Lightweight Malicious Code Classification Method Based on Improved Squeeze Net

With the growth of the Internet,more and more business is being done online,for example,online offices,online education and so on.While this makes people’s lives more convenient,it also increases the risk of the network being attacked by malicious code.Therefore,it is important to identify malicious codes on computer systems efficiently.However,most of the existing malicious code detection methods have two problems:(1)The ability of the model to extract features is weak,resulting in poor model performance.(2)The large scale of model data leads to difficulties deploying on devices with limited resources.Therefore,this paper proposes a lightweight malicious code identification model Lightweight Malicious Code Classification Method Based on Improved SqueezeNet(LCMISNet).In this paper,the MFire lightweight feature extraction module is constructed by proposing a feature slicing module and a multi-size depthwise separable convolution module.The feature slicing module reduces the number of parameters by grouping features.The multi-size depthwise separable convolution module reduces the number of parameters and enhances the feature extraction capability by replacing the standard convolution with depthwise separable convolution with different convolution kernel sizes.In addition,this paper also proposes a feature splicing module to connect the MFire lightweight feature extraction module based on the feature reuse and constructs the lightweight model LCMISNet.The malicious code recognition accuracy of LCMISNet on the BIG 2015 dataset and the Malimg dataset reaches 98.90% and 99.58%,respectively.It proves that LCMISNet has a powerful malicious code recognition performance.In addition,compared with other network models,LCMISNet has better performance,and a lower number of parameters and computations.

Self-Encoded Multiple Access Multiuser Convolutional Codes in Uplink and Downlink Cellular Systems

Self-encoded spread spectrum eliminates the need for traditional pseudo noise (PN) code generators. In a self-encoded multiple access (SEMA) system, the number of users is not limited by the number of available sequences, unlike code division multiple access (CDMA) systems that employ PN codes such as m-, Gold or Kassami sequences. SEMA provides a convenient way of supporting multi-rate, multi-level grades of service in multimedia communications and prioritized heterogeneous networking systems. In this paper, we propose multiuser convolutional channel coding in SEMA that provides fewer cross-correlations among users and thereby reducing multiple access interference (MAI). We analyze SEMA multiuser convolutional coding in additive white Gaussian noise (AWGN) channels as well as fading channels. Our analysis includes downlink synchronous system as well as asynchronous system such as uplink mobile-to-base station communication.

Blind recognition of k/n rate convolutional encoders from noisy observation

Blind recognition of convolutional codes is not only essential for cognitive radio, but also for non-cooperative context. This paper is dedicated to the blind identification of rate k/n convolutional encoders in a noisy context based on Walsh-Hadamard transformation and block matrix (WHT-BM). The proposed algorithm constructs a system of noisy linear equations and utilizes all its coefficients to recover parity check matrix. It is able to make use of fault-tolerant feature of WHT, thus providing more accurate results and achieving better error performance in high raw bit error rate (BER) regions. Moreover, it is more computationally efficient with the use of the block matrix (BM) method. ? 2017 Beijing Institute of Aerospace Information.

Blind reconstruction of convolutional code based on segmented Walsh-Hadamard transform

Walsh-Hadamard transform （WriT） can solve linear error equations on Field F2, and the method can be used to recover the parameters of convolutional code. However, solving the equations with many unknowns needs enormous computer memory which limits the application of WriT. In order to solve this problem, a method based on segmented WriT is proposed in this paper. The coefficient vector of high dimension is reshaped and two vectors of lower dimension are obtained. Then the WriT is operated and the requirement for computer memory is much reduced. The code rate and the constraint length of convolutional code are detected from the Walsh spectrum. And the check vector is recovered from the peak position. The validity of the method is verified by the simulation result, and the performance is proved to be optimal.

Construction of Regular Rate-Compatible LDPC Convolutional Codes

In this paper, we propose a new method to derive a family of regular rate-compatible low-density parity-check（RC-LDPC） convolutional codes from RC-LDPC block codes. In the RC-LDPC convolutional family, each extended sub-matrix of each extended code is obtained by choosing specified elements from two fixed matrices HE1K and HE1K, which are derived by modifying the extended matrices HE1 and HE2 of a systematic RC-LDPC block code. The proposed method which is based on graph extension simplifies the design, and prevent the defects caused by the puncturing method. It can be used to generate both regular and irregular RC-LDPC convolutional codes. All resulted codes in the family are systematic which simplify the encoder structure and have maximum encoding memories which ensure the property. Simulation results show the family collectively offer a steady improvement in performance with code compatibility over binary-input additive white Gaussian noise channel（BI-AWGNC）.

Determination of quantum toric error correction code threshold using convolutional neural network decoders

Quantum error correction technology is an important solution to solve the noise interference generated during the operation of quantum computers.In order to find the best syndrome of the stabilizer code in quantum error correction,we need to find a fast and close to the optimal threshold decoder.In this work,we build a convolutional neural network(CNN)decoder to correct errors in the toric code based on the system research of machine learning.We analyze and optimize various conditions that affect CNN,and use the RestNet network architecture to reduce the running time.It is shortened by 30%-40%,and we finally design an optimized algorithm for CNN decoder.In this way,the threshold accuracy of the neural network decoder is made to reach 10.8%,which is closer to the optimal threshold of about 11%.The previous threshold of 8.9%-10.3%has been slightly improved,and there is no need to verify the basic noise.

Ensemble of High Performance Structured Binary Convolutional LDPC Codes with Moderate Rates

An algebraic construction methodology is proposed to design binary time-invariant convolutional low-density parity-check(LDPC)codes.Assisted by a proposed partial search algorithm,the polynomialform parity-check matrix of the time-invariant convolutional LDPC code is derived by combining some special codewords of an(n,2,n−1)code.The achieved convolutional LDPC codes possess the characteristics of comparatively large girth and given syndrome former memory.The objective of our design is to enable the time-invariant convolutional LDPC codes the advantages of excellent error performance and fast encoding.In particular,the error performance of the proposed convolutional LDPC code with small constraint length is superior to most existing convolutional LDPC codes.

Turbo Codes―A New PCCC Design

Coding techniques have always been a major area of scientific interest. Due to this interest, many coding schemes were invented. Eventually, their implementation in various systems contributed in the evolvement of Wireless Communications. A breakthrough was definitely Turbo coding. Particularly, the concept of joining two or more convolutional encoders in parallel (PCCC) or in serial (SCCC), along with the iterative decoding technique, literally raised the expectations of the anticipated BER performance. In fact, Concatenated Convolutional Codes clearly outperform convolutional codes. Moreover, various systems, either under development or either for future use, will have high standards. The previous systems should present exceptional tolerance of noise effects and consequently a low overall number of received errors. For this purpose a new PCCC design was developed. The system’s performance analysis, using an AWGN channel, showed better results for various iterations compared to other schemes such as typical PCCC, SCCC and finally a Convolutional encoder with a Viterbi decoder.

NEW METHOD TO RECOVER INTERNET PACKET LOSSES USING(2,1,m)SYSTEMATIC CONVOLUTIONAL CODES

A new method to recover packet losses using (2,1,m) convolutional codes is proposed.The erasure correcting decoding algorithm and the decoding determinant theorem is presented. It is also proved that the codes with optimal distance profile have also optimal delay characteristic.Simulation results show that the proposed method can recover the packet losses more efficiently than RS codes over different decoding delay conditions and thus suits for different packet network delay conditions.

A multiple copyright identification watermarking algorithm based on code division multiple access

A multiple watermarking algorithm is presented according to the multiple accessing technique of thecode division multiple access (CDMA) system.Multiple watermarks are embedded into digital images inthe wavelet transform domain.Each of the watermarks is embedded and extracted independently withoutimpacts to each other.Multiple watermarks are convolution encoded and block interleaved,and the or-thogonal Gold sequences are used to spread spectrum of the copyright messages.CDMA encoded water-mark messages are embedded into the wavelet sub-bands excluding the wavelet HH1 sub-bands.The em-bedment amplitude is decided by Watson's perceptual model of wavelet transform domain,and the em-bedment position in the selected wavelet sub-bands is decided randomly by a pseudo-random noise (PN)sequence.As a blind watermarking algorithm,watermarks are extracted without original image.The wa-termarking capacity of proposed algorithm is also discussed.When two watermarks are embedded in animage at the same time,the capacity is larger than the capacity when a single watermark is embedded,and is smaller than the sum of the capacity of two separately embedded watermarks.Experimental resultsshow that the proposed algorithm improves the detection bits error rate (BER) observably,and the multi-pie watermarks have a preferable robustness and invisibility.

Performance of Convolutionally Coded Multicarrier DS-CDMA System

A new convolutionally coded direct sequence (DS) CDMA system is proposed. The outputs of a convolutional encoder modulate multiple band-limited DS-CDMA waveforms. The receiver detects and combines signals for the desired user and feeds a soft-decision Viterbi decoder. The performance of this system is compared to that of a convolutionally coded single carrier DS CDMA system with a Rake receiver. At roughly equivalent receiver complexity, results will demonstrate superior performance of the coded multicarrier system.

Hybrid Deep Learning-Based Adaptive Multiple Access Schemes Underwater Wireless Networks

Achieving sound communication systems in Under Water Acoustic(UWA)environment remains challenging for researchers.The communication scheme is complex since these acoustic channels exhibit uneven characteristics such as long propagation delay and irregular Doppler shifts.The development of machine and deep learning algorithms has reduced the burden of achieving reli-able and good communication schemes in the underwater acoustic environment.This paper proposes a novel intelligent selection method between the different modulation schemes such as Code Division Multiple Access(CDMA),Time Divi-sion Multiple Access(TDMA),and Orthogonal Frequency Division Multiplexing(OFDM)techniques using the hybrid combination of the convolutional neural net-works(CNN)and ensemble single feedforward layers(SFL).The convolutional neural networks are used for channel feature extraction,and boosted ensembled feedforward layers are used for modulation selection based on the CNN outputs.The extensive experimentation is carried out and compared with other hybrid learning models and conventional methods.Simulation results demonstrate that the performance of the proposed hybrid learning model has achieved nearly 98%accuracy and a 30%increase in BER performance which outperformed the other learning models in achieving the communication schemes under dynamic underwater environments.

Theoretical Analysis of Bit-Error Probability for Convolutional Codes with Weight Enumerators

The paper introduces the state reduction algorithm and accelerated state reduction algorithm are used to compute the distance weight enumerator(transfer function)T[x,y] of convolutional codes.Next use computer simulation to compare upper bound on the bit error probability on an additive white Gaussian noise(AWGN) for maximum free distance(MFD) codes of previously found and optimum distance spectrum(ODS) codes with rate 1/4,overall constraint length are 5 and 7,respectively.Finally,a method of how to search for good convolutional codes is given.

Error Probability for Convolutional Codes with Weight Enumerating Function

The paper introduces the state reduction algorithm and accelerated state reduction algorithm are used to compute the distance weight enumerator(transfer function) T[x,y] of convolutional codes.Next use computer simulation to compare upper bound on the bit error probability on an additive white Gaussian noise (AWGN) for maximum free distance (MFD) codes of previously found and optimum distance spectrum (ODS) codes with rate 1/4,overall constraint length are 5 and 7,respectively. Finally,a method of how to search for good convolutional codes is given.

基于改进YOLOv5s 的白酒瓶盖瑕疵检测

目的瓶装白酒生产过程中,瓶盖表面瑕疵会影响产品外观质量。针对白酒瓶盖表面瑕疵检测效率低和目标检测效果差的问题,提出一种基于YOLOv5s的改进算法DTS-YOLO。方法首先,在主干网络中引入可变形卷积,以提高模型对极端长宽比瑕疵的检测精度。其次,引入Transformer编码块,使网络聚焦于提取图像的全局信息。最后,在颈部网络构建C3SE-Lite模块,将C3模块嵌入SE注意力模块的同时引入Ghost卷积,减少参数量的同时,增强对瓶盖瑕疵的检测能力。结果实验结果表明,本文所提方法相较于基础网络,参数量减少了10%,平均精度均值达95%,平均检测速度达30帧/s。结论本文方法有效实现了白酒瓶盖表面瑕疵快速、准确地检测,可广泛应用于瓶装白酒生产过程中瓶盖表面检测。

基于CCS软件的FIR滤波器实验设计

本文借助CCS软件完成FIR滤波器实验设计,采用窗函数法实现FIR滤波器设计,窗函数选择矩形窗。FIR滤波器实验设计主要包括输入序列x(n)、单位脉冲响应h(n)和线性卷积子程序。首先通过x(n)和h(n)设计,求出x(n)和h(n);其次调用线性卷积子程序计算h(n)与x(n)的线性卷积,求得FIR滤波器的输出序列y(n)。借助time/frequency菜单观察y(n)的时域波形和频谱。

基于CCS的“信号分析与处理”实验教学

针对本院目前"信号分析与处理课程"的实验教学现状,结合学生的实际情况,打破了以往习惯用Matlab进行仿真的定式。以实验室配备的NvDK-6000SA嵌入式网络图像与视频实验开发系统为平台,进行了基于CCS的"信号分析与处理"的实验教学研究。在对该系统平台熟悉和掌握的基础上,开出指导性、综合性实验、使学生能深入理解相关的教学内容,提高教学质量。也为部分学生自主独立进行开发研究打下基础,同时也为本科生的毕业设计及研究生创新实验搭建了一个良好的软硬件平台。

基于图卷积的云制造服务编码算法

随着云制造模式及相关技术的发展,越来越多的服务提供者在云平台上发布并提供云服务业务。客户如何在大量功能相似、服务质量相近的云制造服务中检索并选择合适的云服务,已成为云平台运行过程中的难题。将服务关系与服务特征相结合,将制造过程中的协作关系引入服务哈希编码,对制造服务生成二进制编码,提出一种基于图卷积的云制造服务编码检索算法,通过采用汉明距离等方法度量服务间相似性,筛选服务候选集,提高算法效率。实验结果表明:该算法能够准确、有效地为服务平台上的客户提供良好的制造服务候选集。

软判决译码在多进制扩频通信系统中的应用

扩频通信技术能有效提高系统抗干扰能力,因此得到广泛应用;随着频带资源越来越拥挤,多进制扩频因其能够很好的对带宽和传输速率折中,越来越受到关注;同步一直是多进制扩频技术中的关键技术,对采用同步头同步法以及参考信号同步法的误码性能进行对比;系统采用软判决方式做数字调制解调输出提供给译码器,从对数似然比出发,提出一种适用于多进制扩频系统的次最优的软信息提取方式,分析了分别采用硬判决和软判决对系统带来的影响;仿真结果表明,单纯提取软信息后判决的方式对系统误码性能的提升不明显,在误码率BER=1×10^(-3)时,相比硬判决有0.2 dB左右的增益;加入卷积编码后,仿真参数不变分析对整个系统的性能改善时,相比于DSSS(Direct Sequence Spread Spectrum,直接扩频系统)系统的误码性能有5.2 dB左右的提升,软判决译码比硬判决译码有大约1 dB的增益;而考虑到编码效率,单独的分析软判决和硬判决对系统的误码性能的影响时,结果表明,在信噪比较高的信道环境下系统的误码性能得到较大改善,在误码率BER=1×10^(-3)时软判决译码比硬判决译码有0.7 dB左右的增益,软判决译码对整个系统的误码性能有2.5 dB左右的增益的。