A large number of web-based e-Health applications have been developed through time, allowing doctors to access different types of functionalities, like knowing which medication the patient has consumed or performing online consultations. Internet systems for healthcare can be improved by using artificial intelligence mechanisms for the process of detecting diseases and obtaining biological data, allowing medical professionals to have important information that facilitates the diagnosis process and the choice of the correct treatment for each particular person.The proposed research work aims to present an innovative approach when compared to traditional platforms, by providing online vital signs in real time and allowing the visualization of all historical data of a patient. It aims to defend the concept of promoting online consultations, providing complementary functionalities to the traditional methods for performing medical diagnoses through the use of software engineering practices. This investigation led to the conclusion that, in the future, many medical processes will most likely be done online, where this practice is considered extremely helpful for the analysis and treatment of contagious diseases, or cases that require constant monitoring.
Being able to identify fish in aquaculture is essential to optimize their feeding and thereby reduce the cost of production. The use of radio frequency has proven to be a powerful and effective technology for the identification of fish in aquaculture cages. A passive tag inserted into the fish sent information wirelessly from the tag to a receiver at some distance away. The integration of RFID with Internet of Thing (IoT) is a powerful tool not only for the identification of fish but also for fish control to ensure food safety. In this work, we proposed an affordable IoT architecture to increase the access to the data from any device. A prototype was developed and tested in real conditions. Critical challenges have also been identified and addressed.
Passive localization by multiple observes using ambiguous phase difference of arrival (PDOA) of the long baseline interferometer (LBI) can greatly reduce the cost and system complexity when applied to the small platform such as the unmanned aerial vehicle (UAV). To solve the nonlinear and discontinuous problem caused by the 2π ambiguity of PDOA, a quantum-behaved particle swarm optimization (QPSO)-based solution is proposed in this paper. The object function is firstly established using wrapped residual of the PDOA. And then the QPSO algorithm is applied to solve the nonlinear and discontinuous optimization problem. Simulation results verify the effectiveness of the proposed method.
Cache resource allocation and computation offloading are envisioned as two promising solutions to reduce maximal delay in fog radio access networks (F-RANs). Inspired by this, a joint cache and computation resource optimization problem is investigated in this paper. We propose a genetic algorithm-based approach that encodes the optimization order rather than the decision into genes and optimizes the delay stepwise. Furthermore, considering that the running time of the algorithm increases rapidly with the size of the network, a strategy with low time complexity is demanded. To achieve distributed cooperation among agents and reduce the complexity, we innovatively design a multi-agent game-based algorithm so that the original problem is decomposed into a priority calculation problem and several distributed sub-problems. Based on calculated priorities, players adjust their decisions in turn to improve their own delay until no player changes actions. Via simulation, the effectiveness of two proposed algorithms in reducing the delay is verified and the game-based algorithm shows lower time complexity and competitive performance. In addition, the impact of nodes’ storage and computation capability on delay performance is demonstrated and analyzed.
To overcome the large noise and harmonics in the current waveform of BLDC (Brushless Direct Current, BLDC) motor used in traditional automated guided vehicle (AGV), the permanent magnet synchronous motor(PMSM) is selected as drive motor to be introduced in the AGV. And an improved active disturbance rejection control (ADRC) algorithm are presented in the PMSM vector control. And three parts of ADRC, Tracking Differentiator (TD), Extended State Observer (ESO) and Nonlinear State Error Feedback (NLSEF), are designed in the controller to analyze and process the speed, voltage signal and state estimation values and control and compensate parameter errors. To show the control superiority of ADRC, the PI-based and ADRC-based simulation models are both built and simulated with the specific high and low speed, torque and speed suddenly change. Simulation results show that when the motor suddenly decelerates, PI is stable at 0.1s and ADRC was stable at 0.03s, and the overshoot of PI is higher than ADRC, which verifies that the response speed, anti-disturbance performance and robustness of the improved ADRC are significantly better than PI, which would be helpful to introduce the PMSM and ADRC based algorithm to the AGV and the automated container terminals.
For the safety supervision of port environment, we propose a port staff detection and tracking framework. Firstly, the framework is based on Faster-RCNN (Faster Region Convolutional Neural Networks) detection algorithm to identify the port staff in the surveillance video, and obtain the target location information. Based on the Deep SORT (Deep Simple Online and Realtime Tracking) tracking algorithm, we add Gaussian noise reduction and histogram equalization to preprocess the input image, and then use Kalman filter and Hungarian algorithm to predict and match, so as to improve the accuracy of target tracking. The framework effectively improves the accuracy of the algorithm, provides a powerful technical support for port security monitoring, and provides a security guarantee for port staff.
We demonstrate an intensity-modulated bending and refractive index (RI) sensor based on dual-dip long-period fiber gratings (LPFGs) in single-mode fiber using electric arc discharge. As a difference from the conventional LPFGs presenting three resonances, we fabricated dual-dip LPFGs with the same period of 1200 μm in the same wavelength range from 1400 nm to 1600 nm. For the proposed dual-dip LPFGs, there is a middle peak located between the two resonance dips, whose contrast responds and varies regularly with the curvature and surrounding refractive index units (RIU) compared with conventional LPFGs. The dual-dip LPFGs present a bending sensitivity of 3.35 dB/m -1 with a curvature range from 1.038 to 2.506 m -1 and a RI sensitivity of 79.98 dB/RIU in the RI region of 1.425-1.455 RIU. Moreover, the dual-dip LPFGs shows a negligible variation of contrast on temperature. The proposed dual-dip LPFGs have potential applications for bending monitoring and RI sensing fields.
Due to the increasing technological innovation over the last decades, the average life expectancy of a human being has been increasing exponentially. Although this is an excellent step forward for humanity, it has led older population to being more prone to illness, making them more vulnerable to accidents such as falls. In this article a study is made on the existing literature in non-intrusive remote health monitoring systems, towards the design and implementation of an IoT system capable of identifying fall situations and monitor cardiac data. A Systematic Literature Review (SLR) method was considered in this work, focused on reviewing the existing literature on remote health monitoring systems, having fall detection algorithms, based in IoT. The Design Science Research (DSR) methodology was used to seek to enhance technology and science knowledge about this paper’s topic, through the creation of an innovative artifact.The system includes a smart watch (Lily-Go T-Watch-2020 V2), programmable in C under Arduino IDE to detect falls and a photoplethysmography monitoring unit (PPG) based on a Onyx 9560 Bluetooth oximeter, capable of measuring the user’s blood oxygen percentage (SpO2) and heart rate, in real time. It also provides remote monitoring through a user-friendly website to visualize live data about the status of the user. The system was tested in volunteers to show the effectiveness of remote health monitoring systems for the elderly population.
Since fault detection algorithm can only be used to acquire fault occurrence time and fault location, the information related to failure reason is still very limited, thus failing to provide sufficient support for making reasonable failure recovery schemes. Therefore, fault diagnosis algorithm is required to identify the failure types. As the fault features of industrial wireless sensor networks are quite complicated, complete fault-feature knowledge base and feasible diagnosis algorithm are quite necessary during the diagnosis process. Due to this reason, we proposed a fault diagnosis algorithm based on immune danger theory. In this algorithm, through antigen classification process, the fault-feature samples can be classified according to fault types. Through antibody training process, the fault-feature knowledge base with good fault-description ability can be built. When the fault samples enter into diagnosis process, the fault types can be detected according to KNN. The experiment results have shown that the time length required for diagnosis in our algorithm can be shorten significantly while maintaining high accuracy. Its performance could meet the low-delay demand of industrial scenarios perfectly.
Proper dispatching of equipment at the automated terminal in the on-dock rail can reduce energy consumption during loading and unloading, which is significant for the green development of terminals. This paper studies the collaborative scheduling of rail-mounted gantry cranes (RGCs) and automated guided vehicles (AGVs) for on-dock rail. Firstly, this problem is considered with the allowable operating time window of trains and ships, safety margin between the RGCs, heavy load and no-load of AGV, and the waiting time of RGC and AGV. Furthermore, the collaborative scheduling model is established, which takes the minimum energy consumption of RGC and AGV. Self-adaptive chaotic genetic algorithm is designed to solve the model. Finally, experiments were designed to analyze the effects of the number of containers, the delayed arrival time of vessels, and the proportion of dockside containers on the energy consumption of RGCs and AGVs. The results show that the total energy consumption of RGCs and AGVs is the smallest when the number of rail-mounted gantry cranes and AGVs is 1:4. In addition, the number of AGVs should be decreased with the increase of ship delay time and the proportion of quayside containers to reduce energy consumption.
This article describes the development of a solution to tackle the lack of data that physiotherapists have during physical rehabilitation with walking aids. The developed system is based on an ESP32 microcontroller connected to an RFID reader, load cells, and an IMU mounted in a crutch. The data from the measurement channels associated with the smart crutch are acquired and sent to a cloud data storage using WiFi and MQTT protocol. A server application is available for physiotherapists and patients to view and analyze the data from each session. Experimental results are included in the paper associated with system validation with volunteers.
This paper proposes an improved method to optimize the existing energy management strategy (EMS) of hybrid energy storage system (HESS) to improve the energy utilization rate of HESS of pure electric logistics vehicle. Firstly, the sensor is used to identify the road slope coefficient, and then the identified road slope coefficient is added to the input of the fuzzy controller as one of the factors of energy distribution, and the corresponding fuzzy rules are formulated for different slope conditions. Then, the membership function of fuzzy controller is optimized by chaos particle swarm optimization (CPSO) algorithm. Finally, the simulation test is carried out under UDDS urban road driving cycle by using Matlab/Simulink. The test results show that the improved control strategy proposed in this paper can reduce the energy consumption of the whole vehicle by 5.23%, the average current by 6.19% and the battery power consumption by 2.20%.
With the development of shipping industry, more and more attention has been paid to the environmental pollution of waterways and surrounding areas. Accurate prediction of ship speed plays an essential role in ship operation optimization and decision support, and is also one of the key means for ships to achieve energy conservation and emission reduction. Traditional methods of ship speed estimation are mainly based on hydrodynamics and full-size measurement, which have obvious disadvantages such as large computational workload or large measurement investment. In this study, through the analysis of historical ship speed data, a data-driven ship speed prediction approach based on the Elman neural network model is investigated. Furthermore, Genetic Algorithm (GA) is applied to optimize the weights and thresholds of Elman neural network to improve the prediction accuracy and computational efficiency of the algorithm. Finally, the proposed GA-Elman neural network model is experimentally verified by the actual navigation data of an inland electric propulsion vessel, and compared with the BP neural network model and the Elman neural network model. Experimental results show that the speed prediction method based on GA-Elman neural network proposed in this paper has higher prediction accuracy, and the prediction error is reduced by 56.67% and 48% compared with the BP neural network model and Elman neural network model respectively.
Graptolite is the fossil of the graptolite fauna. Experts can identify the chronological order of strata through graptolite species. Graptolite image classification is much more challenging than traditional fine-grained image classification tasks due to the impacts of geological layer mining extrusion, light and noise. In this paper, we propose a multi-scale deep learning method to tackle these problems. By integrating feature from different scale learning, we can accurately locate the discriminative regions. Training these discriminative part images can further identify the subtle differences, and the proposed model is optimal for adapting to the graptolite classification task. Experimental results on the benchmark graptolite dataset show that our method achieves the state-of-the-art performance.
It is well-established that the monitoring and early warning of highway geological disasters in mountainous areas has always been the focus of highway traffic development. This study aims to determine how the application of Internet of Things technology can be better used in order to improve the ability of traffic disaster prevention and reduction .The key data such as displacement changes, cracks, and rainfall were collected by the wireless intelligent sensing mountain road disaster perception network, After analysis, it was combined with the basic information gathering of mountain roads, used to build a intelligent monitoring and decision-making system. The results show that the Internet of Things technology of 5G and BeiDou Positioning Technology has certain reliability in mountain disaster monitoring, can achieve real-time accurate perception of geological disasters, disaster prediction and auxiliary decision-making, and effectively ensure the driving safety of mountain roads.
With the development of bulk cargo automation terminal, the research of condition monitoring and fault diagnosis technology of portal crane is imminent. There is no corresponding mature technology for the condition monitoring of large slewing bearing of portal crane. In this paper, the stress of the portal crane slewing bearing is analyzed by finite element analysis, and the vibration signal of the dangerous point is collected. A method based on constrained independent component analysis (CICA) and ensemble empirical mode decomposition (EEMD) are proposed to monitoring the running state of portal crane and analyze and deal with abnormal signals in real time. The method can effectively reduce the economic loss and safety accident caused by slewing bearing failure. This paper starts with the architecture of the perception layer, network layer and application layer of the Internet of Things. Based on the large portal machine, it develops the real-time monitoring software of the perception layer based on MCGS configuration software, and the remote data query software of the gantry crane based on C#. The system guarantees real-time monitoring and remote data transmission of the running parameters and structural health of the slewing bearing of portal crane, and realizes the functions of data preservation and remote query.
It is feasible to see how communication and information technology have advanced at a rapid pace in today’s world. The introduction of wearable technology is one aspect contributing to this progress and has the potential to be an innovative solution to healthcare challenges since it may be utilized for illness prevention and maintenance, such as physical monitoring, as well as patient management. In order to solve some of the healthcare challenges, this paper proposes the development of an intelligent health monitoring system with alerts and continuous monitoring using wearable devices capable of collecting biometric data on human health. The concept was then proven by the development of a prototype using sensors connected to a micro-controller which transmits its information via MQTT to a Node-RED powered dashboard that handles the health metrics monitoring. The designed prototype has proven satisfactory to provide evidences that support the developed research questions.
With the growth of domestic trade transportation, the role of the dry port in the hinterland becomes more and more obvious, and the proportion of railway transportation between seaport and dry port is also growing gradually in domestic trade transportation. In this paper, the water-rail composite network and its waterway sub-network and railway sub-network are established. The topological index of three networks are calculated and compared on the basis of complex networks. Through the weighted processing of degree centrality, betweenness centrality and closeness centrality, the connectivity score of each port is obtained, and the key nodes of the network and their importance ranking are summarized. The change trend of the robustness index of the composite network is simulated under the two modes of random attack and malicious attack. After the network is damaged in different degrees, the ITAE value is introduced to measure the recovery effect of different recovery strategies. The research results show that the recovery effect of degree centrality-based recovery strategy and betweenness centrality-based recovery strategy is relatively similar, while the recovery effect of closeness centrality-based recovery strategy is not as good as the first two, so optimizing the sequence of ports being recovered will improve the overall recovery efficiency of the networks. The resilience of the network is improved by analyzing the robustness and recovery of the network.
The railway port has promoted the development of sea-rail intermodal transport, and improving the efficiency of sea-rail intermodal transport lies in the synchronous operation of rail gantry cranes(GCs) and collection cards. Therefore, this paper establishes integer programming models for the orbital GC operation process and the collection card scheduling process, and then couples the two models. The coupled model makes it more difficult to solve the entire model. In order to solve this problem, this paper uses the alternating multiplicative direction method to bind complex hard constraints, at which point the original problem is decomposed into a specific orbital GC problem and a specific AGV problem. The overall benefit is highest achieved through the update adjustment of the ADMM algorithm. Finally, the ADMM algorithm and the Lagrange relaxation method are compared and experimented, and the algorithm results show that the ADMM algorithm is superior to the Lagrange relaxation method for the coupling problem of a relatively large number of dispatches.
To meet the demand for intelligent traffic infrastructure, distributed optical fiber sensing, a new sensing technology, has been gradually applied to asphalt pavement health monitoring. This paper used the optical frequency domain reflectometer (OFDR) to collect the data of distributed optical fiber sensors embedded in the test road. By processing and mining the measured data, a traffic information monitoring method based on a peak recognition algorithm was proposed. Compared with the actual traffic information, the results show that the distributed optical fiber sensor can accurately monitor the vehicle type outside the car and realize the identification of vehicle flow, vehicle speed, and load position with high accuracy.
