International Conference on Signal Processing and Communication Security最新文献

{"title":"Feature fusion method for speaker recognition based on embedding mechanism","authors":"JiangKun Zhao, Houpan Zhou, Honglei Liu, Yonghai Du","doi":"10.1117/12.2655318","DOIUrl":"https://doi.org/10.1117/12.2655318","url":null,"abstract":"Speaker recognition is a technology that verifies the identity of a person by his or her voice. Different feature parameters have different potential information in speaker recognition. In order to solve the problem that a single feature parameter cannot fully represent a speaker's identity, this paper proposes a feature fusion approach based on embedding mechanism. The fusion features adopted in our approach are filter bank coefficients (Fbank) and mel frequency cepstrum coefficients (MFCC). Potential and complementary information in two features can be obtained by a neural network model, which takes our embedded features as inputs. The d-vector output of the neural network model is classified using the Softmax loss function and optimized using the generalized end-to-end loss function. Both of the most common models, long short term memory network (LSTM) and bi-directional long short term memory network (BiLSTM), are used as our testbed. Results show that, by using our proposed feature fusion approach, the performance of both models are improved. In particular, the minimum equal error rate is 4.17% under the BiLSTM model, compared with the single MFCC or Fbank feature, which are reduced by 72.2% and 28.4% respectively.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125161827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A robust unwrapping method for local noise phase","authors":"Quan Wu, Qida Yu, J. Yang, Xianchun Zhou","doi":"10.1117/12.2655186","DOIUrl":"https://doi.org/10.1117/12.2655186","url":null,"abstract":"Phase unwrapping algorithm is difficult to apply in INSAR image for the local high-density noise phase attributed to significant blocky noise. To achieve its application in such case, the pixels of noise phase are first detected, and are set to 0 with the automatic mask technique. For the phase that has a blocky noise region, the iteration algorithm of phase filling based on Least-Squares is developed in this study by calculating the unwrapping coefficient k to rebuild the true phase. The algorithm is promoted by MPIPU's ability to fill in the missing phase; it can also significantly suppress the error transfer attributed to iteration filling in the non-mask phase. Some experiments are performed on simulated data. As revealed from the results, the proposed method exhibits robust performance of phase unwrapping on local noise phase.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114357007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved EMD-PSO-LSSVM train wireless network time-delay prediction","authors":"S. Dou, L. Y. Zhang, C. X. Li","doi":"10.1117/12.2655218","DOIUrl":"https://doi.org/10.1117/12.2655218","url":null,"abstract":"A time delay prediction method of train network based on wireless transmission is proposed. EMD is used to decompose the time delay series. The decomposed components with large sample entropy are DWT to form new components, in order to reduce the complexity of prediction. The components with similar sample entropy are combined into new components to reduce the amount of model calculation. Finally, each data component is predicted by particle swarm optimization LSSVM model. The simulation results show that the proposed method has high prediction accuracy.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114620975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on task offloading strategy of mobile edge computing in 5G environment","authors":"Shuai Gao, Lixia Du","doi":"10.1117/12.2655195","DOIUrl":"https://doi.org/10.1117/12.2655195","url":null,"abstract":"With the wide application of 5G technology, more and more computing-intensive tasks and delay-sensitive tasks need to be calculated and processed on user equipment, but limited by the computing power and storage capacity of user equipment, these tasks cannot be efficient processing. The emergence of mobile edge computing (MEC) makes it possible. In this paper, we consider task offloading on Small Cell Network (SCN) structures unique to 5G. Under this network structure, a computational offloading strategy for joint optimization of forward and backward links is designed and implemented. Considering the front-end link and the backward link comprehensively, a computational offloading strategy model aiming at minimizing the total energy cost is established under the premise of delay limitation. Then, the objective function that needs to be optimized for energy is established according to the model, and the objective function is optimized by the improved artificial fish swarm algorithm. Finally, through the simulation of the algorithm, the performance of the improved algorithm is proved.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114851829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A method of unbalanced twin auxiliary classifiers GAN for network intrusion based mutual information","authors":"Wei Xie, Jun Tu","doi":"10.1117/12.2655187","DOIUrl":"https://doi.org/10.1117/12.2655187","url":null,"abstract":"Generative Adversarial Network used in the field of Network Intrusion Detection has become very common, but mode collapse of Generative Adversarial Network and unbalanced distribution of training dataset in Network Intrusion Detection are problems worth solving. Generator and discriminator of Generative Adversarial Network can not fully learn feature information. In this paper, the Twin Auxiliary Classifier GAN is combined with the idea of mutual information modeling. The training is carried out on the Network Intrusion Detection dataset UNSW-NB15. After comparing the original dataset trained by Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine and Multi-layer Perceptron Machine with the expanded dataset generated by Twin Auxiliary Classifier GAN training, the results show that the methods proposed in this paper can improve the performance of each classifier on the test set.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127674781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The design and implementation of I2C driver for wireless sensor terminal equipment","authors":"Lingzhi Zhang, Xunwei Zhao, Xiaobo Sun, Qing Wu, Haixuan Fu, Ming Hu, Mengqi Chen","doi":"10.1117/12.2655410","DOIUrl":"https://doi.org/10.1117/12.2655410","url":null,"abstract":"Aiming at the advantages of less I2C interface lines and simplified control mode, I2C interface is used to read the data of sensor equipment. Firstly, the sensor node is composed of six modules: power supply module, sensor module, calculation module, storage module, communication module and embedded software system, and the functions of these modules are described in detail. Then the master-slave devices corresponding to I2C drive are introduced; Then the I2C protocol and the functions of bme680 sensor used in this scheme are summarized, including the bus composition, communication principle and bus physical topology of I2C. The functions of bme680 sensor introduce bme680 sensor, pin layout and pin assignment. The whole I2C driver design includes the configuration process of bme680 sensor, read-write timing and driver design. The I2C bus device driver is designed, and the driver that reads the data of bme680 sensor device in the sensor node with the new Tang processor m263kiaae is implemented. The driver can successfully read bme680 sensing data.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127981595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting malicious domain names from domain generation algorithms using bi-directional LSTM network","authors":"Suliang Luo, Gang Han, An Li, Jialiang Peng","doi":"10.1117/12.2655178","DOIUrl":"https://doi.org/10.1117/12.2655178","url":null,"abstract":"DNS (Domain Name System /DNS) is one of the most important infrastructures of Internet. People can easily access the rich network resources worldwide using the DNS technology. However, the Domain Generation Algorithm (DGA) is also accompanied by the DNS technology, which is used to generate malicious domain names. To detect DGA malicious domains, the previous studies often used unreal small DNS domain name datasets to train the detection models that always overlooked real user data traffic. These models generally did not have good generalization performance. In this paper, we propose a new DGA malicious domain name detection model based on Bi-directional LSTM network. We also propose a new evaluation metric to evaluate the real unlabeled DNS traffic data. Compared with LSTM model, the detection effect of our proposed model is improved effectively. The experimental results show that the precision of the model and the value of AUC reach 98.4% and 0.9079, respectively.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130474910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A reduced-dimension post-Doppler STAP method based on tensor Tucker decomposition","authors":"Jingya Li, Zhiwei Yang, Jiajia Gou","doi":"10.1117/12.2655354","DOIUrl":"https://doi.org/10.1117/12.2655354","url":null,"abstract":"Space-time adaptive processing (STAP) can effectively suppress the clutter, which plays an important role in ground moving target indication (GMTI). However, it is difficult to obtain sufficient training samples with an increase in the number of spatial channels and adaptive processor dimensions in large arrays, especially in a complex geomagnetic detection environment. Traditional reduced-dimension STAP methods cannot offer significant benefits in real data processing in this issue. Thus, in this paper, a reduced-dimension post-Doppler STAP method based on tensor Tucker decomposition is proposed. Firstly, the distribution characteristics of the clutter spectrum in the post-Doppler domain are analyzed. Then, the feature spaces of beam and Doppler are extracted by tensor Tucker decomposition. Finally, the data dimension is reduced by the feature spaces, and clutter suppression is carried out. The results of the experiments based on real measured data demonstrate that the proposed method can achieve good performance with fewer samples than traditional methods.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134439726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital car key scheme based on BLE SIM card","authors":"Jin-Kook Song, Jingyi Fu, Zuhui Yue, Zheng Li","doi":"10.1117/12.2655177","DOIUrl":"https://doi.org/10.1117/12.2655177","url":null,"abstract":"The digital car key is available on smart devices now. People no longer have to bring the key fob to unlock and start the engine. The existing schemes have some problems, such as poor device compatibility and poor user experience. In this paper, we proposed an unperceived digital car key scheme based on Bluetooth Low Energy (BLE) SIM card. After owner paring, the vehicle automatically locks/unlocks when the terminal device with the BLE SIM card approaches/leaves it. The data of the digital car key is stored in the secure element of the Bluetooth SIM card. The digital credentials are exchanged and mutually authenticated through a Bluetooth connection between the vehicle and the BLE SIM card. Compared to the existing schemes, our scheme has better device compatibility and a better user experience.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129381786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fingerprint map construction based on multi-chain interpolation","authors":"Yanhu Ji","doi":"10.1117/12.2655180","DOIUrl":"https://doi.org/10.1117/12.2655180","url":null,"abstract":"The widespread deployment of wireless devices in indoor environments has made location-based services a hot research topic. Indoor positioning based on received signal strength is the key to providing accurate location services among them. But it needs to build a fingerprint database for the sensing area. Therefore, whether it is to establish or update the fingerprint map, a large number of RSS values of the reference points need to be sampled. This process is time-consuming and labor-intensive, with a huge amount of work. To solve this problem, researchers collect RSSs of some reference points and use them to interpolate other points to form a map of the entire area. This method can effectively reduce the time to create and update the map, but it also reduces the positioning accuracy. According to the propagation characteristics of wireless signals, the signal of the insertion points are formed by the superposition of multiple directional signals. Therefore, the correlation of neighboring points should not be considered only, but should be expanded in different directions. According to the propagation characteristics of actual signals, this paper designs a method based on multi-chain interpolation, which combines the influence of different propagation links on the insertion point to evaluate the signal strength. The basic idea of this method is to perform interpolation calculation in different directions under the given sampling rules. Then the predicted values of insertion points are obtained by using inverse distance weighting. Next, the corresponding signal attenuation Models are obtained by fitting in each direction and the errors are calculated as the direction weights. Finally, the estimation values of the insertion points are obtained. Through repeated iteration, the fingerprint database composed of real points and virtual points is finally formed. Two sampling models are used in this paper. And the sampling rates are 25% and 50% of that of full sampling, which means that the workload of map construction is reduced by 75% and 50% respectively. According to large-scale experiments, the positioning accuracy of the two MCI sampling methods is 13.58% and 4.74% higher than that of the full sampling method respectively. Compared with the classical interpolation method, the MCI method has better stability. Especially when the sampling amount is small, the advantage is more obvious. When the sampling amount is only 25%, the average accuracy is 18.50% higher than that of the full sampling method.","PeriodicalId":105577,"journal":{"name":"International Conference on Signal Processing and Communication Security","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121617404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}