Audio-Text Multimodal Speech Recognition via Dual-Tower Architecture for Mandarin Air Traffic Control Communications

In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.

Beyond 5G Networks: Integration of Communication, Computing, Caching, and Control

In recent years,the exponential proliferation of smart devices with their intelligent applications poses severe challenges on conventional cellular networks.Such challenges can be potentially overcome by integrating communication,computing,caching,and control(i4C)technologies.In this survey,we first give a snapshot of different aspects of the i4C,comprising background,motivation,leading technological enablers,potential applications,and use cases.Next,we describe different models of communication,computing,caching,and control(4C)to lay the foundation of the integration approach.We review current stateof-the-art research efforts related to the i4C,focusing on recent trends of both conventional and artificial intelligence(AI)-based integration approaches.We also highlight the need for intelligence in resources integration.Then,we discuss the integration of sensing and communication(ISAC)and classify the integration approaches into various classes.Finally,we propose open challenges and present future research directions for beyond 5G networks,such as 6G.

International Journal of Systems, Control and Communications(IJSCC)

ISSN (Online): 1755-9359; ISSN (Print): 1755-9340Published in 4 issues per year. Description One of the most dramatic technological developments in the era of information is the deployment of communication networks. This on-going revolution

Separate Dimming Controlling and Data Transmission for an Indoor Visible Light Communication System

Simultaneous dimming controlling and data transmission are usually required in a white LED based indoor visible light communication system.However,the diming controlling of LED normally interferes the data transmission due to the modulation nonlinearity of LED.In order to solve this problem,a scheme by separating the LEDs for the functions of dimming control and data transmission respectively is proposed in this paper.In the scheme,the LEDs used for dimming control function are driven by a dc amplified circuit,and the LEDs for data transmission are driven by a digital modulation circuit respectively.In this way,the modulation distortion to the data signal caused by the modulation nonlinearity can be avoided even if the dimming is at high level dc driven current.The proof-of-concept experiment of a 2.5Mbit/s visible light communication system demonstrates that the dimming controlling and data transmission can be realized simultaneously in a simple way,and the data transmission is not affected by the dimming controlling function.Compared to previous methods,the scheme in this paper is simpler and cost effective,and makes sense when high rate data is transmitted in a visible light communication system.

MULTIPLE ELECTRONIC CONTROL UNITS CALIBRATION SYSTEM BASED ON EXPLICIT CALIBRATION PROTOCOL AND J1939 PROTOCOL

The rising number of electronic control units （ECUs） in vehicles and the decreasing time to market have led to the need for advanced methods of calibration. A multi-ECU calibration system was developed based on the explicit calibration protocol （XCP） and J1939 communication protocol to satisfy the need of calibrating multiple ECUs simultaneously. The messages in the controller area network （CAN） are defined in the J1939 protocol. Each CAN node can get its own calibration messages and information from other ECUs, and block other messages by qualifying the CAN messages with priority, source or destination address. The data field of the calibration message is designed with the XCP, with CAN acting as the transport layer. The calibration sessions are setup with the event-triggered XCP driver in the master node and the responding XCP driver in the slave nodes. Mirroring calibration variables from ROM to RAM enables the user to calibrate ECUs online. The application example shows that the multi-ECU calibration system can calibrate multiple ECUs simultaneously, and the main program can also accomplish its calculation and send commands to the actuators in time. By the multi-ECU calibration system, the calibration effort and time can be reduced and the variables in ECU can get a better match with the variables of other ECUs.

Controlled Secure Direct Communication Protocol via the Three-Qubit Partially Entangled Set of States

In this paper,we first re-examine the previous protocol of controlled quantum secure direct communication of Zhang et al.’s scheme,which was found insecure under two kinds of attacks,fake entangled particles attack and disentanglement attack.Then,by changing the party of the preparation of cluster states and using unitary operations,we present an improved protocol which can avoid these two kinds of attacks.Moreover,the protocol is proposed using the three-qubit partially entangled set of states.It is more efficient by only using three particles rather than four or even more to transmit one bit secret information.Given our using state is much easier to prepare for multiqubit states and our protocol needs less measurement resource,it makes this protocol more convenient from an applied point of view.

Analysis and Improvement of an Efficient Controlled Quantum Secure Direct Communication and Authentication Protocol

The controlled quantum secure direct communication(CQSDC)with authentication protocol based on four particle cluster states via quantum one-time pad and local unitary operations is cryptanalyzed.It is found that there are some serious security issues in this protocol.An eavesdropper(Eve)can eavesdrop on some information of the identity strings of the receiver and the controller without being detected by the selective-CNOT-operation(SCNO)attack.By the same attack,Eve can also steal some information of the secret message that the sender transmits.In addition,the receiver can take the same kind of attack to eavesdrop on some information of the secret message out of the control of the controller.This means that the requirements of CQSDC are not satisfied.At last,we improve the original CQSDC protocol to a secure one.

Controlled Secure Quantum Communication Using Pure Entangled W Class States

We present a controlled secure quantum communication protocol using non-maximally （pure） entangled W states first, and then discuss the basic requirements for a real quantum communication. We show that the authorized two users can exchange their secret messages with the help of the controller after purifying the non-maximally entangled states quantum channel unconditionally securely and simultaneously. Our quantum communication protocol seems even more feasible within present technologies.

Local Bifurcation Analysis of a Delayed Fractional-order Dynamic Model of Dual Congestion Control Algorithms

In this paper, we propose a delayed fractional-order congestion control model which is more accurate than the original integer-order model when depicting the dual congestion control algorithms. The presence of fractional orders requires the use of suitable criteria which usually make the analytical work so harder. Based on the stability theorems on delayed fractionalorder differential equations, we study the issue of the stability and bifurcations for such a model by choosing the communication delay as the bifurcation parameter. By analyzing the associated characteristic equation, some explicit conditions for the local stability of the equilibrium are given for the delayed fractionalorder model of congestion control algorithms. Moreover, the Hopf bifurcation conditions for general delayed fractional-order systems are proposed. The existence of Hopf bifurcations at the equilibrium is established. The critical values of the delay are identified, where the Hopf bifurcations occur and a family of oscillations bifurcate from the equilibrium. Same as the delay, the fractional order normally plays an important role in the dynamics of delayed fractional-order systems. It is found that the critical value of Hopf bifurcations is crucially dependent on the fractional order. Finally, numerical simulations are carried out to illustrate the main results. © 2017 Chinese Association of Automation.

Predictive Decision and Reliable Accessing for UAV Communication in Space-Air-Ground Integrated Networks

The cooperation of multiple Unmanned Aerial Vehicles(UAVs) has become a promising scenario in Space-Air-Ground Integrated Networks(SAGINs) recently due to their widespread applications,where wireless communication is a basic necessity and is normally categorized into control and nonpayload communication(CNPC) as well as payload communication. In this paper, we attempt to tackle two challenges of UAV communication respectively on establishing reliable CNPC links against the high mobility of UAVs as well as changeable communication conditions, and on offering dynamic resource optimization for Quality-of-Service(QoS) guaranteed payload communication with variable link connectivity. Firstly, we propose the concept of air controlling center(ACC), a virtual application equipped on the infrastructure in SAGINs, which can collect global information for estimating UAV trajectory and communication channels. We then introduce the knapsack problem for modelling resource optimization of UAV communication in order to provide optimal access points for both CNPC and payload communication. Meanwhile, using the air controlling information, predictive decision algorithm and handover strategy are introduced for the reliable connection with multiple access points. Simulation results demonstrate that our proposal ensures an approximate always-on reliable accessing of communication links and outperforms the existing methods against high mobility,sparse distribution, and physical obstacles.

Energy Efficiency Optimization for D2D Communications Based on SCA and GP Method

In this paper, we propose an energy-efficient power control scheme for device-to-device(D2D) communications underlaying cellular networks, where multiple D2D pairs reuse the same resource blocks allocated to one cellular user. Taking the maximum allowed transmit power and the minimum data rate requirement into consideration, we formulate the energy efficiency maximization problem as a non-concave fractional programming(FP) problem and then develop a two-loop iterative algorithm to solve it. In the outer loop, we adopt Dinkelbach method to equivalently transform the FP problem into a series of parametric subtractive-form problems, and in the inner loop we solve the parametric subtractive problems based on successive convex approximation and geometric programming method to obtain the solutions satisfying the KarushKuhn-Tucker conditions. Simulation results demonstrate the validity and efficiency of the proposed scheme, and illustrate the impact of different parameters on system performance.

ASIC Design of High-Speed Low-Power HDLC Controller

Combined with the engineering requirement, a high-speed low-power ASIC design of HDLC controller based on RS-485 bus is given in this paper. On principle of Top-Down design, this ASIC design uses multi-techniques to reduce its die area and dynamic power, and overcomes some problems appeared frequently in application systems of the RS-485 circuits formed by the Standard Interface Chips. This design also improves the system reliability and reduces the system area.

Flow Control Strategy for the High Speed Network Based on Control Theory

Design of an effective congestion control scheme is a hot topic in the development of compute network. The flow control scheme can adjust the packet sending rate in source host, thus effectively avoiding the network congestion. This paper proposes a flow control scheme based on discrete control theory. The simulation results show that this method can adjust the sending rate and queue level in buffer rapidly and effectively. The method is easy to implement and applicable to high speed networks.

Intelligent throughput stabilizer for UDP-based rate-control communication system

Michiko Harayama*and Noboru Miyagawa Abstract:In view of the successful application of deep learning,mainly in the field of image recognition,deep learning applications are now being explored in the fields of communication and computer networks.In these fields,systems have been developed by use of proper theoretical calculations and procedures.However,due to the large amount of data to be processed,proper processing takes time and deviations from the theory sometimes occur due to the inclusion of uncertain disturbances.Therefore,deep learning or nonlinear approximation by neural networks may be useful in some cases.We have studied a user datagram protocol(UDP)based rate-control communication system called the simultaneous multipath communication system(SMPC),which measures throughput by a group of packets at the destination node and feeds it back to the source node continuously.By comparing the throughput with the recorded transmission rate,the source node detects congestion on the transmission route and adjusts the packet transmission interval.However,the throughput fluctuates as packets pass through the route,and if it is fed back directly,the transmission rate fluctuates greatly,causing the fluctuation of the throughput to become even larger.In addition,the average throughput becomes even lower.In this study,we tried to stabilize the transmission rate by incorporating prediction and learning performed by a neural network.The prediction is performed using the throughput measured by the destination node,and the result is learned so as to generate a stabilizer.A simple moving average method and a stabilizer using three types of neural networks,namely multilayer perceptrons,recurrent neural networks,and long short-term memory,were built into the transmission controller of the SMPC.The results showed that not only fluctuation reduced but also the average throughput improved.Together,the results demonstrated that deep learning can be used to predict and output stable values from data with complicated time fluctuations that are difficultly analyzed.

Optimization of a Heat Exchanger Using an ARM Core Intelligent Algorithm

In order to optimize heat transfer in a heat exchanger using an ARM(advanced RISC machine)core intelligent computer algorithm,a new type of controller has been designed.The whole control structure of the heat exchange unit has been conceived on the basis of seven functional modules,including data processing and output,human-computer interaction,alarm,and data communication.The main controller and communication controller have been used in a combined fashion and a new MCU(micro control unit)system scheme has been proposed accordingly.A fuzzy controller has been designed by using a fuzzy control algorithm,and a new mode of heat transfer for the heat exchanger has been implemented by combining the fuzzy controller and the PID(proportioning integral derivative)controller.Finally,the model has been applied to an actual heat exchange station to test and verify the performances of the new approach.

Modeling research of train tracing based on UML sequence diagram and UPPAAL

The zone control subsystem is a real-time control system,which requests the correctness of the control process.Train tracing scene is an important function of the zone controller(ZC)in the communication based train control(CBTC)system.In the process of deep development and design,to ensure the safety of the system,the system needs to be modeled,simulated and verified to discover the system design flaws.Unified modeling language(UML)is combined with timed automata,and timed automata network models of train-filter and train tracing demarcation-point are established.At the same time,the verification tool of UPPAAL is applied to simulate the system,and verify the requirements of performance and function of system.The results show that the function of train tracing demaraction-point meets the requirements of system safety and limited activity.Therefore,the method is feasible and can be applied to the modeling and verification of other scenes of train control system.

Effects of Multiple Cleaning and Disinfection Interventions on Infectious Diseases in Children: A Group Randomized Trial in China

Objective To assess the effectiveness of multiple cleaning and disinfection interventions in the homes and kindergartens, in reducing gastrointestinal and respiratory illnesses of children. Methods From October 2010 to September 2011, we performed a prospective, controlled study in China. 408 children under 5 years old were recruited and group randomized into intervention and control groups. Families and kindergartens in the intervention group were provided with antibacterial products for hand hygiene and surface cleaning or disinfection for one year. Each child＇s illness symptoms and sick leave were recorded every day. Results A total of 393 children completed the study, with similar baseline demographics in each of the 2 groups. Except for abdominal pain, the odds of symptoms （fever, cough and expectoration, runny nose and nasal congestion, diarrhea）, illness （acute respiratory illness and gastrointestinal illness）, and sick leave per person each month were significantly reduced by interventions. The rates of fever, diarrhea, acute respiratory illness, gastrointestinal illness and sick leave per person per year were significantly decreased as well. Conclusion Not only the acute respiratory children were significantly reduced by multiple and gastrointestinal illness but the sick leave rate in interventions.

Robust attitude coordinated control for spacecraft formation with communication delays

In this paper,attitude coordinated tracking control algorithms for multiple spacecraft formation are investigated with consideration of parametric uncertainties,external disturbances,communication delays and actuator saturation.Initially,a sliding mode delay-dependent attitude coordinated controller is proposed under bounded external disturbances.However,neither inertia uncertainty nor actuator constraint has been taken into account.Then,a robust saturated delaydependent attitude coordinated control law is further derived,where uncertainties and external disturbances are handled by Chebyshev neural networks（CNN）.In addition,command filter technique is introduced to facilitate the backstepping design procedure,through which actuator saturation problem is solved.Thus the spacecraft in the formation are able to track the reference attitude trajectory even in the presence of time-varying communication delays.Rigorous analysis is presented by using Lyapunov-Krasovskii approach to demonstrate the stability of the closed-loop system under both control algorithms.Finally,the numerical examples are carried out to illustrate the efficiency of the theoretical results.

ROBUST OUTPUT FEEDBACK STABILIZATION OF NONLINEAR NETWORKED SYSTEMS VIA A FINITE DATA-RATE COMMUNICATION CHANNEL

This paper addresses a robust stabilization problem of a class of uncertain nonlinear systems using output measurements via a finite data-rate communication channel. The authors assumes that there exist an observer and a control law for the systems in the absence of any finite data-rate communi- cation channel. Based on the observer and the control law, the authors constructs an encoder/decoder pair and provides a sufficient condition, including suitable sampling period and data rate, which will guarantee the stability of the closed-loop systems when a finite data-rate communication channel is introduced.

Preparation of a New Type of Multiqubit Entangled States in Cavity QED

Recently Yang,Chu,and Han [Phys.Rev.A 70 (2004) 022329] presented a new type of multipartiteentangled states for implementing efficient many-party controlled teleportation of multiqubit quantum information.Herewe propose a simple scheme for preparing such a type of multi-atom entangled states in cavity quantum electrodynamics(QED).The scheme involves atom-cavity interaction with large detuning,and is immune to the cavity decay and thethermal field states.Some practical analyses show its availability with the present technology.