營者就應如何管理社交網絡提供了具說服力的建議。