Miao Du

Miao Du, Qin Yu, Shaomin Fei et al.

Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system.

Ruisen Luo, Tianran Sun, Chen Wang et al.

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and computational resources, such as voice command recognition in vehicles and robot interaction. At present, the mainstream methods in automatic speech keyword recognition are based on long short-term memory (LSTM) networks with attention mechanism. However, due to inevitable information losses for the LSTM layer caused during feature extraction, the calculated attention weights are biased. In this paper, a novel approach, namely Multi-layer Attention Mechanism, is proposed to handle the inaccurate attention weights problem. The key idea is that, in addition to the conventional attention mechanism, information of layers prior to feature extraction and LSTM are introduced into attention weights calculations. Therefore, the attention weights are more accurate because the overall model can have more precise and focused areas. We conduct a comprehensive comparison and analysis on the keyword spotting performances on convolution neural network, bi-directional LSTM cyclic neural network, and cyclic neural network with the proposed attention mechanism on Google Speech Command datasets V2 datasets. Experimental results indicate favorable results for the proposed method and demonstrate the validity of the proposed method. The proposed multi-layer attention methods can be useful for other researches related to object spotting.

Chen Wang, Xiaomei Yang, Shaomin Fei et al.

Quantization can be used to form new vectors/matrices with shared values close to the original. In recent years, the popularity of scalar quantization for value-sharing applications has been soaring as it has been found huge utilities in reducing the complexity of neural networks. Existing clustering-based quantization techniques, while being well-developed, have multiple drawbacks including the dependency of the random seed, empty or out-of-the-range clusters, and high time complexity for a large number of clusters. To overcome these problems, in this paper, the problem of scalar quantization is examined from a new perspective, namely sparse least square optimization. Specifically, inspired by the property of sparse least square regression, several quantization algorithms based on $l_1$ least square are proposed. In addition, similar schemes with $l_1 + l_2$ and $l_0$ regularization are proposed. Furthermore, to compute quantization results with a given amount of values/clusters, this paper designed an iterative method and a clustering-based method, and both of them are built on sparse least square. The paper shows that the latter method is mathematically equivalent to an improved version of k-means clustering-based quantization algorithm, although the two algorithms originated from different intuitions. The algorithms proposed were tested with three types of data and their computational performances, including information loss, time consumption, and the distribution of the values of the sparse vectors, were compared and analyzed. The paper offers a new perspective to probe the area of quantization, and the algorithms proposed can outperform existing methods especially under some bit-width reduction scenarios, when the required post-quantization resolution (number of values) is not significantly lower than the original number.

Miao Du

Service virtualisation is a method to create virtual service models that can mimic interaction behaviors between a system under test and the target system. With service virtualisation, the development team can get access to the production-like conditions whenever and however many times they need, enabling frequent and comprehensive testing. Previous techniques for service virtualisation have relied on explicitly modelling the target services by a service expert and require detailed knowledge of message protocol and structure. However, neither of these are necessarily available. In this thesis, we introduce our novel opaque response generation approach. This approach enables services to be virtualised automatically without any expert knowledge or documentation of system protocol and interaction behaviours. Given a collection of interactions exchanged between a system under test and a target real service, our approach can 1) organise the same type of interactions into the same cluster and derive a cluster prototype for each cluster; 2) search a given incoming request for its the most similar request in the interaction library; 3) learn knowledge from the incoming request and the recorded interaction; and 4) generate a response. A framework and proof-of-concept implementation of our opaque response generation approach is described. Experimental results show our opaque response generation approach is able to automatically generate accurate responses in real time with an accuracy rate over 99% on average.

Steve Versteeg, Miao Du, Jean-Guy Schneider et al.

Large enterprise software systems make many complex interactions with other services in their environment. Developing and testing for production-like conditions is therefore a very challenging task. Current approaches include emulation of dependent services using either explicit modelling or record-and-replay approaches. Models require deep knowledge of the target services while record-and-replay is limited in accuracy. Both face developmental and scaling issues. We present a new technique that improves the accuracy of record-and-replay approaches, without requiring prior knowledge of the service protocols. The approach uses Multiple Sequence Alignment to derive message prototypes from recorded system interactions and a scheme to match incoming request messages against prototypes to generate response messages. We use a modified Needleman-Wunsch algorithm for distance calculation during message matching. Our approach has shown greater than 99% accuracy for four evaluated enterprise system messaging protocols. The approach has been successfully integrated into the CA Service Virtualization commercial product to complement its existing techniques.

Steve Versteeg, Miao Du, John Bird et al.

Service virtualisation is a supporting tool for DevOps to generate interactive service models of dependency systems on which a system-under-test relies. These service models allow applications under development to be continuously tested against production-like conditions. Generating these virtual service models requires expert knowledge of the service protocol, which may not always be available. However, service models may be generated automatically from network traces. Previous work has used the Needleman-Wunsch algorithm to select a response from the service model to play back for a live request. We propose an extension of the Needleman-Wunsch algorithm, which uses entropy analysis to automatically detect the critical matching fields for selecting a response. Empirical tests against four enterprise protocols demonstrate that entropy weighted matching can improve response accuracy.

Miao Du, Steve Versteeg, Jean-Guy Schneider et al.

Enterprise software systems make complex interactions with other services in their environment. Developing and testing for production-like conditions is therefore a challenging task. Prior approaches include emulations of the dependency services using either explicit modelling or record-and-replay approaches. Models require deep knowledge of the target services while record-and-replay is limited in accuracy. We present a new technique that improves the accuracy of record-and-replay approaches, without requiring prior knowledge of the services. The approach uses multiple sequence alignment to derive message prototypes from recorded system interactions and a scheme to match incoming request messages against message prototypes to generate response messages. We introduce a modified Needleman-Wunsch algorithm for distance calculation during message matching, wildcards in message prototypes for high variability sections, and entropy-based weightings in distance calculations for increased accuracy. Combined, our new approach has shown greater than 99% accuracy for four evaluated enterprise system messaging protocols.

Rajesh Mathur, Scott Miles, Miao Du

Checking software application suitability using automated software tools has become a vital element for most organisations irrespective of whether they produce in-house software or simply customise off-the-shelf software applications for internal use. As software solutions become ever more complex, the industry becomes increasingly dependent on software automation tools, yet the brittle nature of the available software automation tools limits their effectiveness. Companies invest significantly in obtaining and implementing automation software but most of the tools fail to deliver when the cost of maintaining an effective automation test suite exceeds the cost and time that would have otherwise been spent on manual testing. A failing in the current generation of software automation tools is they do not adapt to unexpected modifications and obstructions without frequent (and time expensive) manual interference. Such issues are commonly acknowledged amongst industry practitioners, yet none of the current generation of tools have leveraged the advances in machine learning and artificial intelligence to address these problems. This paper proposes a framework solution that utilises machine learning concepts, namely fuzzy matching and error recovery. The suggested solution applies adaptive techniques to recover from unexpected obstructions that would otherwise have prevented the script from proceeding. Recovery details are presented to the user in a report which can be analysed to determine if the recovery procedure was acceptable and the framework will adapt future runs based on the decisions of the user. Using this framework, a practitioner can run the automated suits without human intervention while minimising the risk of schedule delays.