Search results

The purpose of this research is to achieve multi-task autonomous driving by adjusting the network architecture of the model. Meanwhile, after achieving multi-task autonomous driving, the authors found that the trained neural network model performs poorly in untrained scenarios. Therefore, the authors proposed to improve the transfer efficiency of the model for new scenarios through transfer learning.

First, the authors achieved multi-task autonomous driving by training a model combining convolutional neural network and different structured long short-term memory (LSTM) layers. Second, the authors achieved fast transfer of neural network models in new scenarios by cross-model transfer learning. Finally, the authors combined data collection and data labeling to improve the efficiency of deep learning. Furthermore, the authors verified that the model has good robustness through light and shadow test.

This research achieved road tracking, real-time acceleration–deceleration, obstacle avoidance and left/right sign recognition. The model proposed by the authors (UniBiCLSTM) outperforms the existing models tested with model cars in terms of autonomous driving performance. Furthermore, the CMTL-UniBiCL-RL model trained by the authors through cross-model transfer learning improves the efficiency of model adaptation to new scenarios. Meanwhile, this research proposed an automatic data annotation method, which can save 1/4 of the time for deep learning.

This research provided novel solutions in the achievement of multi-task autonomous driving and neural network model scenario for transfer learning. The experiment was achieved on a single camera with an embedded chip and a scale model car, which is expected to simplify the hardware for autonomous driving.

During the supply chain disruptions caused by COVID-19, logistics service providers (LSPs) have invested heavily in innovations to enhance their supply chain resilience capabilities. However, only little attention has been given so far to the nature of these innovative capabilities, in particular to what extent LSPs were able to repurpose capabilities to build supply chain resilience. In response, using the concept of exaptation, this study identifies to what extent LSPs have discovered and utilized latent functions to build supply chain resilience capabilities during a disruptive event of high impact and low probability.

This conceptual paper uses a theory building approach to advance the literature on supply chain resilience by delineating the relationship between exaptation and supply chain resilience capabilities in the context of COVID-19. To do so, we propose two frameworks: (1) to clarify the role of exaptation for supply chain resilience capabilities and (2) to depict four different exaptation dimensions for the supply chain resilience capabilities of LSPs.

We illustrate how LSPs have repurposed original functions into new products or services to build their supply chain resilience capabilities and combine the two critical concepts of exploitation and exploration capabilities to identify four exaptation dimensions in the context of LSPs, namely impeded exaptation, configurative exaptation, transformative exaptation and ambidextrous exaptation.

As one of the first studies linking exaptation and supply chain resilience, the framework and subsequent categorization advance the understanding of how LSPs can build exapt-driven supply chain resilience capabilities and synthesize the current literature to offer conceptual clarity regarding the varied implications and outcomes linked to the repurposing of capabilities.

Digital twin (DT) and building information modeling (BIM) are interconnected in some ways. However, there has been some misconception about how DT differs from BIM. As a result, industry professionals reject DT even in BIM-based construction projects due to reluctance to innovate. Furthermore, researchers have repeatedly developed tools and techniques with the same goals using DT and BIM to assist practitioners in construction projects. Therefore, this study aims to assist industry professionals and researchers in understanding the relationship between DT and BIM and synthesize existing works on DT and BIM.

A systematic review was conducted on published articles related to DT and BIM. A total record of 54 journal articles were identified and analyzed.

The analysis of the selected journal articles revealed four types of relationships between DT and BIM: BIM is a subset of DT, DT is a subset of BIM, BIM is DT, and no relationship between BIM and DT. The existing research on DT and BIM in construction projects targets improvements in five areas: planning, design, construction, operations and maintenance, and decommissioning. In addition, several areas have emerged, such as developing geo-referencing approaches for infrastructure projects, applying the proposed methodology to other construction geometries and creating 3D visualization using color schemes.

This study contributed to the existing body of knowledge by overviewing existing research related to DT and BIM in construction projects. Also, it reveals research gaps in the body of knowledge to point out directions for future research.

This paper aims to investigate how congruent keywords are used in information security policies (ISPs) to pinpoint and guide clear actionable advice and suggest a metric for measuring the quality of keyword use in ISPs.

A qualitative content analysis of 15 ISPs from public agencies in Sweden was conducted with the aid of Orange Data Mining Software. The authors extracted 890 sentences from these ISPs that included one or more of the analyzed keywords. These sentences were analyzed using the new metric – keyword loss of specificity – to assess to what extent the selected keywords were used for pinpointing and guiding actionable advice. Thus, the authors classified the extracted sentences as either actionable advice or other information, depending on the type of information conveyed.

The results show a significant keyword loss of specificity in relation to pieces of actionable advice in ISPs provided by Swedish public agencies. About two-thirds of the sentences in which the analyzed keywords were used focused on information other than actionable advice. Such dual use of keywords reduces the possibility of pinpointing and communicating clear, actionable advice.

The suggested metric provides a means to assess the quality of how keywords are used in ISPs for different purposes. The results show that more research is needed on how keywords are used in ISPs.

The authors recommended that ISP designers exercise caution when using keywords in ISPs and maintain coherency in their use of keywords. ISP designers can use the suggested metrics to assess the quality of actionable advice in their ISPs.

The keyword loss of specificity metric adds to the few quantitative metrics available to assess ISP quality. To the best of the authors’ knowledge, applying this metric is a first attempt to measure the quality of actionable advice in ISPs.

Entrepreneurial ventures aspiring to disrupt existing market incumbents often use business-model innovation to increase the attractiveness of their offerings. A value proposition is the central element of a business model, and is critical for this purpose. However, how entrepreneurial ventures modify their value propositions to increase the attractiveness of their comparatively inferior offerings is not well understood. The purpose of this paper is to analyze the value proposition innovation (VPI) of aspiring disruptors.

The authors used a flexible pattern matching approach to ground the inductive findings in extant theory. The authors conducted 21 semi-structured interviews with managers from startups in the global electric vehicle industry.

The authors developed a framework, showing two factors, determinants and tactics, that play a key role in VPI connected by a continuous feedback loop. Directed by the determinants of cognitive antecedents, development drivers and realization capabilities, aspiring disruptors determine the scope, focus and priorities of various configuration and support tactics to enable and secure the success of their value proposition.

The authors contribute to theory by showing how cognitive antecedents, development drivers and capabilities determine VPI tactics to disrupt existing market incumbents, furthering the understanding of configuration tactics. The results have important implications for disruptive innovation theory, and entrepreneurship research and practice, as they offer an explanatory framework to analyze strategies of aspiring disruptors who increase the attractiveness of sustainable technologies, thereby accelerating their diffusion.

Agriculture is the backbone of a country, contributing more than half of the sector of economy throughout the world. The need for precision agriculture is essential in evaluating the conditions of the crops with the aim of determining the proper selection of pesticides. The conventional method of pest detection fails to be stable and provides limited accuracy in the prediction. This paper aims to propose an automatic pest detection module for the accurate detection of pests using the hybrid optimization controlled deep learning model.

The paper proposes an advanced pest detection strategy based on deep learning strategy through wireless sensor network (WSN) in the agricultural fields. Initially, the WSN consisting of number of nodes and a sink are clustered as number of clusters. Each cluster comprises a cluster head (CH) and a number of nodes, where the CH involves in the transfer of data to the sink node of the WSN and the CH is selected using the fractional ant bee colony optimization (FABC) algorithm. The routing process is executed using the protruder optimization algorithm that helps in the transfer of image data to the sink node through the optimal CH. The sink node acts as the data aggregator and the collection of image data thus obtained acts as the input database to be processed to find the type of pest in the agricultural field. The image data is pre-processed to remove the artifacts present in the image and the pre-processed image is then subjected to feature extraction process, through which the significant local directional pattern, local binary pattern, local optimal-oriented pattern (LOOP) and local ternary pattern (LTP) features are extracted. The extracted features are then fed to the deep-convolutional neural network (CNN) in such a way to detect the type of pests in the agricultural field. The weights of the deep-CNN are tuned optimally using the proposed MFGHO optimization algorithm that is developed with the combined characteristics of navigating search agents and the swarming search agents.

The analysis using insect identification from habitus image Database based on the performance metrics, such as accuracy, specificity and sensitivity, reveals the effectiveness of the proposed MFGHO-based deep-CNN in detecting the pests in crops. The analysis proves that the proposed classifier using the FABC+protruder optimization-based data aggregation strategy obtains an accuracy of 94.3482%, sensitivity of 93.3247% and the specificity of 94.5263%, which is high as compared to the existing methods.

The proposed MFGHO optimization-based deep-CNN is used for the detection of pest in the crop fields to ensure the better selection of proper cost-effective pesticides for the crop fields in such a way to increase the production. The proposed MFGHO algorithm is developed with the integrated characteristic features of navigating search agents and the swarming search agents in such a way to facilitate the optimal tuning of the hyperparameters in the deep-CNN classifier for the detection of pests in the crop fields.

This paper seeks to systematically review and synthesise existing research knowledge on African women entrepreneurship to identify gaps for future studies.

The paper conducted a systematic literature review of published studies from 1990 to 2020 on women entrepreneurship in Africa using a 5M gender aware framework of Brush et al. (2009).

The systematic literature review of published studies found the fragmentation, descriptive and prescriptive orientation of studies on Africa women entrepreneurship and devoid of theoretical focus. Further, women entrepreneurship studies tended to be underpinned from various disciplines, less from the entrepreneurship lens, mostly quantitative, and at its infancy stage of development. With a primary focus on development, enterprise performance and livelihood, studies rarely attended to issues of motherhood and the nuanced understanding of women entrepreneurship’s embeddedness in family and institutional contexts of Africa.

The paper questions the view that women entrepreneurship is a “panacea” and unravels how family context, customary practices, poverty and, rural-urban and formal/informal divide, significantly shape and interact with African women entrepreneurs’ enterprising experience and firm performance.

The findings and analyses indicate that any initiatives to support women empowerment via entrepreneurship should consider the socially constructed nature of women entrepreneurship and the subtle interplay of the African institutional contexts’ intricacies, spatial and locational differences which significantly influence women entrepreneurs’ choices, motivations and goals for enterprising.

The paper contributes to a holistic understanding of women entrepreneurship in Africa by using a 5M framework to review the research knowledge. In addition, the paper not only identifies unexplored/or less examined issues but also questions the taken-for-granted assumptions of existing knowledge and suggest adoption of context- and gender-sensitive theories and methods.

Exploration and exploitation have long been documented as prominent approaches to business management and organizational adaptation to external environment. Maintaining balance between these activities is a key to survival and prosperity. However, there is little direct evidence of the effect of such combined usage of both approaches on firm performance in times of crisis, especially within small- and medium-sized enterprises (SMEs). The purpose of this paper is to reveal the role of balanced ambidexterity in shaping firm performance during COVID-19 recession.

Based on a survey of 333 Russian SMEs, the authors test the proposed theoretical framework linking innovative ambidexterity to firm performance level and variability taking into account technological uncertainty.

The results show that innovative ambidexterity tends to increase level and decrease variability of performance outcomes, whereas technological uncertainty acts as a positive contingency for this impact.

The results provide an improved understanding of ambidexterity and organizational literatures by clarifying the contingent nature of the ambidexterity–firm performance relationship during COVID-19 recession.

Warranty-based big data analysis has attracted a great deal of attention because of its key capabilities and role in improving product quality while minimizing costs. Information and details about particular parts (components) repair and replacement during the warranty term, usually stored in the after-sales service database, can be used to solve problems in a variety of sectors. Due to the small number of studies related to the complete analysis of parts failure patterns in the automotive industry in the literature, this paper focuses on discovering and assessing the impact of lesser-studied factors on the failure of auto parts in the warranty period from the after-sales data of an automotive manufacturer.

The interconnected method used in this study for analyzing failure patterns is formed by combining association rules (AR) mining and Bayesian networks (BNs).

This research utilized AR analysis to extract valuable information from warranty data, exploring the relationship between component failure, time and location. Additionally, BNs were employed to investigate other potential factors influencing component failure, which could not be identified using Association Rules alone. This approach provided a more comprehensive evaluation of the data and valuable insights for decision-making in relevant industries.

This study's findings are believed to be practical in achieving a better dissection and providing a comprehensive package that can be utilized to increase component quality and overcome cross-sectional solutions. The integration of these methods allowed for a wider exploration of potential factors influencing component failure, enhancing the validity and depth of the research findings.

The business ambiguity because of COVID-19 has brought the tourism industry under stress. Using the service-dominant-logic and elaboration-likelihood-model, this study tested the effects of destination-based cognitive, affective and behavioral customer brand engagement (CBE) on customer brand co-creation (CBC). This research also examined the effects of involvement and CBC on customer revisit intention (CRI) during the COVID-19 pandemic. This study also tested the moderating role of customers’ age among the modeled relationships.

Investigating these matters, a sample of 315 tourists was recruited and adopted a mixed-method approach, including structural equation modeling (SEM) as well as fuzzy set qualitative-comparative analysis (fsQCA).

SEM results render that CBE’s dimensions exercise different impacts on CBC, which affect revisit-intention. Results ascertain customer involvement’s direct effects on CBC and revisit intention. Multi-group analysis uncovers that consumer age significantly moderates the CBC and CRI relationship, and their effect increases as consumers get older. The fsQCA results revealed more heterogenous combinations to predict CBC and revisit intention.

This study focuses on CBE, CBC and involvement, and contributes unique insight to tourism marketing research; thus, it identifies plentiful opportunities for further research, as summarized.

This study offers key implications for destinations to build tourism/marketing strategies to strengthen the CBE/CBC or tourist/destination–brand relationship.

Though CBE/CBC and involvement are identified as important research priorities, empirically derived insights among these and related factors remain limited in the course of the COVID-19 crisis.

本文采用结构方程模型(SEM)和模糊集定性比较分析(fsQCA)相结合的方法, 对315名游客进行了调查。

由于新型冠状病毒感染症(COVID-19)产生的业务不定性给旅游业带来了压力。本研究运用服务主导逻辑和精细似然模型, 检验了基于目的地的认知、情感和行为顾客品牌参与(CBE)对顾客品牌共同创造(CBC)的影响。本研究还考察了COVID-19大流行期间参与和CBC对客户重访意愿(CRI)的影响。检验了顾客年龄在模型关系中的调节作用。

SEM结果表明, CBE的维度对CBC有不同的影响, 而这种影响又会影响着重游意愿。结果确定了游客参与对CBC和重访意愿的直接影响。多群体分析发现, 消费者年龄显著调节CBC和CRI关系, 且随着消费者年龄的增长, 其作用增强。fsQCA结果显示需更多的异质组合来预测CBC和再访意向。

-本研究关注CBE、CBC和参与, 为旅游营销研究提供了独特的见解, 因此总结出了许多进一步研究的机会。

本研究为目的地建立旅游/营销策略以加强CBE/CBC或游客/目的地-品牌关系提供了重要启示。

尽管CBE/CBC和参与被认为重要的研究重点, 但在covid −19危机期间, 从这些因素和相关因素中得出的经验见解仍然有限。

Para investigar estas cuestiones, se seleccionó una muestra de 315 turistas y se utilizó un enfoque metodológico mixto que incluía el modelo de ecuaciones estructurales (SEM) y el análisis cualitativo-comparativo de conjuntos difusos (fsQCA).

La confusión empresarial debida a la pandemia del COVID-19 ha sometido al sector turístico a una fuerte tensión. Utilizando la lógica dominante del servicio y el modelo de elaboración de verosimilitud, este estudio examinó los efectos del compromiso cognitivo, afectivo y comportamental del cliente con la marca del destino (CBE) en la cocreación de la marca (CBC). Esta investigación también analizó los efectos de la implicación y la CBC en la intención de revisita (IRC) durante la pandemia COVID-19. Este estudio también evaluó el papel moderador de la edad de los clientes entre las relaciones establecidas.

Los resultados del SEM muestran que las dimensiones de la CBE ejercen diferentes impactos sobre la CBC, que afectan a la intención de revisita. Los resultados determinan los efectos directos de la implicación del cliente sobre la CBC y la intención de revisita. El análisis multigrupo revela que la edad del consumidor modera significativamente la relación entre el CBC y el IRC, y que su efecto aumenta a medida que los consumidores envejecen. Los resultados del fsQCA revelaron combinaciones más heterogéneas para predecir el CBC y la intención de volver a visitar.

Este estudio se centra en la CBE, la CBC y la implicación, y aporta una visión única a la investigación del marketing turístico, por lo que identifica numerosas oportunidades para futuras investigaciones.

Este estudio ofrece implicaciones clave para que los destinos construyan estrategias de turismo/marketing en el fortalecimiento de la relación CBE/CBC o turista/destino-marca.

Aunque la CBE/CBC y la implicación se identifican como importantes prioridades de investigación, las percepciones derivadas empíricamente entre estos factores y otros relacionados siguen siendo limitadas en el transcurso de la crisis del COVID-19.