2024 Vol. 33, No. 1

Review on Security Defense Technology Research in Edge Computing Environment
SHANG Ke, HE Weizhen, ZHANG Shuai
2024, 33(1): 1-18. doi: 10.23919/cje.2022.00.170
Abstract(505) HTML (254) PDF(123)
Edge computing, which achieves quick data processing by sinking data computing and storage to the network edge, has grown rapidly along with the Internet of things. The new network architecture of edge computing brings new security challenges. Based on this, this paper investigates the edge computing security literature published in recent years and summarizes and analyzes research work on edge computing security from different attack surfaces. We start with the definition and architecture of edge computing. From the attack surface between device and edge server, as well as on edge servers, the research describes the security threats and defense methods of edge computing. In addition, the cause of the attack and the pros and cons of defense methods is introduced. The challenges and future research directions of edge computing are given.
The Exchange Attack and the Mixture Differential Attack Revisited: From the Perspective of Automatic Evaluation
QIAO Kexin, ZHANG Zhiyu, NIU Zhongfeng, ZHU Liehuang
2024, 33(1): 19-29. doi: 10.23919/cje.2023.00.008
Abstract(375) HTML (192) PDF(57)
Recent results show that the differential properties within quadruples boom as a new inspiration in cryptanalysis of Advanced Encryption Standard (AES)-like constructions. These methods include the exchange attack proposed in Asiacrypt’19, the mixture differential attack proposed in ToSC’18, etc., where the essential properties are obtained by manually scrutinizing the structures of the AES-like constructions. This paper presents a novel framework and an automatic tool based on mixed integer linear programming to search for mixture differential distinguishers for general constructions. This framework considers what equality patterns among quadruples can make a distinguisher and traces how the patterns propagate through cipher components with accurate probability estimation. With this tool, a 5-round AES distinguishing attack with lower complexity and more 6-round distinguishing attacks in the chosen plaintext scenarios are deduced. We prove that no exchange-type or mixture differential distinguisher exists for 7 and above rounds AES if the details of the Sbox and MixColumns matrix are not taken into account.
Privacy Preserving Algorithm for Spectrum Sensing in Cognitive Vehicle Networks
LI Hongning, HU Tonghui, CHEN Jiexiong, WU Xiuqiang, PEI Qingqi
2024, 33(1): 30-42. doi: 10.23919/cje.2022.00.007
Abstract(436) HTML (217) PDF(89)
The scarcity of spectrum resources fails to meet the increasing throughput demands of vehicular networks. There is an urgent need to maximize the utilization of spectrum bands in mobile networks. To ascertain the availability of spectrum bands, users should engage in wireless channel sensing and collaboration. However, spectrum sensing data always involves users’ privacy, such as their location. This paper first introduces sensing trajectory inference attack in cognitive vehicular networks and then proposes a data confusion-based privacy-preserving algorithm and a cryptonym array-based privacy-preserving aggregation scheme for spectrum sensing in cognitive vehicular networks. Unlike existing methods, the proposed schemes transmit confused data during the aggregation process. This deliberate obfuscation makes it almost impossible to infer users’ location from the transmitted data. The analysis demonstrates the resilience of the proposed schemes against sensing trajectory inference attack.
A Secure Mutual Authentication Protocol Based on Visual Cryptography Technique for IoT-Cloud
Ehui Brou Bernard, CHEN Chen, WANG Shirui, GUO Hua, LIU Jianwei
2024, 33(1): 43-57. doi: 10.23919/cje.2022.00.339
Abstract(1050) HTML (512) PDF(49)
Because of the increasing number of threats in the IoT cloud, an advanced security mechanism is needed to guard data against hacking or attacks. A user authentication mechanism is also required to authenticate the user accessing the cloud services. The conventional cryptographic algorithms used to provide security mechanisms in cloud networks are often vulnerable to various cyber-attacks and inefficient against new attacks. Therefore, developing new solutions based on different mechanisms from traditional cryptography methods is required to protect data and users’ privacy from attacks. Different from the conventional cryptography method, we suggest a secure mutual authentication protocol based on the visual cryptography technique in this paper. We use visual cryptography to encrypt and decrypt the secret images. The mutual authentication is based on two secret images and tickets. The user requests the ticket from the authentication server (AS) to obtain the permission for accessing the cloud services. Three shared secret keys are used for encrypting and decrypting the authentication process. We analyze the protocol using the Barrows-Abadi-Needham (BAN)-logic method and the results show that the protocol is robust and can protect the user against various attacks. Also, it can provide a secure mutual authentication mechanism.
FlowGANAnomaly: Flow-Based Anomaly Network Intrusion Detection with Adversarial Learning
LI Zeyi, WANG Pan, WANG Zixuan
2024, 33(1): 58-71. doi: 10.23919/cje.2022.00.173
Abstract(1454) HTML (727) PDF(97)
In recent years, low recall rates and high dependencies on data labelling have become the biggest obstacle to developing deep anomaly detection (DAD) techniques. Inspired by the success of generative adversarial networks (GANs) in detecting anomalies in computer vision and imaging, we propose an anomaly detection model called FlowGANAnomaly for detecting anomalous traffic in network intrusion detection systems (NIDS). Unlike traditional GAN-based approaches, which are composed of a flow encoder, a convolutional encoder-decoder-encoder, a flow decoder and a convolutional encoder, the architecture of this model consists of a generator (G) and a discriminator (D). FlowGANAnomaly maps the different types of traffic feature data from separate datasets to a uniform feature space, thus can capture the normality of network traffic data more accurately in an adversarial manner to mitigate the problem of the high dependence on data labeling. Moreover, instead of simply detecting the anomalies by the output of D, we proposed a new anomaly scoring method that integrates the deviation between the output of two Gs’ convolutional encoders with the output of D as weighted scores to improve the low recall rate of anomaly detection. We conducted several experiments comparing existing machine learning algorithms and existing deep learning methods (AutoEncoder and VAE) on four public datasets (NSL-KDD, CIC-IDS2017, CIC-DDoS2019, and UNSW-NB15). The evaluation results show that FlowGANAnomaly can significantly improve the performance of anomaly-based NIDS.
SAT-Based Automatic Searching for Differential and Linear Trails: Applying to CRAX
HAN Yiyi, WANG Caibing, NIU Zhongfeng, HU Lei
2024, 33(1): 72-79. doi: 10.23919/cje.2022.00.313
Abstract(528) HTML (262) PDF(82)
Boolean satisfiability problem (SAT) is now widely applied in differential cryptanalysis and linear cryptanalysis for various cipher algorithms. It generated many excellent results for some ciphers, for example, Salsa20. In this research, we study the differential and linear propagations through the operations of addition, rotation and XOR (ARX), and construct the SAT models. We apply the models to CRAX to search differential trails and linear trails automatically. In this sense, our contribution can be broadly divided into two parts. We give the bounds for differential and linear cryptanalysis of Alzette both up to 12 steps, by which we present a 3-round differential attack and a 3-round linear attack for CRAX. We construct a 4-round key-recovery attack for CRAX with time complexity $ 2^{89} $ times of 4-round encryption and data complexity $ 2^{25} $.
Constructing the Impossible Differential of Type-II GFN with Boolean Function and Its Application to WARP
SHI Jiali, LIU Guoqiang, LI Chao
2024, 33(1): 80-89. doi: 10.23919/cje.2022.00.132
Abstract(586) HTML (291) PDF(45)
Type-II generalized Feistel network (GFN) has attracted a lot of attention for its simplicity and high parallelism. Impossible differential attack is one of the powerful cryptanalytic approaches for word-oriented block ciphers such as Feistel-like ciphers. We deduce the impossible differential of Type-II GFN by analyzing the Boolean function in the middle round. The main idea is to investigate the expression with the variable representing the plaintext (ciphertext) difference words for the internal state words. By adopting the miss-in-the-middle approach, we can construct the impossible differential of Type-II GFN. As an illustration, we apply this approach to WARP, a lightweight 128-bit block cipher with a 128-bit key which was presented by Banik et al. at SAC 2020. The structure of WARP is a 32-branch Type-II GFN. Therefore, we find two 21-round truncated impossible differentials and implement a 32-round key recovery attack on WARP. For the 32-round key recovery attack on WARP, some observations are used to mount an effective attack. Taking the advantage of the early abort technique, the data, time, and memory complexities are 2125.69 chosen plaintexts, 2126.68 32-round encryptions, and 2100-bit, repectively. To the best of our knowledge, this is the best attack on WARP in the single-key scenario.
SwiftTheft: A Time-Efficient Model Extraction Attack Framework Against Cloud-Based Deep Neural Networks
YANG Wenbin, GONG Xueluan, CHEN Yanjiao, WANG Qian, DONG Jianshuo
2024, 33(1): 90-100. doi: 10.23919/cje.2022.00.377
Abstract(313) HTML (159) PDF(39)
With the rise of artificial intelligence and cloud computing, machine-learning-as-a-service platforms, such as Google, Amazon, and IBM, have emerged to provide sophisticated tasks for cloud applications. These proprietary models are vulnerable to model extraction attacks due to their commercial value. In this paper, we propose a time-efficient model extraction attack framework called SwiftTheft that aims to steal the functionality of cloud-based deep neural network models. We distinguish SwiftTheft from the existing works with a novel distribution estimation algorithm and reference model settings, finding the most informative query samples without querying the victim model. The selected query samples can be applied to various cloud models with a one-time selection. We evaluate our proposed method through extensive experiments on three victim models and six datasets, with up to 16 models for each dataset. Compared to the existing attacks, SwiftTheft increases agreement (i.e., similarity) by 8% while consuming 98% less selecting time.
Echo State Network Based on Improved Knowledge Distillation for Edge Intelligence
ZHOU Jian, JIANG Yuwen, XU Lijie, ZHAO Lu, XIAO Fu
2024, 33(1): 101-111. doi: 10.23919/cje.2022.00.292
Abstract(179) HTML (90) PDF(26)
Echo state network (ESN) as a novel artificial neural network has drawn much attention from time series prediction in edge intelligence. ESN is slightly insufficient in long-term memory, thereby impacting the prediction performance. It suffers from a higher computational overhead when deploying on edge devices. We firstly introduce the knowledge distillation into the reservoir structure optimization, and then propose the echo state network based on improved knowledge distillation (ESN-IKD) for edge intelligence to improve the prediction performance and reduce the computational overhead. The model of ESN-IKD is constructed with the classic ESN as a student network, the long and short-term memory network as a teacher network, and the ESN with double loop reservoir structure as an assistant network. The student network learns the long-term memory capability of the teacher network with the help of the assistant network. The training algorithm of ESN-IKD is proposed to correct the learning direction through the assistant network and eliminate the redundant knowledge through the iterative pruning. It can solve the problems of error learning and redundant learning in the traditional knowledge distillation process. Extensive experimental simulation shows that ESN-IKD has a good time series prediction performance in both long-term and short-term memory, and achieves a lower computational overhead.
Formal Verification of Data Modifications in Cloud Block Storage Based on Separation Logic
ZHANG Bowen, JIN Zhao, WANG Hanpin, CAO Yongzhi
2024, 33(1): 112-127. doi: 10.23919/cje.2022.00.116
Abstract(359) HTML (179) PDF(42)
Cloud storage is now widely used, but its reliability has always been a major concern. Cloud block storage (CBS) is a famous type of cloud storage. It has the closest architecture to the underlying storage and can provide interfaces for other types. Data modifications in CBS have potential risks such as null reference or data loss. Formal verification of these operations can improve the reliability of CBS to some extent. Although separation logic is a mainstream approach to verifying program correctness, the complex architecture of CBS creates some challenges for verifications. This paper develops a proof system based on separation logic for verifying the CBS data modifications. The proof system can represent the CBS architecture, describe the properties of the CBS system state, and specify the behavior of CBS data modifications. Using the interactive verification approach from Coq, the proof system is implemented as a verification tool. With this tool, the paper builds machine-checked proofs for the functional correctness of CBS data modifications. This work can thus analyze the reliability of cloud storage from a formal perspective.
Fast Cross-Platform Binary Code Similarity Detection Framework Based on CFGs Taking Advantage of NLP and Inductive GNN
PENG Jinxue, WANG Yong, XUE Jingfeng, LIU Zhenyan
2024, 33(1): 128-138. doi: 10.23919/cje.2022.00.228
Abstract(346) HTML (172) PDF(26)
Cross-platform binary code similarity detection aims at detecting whether two or more pieces of binary code are similar or not. Existing approaches that combine control flow graphs (CFGs)-based function representation and graph convolutional network (GCN)-based similarity analysis are the best-performing ones. Due to a large amount of convolutional computation and the loss of structural information, the use of convolution networks will inevitably bring problems such as high overhead and sometimes inaccuracy. To address these issues, we propose a fast cross-platform binary code similarity detection framework that takes advantage of natural language processing (NLP) and inductive graph neural network (GNN) for basic blocks embedding and function representation respectively by simulating extracting structural features and temporal features. GNN’s node-centric and small batch is a suitable training way for large CFGs, it can greatly reduce computational overhead. Various NLP basic block embedding models and GNNs are evaluated. Experimental results show that the scheme with long short term memory (LSTM) for basic blocks embedding and inductive learning-based GraphSAGE(GAE) for function representation outperforms the state-of-the-art works. In our framework, we can take only 45% overhead. Improve efficiency significantly with a small performance trade-off.
FSCIL-EACA: Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification
ZHANG Ruru, E Haihong, SONG Meina
2024, 33(1): 139-152. doi: 10.23919/cje.2022.00.396
Abstract(373) HTML (185) PDF(128)
The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning (FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation (CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented (EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability, guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.
Graph Signal Reconstruction from Low-Resolution Multi-Bit Observations
LIU Zhaoting, YU Chen, WANG Yafeng, LIU Shuchen
2024, 33(1): 153-160. doi: 10.23919/cje.2022.00.272
Abstract(273) HTML (134) PDF(28)
Low hardware cost and power consumption in information transmission, processing and storage is an urgent demand for many big data problems, in which the high-dimensional data often be modelled as graph signals. This paper considers the problem of recovering a smooth graph signal by using its low-resolution multi-bit quantized observations. The underlying problem is formulated as a regularized maximum-likelihood optimization and is solved via an expectation maximization scheme. With this scheme, the multi-bit graph signal recovery (MB-GSR) is efficiently implemented by using the quantized observations collected from random subsets of graph nodes. The simulation results show that increasing the sampling resolution to 2 or 3 bits per sample leads to a considerable performance improvement, while the energy consumption and implementation costs remain much lower compared to the implementation of high resolution sampling.
Sensing Matrix Optimization for Random Stepped-Frequency Signal Based on Two-Dimensional Ambiguity Function
LYU Mingjiu, CHEN Hao, YANG Jun, WU Xia, ZHOU Ming, MA Xiaoyan
2024, 33(1): 161-174. doi: 10.23919/cje.2022.00.046
Abstract(322) HTML (161) PDF(33)
Compressive sensing technique has been widely applied to achieve range-Doppler reconstruction of high frequency radar by utilizing sparse random stepped-frequency (SRSF) signal, which can suppress the complex electromagnetic interference and greatly reduce the coherent processing interval. An important way to improve the performance of sparse signal reconstruction is to optimize the sensing matrix (SM). However, the existing research on the SM optimization needs to design a measurement matrix with superior performance, which needs a large amount of computation and does not consider the influence of the waveform parameters design. In order to improve the superior reconstruction performance, a novel SM optimization approach for SRSF signal is proposed by using two-dimensional ambiguity function (TDAF) in this paper. Firstly, based on the two-dimensional sparse reconstruction model of the SRSFs, the internal relationship between the waveform parameters and the SM was derived. Secondly, the SM optimization problem was directly transformed into the waveform design of SRSFs. Furthermore, on the basis of analyzing the relationship between the mutual coherence matrix of SM and the TDAF matrix of SRSFs, the purpose of optimizing the SM can be achieved by designing the TDAF of the SRSFs. Based on this analysis, a sparse waveform optimization method with joint constraints of maximum and mean sidelobes of the TDAF by using the genetic algorithm was derived. Compared with the traditional SM optimization method, our method not only avoids generating a new measurement matrix, but also further reduces the complexity of the waveform optimization. Simulation experiments verified the effectiveness of the proposed method.
Rapid Phase Ambiguity Elimination Methods for DOA Estimator via Hybrid Massive MIMO Receive Array
ZHAN Xichao, SUN Zhongwen, SHU Feng, CHEN Yiwen, CHENG Xin, WU Yuanyuan, ZHANG Qi, LI Yifan, ZHANG Peng
2024, 33(1): 175-184. doi: 10.23919/cje.2022.00.112
Abstract(350) HTML (178) PDF(29)
For a sub-connected hybrid multiple-input multiple-output (MIMO) receiver with K subarrays and N antennas, there exists a challenging problem of how to rapidly remove phase ambiguity in only single time-slot. A direction of arrival (DOA) estimator of maximizing received power (Max-RP) is proposed to find the maximum value of K-subarray output powers, where each subarray is in charge of one sector, and the center angle of the sector corresponding to the maximum output is the estimated true DOA. To make an enhancement on precision, Max-RP plus quadratic interpolation (Max-RP-QI) method is designed. In the proposed Max-RP-QI, a quadratic interpolation scheme is adopted to interpolate the three DOA values corresponding to the largest three receive powers of Max-RP. To achieve the Cramer Rao lower bound, a Root-MUSIC plus Max-RP-QI scheme is developed. Simulation results show that the proposed three methods eliminate the phase ambiguity during one time-slot and also show low computational complexities. The proposed Root-MUSIC plus Max-RP-QI scheme can reach the Cramer Rao lower bound, and the proposed Max-RP and Max-RP-QI are still some performance losses 2–4 dB compared to the Cramer Rao lower bound.
Study on Coded Permutation Entropy of Finite Length Gaussian White Noise Time Series
SUN Huihui, ZHANG Xiaofeng
2024, 33(1): 185-194. doi: 10.23919/cje.2022.00.209
Abstract(478) HTML (242) PDF(26)
As an extension of permutation entropy (PE), coded permutation entropy (CPE) improves the performance of PE by making a secondary division for ordinal patterns defined in PE. In this study, we provide an exploration of the statistical properties of CPE using a finite length Gaussian white noise time series theoretically. By means of the Taylor series expansion, the approximate expressions of the expected value and variance of CPE are deduced and the Cramér-Rao low bound (CRLB) is obtained to evaluate the performance of the CPE estimator. The results indicate that CPE is a biased estimator, but the bias only depends on relevant parameters of CPE and it can be easily corrected for an arbitrary time series. The variance of CPE is related to the encoding patterns distribution, and the value converges to the CRLB of the CPE estimator when the time series length is large enough. For a finite-length Gaussian white noise time series model, the predicted values can match well with the actual values, which further validates the statistic theory of CPE. Using the theoretical expressions of CPE, it is possible to better understand the behavior of CPE for most of the time series.
Visible Light Indoor Positioning System Based on Pisarenko Harmonic Decomposition and Neural Network
2024, 33(1): 195-203. doi: 10.23919/cje.2022.00.161
Abstract(333) HTML (165) PDF(21)
Visible-light indoor positioning is a new generation of positioning technology that can be integrated into smart lighting and optical communications. The current received signal strength (RSS)-based visible-light positioning systems struggle to overcome the interferences of background and indoor-reflected noise. Meanwhile, when ensuring the lighting, it is impossible to use the superposition of each light source to accurately distinguish light source information; furthermore, it is difficult to achieve accurate positioning in complex indoor environments. This study proposes an indoor positioning method based on a combination of power spectral density detection and a neural network. The system integrates the mechanism for visible-light radiation detection with RSS theory, to build a back propagation neural network model fitting for multiple reflection channels. Different frequency signals are loaded to different light sources at the beacon end, and the characteristic frequency and power vectors are obtained at the location end using the Pisarenko harmonic decomposition method. Then, a complete fingerprint database is established to train the neural network model and conduct location tests. Finally, the location effectiveness of the proposed algorithm is verified via actual positioning experiments. The simulation results show that, when four groups of sinusoidal waves with different frequencies are superimposed with white noise, the maximum frequency error is 0.104 Hz and the maximum power error is 0.0362 W. For the measured positioning stage, a 0.8 m × 0.8 m × 0.8 m solid wood stereoscopic positioning model is constructed, and the average error is 4.28 cm. This study provides an effective method for separating multi-source signal energies, overcoming background noise, and improving indoor visible-light positioning accuracies.
Link Prediction Method Fusion with Local Structural Entropy for Directed Network
LIU Shuxin, CHEN Hongchang, WU Lan, WANG Kai, LI Xing
2024, 33(1): 204-216. doi: 10.23919/cje.2022.00.166
Abstract(227) HTML (113) PDF(21)
Link prediction utilizes accessible network information to complement or predict the network links. Similarity is an important prerequisite for link prediction which means links more likely occurs between two similar nodes. Existing methods utilize the similarity of nodes but neglect of network structure. However the link direction leads to a far more complex structure and contains more information useful than the undirected networks. Most classic methods are difficult to depict the distribution of the network structure with incidental direction so the similarity characteristics of the network structure itself are lost. In this respect, a new method of local structure entropy is proposed to depict the directed structural distribution characteristics, which can be used to evaluate the degree of local structural similarity of nodes and then applied to link prediction methods. Experimental results on 8 real directed networks show that this method is effective for both area under the receiver operating characteristic curve (AUC) and ranking-score measures, and improved predictive capacity of the baseline methodology.
A Task Scheduling Algorithm Based on Clustering Pre-processing in Space-Based Information Network
WANG Yufei, LIU Jun, ZHANG Shengnan, XU Sai, WANG Jingyi
2024, 33(1): 217-230. doi: 10.23919/cje.2022.00.114
Abstract(234) HTML (117) PDF(29)
With the diversification of space-based information network task requirements and the dramatic increase in demand, the efficient scheduling of various tasks in space-based information network becomes a new challenge. To address the problems of a limited number of resources and resource heterogeneity in the space-based information network, we propose a bilateral pre-processing model for tasks and resources in the scheduling pre-processing stage. We use an improved fuzzy clustering method to cluster tasks and resources and design coding rules and matching methods to match similar categories to improve the clustering effect. We propose a space-based information network task scheduling strategy based on an ant colony simulated annealing algorithm for the problems of high latency of space-based information network communication and high resource dynamics. The strategy can efficiently complete the task and resource matching and improve the task scheduling performance. The experimental results show that our proposed task scheduling strategy has less task execution time and higher resource utilization than other algorithms under the same experimental conditions. It has significantly improved scheduling performance.
Drug-Target Interactions Prediction Based on Signed Heterogeneous Graph Neural Networks
CHEN Ming, JIANG Yajian, LEI Xiujuan, PAN Yi, JI Chunyan, JIANG Wei
2024, 33(1): 231-244. doi: 10.23919/cje.2022.00.384
Abstract(677) HTML (338) PDF(119)
Drug-target interactions (DTIs) prediction plays an important role in the process of drug discovery. Most computational methods treat it as a binary prediction problem, determining whether there are connections between drugs and targets while ignoring relational types information. Considering the positive or negative effects of DTIs will facilitate the study on comprehensive mechanisms of multiple drugs on a common target, in this work, we model DTIs on signed heterogeneous networks, through categorizing interaction patterns of DTIs and additionally extracting interactions within drug pairs and target protein pairs. We propose signed heterogeneous graph neural networks (SHGNNs), further put forward an end-to-end framework for signed DTIs prediction, called SHGNN-DTI, which not only adapts to signed bipartite networks, but also could naturally incorporate auxiliary information from drug-drug interactions (DDIs) and protein-protein interactions (PPIs). For the framework, we solve the message passing and aggregation problem on signed DTI networks, and consider different training modes on the whole networks consisting of DTIs, DDIs and PPIs. Experiments are conducted on two datasets extracted from DrugBank and related databases, under different settings of initial inputs, embedding dimensions and training modes. The prediction results show excellent performance in terms of metric indicators, and the feasibility is further verified by the case study with two drugs on breast cancer.
Real-Time 3D Ultrasound Imaging System Based on a Hybrid Reconstruction Algorithm
LYU Yifei, SHEN Yu, ZHANG Mingbo, WANG Junchen
2024, 33(1): 245-255. doi: 10.23919/cje.2023.00.002
Abstract(673) HTML (334) PDF(85)
As a safe and convenient imaging technology in clinical routine diagnosis, ultrasound imaging can provide real-time 2D images of internal tissues and organs. To realize real-time 3D image reconstruction, pixel nearest neighbor interpolation (PNN) reconstruction algorithm and Bezier interpolation algorithm are combined into a hybrid reconstruction algorithm. On this basis, a real-time interactive 3D ultrasound imaging system is developed. Through temporal calibration and spatial calibration, the six degrees of freedom poses of 2D ultrasound images can be accurately collected. The 3D volume reconstructed by the proposed 3D reconstruction algorithm is visualized by volume rendering. A multi-thread software system allows parallel operation of data acquisition, 3D reconstruction, volume visualization and other functions. 3D imaging experiments on a 3D printing femur model, a neck phantom and the neck of human volunteers were performed for systematic evaluation. When the reconstruction voxel size was set to be (0.53 mm3, 1.03 mm3, 1.53 mm3), the reconstruction errors of the femur and trachea model were respectively (0.23 mm, 0.31 mm, 0.56 mm) and (0.62 mm, 0.88 mm, 1.41 mm). Clinical feasibility was demonstrated by application of the 3D ultrasound imaging on the neck of human volunteers.
An Encoding-Decoding Framework Based on CNN for circRNA-RBP Binding Sites Prediction
GUO Yajing, LEI Xiujuan, PAN Yi
2024, 33(1): 256-263. doi: 10.23919/cje.2022.00.361
Abstract(338) HTML (161) PDF(40)
Predicting RNA binding protein (RBP) binding sites on circular RNAs (circRNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but they cannot fully learn the features. Therefore, we propose circ-CNNED, a convolutional neural network (CNN)-based encoding and decoding framework. We first adopt two encoding methods to obtain two original matrices. We preprocess them using CNN before fusion. To capture the feature dependencies, we utilize temporal convolutional network (TCN) and CNN to construct encoding and decoding blocks, respectively. Then we introduce global expectation pooling to learn latent information and enhance the robustness of circ-CNNED. We perform circ-CNNED across 37 datasets to evaluate its effect. The comparison and ablation experiments demonstrate that our method is superior. In addition, motif enrichment analysis on four datasets helps us to explore the reason for performance improvement of circ-CNNED.
Research on Modeling and Parameter Identification of Comprehensive Load Model of Distribution Network in Industrial Park
WANG Tingling, YAN Xiaohe
2024, 33(1): 264-273. doi: 10.23919/cje.2022.00.024
Abstract(143) HTML (72) PDF(12)
With the rapid development of industrial parks, its load model research has become a hot spot. In order to study the load of power system in industrial park, based on the characteristics of the industrial park load, a comprehensive load admittance static model with full voltage range adaptability is considered, and a comprehensive load model of distribution network of the industrial park is established. A complete parameter identification of the model is carried out through chaos particle swarm optimization. The simulation results show that the model can effectively describe the load characteristics of the distribution network in industrial parks.
The Investigation of Data Voting Algorithm for Train Air-Braking System Based on Multi-Classification SVM and ANFIS
WANG Juhan, GAO Ying, CAO Yuan, TANG Tao
2024, 33(1): 274-281. doi: 10.23919/cje.2021.00.428
Abstract(264) HTML (133) PDF(24)
The pressure data of the train air braking system is of great significance to accurately evaluate its operation state. In order to overcome the influence of sensor fault on the pressure data of train air braking system, it is necessary to design a set of sensor fault-tolerant voting mechanism to ensure that in the case of a pressure sensor fault, the system can accurately identify and locate the position of the faulty sensor, and estimate the fault data according to other normal data. A fault-tolerant mechanism based on multi-classification support vector machine (SVM) and adaptive network-based fuzzy inference system (ANFIS) is introduced. Multi-classification SVM is used to identify and locate the system fault state, and ANFIS is used to estimate the real data of the fault sensor. After estimation, the system will compare the real data of the fault sensor with the ANFIS estimated data. If it is similar, the system will recognize that there is a false alarm and record it. Then the paper tests the whole mechanism based on the real data. The test shows that the system can identify the fault samples and reduce the occurrence of false alarms.
Multi-Sensor Fusion Adaptive Estimation for Nonlinear Under-observed System with Multiplicative Noise
CUI Yongpeng, SUN Xiaojun
2024, 33(1): 282-292. doi: 10.23919/cje.2022.00.364
Abstract(285) HTML (143) PDF(106)
The adaptive fusion estimation problem was studied for the multi-sensor nonlinear under-observed systems with multiplicative noise. A one-step predictor with state update equations was designed for the virtual state with virtual noise first of all. An extended incremental Kalman filter (EIKF) was then proposed for the nonlinear under-observed systems. Furthermore, an adaptive filtering method was given for optimization. The fusion adaptive incremental Kalman filter weighted by scalar was finally proposed. The comparison analysis was made to verify the optimization of the state estimation using adaptive filtering method in the filtering process.
No Reference Image Sharpness Assessment Based on Global Color Difference Variation
SHI Chenyang, LIN Yandan
2024, 33(1): 293-302. doi: 10.23919/cje.2022.00.058
Abstract(729) HTML (360) PDF(36)
Image quality assessment (IQA) model is designed to measure the image quality in consistent with subjective ratings by computational models. In this research, a valid no reference IQA (NR-IQA) model for color image sharpness assessment is proposed based on local color difference map in a color space. In the proposed model, the absolute color difference variation and relative color difference variation are combined to evaluate sharpness in YIQ color space (a color coordinate system for the development of the United States color television system). The difference between sharpest and blurriest spot of an image is represented by the absolute color difference variation, and relative color difference variation expresses the variation in the image content. Extensive experiments are performed on five publicly available benchmark synthetic blur databases and two real blur databases, and the results prove that the proposed model work better than the other state-of-the-art and latest NR-IQA models for the prediction accuracy on blurry images. Besides, the model maintains the lowest computational complexity.
Deep Guided Attention Network for Joint Denoising and Demosaicing in Real Image
2024, 33(1): 303-312. doi: 10.23919/cje.2022.00.414
Abstract(394) HTML (197) PDF(53)
Denoising (DN) and demosaicing (DM) are the first crucial stages in the image signal processing pipeline. Recently, researches pay more attention to solve DN and DM in a joint manner, which is an extremely undetermined inverse problem. Existing deep learning methods learn the desired prior on synthetic dataset, which limits the generalization of learned network to the real world data. Moreover, existing methods mainly focus on the raw data property of high green information sampling rate for DM, but occasionally exploit the high intensity and signal-to-noise (SNR) of green channel. In this work, a deep guided attention network (DGAN) is presented for real image joint DN and DM (JDD), which considers both high SNR and high sampling rate of green information for DN and DM, respectively. To ease the training and fully exploit the data property of green channel, we first train DN and DM sub-networks sequentially and then learn them jointly, which can alleviate the error accumulation. Besides, in order to support the real image JDD, we collect paired raw clean RGB and noisy mosaic images to conduct a realistic dataset. The experimental results on real JDD dataset show the presented approach performs better than the state-of-the-art methods, in terms of both quantitative metrics and qualitative visualization.
Troy: Efficient Service Deployment for Windows Systems
ZHANG Deyu, XIE Yu, XU Mucong, CHENG En, KUI Xiaoyan, HE Bangwen, LI Yunhao
2024, 33(1): 313-322. doi: 10.23919/cje.2022.00.405
Abstract(210) HTML (102) PDF(19)
The modern university computer lab and kindergarden through 12th grade classrooms require a centralized solution to efficiently manage a large number of desktops. The existing solutions either bring virtualization overhead in runtime or requires loading a large image over 30 GB leading to an unacceptable network latency. In this work, we propose Troy which takes advantage of the differencing virtual hard disk techniques in Windows systems. As such, Troy only loads the modifications made on one machine to all other machines. Troy consists of two modules that are responsible to generate an initial image and merge a differencing image with its parent image, respectively. Specifically, we identify the key fields in the virtual hard disk image that links the differencing image and the parent image and find the modified blocks in the differencing images that should be used to replace the blocks in the parent image. We further design a lazy copy solution to reduce the I/O burden in image merging. We have implemented Troy on bare metal machines. The evaluation results show that the performance of Troy is comparable to the native implementation in Windows, without requiring the Windows environment.