Data Transmission Layer Research Articles

A smart agriculture IoT system based on deep reinforcement learning

Abstract Smart agriculture systems based on Internet of Things are the most promising to increase food production and reduce the consumption of resources like fresh water. In this study, we present a smart agriculture IoT system based on deep reinforcement learning which includes four layers, namely agricultural data collection layer, edge computing layer, agricultural data transmission layer, and cloud computing layer. The presented system integrates some advanced information techniques, especially artificial intelligence and cloud computing, with agricultural production to increase food production. Specially, the most advanced artificial intelligence model, deep reinforcement learning is combined in the cloud layer to make immediate smart decisions such as determining the amount of water needed to be irrigated for improving crop growth environment. We present several representative deep reinforcement learning models with their broad applications. Finally, we talk about the open challenges and the potential applications of deep reinforcement learning in smart agriculture IoT systems.

Video data wireless transmission method based on cross-layer bitrate adaptation and error control

Aiming at the difficulty of video data transmission in wireless transmission, the idea of cross-layer design is taken as the main line, and the wireless transmission method of video data based on cross-layer code rate adaptation and error control is studied. The MAC layer rate adaptation technology, application layer video codec technology and its rate control technology, transport layer data transmission protocol and its packet encapsulation strategy are studied. The design of video transmission system based on cross-layer design is realized. Aiming at the RTP transmission of H.264 video stream, this paper studies the RTP packet encapsulation mode of H.264 data, and implements an adaptive packet encapsulation strategy based on MAC layer channel quality estimation. Aiming at the RTP transmission of H.264 video stream, the RTP packet encapsulation mode of H.264 data is studied. The adaptive packet encapsulation strategy is implemented based on the MAC layer channel quality estimation. The performance test of the proposed rate control strategy and packet encapsulation strategy is carried out in the actual test environment, and compared with the existing methods. The results show that the proposed strategy is in the case of long communication distance or node movement. The proposed method can reduce the header overhead by 50% and barely 50% of the throughput, and the performance in terms of video playback quality and image PSNR is better than the existing strategy.

An IoT based framework for energy monitoring and analysis of die casting workshop

In order to reduce the impact on resource shortage and environmental pollution caused by the massive use of energy, meeting the requirements of the fierce market competition, manufacturing enterprises must strengthen the awareness of the energy utilization in the workshop. As a widely distributed manufacturing system, die casting workshop consumes lots of energy with low efficiency. Due to the dynamic and complicated of energy usage, an effective energy monitoring and analysis method is still lacked in die casting workshop. This paper divides the die casting workshop into die casting machine level, die casting task level, and die casting workshop level and it proposes an energy monitoring and analysis system including data acquisition layer, data transmission layer, data storage layer, data processing layer, and data display layer based on Internet of Things (IoT) technology. A set of indicators, such as energy per process in die casting workshop, energy per part in die casting task, and energy per part in die casting machine, and so on, were calculated to interpret the energy data and evaluate the performance of a die casting workshop through data mining. With the application of the proposed system in a die casting workshop, enterprise managers can easily find potential opportunities for energy consumption reduction, and energy efficiency improvement, and propose ways to reduce energy consumption cost. The feasibility and practicability of the developed energy monitoring and analysis system was verified through a case study.

Emotion-aware system design for the battlefield environment

With the increasing amount of information and the growth of data sources on the battlefield, it is important to achieve better battlefield decision-making through the faster and more accurate emotion awareness provided by big data. Existing battlefield systems are mainly focused on logical information acquisition, rarely considering emotion factors. In this paper, an emotion-aware system for the battlefield environment (ESBE) is proposed to achieve various functions, including target localization, target recognition, motion behavior identification, etc., to support intelligent decision-making based on the emotional state of soldiers and other valuable information about the battlefield environment. The ESBE architecture consists of three layers: data-sensing, data-transmission, and data-processing. A heterogeneous network is introduced in data-transmission layer to speed up the transmission ratio and increase the network throughput. In the data-processing layer, cloud technology is introduced to store the big data while information fusion based on a variety of technologies is executed to process the big data. Then, the elaborated function of each architecture layer, such as the fundamental process of the ESBE system, as well as some function provided by the ESBE, is presented separately. Last but not least, the ESBE system is compared with four other existing systems in terms of functions and technologies.

A novel and smart automatic light-seeking flowerpot for monitoring flower growth environment

Although the flowerpot is widely used for indoor flowers, it cannot meet the needs of intelligent management during the uncared-for period. The objective of this study was to design a new microcontroller-based smart flowerpot. Its overall system was composed of three parts: information collection layer, automatic control layer and data transmission layer. Firstly, in the process of collecting information, the Laiyite criterion and the normalized weighted average algorithm were adopted to improve the accuracy of information collection. Secondly, for making precise control decisions, the fuzzy control was used to achieve automatic on-demand watering. Finally, the method for comparative analysis of regional light intensity was utilized to achieve light-seeking and light-supplementing. Experimental results showed that the smart flowerpot had strong anti-jamming performance for information collection, the relative soil moisture of flowers could be stably maintained near the optimum humidity (65%), and the light was well-distributed on the flower with the error angle of light-supplementing ranged from –3° to 3°. Keywords: smart flowerpot, automatic watering, seeking light, supplementing light control, microcontroller DOI: 10.25165/j.ijabe.20181102.2786 Citation: Zhang X H, Liu D, Fan C G, Du J L, Meng F F, Fang J L. A novel and smart automatic light-seeking flowerpot for monitoring flower growth environment. Int J Agric & Biol Eng, 2018; 11(2): 184–189.

A novel and smart automatic light-seeking flowerpot for monitoring flower growth environment

Although the flowerpot is widely used for indoor flowers, it cannot meet the needs of intelligent management during the uncared-for period. The objective of this study was to design a new microcontroller-based smart flowerpot. Its overall system was composed of three parts: information collection layer, automatic control layer and data transmission layer. Firstly, in the process of collecting information, the Laiyite criterion and the normalized weighted average algorithm were adopted to improve the accuracy of information collection. Secondly, for making precise control decisions, the fuzzy control was used to achieve automatic on-demand watering. Finally, the method for comparative analysis of regional light intensity was utilized to achieve light-seeking and light-supplementing. Experimental results showed that the smart flowerpot had strong anti-jamming performance for information collection, the relative soil moisture of flowers could be stably maintained near the optimum humidity (65%), and the light was well-distributed on the flower with the error angle of light-supplementing ranged from –3° to 3°. Keywords: smart flowerpot, automatic watering, seeking light, supplementing light control, microcontroller DOI: 10.25165/j.ijabe.20181102.2786 Citation: Zhang X H, Liu D, Fan C G, Du J L, Meng F F, Fang J L. A novel and smart automatic light-seeking flowerpot for monitoring flower growth environment. Int J Agric & Biol Eng, 2018; 11(2): 184–189.

Design and Implementation of Broadcasting and Television Program Monitoring System

In this paper, we proposed a monitoring system called broadcasting and television program monitoring system (BTP-MS) used for improving the program monitoring with respect to automatic, intelligent and network level. To achieve the goal of enhancing the system monitoring ability, we designed a four-layer model of BTP-MS composed by data collection layer, transmission and storage layer, dispatching and configuration layer and data analysis layer, respectively. The designed BTP-MS model was implemented both in hardware and software. The results demonstrated that the designed model could greatly improve the efficiency and stability of program monitoring to ensure the broadcasting safety.

The Architecture of an Automatic eHealth Platform With Mobile Client for Cerebrovascular Disease Detection.

BackgroundIn recent years, cerebrovascular disease has been the leading cause of death and adult disability in the world. This study describes an efficient approach to detect cerebrovascular disease.ObjectiveIn order to improve cerebrovascular treatment, prevention, and care, an automatic cerebrovascular disease detection eHealth platform is designed and studied.MethodsWe designed an automatic eHealth platform for cerebrovascular disease detection with a four-level architecture: object control layer, data transmission layer, service supporting layer, and application service layer. The platform has eight main functions: cerebrovascular database management, preprocessing of cerebral image data, image viewing and adjustment model, image cropping compression and measurement, cerebrovascular segmentation, 3-dimensional cerebrovascular reconstruction, cerebrovascular rendering, cerebrovascular virtual endoscope, and automatic detection. Several key technologies were employed for the implementation of the platform. The anisotropic diffusion model was used to reduce the noise. Statistics segmentation with Gaussian-Markov random field model (G-MRF) and Stochastic Estimation Maximization (SEM) parameter estimation method were used to realize the cerebrovascular segmentation. Ball B-Spline curve was proposed to model the cerebral blood vessels. Compute unified device architecture (CUDA) based on ray-casting volume rendering presented by curvature enhancement and boundary enhancement were used to realize the volume rendering model. We implemented the platform with a network client and mobile phone client to fit different users.ResultsThe implemented platform is running on a common personal computer. Experiments on 32 patients’ brain computed tomography data or brain magnetic resonance imaging data stored in the system verified the feasibility and validity of each model we proposed. The platform is partly used in the cranial nerve surgery of the First Hospital Affiliated to the General Hospital of People's Liberation Army and radiology of Beijing Navy General Hospital. At the same time it also gets some applications in medical imaging specialty teaching of Tianjin Medical University. The application results have also been validated by our neurosurgeon and radiologist.ConclusionsThe platform appears beneficial in diagnosis of the cerebrovascular disease. The long-term benefits and additional applications of this technology warrant further study. The research built a diagnosis and treatment platform of the human tissue with complex geometry and topology such as brain vessel based on the Internet of things.

Application of Participatory Sensing in Meteorological Information Service System

In order to make weather forecast data more precise and help users to make right decisions, a new method that applying participatory sensing in meteorological information service system is put forward in this paper. The participatory sensing architecture consists of four layers: sensing layer, data transmission layer, data processing layer and application layer. The key technologies involved in each layer are analyzed. Its explained how to fuse sensing data collected from sensors carried by users mobile phone with traditional meteorological data. The weather information service prototype system based on participatory sensing is realized. Through the example, its proved that this system is feasible and effective to improve the precision of weather forecast.

QoSockets: a new extension to the sockets API for end-to-end application QoS management

The key question addressed by this paper is how multimedia applications can adapt to the QoS delivered by the network and vice versa. QoSockets is an extension to the sockets mechanism, to enable QoS reservation and management. QoSockets automatically generates the instrumentation to monitor QoS. QoSockets mediates interactions among applications and transport protocols, and collects in QoS MIBs statistics on the QoS delivered. The main advantages are: support of single API for transport layer QoS negotiation, connection establishment, and data transmission; support of a single QoS negotiation protocol; generality across application QoS needs; and automatic management of application QoS needs.