Biblio

We present a ternary source coding scheme in this paper, which is a special class of low density generator matrix (LDGM) codes. We prove that a ternary linear block LDGM code, whose generator matrix is randomly generated with each element independent and identically distributed, is universal for source coding in terms of the symbol-error rate (SER). To circumvent the high-complex maximum likelihood decoding, we introduce a special class of convolutional LDGM codes, called block Markov superposition transmission of repetition (BMST-R) codes, which are iteratively decodable by a sliding window algorithm. Then the presented BMST-R codes are applied to construct a tandem scheme for Gaussian source compression, where a dead-zone quantizer is introduced before the ternary source coding. The main advantages of this scheme are its universality and flexibility. The dead-zone quantizer can choose a proper quantization level according to the distortion requirement, while the LDGM codes can adapt the code rate to approach the entropy of the quantized sequence. Numerical results show that the proposed scheme performs well for ternary sources over a wide range of code rates and that the distortion introduced by quantization dominates provided that the code rate is slightly greater than the discrete entropy.

TVM(tensor virtual machine) as a deep learning compiler which supports the conversion of machine learning models into TVM IR(intermediate representation) and to optimise the generation of high-performance machine code for various hardware platforms. While the traditional approach is to parallelise the cyclic transformations of operators, in this paper we partition the implementation of the operators in the deep learning compiler TVM with parallel scheduling to derive a faster running time solution for the operators. An optimisation algorithm for partitioning and parallel scheduling is designed for the deep learning compiler TVM, where operators such as two-dimensional convolutions are partitioned into multiple smaller implementations and several partitioned operators are run in parallel scheduling to derive the best operator partitioning and parallel scheduling decisions by means of performance estimation. To evaluate the effectiveness of the algorithm, multiple examples of the two-dimensional convolution operator, the average pooling operator, the maximum pooling operator, and the ReLU activation operator with different input sizes were tested on the CPU platform, and the performance of these operators was experimentally shown to be improved and the operators were run speedily.

This work analyzed the coding gain that is provided in 6LoWPAN transceivers when channel-coding methods are used. There were made improvements at physical layer of 6LoWPAN technology in the system suggested. Performance analysis was performed using turbo, LDPC and convolutional codes on IEEE 802.15.4 standard that is used in the relevant physical layer. Code rate of convolutional and turbo codes are set to 1/3 and 1/4. For LDPC codes, the code rate is set as 3/4 and 5/6. According to simulation results obtained from the MATLAB environment, turbo codes give better results than LDPC and convolutional codes. It is seen that an average of 3 dB to 8 dB gain is achieved in turbo codes, in LDPC and convolutional coding, it is observed that the gain is between 2 dB and 6 dB depending on the modulation type and code rate.

Based on the structure of turbo-polar codes, a secure symmetric encryption scheme is proposed to enhance information transmission security in this paper. This scheme utilizes interleaving at information bits and puncturing at parity bits for several times in the encoder. Correspondingly, we need to do the converse interleaving and fill zeros accurately at punctured position. The way of interleaving and puncturing is controlled by the private key of symmetric encryption, making sure the security of the system. The security of Secure Turbo-Polar Codes (STPC) is analyzed at the end of this paper. Simulation results are given to shown that the performance and complexity of Turbo-Polar Codes have little change after symmetric encryption. We also investigate in depth the influence of different remaining parity bit ratios on Frame Error Rate (FER). At low Signal to Noise Rate (SNR), we find it have about 0.6dB advantage when remaining parity bit ratio is between 1/20 and 1/4.

Cyber-attacks toward cyber-physical systems are one of the main concerns of smart grid's operators. However, many of these cyber-attacks, are toward unmanned substations where the cyber-attackers needs to be close enough to substation to malfunction protection and control systems in substations, using Electromagnetic signals. Therefore, in this paper, a new threat detection algorithm is proposed to prevent possible cyber-attacks toward unmanned substations. Using surveillance camera's streams and based on You Only Look Once (YOLO) V3, suspicious objects in the image are detected. Then, using Intersection over Union (IOU) and Generalized Intersection Over Union (GIOU), threat distance is estimated. Finally, the estimated threats are categorized into three categories using color codes red, orange and green. The deep network used for detection consists of 106 convolutional layers and three output prediction with different resolutions for different distances. The pre-trained network is transferred from Darknet-53 weights trained on 80 classes.

For the purpose of outdoor advertising market researching, AD images are recaptured and uploaded everyday for statistics. But the quality of the recaptured advertising images are often affected by conditions such as angle, distance, and light during the shooting process, which consequently reduce either the speed or the accuracy of the retrieving algorithm. In this paper, we proposed a hash retrieval method based on convolutional neural networks for recaptured images. The basic idea is to add a hash layer to the convolutional neural network and then extract the binary hash code output by the hash layer to perform image retrieval in lowdimensional Hamming space. Experimental results show that the retrieval performance is improved compared with the current commonly used hash retrieval methods.

We investigate a deep learning model for action recognition that simultaneously extracts spatio-temporal information from a raw RGB input data. The proposed multiple spatio-temporal scales recurrent neural network (MSTRNN) model is derived by combining multiple timescale recurrent dynamics with a conventional convolutional neural network model. The architecture of the proposed model imposes both spatial and temporal constraints simultaneously on its neural activities. The constraints vary, with multiple scales in different layers. As suggested by the principle of upward and downward causation, it is assumed that the network can develop a functional hierarchy using its constraints during training. To evaluate and observe the characteristics of the proposed model, we use three human action datasets consisting of different primitive actions and different compositionality levels. The performance capabilities of the MSTRNN model on these datasets are compared with those of other representative deep learning models used in the field. The results show that the MSTRNN outperforms baseline models while using fewer parameters. The characteristics of the proposed model are observed by analyzing its internal representation properties. The analysis clarifies how the spatio-temporal constraints of the MSTRNN model aid in how it extracts critical spatio-temporal information relevant to its given tasks.

While recent studies have shed light on the expressivity, complexity and compositionality of convolutional networks, the real inductive bias of the family of functions reachable by gradient descent on natural data is still unknown. By exploiting symmetries in the preactivation space of convolutional layers, we present preliminary empirical evidence of regularities in the preimage of trained rectifier networks, in terms of arrangements of polytopes, and relate it to the nonlinear transformations applied by the network to its input.

Wireless technology has seen a tremendous growth in the recent past. Orthogonal Frequency Division Multiplexing (OFDM) modulation scheme has been utilized in almost all the advanced wireless techniques because of the advantages it offers. Hence in this aspect, SystemVue based OFDM transceiver has been developed with AWGN as the channel noise. To mitigate the channel noise Convolutional code with Viterbi decoder has been depicted. Further to protect the information from the malicious users the data is scrambled with the aid of gold codes. The performance of the transceiver is analysed through various Bit Error Rate (BER) versus Signal to Noise Ratio (SNR) graphs.

In recent years, the demand for high reliability in industrial wireless communication has been increasing. To meet the strict requirement, many researchers have studied various bit interleaving coding schemes for long packet transmission in industrial wireless networks. Current research shows that the use of bit interleaving structure can improve the performance of the communication system for long packet transmission, but to improve reliability of industrial wireless communications by combining the bit interleaving and channel coding for short packets still requires further analysis. With this aim, bit interleaving structure is applied to convolution code coding scheme for short packet transmission in this paper. We prove that the use of interleaver fail to improve the reliability of data transmission under the circumstance of short packet transmission.

Originally implemented by Google, QUIC gathers a growing interest by providing, on top of UDP, the same service as the classical TCP/TLS/HTTP/2 stack. The IETF will finalise the QUIC specification in 2019. A key feature of QUIC is that almost all its packets, including most of its headers, are fully encrypted. This prevents eavesdropping and interferences caused by middleboxes. Thanks to this feature and its clean design, QUIC is easier to extend than TCP. In this paper, we revisit the reliable transmission mechanisms that are included in QUIC. More specifically, we design, implement and evaluate Forward Erasure Correction (FEC) extensions to QUIC. These extensions are mainly intended for high-delays and lossy communications such as In-Flight Communications. Our design includes a generic FEC frame and our implementation supports the XOR, Reed-Solomon and Convolutional RLC error-correcting codes. We also conservatively avoid hindering the loss-based congestion signal by distinguishing the packets that have been received from the packets that have been recovered by the FEC. We evaluate its performance by applying an experimental design covering a wide range of delay and packet loss conditions with reproducible experiments. These confirm that our modular design allows the protocol to adapt to the network conditions. For long data transfers or when the loss rate and delay are small, the FEC overhead negatively impacts the download completion time. However, with high packet loss rates and long delays or smaller files, FEC allows drastically reducing the download completion time by avoiding costly retransmission timeouts. These results show that there is a need to use FEC adaptively to the network conditions.

Adaptive steganography aims to reduce distortion in the embedding process, typically using Syndrome Trellis Codes (STCs). However, in the case of non-adversarial noise, these are a bad choice: syndrome codes are fragile by design, amplifying the channel error rate into unacceptably-high payload error rates. In this paper we examine the fragility of STCs in the noisy channel, and consider how this can be mitigated if their use cannot be avoided altogether. We also propose an extension called Dual-Syndrome Trellis Codes, that combines error correction and embedding in the same Viterbi process, which slightly outperforms a straight-forward combination of standard forward error correction and STCs.

The general idea to achieve error detection and correction is to add some extra bit to an original message, in which the receiver can use to check the flexibility of the message which has been delivered, and to recover the noisy data. Turbo code is one of the forward error correction method, which is able to achieve the channel capacity, with nearer Shannon limit, encoding and decoding of text and images are performed. Methods and the working have been explained in this paper. The error has also introduced and detection and correction of errors have been achieved. Transmission will be secure it can secure the information by the theft.

The goal of content-based recommendation system is to retrieve and rank the list of items that are closest to the query item. Today, almost every e-commerce platform has a recommendation system strategy for products that customers can decide to buy. In this paper we describe our work on creating a Generative Adversarial Network based image retrieval system for e-commerce platforms to retrieve best similar images for a given product image specifically for shoes. We compare state-of-the-art solutions and provide results for the proposed deep learning network on a standard data set.

For secure and high-quality wireless transmission, we propose a chaos multiple-input multiple-output (C-MIMO) transmission scheme, in which physical layer security and a channel coding effect with a coding rate of 1 are obtained by chaotic MIMO block modulation. In previous studies, we introduced a log-likelihood ratio (LLR) to C-MIMO to exploit LLR-based outer channel coding and turbo decoding, and obtained further coding gain. However, we only studied the concatenation of turbo code, low-density parity check (LDPC) code, and convolutional code which were relatively high-complexity or weak codes; thus, outer code having further low-complexity and strong error correction ability were expected. In particular, a transmission system with short and good code is required for control signaling, such as in 5G networks. Therefore, in this paper, we propose a polar code concatenation to C-MIMO, and introduce soft successive decoding (SCAD) and soft successive cancellation list decoding (SSCLD) as LLR-based turbo decoding for polar code. We numerically evaluate the bit error rate performance of the proposed scheme, and compare it to the conventional LDPC-concatenated transmission.

Static vulnerability detection has shown its effectiveness in detecting well-defined low-level memory errors. However, high-level control-flow related (CFR) vulnerabilities, such as insufficient control flow management (CWE-691), business logic errors (CWE-840), and program behavioral problems (CWE-438), which are often caused by a wide variety of bad programming practices, posing a great challenge for existing general static analysis solutions. This paper presents a new deep-learning-based graph embedding approach to accurate detection of CFR vulnerabilities. Our approach makes a new attempt by applying a recent graph convolutional network to embed code fragments in a compact and low-dimensional representation that preserves high-level control-flow information of a vulnerable program. We have conducted our experiments using 8,368 real-world vulnerable programs by comparing our approach with several traditional static vulnerability detectors and state-of-the-art machine-learning-based approaches. The experimental results show the effectiveness of our approach in terms of both accuracy and recall. Our research has shed light on the promising direction of combining program analysis with deep learning techniques to address the general static analysis challenges.

Hierarchical approaches for representation learning have the ability to encode relevant features at multiple scales or levels of abstraction. However, most hierarchical approaches exploit only the last level in the hierarchy, or provide a multiscale representation that holds a significant amount of redundancy. We argue that removing redundancy across the multiple levels of abstraction is important for an efficient representation of compositionality in object-based representations. With the perspective of feature learning as a data compression operation, we propose a new greedy inference algorithm for hierarchical sparse coding. Convolutional matching pursuit with a L0-norm constraint was used to encode the input signal into compact and non-redundant codes distributed across levels of the hierarchy. Simple and complex synthetic datasets of temporal signals were created to evaluate the encoding efficiency and compare with the theoretical lower bounds on the information rate for those signals. Empirical evidence have shown that the algorithm is able to infer near-optimal codes for simple signals. However, it failed for complex signals with strong overlapping between objects. We explain the inefficiency of convolutional matching pursuit that occurred in such case. This brings new insights about the NP-hard optimization problem related to using L0-norm constraint in inferring optimally compact and distributed object-based representations.

Performing large-scale malware classification is increasingly becoming a critical step in malware analytics as the number and variety of malware samples is rapidly growing. Statistical machine learning constitutes an appealing method to cope with this increase as it can use mathematical tools to extract information out of large-scale datasets and produce interpretable models. This has motivated a surge of scientific work in developing machine learning methods for detection and classification of malicious executables. However, an optimal method for extracting the most informative features for different malware families, with the final goal of malware classification, is yet to be found. Fortunately, neural networks have evolved to the state that they can surpass the limitations of other methods in terms of hierarchical feature extraction. Consequently, neural networks can now offer superior classification accuracy in many domains such as computer vision and natural language processing. In this paper, we transfer the performance improvements achieved in the area of neural networks to model the execution sequences of disassembled malicious binaries. We implement a neural network that consists of convolutional and feedforward neural constructs. This architecture embodies a hierarchical feature extraction approach that combines convolution of n-grams of instructions with plain vectorization of features derived from the headers of the Portable Executable (PE) files. Our evaluation results demonstrate that our approach outperforms baseline methods, such as simple Feedforward Neural Networks and Support Vector Machines, as we achieve 93% on precision and recall, even in case of obfuscations in the data.

In the recent years many companies are shifting towards cloud for expanding their business profit with least additional cost. Cloud computing is a growing technology which has emerged from the development of grid computing, virtualization and utility computing. Cloud computing is a model for enabling convenient, on-demand network access to a shared pool of configurable computing resources like networks, servers, storage, applications, and services that can be rapidly provisioned and released with minimal management effort or service provider interaction. There was a huge data loss during the recent Chennai floods during Dec 2015. If these data would have been stored at distributed data centers great loss could have been prevented. Though, such natural calamities are tempting many users to shift towards the cloud storage, security threats are inhibiting them to shift towards the cloud. Many solutions have been addressed for these security issues but they do not give guaranteed security. By guaranteed security we mean confidentiality, integrity and availability. Some of the existing techniques for providing security are Cryptographic Protocols, Data Sanitization, Predicate Logic, Access Control Mechanism, Honeypots, Sandboxing, Erasure Coding, RAID(Redundant Arrays of Independent Disks), Homomorphic Encryption and Split-Key Encryption. All these techniques either cannot work alone or adds computational and time complexity. An alternate scheme of combining encryption and channel coding schemes at one-go is proposed for increasing the levels of security. Hybrid encryption scheme is proposed to be used in the interleaver block of Turbo coder for avoiding burst error. Hybrid encryption avoids sharing of secret key via the unsecured channel. This provides both security and reliability by reducing error propagation effect with small additional cost and computational overhead. Time complexity can be reduced when encryption and encoding are done as a single process.