Search

The aim of this article is to investigate the optimization of electric vehicle charging and swapping for green logistics, as well as path planning considering urban impedance. We improved a road impedance function model suitable for urban road traffic in China to calculate the actual traffic time based on real-time traffic data and the intricate urban road environment. This model is then applied to address the delivery optimization problem. Furthermore, a robust computational approach is introduced to estimate battery degradation costs, accounting for environmental temperature and depth of discharge. The logistics delivery model is effectively tackled using genetic algorithms, and simulation results demonstrate the considerable advantages of electric vehicle swapping, effectively mitigating energy wastage and environmental pollution. Additionally, the integration of road impedance modeling for path optimization proves to significantly reduce logistics costs, time expenditures, and enhance logistics efficiency. A comprehensive sensitivity analysis is also conducted to elucidate the factors influencing electric vehicle battery degradation, revealing a direct correlation between higher temperatures, deeper discharge depth, and increased battery loss. The study underscores the paramount significance of this research for the development and optimization of urban green logistics systems.

Neonatal sleep staging is crucial for understanding infant brain development and assessing neurological health. This study explores the optimal electrode configuration to reduce technical complexities and potential risks of causing skin irritation to neonates during data collection. A Multi-Branch Convolutional Neural Network (CNN) is used to categorize neonatal sleep states based on single-channel Electroencephalography (EEG) data. The proposed model was trained and tested on 16803 30-second segments from 64 infants, all of whom were at post-menstrual age between 36 and 43 weeks at the Children’s hospital of Fudan University. A total of 74 extracted time and frequency domain linear and non-linear features are applied to improve the performance of a Multi-Branch CNN-based classification model. Additionally, using principal component analysis (PCA), feature selection and feature importance are also applied to identify the most important features. Notably, the F3 channel outperforms other single-channels and has accuracy and kappa values 74.27±0.80% and 0.61, respectively. Furthermore, a combination of four left-side electrodes yields slightly better classification accuracy (75.36±0.57%) compared to the four right-side electrodes (74.76±1.10%), with corresponding kappa values of 0.63 and 0.62, respectively. In addition to providing insights into optimal electrode configuration using single-channel and multi-channel EEG data, the results highlight the critical role played by specific EEG channels in sleep stage classification. This research has the potential to enhance neonate care and monitor sleep more effectively, enabling early detection of sleep-related abnormalities such as sleep disorders. Furthermore, this research effectively captures information from a single-channel, reducing computing load while maintaining commendable performance. Additionally, integrating time and frequency domain linear and non-linear features into neonatal sleep staging can enhance accuracy and provide a deeper insight into the complex dynamics and irregularities of newborn’s sleep patterns.

A limited number of electroencephalography (EEG) channels are useful for neonatal sleep classification, particularly in the Internet of Medical Things (IoMT) field, where compact and lightweight devices are essential to monitoring health effectively. A streamlined and cost-effective IoMT solution can be achieved by utilizing fewer EEG channels, thereby reducing data transmission and device processing requirements. Using only two channels of an EEG device, this study presents a binary and multistage classification of neonatal sleep. The binary classification (sleep vs awake) achieved an accuracy of 87.56%, and a Cohen’s kappa of 74.13%. The quiet sleep ( $Q_{S}$ ) detection accuracy was 95.63%, with a Cohen’s kappa of 83.87%. For the three-stage classification, accuracy was 83.72%, and Cohen’s kappa was 69.73%. With only two channels, these are the highest performance parameters. The focus is on the fusion of features extracted through flexible analytical wavelet transform (FAWT) & discrete wavelet transform (DWT), ensemble-based voting models, and fewer channels. To feed crucial features into the ensemble-based voting model, feature importance, feature selection, and validation mechanisms were used. To design the voting classifier, several machine learning models were used, compared, and optimized. With SelectKBest feature selection, the proposed methodology was found to be the most effective. By using only two channels, this study shows the practicality of classifying neonatal sleep stages.

To address the problems of slow convergence speed, easy to fall into local minima and low convergence accuracy presented by previous algorithms in DC distribution network fault location, this paper adopts the improved artificial bee colony slime mould algorithm (SMA) to improve and solve. On the basis of SMA, an adaptive adjustable feedback factor and an improved crossover operator are introduced to improve the convergence speed; artificial bee colony (ABC) algorithm is introduced to improve the search ability to jump out of local minima, and the artificial bee colony slime mould algorithm (ISMA) is formed. Firstly, based on the six-terminal DC distribution network topology, a mathematical model of bipolar short-circuit fault as well as single-pole grounded short-circuit fault is established based on a fault occurring between G-VSC and W-VSC as an example. Then the principle of the improved ISMA is introduced in detail, and a suitable fitness function is established as the measure of fault location in DC distribution network. Finally, experimental simulations are conducted to obtain fault points from the optimization search and compare them with the actual values to verify the accuracy of the algorithm. In addition, the efficiency and robustness of ISMA are further verified by comparing with other algorithms.

With the globalization of the economy and financial markets today, predicting stock rankings and constructing appropriate portfolio strategies have become hot research topics for many scholars. However, because the stock market has different styles in different periods, market-style switching will seriously affect the prediction performance of the model. To eliminate the influence of style exposure and make the stock selection performance of the deep learning model more balanced, we propose an adversarial game neural network model based on LSTM and an attention mechanism for stock ranking prediction. We also combined trading tasks to construct an MS-WRSE loss function that considers stock rankings to optimize the network. Compared with classic time series prediction models, the adversarial game neural network can eliminate the influence of market-style factors on stock ranking predictions through the mutual game between the main neural network and the auxiliary neural network. This can strengthen the stock selection performance of the model.

With the increase of travel demands in the networked metro system, more and more metro transfer stations are suffering from oversaturated situations, leading to the accumulation of passengers in the transfer corridor and boarding area with potential accident risks. To further improve the transfer efficiency and passenger accumulation safety at transfer stations, the joint operation strategy is adopted. Metro trains are allowed to run across different metro lines and passengers switch other lines without transfer. This paper proposes 1) a meaningful, yet simple, way for defining the running strategy of trains for joint operation with two intersecting metro lines and 2) an optimal model for the train frequency to minimize indicators associated with the passenger service and train capacity. Regulation constraints such as waiting time of through and transfer passengers, number of available trains, load factor, and departure interval are taken into account. Finally, a case study of the joint operation in the Beijing metro system is implemented to demonstrate the performance and effectiveness of the proposed approaches.

The primary objective of this work was the utilization of the pulsed acoustic wave (PAW) method to explore the feasibility of measuring soil water content (SWC) based on the soil acoustic parameter acquisition (SAPA) system. Acoustic parameters (pulse acoustic velocity and acoustic attenuation coefficient) were collected from paddy soil (clay), red soil (loam), and lateritic-red soil (clay loam) under different SWCs. The calibration models of the pulse acoustic velocity, the attenuation coefficient, and the double acoustic parameters with the soil volumetric water content (SVWC) were established through fitting analysis. We studied the repeatability and reproducibility of the calibration models and conducted an extensive field experiment for 40 days to evaluate the calibration model's ability to predict SVWC. The results showed that the repeatability and reproducibility of the SVWC calibration model based on pulse acoustic velocity were the best, which showed that the acoustic velocity was more suitable for the inversion of SVWC than the acoustic attenuation coefficient. The 40-day field study's experimental results also verified the potential value of pulse acoustic velocity in SVWC detection.

The large-scale application of wind power and photovoltaic power solves the energy crisis and alleviates the environmental problems caused by the use of conventional energy. However, they are at risk of being randomly tripped from the network when faced to voltage sag and severe fault events, which will lead to a sudden reduction of active power output and also complicates fault recovery process of the whole system. Moreover, it may also aggravate failures and lead to large-scale power outages, which stimulates a growing interest in analyzing the low-voltage ride-through (LVRT) capabilities of the renewable energy systems (RES) and improving the performance through developing various mathematical models and analysis tools. In this paper, a systematical overview of cause, classification of voltage sag phenomena and voltage sag emulating techniques is presented, and four voltage sag generators (VSGs) are discussed and compared, which include generator based-VSG, shunt impedance based-VSG, transformer based-VSG and full converter based-VSG. Furthermore, a closed-loop detection platform based on real-time digital simulator (RTDS) for the converter controller of a permanent magnet synchronous generator (PWSG) set is introduced, to investigate the LVRT performance of the WT system under grid voltage sag conditions. Finally, the application of VSG in RES are presented and the future research directions are also discussed.

With the increasing penetration level of large-scale photovoltaic (PV) generator connected to the grid, an accurate simulation model is required for the dynamic analysis of the PV system. However, the detailed electromagnetic simulation of the large-scale system is complex and the dynamic response capability is estimated with obstacle caused by large computational burdens. Therefore, a precise dynamic aggregated model is indispensable for the displacement of the large-scale PV system. The structure-preservation based aggregated model with comprehensive equivalent parameters for large-scale PV system is proposed in this paper. A complete two-stage PV system model is established to analyze the dynamics of the system. Then, the aggregation method is obtained by comparing the dynamic equations of the detailed model with the aggregated model, which is based on the energy relationship in the PV system. Furthermore, four different case studies are considered including the aggregation of identical and different ten parallel-connected PV units both under the same irradiance condition, and the aggregation of different ten parallel-connected PV units under different irradiance and weak grid scenarios, where the aggregation models are obtained through the proposed equivalent modeling method. Finally, the effectiveness of the proposed aggregation method is verified by the simulation results from PSCAD/EMTDC platform, and the consistency between the aggregated model and the detailed model is confirmed under different disturbances of irradiance variation, and continuous symmetric and asymmetric grid faults.

For the current development of green civil aviation, this study aims to optimize the green four-dimensional (4D) trajectory of commercial flight by taking into account conventional cost and environmental cost. Some fundamental models, efficient processing methodologies, and conventional objectives are proposed to construct the framework of trajectory optimization. Based on the environmental cost including greenhouse gas cost and harmful gas cost, green objective functions are presented. The $\text{A}^\ast $ algorithm and the trapezoidal collocation method are employed to optimize the lateral path and vertical profile for 4D optimization trajectory generation. A case study for the A320 from Barcelona Airport to Frankfurt Airport yields the results that the optimal costs can be obtained under different objectives and the total cost can be more optimized by adjusting the weights of environmental cost and conventional cost. The study builds an aided tool for 4D trajectory optimization and demonstrates that environmental factors and conventional factors should be taken into comprehensive consideration when constructing the flight trajectory in the future, as well as it can underpin the green and sustainable development of the air transport industry.

With the extensive installation of intelligent electronic devices with bi-directional fault monitoring capabilities, richer fault direction information can be collected and utilized to achieve an accurate fault diagnosis. In this paper, we consider the fault diagnosis problem in active distribution systems with distributed generators connected, such as rotating electrical machine power sources and centralized inverter interfaced renewable energy resources. The fault diagnosis problem is modeled as a linear integer programming problem with an objective to minimize the numbers of fault zones and false alarms. A novel functional form is derived to capture the expected alarms sent by bi-directional fault monitoring devices to be compared with the actual alarms received by the dispatch center. Uncertainties in both the monitoring and communication stages are considered in the model by formulating the numbers of false alarms in the objective function. Three types of suspected false alarms can be detected: “missing alarms”, “distorted alarms”, and “reverse alarms”. By solving the developed optimization model for fault diagnosis, false alarms and suspected fault zones can be found. Case studies in a modified IEEE 33-bus system and a 55-bus system in Guangzhou, China are carried out in several different scenarios with multiple faults to demonstrate the performance of the proposed model. Numerical tests show that the proposed approach is superior in computational time such that it can be used for real-time fault diagnosis in active distribution systems.

Stroke is a serious lethal factor for human beings, and thus its unique pathogenic factors and underlying molecular mechanisms must be thoroughly investigated. Current complicated examination and treatment approaches on stroke reflect the complicated pathogenesis of stroke, which involves two major pathogenic factors: phenotypic characteristic and genetic background. Stroke occurrences with different symptoms and pathogenic characteristics may be induced by genetic variations. However, epigenetic contribution and regulation on stroke pathogenesis have been neglected for a long time and thus environmental influence on stroke onset is often underestimated. In this study, relied on our newly presented computational method, we re-screened out the genome methylation data of stroke patients with different subtypes and identified a group of functional methylated or demethylated genes. Recent reports validated the abnormal methylation status of the all identified genes in the pathogenesis of stroke. The genes were associated with biological functions involved in stroke onset. Further functional enrichment analysis confirmed and summarized the novel specific pathogenic roles of ion binding and focal adhesion in the regulation of stroke at the methylation level.

To bolster the resilience of power systems against typhoon disasters, this paper develops a holistic framework of wind disaster warning for transmission lines. This paper proposes a hybrid prediction model to quantify the transmission line damage probability under typhoon disaster based on extreme value type I probability distribution, Monte Carlo method, and Random Forest. Specifically, this paper uses the extreme value type I probability distribution and the Monte Carlo method to simulate the random wind field, and predict the damage probability of transmission lines under each wind field using the Random Forest method. This paper takes typhoon “Mangkhut” in 2018 as a case study, and compare the performance of the hybrid model based on random wind field with the Random Forest method under predicted and measured wind field. The results demonstrate that the hybrid model can effectively utilize wind speed data to obtain a more reliable prediction and achieves the best synthetic similarity to the actual damage situations.

Recently, most wireless power transmission (WPT) systems have used a “one-to-one” charging method of one receiving coil to one transmitting coil. However, when the receiving coil is offset in this way, the mutual inductance between the transmitting and receiving coils will be weakened, and the flexibility of the WPT system application will also be reduced. Therefore, how to realize the “one-to-many” transmission mode of one transmitting coil to multiple receiving coils and ensure the power stability of multiple loads is an urgent problem to be solved. In order to solve the above problems, the LCC-S topology is combined with the three-phase circuit, and a three-phase omnidirectional WPT system coil scheme is proposed based on the power characteristics of the three-phase LCC-S topology in this paper. Firstly, the influence of the resonance compensation topology on power characteristics is analyzed through circuit theory and a more suitable LCC-S topology is chosen. Then, the optimal coil scheme of the three-phase omnidirectional WPT system is proposed based on the law of mutual inductance. Compared with the original scheme, the theoretical calculation results show that the power fluctuation of the system is reduced by 75.13%. Finally, a set of three-phase WPT system model and test systems similar to the theory are established, which effectively verify the improvement of the proposed scheme, and verify the correctness and feasibility of the scheme.

Minimally invasive surgical robots have received more and more attention from medical patients because of their higher surgical accuracy and higher safety than doctors. Minimally invasive surgery is rapidly revolutionizing the treatment of traditional surgery. In order to solve the problem that the surgical robot has a redundant degree of freedom, which makes the kinematics solution more complicated, this paper analyzes the kinematics of the coordinate system block. Aiming at the problem that the strategy search algorithm needs to re-learn when the target pose changes, a convolutional neural network control strategy is studied and constructed. By designing the structure of the convolutional neural network visual layer and motor control layer, the loss function and sampling of the training process are established. Aiming at the problem of long training time of convolutional neural network, an effective pre-training method is proposed to shorten the training time of the neural network. At the same time, the effectiveness of the above method and the end-to-end control of the convolutional neural network strategy are verified through simulation experiments. The physical structure of the manipulator body is analyzed, and the forward and inverse kinematic equations of the manipulator are established by the D-H method. Monte Carlo method was used to analyze the working space of the manipulator, and low-latency control and simulation experiments were carried out on the movement trajectory of the manipulator in joint space and Cartesian space. The results show that the low-latency control algorithm in this paper is effective to control the mechanical arm of the minimally invasive medical surgery robot.

Despite the rapid development of natural language processing (NLP) implementation in electronic medical records (EMRs), Chinese EMRs processing remains challenging due to the limited corpus and specific grammatical characteristics, especially for radiology reports. In this study, we designed an NLP pipeline for the direct extraction of clinically relevant features from Chinese radiology reports, which is the first key step in computer-aided radiologic diagnosis. The pipeline was comprised of named entity recognition, synonyms normalization, and relationship extraction to finally derive the radiological features composed of one or more terms. In named entity recognition, we incorporated lexicon into deep learning model bidirectional long short-term memory-conditional random field (BiLSTM-CRF), and the model finally achieved an F1 score of 93.00%. With the extracted radiological features, least absolute shrinkage and selection operator and machine learning methods (support vector machine, random forest, decision tree, and logistic regression) were used to build the classifiers for liver cancer prediction. For liver cancer diagnosis, random forest had the highest predictive performance in liver cancer diagnosis (F1 score 86.97%, precision 87.71%, and recall 86.25%). This work was a comprehensive NLP study focusing on Chinese radiology reports and the application of NLP in cancer risk prediction. The proposed NLP pipeline for the radiological feature extraction could be easily implemented in other kinds of Chinese clinical texts and other disease predictive tasks.

At present, nanomaterials with high-quality photoelectric properties are urgently needed to be used in the manufacture of solar cells. In this study, the hydrothermal synthesis method was first used to grow ZnO nanorod arrays, and then a layer of WO3 thin film with controllable thickness was prepared on ZnO nanorod arrays by magnetron sputtering, forming a series of WO3@ZnO nanocomposite heterojunction. We found that the value of the photocurrent of the prepared nanocomposite samples is nearly 30 times higher than WO3 films under illumination, and it is more stable. The results show that this controllable microstructure can further modify the surface properties of ZnO nanorods, and possess the high visible absorption and photoelectric conversion efficiency. By controlling the thickness of the WO3 film, the band can be regulated and ultimately optimized the photoelectrochemical properties of the composite structure.

Public-key encryption with keyword search (PEKS) enables users to search on encrypted data, which is applicable to the scenario of sharing data in the cloud storage. In this paper, we focus on how to construct a PEKS scheme via obfuscation. Our basic scheme is built on the differing-inputs obfuscation (diO) and can be considered as an initial attempt to apply diO in the PEKS field. The scheme supports searching on encrypted data by providing to the cloud server an obfuscated simple “decrypt-then-compare” circuit with the secret key and the queried keyword hardwired in it. More interestingly, the scheme can be simply improved to resist off-line keyword guessing attacks (KGAs) as the standard PEKS scheme rather than a designated tester one. For complex search conditions, our scheme can be easily extended to multiple functionalities, such as conjunctive and fuzzy keyword search. Furthermore, it can be extended to the PEKS scheme in the multi-user setting.

In this paper, we consider a Q-learning-based power allocation strategy for a secure physical-layer system under dynamic radio environments. In such a system, the transmitter sends the information to the receiver threatened by M(M ≥ 2) intelligent attackers which have several attack modes and will bring out the severe issue of information security. To safeguard the system security, we formulate the insecure problem as a stochastic game which consists of M+1 players: the transmitter which can flexibly choose its transmit power, and M smart attackers that can determine their attack types. Then, the Nash equilibria (NEs) of the physical-layer secure game are derived, and their existence conditions are taken into account. The simulation results show that the proposed power allocation strategy in the stochastic game can efficiently suppress the attack rate of smart attackers even if there exist multiple smart attackers.

Digital twin is a significant way to achieve smart manufacturing, and provides a new paradigm for fault diagnosis. Traditional data-based fault diagnosis methods mostly assume that the training data and test data are following the same distribution and can acquire sufficient data to train a reliable diagnosis model, which is unrealistic in the dynamic changing production process. In this paper, we present a two-phase digital-twin-assisted fault diagnosis method using deep transfer learning (DFDD), which realizes fault diagnosis both in the development and maintenance phases. At first, the potential problems that are not considered at design time can be discovered through front running the ultra-high-fidelity model in the virtual space, while a deep neural network (DNN)-based diagnosis model will be fully trained. In the second phase, the previously trained diagnosis model can be migrated from the virtual space to physical space using deep transfer learning for real-time monitoring and predictive maintenance. This ensures the accuracy of the diagnosis as well as avoids wasting time and knowledge. A case study about fault diagnosis using DFDD in a car body-side production line is presented. The results show the superiority and feasibility of our proposed method.

With the ever-growing complexity of a modern power system, decentralized control is becoming a more advantageous framework for maintaining its stable operation. Recently, some research work has been done on decentralized control for mitigating inter-area oscillations based on dynamic state estimation. This paper illustrates that in the decentralized control scheme, the use of dynamic state estimation can compromise controller performance and decrease the damping of inter-area oscillations. To address this problem, this paper proposes a cooperative-based supplementary excitation control strategy for damping inter-area oscillations using dynamic state information. By eigenvalue analysis, this paper reveals the relationship between the estimator's parameter and inter-area modes. Furthermore, communication is utilized in the proposed controller to neutralize the adverse impact of using dynamic state estimation on damping performance. The connection between the communication structure and inter-area modes is also analytically given. Finally, the well-known New England test system with 10 generators and 39 buses is employed to demonstrate the analytical results.

This paper proposes an alterable weight minimum spanning tree (AW-MST) method to plan electrical collector systems (ECSs) in tidal current generation farms (TCGFs) toward economic objectives. First, a sector-division-based fuzzy c-means (FCM) grouping algorithm is proposed. The tidal current turbines (TCTs) in the TCGF are divided into several sectors by the improved FCM algorithm to relieve the computational burden. Meanwhile, trans-region crossings and overloads of submarine cables can be simultaneously avoided. Second, an ECS planning model is established which fully considers the tidal current velocity (TCV) characteristics and ECS investment and operating costs. Since the variable factors cannot be considered by the common minimum spanning tree algorithms, alterable weights are used in the AW-MST to optimize the variable factors, including power losses and cable types. Finally, the two different TCGFs and the measured TCV datasets collected from North of Orkney, Scotland, were used to verify the effectiveness and adaptability of the proposed method.

With the development of intelligent connected vehicles (ICVs), there emerge many new services and applications which involve intensive computation. To support the intensive computation in vehicle-to-everything (V2X) communication system, the framework of edge computing networks has been proposed, which exploits the computation ability of edge nodes at the cost of wireless transmission. Hence, it is of vital importance to predict the wireless channel parameters, which can help schedule the system resource management and optimize the system performance in advance. To fulfil this challenge, this paper proposes a novel prediction model based on long short-term memory (LSTM) network, which is powerful in capturing valuable information in the sequence and hence is good at analyzing the spatio-temporal correlation in the channel parameters. To validate the proposed model, we conduct extensive simulations to show that the proposed model is quite effective in the channel prediction. In particular, the proposed model can outperform the conventional ones substantially.

As the core of the rail freight flow organization process, train formation problem (TFP) has attracted much attention. In Chinese practice, car flow routing, TFP, and train routing are usually optimized sequentially to reduce the complexity of computation, which may result in a local optimum, and even no feasible solution. To address this issue, this paper studies the integrated optimization of the three sub problems with aims to minimize the total cost of transportation cost, accumulation cost, and classification cost. An integer linear arc-based model incorporating the unitary and in-tree rules of a shipment is first formulated and solved by the state-of-the-art solver GUROBI. Since GUROBI can't deal with the large test cases, a path-based model is built and solved by a bespoken two-phase algorithm. The first phase of the algorithm is Benders-and-Price approach that combines Benders decomposition and column generation, and the second phase is to solve the arc-based model with some variables fixed as the corresponding values fetched from the first phase. The results show that the proposed algorithm outperforms GUROBI, and the acceleration techniques, i.e., trust region and Pareto-optimal cuts, can improve the convergence efficiency of Benders decomposition significantly.

Considering that the hydrocyclone will be affected by internal and external fluid forces in practical work, the numerical simulation method of fluid-structure interaction(FSI) of the hydrocyclone is proposed, and the finite volume method is used in the fluid domain and the finite element method is used in the solid domain. According to the numerical simulation of the flow around a circular cylinder, the magnitude and frequency of fluid flow around the hydrocyclone are obtained. On this basis, the numerical simulation and experimental research of the hydrocyclone are carried out, and the vibration characteristic of the hydrocyclone under the FSI condition is discussed, which the modal frequencies and modes of the hydrocyclone, the structural displacement and stress distribution characteristics of the FSI interface under periodic excitation are obtained. The results of numerical simulation and measured are compared and analyzed. The distribution trend and position of the maximum acceleration values are in good agreement between the measured and numerical simulation. The maximum deformation and the maximum acceleration values position of the hydrocyclone structure which is near the intersection between small conical section and tail pipe, and the structural deformation and maximum acceleration values of the hydrocyclone increase with the increase of inlet velocity. The analysis shows that the FSI model of the hydrocyclone is reasonable. Moreover, the influencing factors of fluid flow around the hydrocyclone should be considered in the future design and application of the hydrocyclone.

With the wide application of nuclear magnetic resonance imaging, the multiplicative bias field in nuclear magnetic resonance images has created great difficulties for doctors in reading diagnostics and for computers in autoprocessing. Most previous methods eliminate the bias field in the image by estimating a single unknown bias field. An improved method that uses the nonparametric maximum likelihood to jointly eliminate bias from multiple magnetic resonance imaging (MRI) images is proposed in this paper. The method uses the statistics from the same location across different patient images, rather than within an image, and builds a “multiresolution” nonparametric tissue model conditioned on image location. We use a separate and nonparametric model to consider the intensity values at each pixel and utilize nonparametric maximum likelihood distance measures to simultaneously eliminate the bias of magnetic resonance (MR) images from different patients. Finally, the performance of the same was tested on a synthetic MRI dataset and a real MRI dataset and is found that the proposed algorithm provides better performance than the method of using entropy minimization across images and the most popular and widely used method, N4.

Steganography is to embed secret information into digital media and minimize the distortion caused by data embedding. The JPEG is a widely used image compression format, and many JPEG images transmitted on the network are double compressed. Most of the existing steganography algorithms mainly use the single compressed images as the embedded carrier of secret information while rarely taking advantage of the double compressed images. However, the double compressed operation usually leads to changes in the statistical characteristics of images. Therefore, the minor changes caused by steganography can be confused by double compression operation to achieve the purpose of concealing embedding operation. This paper proposes a secure JPEG double compression (DC) steganographic scheme based on irregular discrete cosine transformation (DCT) and coefficients distribution (IDCD-JDS), which can obtain less statistical detectability. The minimum distortion function is designed according to the fact that the statistical distribution of the double compressed images has periodic peaks and valleys as well as multiple irregular intervals. By using the syndrome trellis coding (STC) to embed secret information, the modifications are limited to regions that are difficult to detect. The quality factors (QF) relationship between the first and second compression is further studied to explore the effective range for double compressed images so that the proposed algorithm can achieve better performance under different conditions. The experiments show that this scheme can reduce the embedding change by utilizing the inherent statistical distribution and irregular block complexity in double compressed images, and it performs better than the existing methods.

In this paper, we investigate the power control strategy of intelligent secure communication with statistic channel state information (CSI) for Internet of Things (IoT) networks, where a transceiver and an attacker with several attack types, including silent, eavesdrop, jamming and spoofing, are considered. In order to solve the security problem that the transmitter only knows the statistical CSI of attacker, we propose a power control strategy based on Q-learning. In particular, Alice and Eve can choose their actions flexibly to maximize their reward under different system state and learn their best strategy according to the proposed strategy. In addition, the interactions between Alice and Eve are formulated as a zero-sum game, the Nash equilibrium and its existence conditions are deduced. Simulation results show that the impact of statistical CSI of attacker on system security performance can be reflected by the cost of attacker to launch attack and the average channel gain parameters. More importantly, the obtained results also show that the proposed power control strategy based on statistical CSI of attacker is worse than the scheme based on instantaneous CSI for statistical CSI leads a performance loss in terms of security.

Low-energy adaptive clustering routing protocol is a low-power adaptive hierarchical routing protocol designed for IoT, which has the function of extending network life time. In order to balance the energy consumption of wireless sensor network nodes and extend the life cycle of the whole network, the cluster heads are randomly selected in the classical clustering LEACH algorithm of the wireless sensor network of the Internet of Things, and the residual energy, node position and node density of the nodes are not considered. The problem is solved by the research of LEACH protocol, the selection of cluster head and the communication mechanism between cluster head and Sink. An improved clustering routing algorithm of LEACH protocol is proposed. The simulation experiment proves that the improved LEACH algorithm has more energy consumption than the comparison algorithm, the lowest power consumption of the cluster head node, and better network connectivity and reliability.

Vehicular ad hoc networks (VANETs) have increased in popularity in recent years and play an extremely important role in the intelligent transportation field. However, the demands of larger communication networks and the integrated message verification process for ensuring security incur more communication and computation overheads, and directly affect the efficiency of existing VANET schemes. To address this issue, this paper proposes a novel and practical conditional privacy-preserving authentication scheme, which uses the registration list instead of the revocation list to reduce the communication overhead. Specifically, our scheme can prevent malicious vehicles from disrupting the security features of VANETs. Moreover, we do not use the bilinear pairing operation, which is the most complicated operation in modern cryptography, thus significantly reducing the computation overhead and communication overhead. Security and performance analyses demonstrate that our proposed scheme is more secure and efficient than current schemes, and that the proposed scheme is more suitable for VANET deployments.

Retinal layer segmentation from optical coherence tomography (OCT) is of fundamental importance for measuring retinal layer thicknesses. These thickness measurements have been shown to correlate well with the severity of different ocular diseases; hence, they provide useful diagnostic information concerning diseases. Manual segmentation of retinal layers from OCT remains dominant in ophthalmological clinical practice but has serious drawbacks: it is time consuming, labor intensive, and results in inter/intrarater variations. Computer aided segmentation has attracted intensive research attention because it holds the potential not only to provide repeatable, quantitative, and objective results but also to reduce the time and effort required to delineate the retinal layers. However, most of the existing computer based retinal layer segmentation techniques focus on segmenting specific layers by exploring their unique characteristics; thus, they can fail to segment a retinal layer that is totally different. In this paper, we propose a generative retinal layer segmentation method based on groupwise curve alignment that combines the capabilities of segmenting different retinal layers into a unified framework. This method is unique for both its accuracy and its ability to segment any retinal layer without any special modifications. We experimentally validate that the proposed method outperforms a representative state-of-the-art technique by using images of both normal healthy eyes and diseased eyes. Our method is potentially useful in a large variety of practical applications involving retinal layer segmentation from OCT.

Frequent structures have emerged as resolving the structural pattern mining issues, such as chemistry, Web applications, and other related problems. Top-k subgraph query as an important technology of graph search is widely used in emerging fields. Different from the traditional subgraph query, the query requirement studied in this paper has two unique properties: 1) data graphs change dynamically over time, including vertices/edges insert, delete, and frequent labels update and 2) query with limits of labels and k. Existing graph index and query techniques rarely considered these. Therefore, this paper proposes a method called frequent subgraph dynamic Top-k query with label value constraint to address both the challenges. We propose a two-level index with the frequent structure mapping and label value aggregation, which locates the query structure quickly, then prunes, and filters according to the constraint to narrow search range and improve query efficiency. The method uses a two-level index to filter the initial result and combines the dynamic changes of graphs to modify query results. In addition, it also proposed an incremental dynamic maintenance strategy over the proposed index, which only updated the partial contents to avoid the high cost caused by global update. The experimental results demonstrate that the proposed Top-k query method outperforms the baseline approaches up to 37%.

In this paper, we investigate a secure communication system, where one transmitter sends some confidential message to one receiver, under the smart attack from one unmanned aerial vehicle (UAV). The UAV utilizes the programmable radio devices to execute multiple attack types, such as eavesdropping, jamming, and spoofing. We consider the practical communication scenarios where there are a limited number of pilot signals for channel estimation, and the channel estimation at the receiver side may be imperfect. To deal with the joint impact of smart attack and imperfect channel estimation, we use the non-cooperative game theory to propose a Q-learning-based power control algorithm in order to obtain an adaptive policy for the transmitter. In this algorithm, a Nash equilibrium strategy of the game under imperfect channel estimation is devised to maximize the utility of the transmitter and, meanwhile, suppress the smart attack from the UAV. The simulation results indicate that this strategy can effectively decrease the attack rate of the UAV attacker and increase the system secrecy capacity, regardless of the channel estimation accuracy. Moreover, the impact of the channel estimation error on the attack rate and secrecy capacity is also reflected.

The emergence of 5G networks will allow cloud computing providers to offer more convenient services. However, security and privacy issues of cloud services in 5G networks represent huge challenges. Recently, to improve security and privacy, a novel primitive was proposed by Ma et al. in TIFS 2015, called public key encryption with equality test supporting flexible authorization (PKEET-FA). However, the PKEET scheme lacks verification for equality test results to check whether the cloud performed honestly. In this paper, we expand the study of PKEET-FA and propose a verifiable PKEET (V-PKEET) scheme, which, to the best of our knowledge, is the first work that achieves verification in PKEET. Moreover, V-PKEET has been designed for three types of authorization to dynamically protect the privacy of data owners. Therefore, it further strengthens security and privacy in 5G networks.

Fault diagnosis is an important topic both in practice and research. There is intense pressure on industrial systems to continue reducing unscheduled downtime, performance degradation, and safety hazards, which requires detecting and recovering from potential faults as early as possible. From the historical perspective, this paper divides fault diagnosis into previous research and industrial big data era. According to primary drivers, this paper classifies fault diagnosis into knowledge-driven, data-driven, and value-driven methods. Among them, the former two approaches belong to the previous research on fault diagnosis. They mainly depend on expert experience and shallow models to detect and extract failures from relatively small size data. With the continuous exponential growth of data, it is insufficient to mine valuable fault information from massive multi-source heterogeneous data. The huge diagnostic value embodied in industrial big data has driven the emergence of the third category, which belongs to fault diagnosis based on big data. It consists of big data processing and analysis corresponding to high efficiency, cost effectiveness, and generality, which can deal well with problems that previous methods faced. We introduce the concept of a device electrocardiogram from the perspective of applicability to outline the present status of fault diagnosis for big data, and compare it with traditional diagnostic system. We also discuss issues and challenges that need to be further considered. It would be great valuable to integrate or explore more advanced diagnostic methods to handle collected industrial big data and put them into practice to mine the huge hidden diagnostic value.