Automatic modulation classification (AMC) has been intriguing many researchers as it has many civil and military applications. Recently, cooperative AMC (CAMC) using a dynamic or ad hoc sensor network becomes appealing and challenging. As the unmanned aerial vehicles (UAVs) can facilitate three-dimensional communication/sensor network, we propose a novel CAMC approach based on a dynamic (ad hoc) UAV network. In our proposed new CAMC approach, the local classification decisions, which are made by spatially distributed nodes (UAVs) using our previously proposed graph-based modulation classifier, are gathered to reach an overall decision by a new weighted voting mechanism pertinent to individual received signal qualities. Note that the fusion center does not have to be a fixed UAV and it can be dynamically reassigned to any UAV within the same network in each sensing interval. The corresponding weights to individual UAVs are to be determined according to their cumulative states and the temporal discount factor. As a result, our proposed new CAMC approach can be fully distributed as no control center (or hub) is necessary. Besides, our new CAMC scheme can accommodate realistic ad hoc network variations to allow the existing UAVs to depart and/or the new UAVs to join in any sensing interval. Monte Carlo simulation results demonstrate that our proposed new CAMC scheme is quite robust and outperforms the existing CAMC method.

Cooperative automatic modulation classification (CAMC) using a swarm of sensors is intriguing nowadays as it would be much more robust than the conventional single-sensing-node automatic modulation classification (AMC) method. We propose a novel robust CAMC approach using vectorized soft decision fusion in this work. In each sensing node, the local Hamming distances between the graph features acquired from the unknown target signal and the training modulation candidate signals are calculated and transmitted to the fusion center (FC). Then, the global CAMC decision is made by the indirect vote which is translated from each sensing node’s Hamming-distance sequence. The simulation results demonstrate that, when the signal-to-noise ratio (SNR) was given by $\eta$ ≥ $0\mathrm{dB}$, our proposed new CAMC scheme’s correct classification probability $P_{\mathrm{cc}}$ could reach up close to $100\%$. On the other hand, our proposed new CAMC scheme could significantly outperform the single-node graph-based AMC technique and the existing decision-level CAMC method in terms of recognition accuracy, especially in the low-SNR regime.

There are some problems in the development of vocational Chinese, such as the unsystematic teaching materials, the unreasonable curriculum, the simple cultivation mode and insufficient professional teachers. Therefore, it puts forward strategies such as creation of special courses, optimization of training objectives and establishment of “Double Tutor” system. In terms of personnel training, we should clarify the career orientation and update the training concept. We recommend establishing a flexible joint training and exchange student system and advocating School-enterprise cooperation.

The idea of “Production-Oriented Approach” (POA) is to solve the disadvantage of “separation of learning and application”. This paper analyzes how to do each process and puts forward specific teaching strategies in vocational Chinese teaching. It includes workplace case analysis, dilemma and demand orientation, disciplinary integration, student immersion participation. New technology can make learning more diverse. It includes the use of modern media technology, development of three-dimensional intelligent teaching materials and development of professional web learning resource library. POA connect with new technology can improve vocational Chinese teaching.