No abstract

In recent years, intelligent transportation system (ITS) techniques have been widely exploited to enhance the quality of public services. As one of the worldwide leaders in recycling, Taiwan adopts the waste collection and disposal policy named "trash doesn't touch the ground", which requires the public to deliver garbage directly to the collection points for awaiting garbage collection. This study develops a travel time prediction system based on data clustering for providing real-time information on the arrival time of waste collection vehicle (WCV). The developed system consists of mobile devices (MDs), on-board units (OBUs), a fleet management server (FMS), and a data analysis server (DAS). A travel time prediction model utilizing the adaptive-based clustering technique coupled with a data feature selection procedure is devised and embedded in the DAS. While receiving inquiries from users' MDs and relevant data from WCVs' OBUs through the FMS, the DAS performs the devised model to yield the predicted arrival time of WCV. Our experiment result demonstrates that the proposed prediction model achieves an accuracy rate of 75.0% and outperforms the reference linear regression method and neural network technique, the accuracy rates of which are 14.7% and 27.6%, respectively. The developed system is effective as well as efficient and has gone online.

The problem of automatically tuning and matching a probe is considered, and attention is drawn to the main cause of difficulty: the interaction of tuning and matching mechanisms. The use of a doubly resonant, inductively coupled probe is therefore advocated, for to first order, tuning, and matching are then orthogonal for small perturbations. It is shown that when such a probe is equipped with negative feedback control of tuning and matching elements, driven by error signals derived from a bridge and the NMR spectrometer, stable and rapid automatic tuning and matching are achieved. The importance of approximately correct phasing of the error signals is emphasized, but the restriction of having to have specific cable lengths to achieve this task is removed. The effects of small errors of phasing are then considered and shown to be unimportant for the chosen probe, in contrast to the situation for other, nonorthogonal probe types. Suggestions for orthogonalization of two common capacitively coupled probe designs are made, and a practical instrument design is then given that, with the addition of external components, can also be used if the NMR receiver cannot be pressed into service.

This editorial introduces the Special Issue, entitled “Deep Learning (DL) Techniques for Agronomy Applications”, of Agronomy. Topics covered in this issue include three main parts: (I) DL-based image recognition techniques for agronomy applications, (II) DL-based time series data analysis techniques for agronomy applications, and (III) behavior and strategy analysis for agronomy applications. Three papers on DL-based image recognition techniques for agronomy applications are as follows: (1) “Automatic segmentation and counting of aphid nymphs on leaves using convolutional neural networks,” by Chen et al.; (2) “Estimating body condition score in dairy cows from depth images using convolutional neural networks, transfer learning, and model ensembling techniques,” by Alvarez et al.; and (3) “Development of a mushroom growth measurement system applying deep learning for image recognition,” by Lu et al. One paper on DL-based time series data analysis techniques for agronomy applications is as follows: “LSTM neural network based forecasting model for wheat production in Pakistan,” by Haider et al. One paper on behavior and strategy analysis for agronomy applications is as follows: “Research into the E-learning model of agriculture technology companies: analysis by deep learning,” by Lin et al.

No abstract

Ship detection is one of the most important research contents of ship intelligent navigation and monitoring. As a supplement to classical navigational equipment such as radar and the Automatic Identification System (AIS), target detection based on computer vision and deep learning has become a new important method. A target detector called YOLOv3 has the advantages of detection speed and accuracy and meets the real-time requirements for ship detection. However, YOLOv3 has a large number of backbone network parameters and requires high hardware performance, which is not conducive to the popularization of applications. On the basis of YOLOv3, this paper proposes a lightweight ship detection model (LSDM) in which the backbone network is improved by using dense connection inspired from DenseNet, and the feature pyramid networks are improved by using spatial separation convolution to replace normal convolution. The two improvements reduce parameters and optimize the network structure greatly. The experimental results show that, with only one-third of parameters of YOLOv3, the LSDM has higher accuracy and speed for ship detection. In addition, the LSDM is simplified further by reducing the number of densely connected units to form a model called LSDM-tiny. The experimental results show that, LSDM-tiny has similar detection speed with YOLOv3-tiny, but has a lot higher accuracy.

This study investigates a three-dimensional single container loading problem, which aims to pack a given set of unequal-size rectangular boxes into a single container such that the length of the occupied space in the container is minimized. Motivated by the practical logistics instances in literature, the problem under study is formulated as a zero-one mixed integer linear programming model. Due to the NP-hardness of the studied problem, a simple but effective loading placement heuristic is proposed for solving large-size instances. The experimental results demonstrate that the developed heuristic is capable of solving the instances with more than two hundred boxes and more efficient than the state-of-the-art mixed integer linear program and existing heuristic methods.

The prevention and control of nosocomial infection (NI) are becoming increasingly difficult, and its mechanism is becoming increasingly complex. A globally aging population means that an increasing proportion of patients have a susceptible constitution, and the frequent occurrence of severe infectious diseases has also led to an increase in the cost of prevention and control of NI. Medical buildings’ spatial environment design for the prevention of NI has been a hot subject of considerable research, but few previous studies have summarized the design criteria for a medical building environment to control the risk of NI. Thus, there is no suitable evaluation framework to determine whether the spatial environment of a medical building is capable of inhibiting the spread of NI. In the context of the global spread of COVID-19, it is necessary to evaluate the performance of the existing medical building environment in terms of inhibiting the spread of NI and to verify current environmental improvement strategies for the efficient and rational use of resources. This study determines the key design elements for the spatial environment of medical buildings, constructs an evaluation framework using exploratory factor analysis, verifies the complex dominant influence relationship, and prioritizes criteria in the evaluation framework using the decision-making trial and evaluation laboratory- (DEMATEL-) based analytical network process (ANP) (DANP). Using representative real cases, this study uses the technique for order preference by similarity to ideal solution (TOPSIS) to evaluate and analyze the performance with the aspiration level of reducing the NI risk. A continuous and systematic transformation design strategy for these real cases is proposed. The main contributions of this study include the following: (1) it creates a systematic framework that allows hospital decision-makers to evaluate the spatial environment of medical buildings; (2) it provides a reference for making design decisions to improve the current situation using the results of a performance evaluation; (3) it draws an influential network relation map (INRM) and the training of influence weights (IWs) for criteria. The sources of practical problems can be identified by the proposed evaluation framework, and the corresponding strategy can be proposed to avoid the waste of resources for the prevention of epidemics.