Search Results (6)

Potato malformation seriously affects commercial value, and its removal has become one of the core steps in the post-harvest and pre-sales process of potatoes. At present, this work mainly relies on manual visual inspection, which requires a lot of labor and incurs high investment costs. Therefore, precise and efficient automatic detection technology urgently needs to be developed. Due to the efficiency of deep learning based on image information in the field of complex object feature extraction and pattern recognition, this study proposes the use of the YOLOv3 algorithm to undertake potato malformation classification. However, the target box regression loss function MSE of this algorithm is prone to small errors being ignored, and the model code is relatively large, which limits its performance due to the high demand for computing hardware performance and storage space. Accordingly, in this study, CIOU loss is introduced to replace MSE, and thus the shortcoming of the inconsistent optimization direction of the original algorithm’s loss function is overcome, which also significantly reduces the storage space and computational complexity of the network model. Furthermore, deep separable convolution is used instead of traditional convolution. Deep separable convolution first convolves each channel, and then combines different channels point by point. With the introduction of an inverted residual structure and the use of the h-swish activation function, deep separable convolution based on the MobileNetv3 structure can learn more comprehensive feature representations, which can significantly reduce the computational load of the model while improving its accuracy. The test results showed that the model capacity was reduced by 66%, mAP was increased by 4.68%, and training time was shortened by 6.1 h. Specifically, the correctness rates of malformation recognition induced by local protrusion, local depression, proportional imbalance, and mechanical injury within the test set range were 94.13%, 91.00%, 95.52%, and 91.79%, respectively. Misjudgment mainly stemmed from the limitation of training samples and the original accuracy of the human judgment in type labeling. This study lays a solid foundation for the final establishment of an intelligent recognition and classification picking system for malformed potatoes in the next step. Full article

Despite the emergence of a presale mechanism that reduces manufacturing and ordering risks for retailers, optimizing the real-time pricing strategy in this mechanism and unknown demand environment remains an unsolved issue. Consequently, we propose an automatic real-time pricing system for e-retailers under the inventory backlog impact in the presale mode, using deep reinforcement learning technology based on the Dueling DQN algorithm. This system models the multicycle pricing problem with a finite sales horizon as a Markov decision process (MDP) to cope with the uncertain environment. We train and evaluate the proposed environment and agent in a simulation environment and compare it with two tabular reinforcement learning algorithms (Q-learning and SARSA). The computational results demonstrate that our proposed real-time pricing learning framework for joint inventory impact can effectively maximize retailers’ profits and has universal applicability to a wide range of presale models. Furthermore, according to a series of experiments, we find that retailers should not neglect the impact of the presale or previous prices on consumers’ purchase behavior. If consumers pay more attention to past prices, the retailer must decrease the current price. When the cost of inventory backlog increases, they need to offer deeper discounts in the early selling period. Additionally, introducing blockchain technology can improve the transparency of commodity traceability information, thus increasing consumer demand for purchase. Full article

This paper explains the project’s objectives, identifies the key stakeholders, defines the project manager’s authority and provides a preliminary breakdown of roles and responsibilities. For the project’s future, it acts as a source of authority. This paper’s objective is to record the justifications for starting the project, its goals, limitations, solution instructions and the names of the principal stakeholders. This manuscript is meant to be used as a “Project Management Plan Light” for small and medium-sized projects when it would be uneconomical to prepare an entire collection of documents that make up a project management plan. A global media cloud will be provided and managed by the ABC cloud company inside of a consumer’s current premises. In this paper, the authors explain the end-to-end delivery of cloud and compute services. The article mainly focuses on the delivery of virtual machines (VMs), graphics processing unit (GPUs), cloud storage, transcoding, packaging, 24/7 customer support and billing modules for the services used by end customers. The process starts with customer requirements gathering to initiate the feasibility check for the services desired or required by the clients. Pre-sale solution engineers capture all the customer requirements in the solution design document to review with the engineering and delivery team for the implementation. Based on the solution design document, the solution engineer needs to raise the system’s feasibility for the local loops, cross connects, VMs, GPUs, storage, transcoders and packagers required to meet the end customer expectations on the service delivery. The solution engineer must sign-off on the solution design document agreed with end customer from the engineering and technical team. The program manager and technical team review the solution design document and confirm the order ID requirement in the system for the sales team to share with the order entry team to log the orders for a signed customer order form (COF). The program manager will initiate the service delivery for these order IDs logged in to the system for these services. Once services are ready for customer delivery, a technical team will share the customer portal with the end customer and provide training to the teams at the customer end use the required resources for cloud, compute and storage uses. Along with the services mentioned above, customers can access the usage and billing information in the customer portal. Moreover, the program manager is to share the project closure document, including the information about the services, reference IDs to log the trouble ticket with the supplier’s 24/7 support team and billing start date for customer acceptance. Full article

In this study, we investigate inventory allocation and pricing strategies for retailers by incorporating demand information into the issue of inventory allocation during the presale period. In a presale system, retailers offer presale goods at a price lower than the retail price. By offering products at a discount, retailers may attract additional demand. In addition, this system enables retailers to reduce the uncertainty of market demand and establish a strategy for inventory allocation based on the results of presales. A Bayesian approach was employed to analyze and update demand information, and inventory allocation was formulated as a newsvendor problem to determine the optimal policy that maximizes retailer profit. A numerical analysis was conducted to validate the effectiveness of the proposed strategy. Results suggest that the proposed strategies can support retailers by more accurately predicting demand and achieving higher profits with less inventory. Furthermore, retailers can experience greater benefits from risk-averse customers than from risk-neutral customers. Full article

Virtual reality (VR) technologies have advanced rapidly in the past few years, and many industries have adopted these cutting-edge technologies for diverse applications to improve their industrial competitiveness. VR has also received considerable recognition in the architecture, engineering, and construction industries, because it can potentially reduce project costs, delivery time, and quality risks, by allowing users to experience unbuilt spaces before breaking ground, resolving construction conflicts virtually, and reviewing complex details in immersive environments. In the real estate market, VR can also play an important role in affecting buyers’ housing purchasing decisions, especially for housing markets in Asia, where the pre-sale system is extremely common. Applying VR to the pre-sale housing system is promising, because the concept of pre-sale refers to a strategy adopted by developers that sell housing through agreements on residential units that have not been constructed yet, and VR at this stage could be a useful tool for visual communication in a true-to-scale environment. However, does VR really benefit sales in the housing market? Can clients accept using VR, instead of using traditional materials (i.e., paper-based images and physical models), to navigate and experience housing projects? The objective of this study is to develop a VR-based navigation system for a pre-sale housing project in Taiwan. We invited 30 potential clients to test the system and explore the implications of using it for project navigation. The results reveal that VR enhances the understandings of a project (perceived usefulness) and increases clients’ intention to purchase, while the operation of VR (perceived ease-of-use) is still the major challenge to affect clients’ satisfaction and the developer’s acceptance with respect to applying it to future housing sales. Full article

Housing quality (HQ) has been a long-standing concern for both developers and homebuyers. Currently, HQ depends on the expected profit and subjectivity of the developers, and homebuyers only have a passive choice of whether to accept housing with such quality. Asian housing supply markets have largely adopted the presale housing system. Under this system, developers are able to verify future occupants before commencing construction, enabling them to provide customized designs and differentiated quality items in order to meet user demands and value. Consequently, HQ can be enhanced. A cost–quality trade-off model was developed using a genetic algorithm to help decision-makers identify the optimal HQ differentiation strategy that simultaneously satisfies homebuyers’ expectations of quality and developers’ expectations of profits. The findings showed that the presale housing system effectively improves HQ. A 6% increase in homebuyers’ budgets can achieve the optimal quality improvement effect, while an 8% or more increase in developers’ construction costs in order to improve HQ can generate an additional premium for the developers. Full article