Boosting Adversarial Training with Learnable Distribution

In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.However,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial training.This paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture model.The distribution centroid is built to classify samples and constrain the distribution of the sample features.The natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the model.The proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial training.This algorithm gradually increases the accuracy and robustness of the model by scaling perturbation.Finally,the proposed method outputs the predicted labels and the distance between the sample and the distribution centroid.The distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model defense.The effectiveness of the proposed method is demonstrated through comprehensive experiments.

The abundance,distribution,and enrichment mechanism of harmful trace elements in coals from Guizhou,Southwestern China

Coal seams can enrich a variety of harmful trace elements under specific geological conditions.The spatial distribution of harmful trace elements in coal is extremely uneven,and the distribution characteristics of each element content are different.The harmful elements released in the process of coal mining and utilization will cause serious harm to the environment and the human body.It is of great resource significance to study the geochemistry of coal that affects the enrichment and distribution characteristics of harmful trace elements.Based on the domestic and foreign literature on coal geochemistry in Guizhou published by previous investigators,this study counted 1097 sample data from 23 major coal-producing counties in Guizhou Province,systematically summarized the relevant research results of harmful trace elements in the coal of Guizhou,and revealed the overall distribution and enrichment characteristics of harmful trace elements in the coal of Guizhou.The results show that the average contents of Cd,Pb,Se,Cu,Mo,U,V,As,Hg,and Cr in coal of Guizhou are higher than those in Chinese coal and world coal.A variety of harmful trace elements in the coal of Guizhou have high background values,especially in Liupanshui,Xingyi and Qianbei coalfield.The enrichment of various harmful trace elements in the Late Permian coal in Guizhou is mainly related to the combined action of various geological and geochemical factors.The supply of terrigenous debris and sedimentary environment may be the basic background of the enrichment of harmful elements in western Guizhou,while low-temperature hydrothermal activity and volcanic ash deposition may be the main reasons for the enrichment of harmful elements in southwestern Guizhou.

Deep learning CNN-APSO-LSSVM hybrid fusion model for feature optimization and gas-bearing prediction

Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.

Human Visual Attention Mechanism-Inspired Point-and-Line Stereo Visual Odometry for Environments with Uneven Distributed Features

Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly distributed features because dense features occupy excessive weight.Herein,a new human visual attention mechanism for point-and-line stereo visual odometry,which is called point-line-weight-mechanism visual odometry(PLWM-VO),is proposed to describe scene features in a global and balanced manner.A weight-adaptive model based on region partition and region growth is generated for the human visual attention mechanism,where sufficient attention is assigned to position-distinctive objects(sparse features in the environment).Furthermore,the sum of absolute differences algorithm is used to improve the accuracy of initialization for line features.Compared with the state-of-the-art method(ORB-VO),PLWM-VO show a 36.79%reduction in the absolute trajectory error on the Kitti and Euroc datasets.Although the time consumption of PLWM-VO is higher than that of ORB-VO,online test results indicate that PLWM-VO satisfies the real-time demand.The proposed algorithm not only significantly promotes the environmental adaptability of visual odometry,but also quantitatively demonstrates the superiority of the human visual attention mechanism.

Grid Side Distributed Energy Storage Cloud Group End Region Hierarchical Time-Sharing Configuration Algorithm Based onMulti-Scale and Multi Feature Convolution Neural Network

There is instability in the distributed energy storage cloud group end region on the power grid side.In order to avoid large-scale fluctuating charging and discharging in the power grid environment and make the capacitor components showa continuous and stable charging and discharging state,a hierarchical time-sharing configuration algorithm of distributed energy storage cloud group end region on the power grid side based on multi-scale and multi feature convolution neural network is proposed.Firstly,a voltage stability analysis model based onmulti-scale and multi feature convolution neural network is constructed,and the multi-scale and multi feature convolution neural network is optimized based on Self-OrganizingMaps(SOM)algorithm to analyze the voltage stability of the cloud group end region of distributed energy storage on the grid side under the framework of credibility.According to the optimal scheduling objectives and network size,the distributed robust optimal configuration control model is solved under the framework of coordinated optimal scheduling at multiple time scales;Finally,the time series characteristics of regional power grid load and distributed generation are analyzed.According to the regional hierarchical time-sharing configuration model of“cloud”,“group”and“end”layer,the grid side distributed energy storage cloud group end regional hierarchical time-sharing configuration algorithm is realized.The experimental results show that after applying this algorithm,the best grid side distributed energy storage configuration scheme can be determined,and the stability of grid side distributed energy storage cloud group end region layered timesharing configuration can be improved.

Zonal distribution features of high frequency planetary waves in the oceans derived from satellite altimeter data

Based on TOPEX/Poseidon (T/P) and ERS-1 and 2 satellite altimeter data between October 1992 and December 2000, high frequency oscillations with periods less than 150 d are analyzed and their spatial distributions are described. The ratio, instead of the energy itself, of the energy corresponding to certain frequency band from power spectrum relative to the total energy in the 20～143 d range is analyzed. The results show that the period of the most energetic oscillations in this band increases with latitude from about 1 month near the tropics to about 4 months near 30°, in agreement with the latitudinal dependency of the phase speed of westward propagating long Rossby waves,which dominate the variability in those latitudes.As a result,the global spatial distributions of the period of the dominant oscillations are largely zonal, with relatively small differences between different ocean basins. It suggests that the oscillations with periods around 60 d are mainly associated with planetary Rossby waves except the often regarded as tidal aliasing.

Feature Extraction Method Based on Pseudo-Wigner-Ville Distribution for Rotational Machinery in Variable Operating Conditions

In the case of fault diagnosis for roller bearings, the conventional diagnosis approaches by using the time interval of energy impacts in time-frequency distribution or the pass-frequencies are based on the assumption that machinery operates under a constant rotational speed. However, when the rotational speed varies in the broader range, the pass-frequencies vary with the change of rotational speed and bearing faults cannot be identified by the interval of impacts. Researches related to automatic diagnosis for rotational machinery in variable operating conditions were quite few. A novel automatic feature extraction method is proposed based on a pseudo-Wigner-Ville distribution （PWVD） and an extraction of symptom parameter （SP）. An extraction method for instantaneous feature spectrum is presented using the relative crossing information （RCI） and sequential inference approach, by which the feature spectrum from time-frequency distribution can be automatically, sequentially extracted. The SPs are considered in the frequency domain using the extracted feature spectrum to identify among the conditions of a machine. A method to obtain the synthetic symptom parameter is also proposed by the least squares mapping （LSM） technique for increasing the diagnosis sensitivity of SP. Practical examples of diagnosis for bearings are given in order to verify the effectiveness of the proposed method. The verification results show that the features of bearing faults, such as the outer-race, inner-race and roller element defects have been effectively extracted, and the proposed method can be used for condition diagnosis of a machine under the variable rotational speed.

Cytogenetic Mapping of Disease Resistance Genes and Analysis of Their Distribution Features on Chromosomes in Maize

Cytogenetic maps of four clusters of disease resistance genes were generated by ISH of the two RFLP markers tightly linked to and flanking each of maize resistance genes and the cloned resistance genes from other plant species onto maize chromosomes, combining with data published before. These genes include Helminthosporium turcium Pass resistance genes Ht1, Htn1 and Ht2, Helminthosporium maydis Nisik resistance genes Rhm1 and Rhm2, maize dwarf mosaic virus resistance gene Mdm1, wheat streak mosaic virus resistance gene Wsm1, Helminthosporium carbonum ULLstrup resistance gene Hml and the cloned Xanthomonas oryzae pv. Oryzae resistance gene Xa21 of rice, Cladosporium fulvum resistance genes Cf-9 and Cf-2.1 of tomato,and Pseudomonas syringae resistance gene RPS2 of Arabidopsis. Most of the tested disease resistance genes located on the four chromosomes, i.e., chromosomes1, 3, 6 and 8, and they closely distributed at the interstitial regions of these chromosomal long arms with percentage distances ranging 31.44(±3.72)-72.40(±3.25) except for genes Rhm1, Rhm2, Mdm1 and Wsm1 which mapped on the satellites of the short arms of chromosome6. It showed that the tested RFLP markers and genes were duplicated or triplicated in maize genome. Homology and conservation of disease resistance genes among species, and relationship between distribution features and functions of the genes were discussed. The results provide important scientific basis for deeply understanding structure and function of disease resistance genes and breeding in maize.

Distributional features of temperature and salinity in the southern Taiwan Strait and its adjacent sea areas in late summer, 1994

Based on the CTD data obtained in the southern Taiwan Strait and its adjacent areas in August and September of 1994, the distributional features of the temperature and salinity in the studied area have been analyzed in detail. The results are as follows: (1) There are two low temperature and high salinity regions in the nearshore area between Dongshan and Shantou and in the southeastern Taiwan Shoal, respectively, which may be caused by upwellings. (2) There exists a cold eddy in the northwestern sea area and a warm eddy with two high temperature cores in the eastern sea area of the Dongsha Islands, which are related to the anti-cyclonic turning of the seawater near the Dongsha Islands. (3) A westward high temperature and high salinity water tongue extends through the northern Luzon Strait and reaches the sea areas near the Dengsha Islands and southern Taiwan Strait.

Petroleum Hydrocarbon Distribution Features in Water and Sediment off Fujian Shore

This study on the distribution features of petroleum hydrocarbon in water and sediment off the Fujian shore using data obtained from the baseline research on oceanic contamination in Fujian showed that: during the research period, petroleum hydrocarbon concentrations in water varied from 5.77 μg/L to 37.28 μg/L, averaged 14.48 μg/L; was lower in the wet season than in the dry season; and was highest in the Minjiang Estuary and Jiulong Estuary in both seasons. The petroleum hydrocarbon concentrations in shore sediment varied from 14.48 mg/kg to 784.36 mg/kg, averaged 133.3 mg/kg, and was closely related to sediment types (granularity).

CHANGING FEATURES AND TREND OF LIGHT INDUSTRY DISTRIBUTION IN NORTHEAST CHINA

Modern industry in northeast China started from light industry. From the end of 19th century to 1931 was the phase of initial development of light industry in northeast China. During this period, the development of light industry gave priority to grain processing industry. After occupying northeast China, Japanese vigorously developed heavy industry to meet the needs of munitions and paid more attention to raw materials and semi-finished articles industry for the purpose of the war. Light industry was impeded and developed slowly. After the founding of New China, large-scale economic construction took place in northeast and heavy industry received prior investment and equipment. Northeast region became the first heavy industry base through several five-year plans, the development of light industry made giant strides. The present features of light industry distribution are: difference of light industry distribution, similarity of light industry structure, and imbalance of light industry development.

Research on the Distributional Features of and Interrelationships Between the Dissolved Oxygen, Salinity, pH Value and Nutrient Salts in the Honghai Bay Waters

In this paper, the environmental factors are surveyed of the mariculture waters of the Honghai Bay from the late spring to the early summer (June) in 1998. The distributional features and variation laws of dissolved oxygen, salinity, pH value and nutrient salts in the sea water are expounded. Also discussed are their relationships between each other. The results show that the contents of dissolved oxygen and pH value in the sea water increase with the increasing temperature from north (except for No.15~17 stations) to south (expect for No.6 station). At the same time it is affirmed that photosynthesis is the major cause of the high contents of dissolved oxygen and pH value. And the nutrient salt shows a negative correlation with salinity. The total content of phytoplankton obviously increased with the reduction of nutrient salts from north to south.

Analysis of Temporal and Spatial Distribution and Large-Scale Circulation Features of Extreme Weather Events in Shanxi Province, China in Recent 30 Years

Extreme weather events such as persistent high temperatures, heavy rains or sudden cold waves in Shanxi Province in China have brought great losses and disasters to people’s production and life. It is of great practical significance to study the temporal and spatial distribution characteristics of extreme weather events and the circulation background field. We selected daily high temperature data (≥35°C), daily minimum temperature data and daily precipitation data (≥50 mm) from 109 meteorological stations in Shanxi Province, China from 1981 to 2010, then set the period in which the temperature is ≥35°C for more than 3 days as a high temperature extreme weather event, define the station in which 24 hour cumulative precipitation is ≥50 mm precipitation on a certain day (20 - 20 hours, Beijing time) as a rainstorm weather, and determine the cold air activity with daily minimum temperature dropped by more than 8°C for 24 hours, or decreased by 10°C for 48 h, and a daily minimum temperature of ≤4°C as a cold weather process. We statistically analyze the temporal and spatial characteristics and trends of high temperature, heavy rain and cold weather and the circulation background field. We count the number of extreme weather events such as persistent high temperatures, heavy rains and cold weather frosts in Shanxi, and analyze the temporal and spatial distribution characteristics, trends and general circulation background of extreme weather events. We analyze and find out the common features of the large-scale circulation background field in various extreme weather events. Through the study of the temporal and spatial distribution characteristics of extreme weather events in Shanxi, including persistent high temperature, heavy rain or sudden cold wave frost weather, we summarize the large-scale circulation characteristics of such extreme weather events. It will provide some reference for future related weather forecasting.

Effect of geomorphologic features and climate change on vegetation distribution in the arid hot valleys of Jinsha River,Southwest China

Rapid change of climate in vertical and considerable geomorphologic features form a typical diversity and distribution of biota in mountain ecosystems,i.e.,the subalpine forest zone(SFZ),the valley savanna zone(VSZ),and the transition zone between them.The arid hot valley in the middle and lower reaches of Jinsha River,China represents a well target area to study distribution and the driving factors in these typical mountain ecosystems.Therefore,this study selects four sub-sample areas in the arid-hot valley to explore the distinctive changes of vegetation during 1990 to 2020,and their driving factors in the three different vegetation zones on spatiotemporal scales.On the spatial scale,the Moran’s index was applied to identify the transition zone between the SFZ and the VSZ.Results show that the VSZ at low altitudes(less than 600-1000 m from the valley bottom)is mainly affected by geomorphologic features,especially the slope aspect.With increase in altitude,the climate factors(e.g.,humidity,temperature,etc.)play a more significant role in the development of the SFZ,while the effect of geomorphologic features gradually weakens.On the time scale,The SFZ at higher altitudes experienced more rapid changes in temperature(temperature increase of 1.41°C over the last 60 years)than the VSZ at lower altitudes(temperature increase of 0.172°C over the past 60 years).It caused the forest cover increase faster than that of savanna grassland.Humidity and heat conditions are altered by topography and climate conditions,which shapes the development and physiology of plants as they adapt to the different climatic zones.Furthermore,according to the driving factors(geomorphologic and climate factors)of vegetation distribution found in this study,it suggests that suitable tree species should be planted in the transition zone to evolve into the forest zone and making the forest zone to recover from high to low altitudes gradually.

Medical Feature Selection Approach Based on Generalized Normal Distribution Algorithm

This paper proposes a new pre-processing technique to separate the most effective features from those that might deteriorate the performance of the machine learning classifiers in terms of computational costs and classification accuracy because of their irrelevance,redundancy,or less information;this pre-processing process is often known as feature selection.This technique is based on adopting a new optimization algorithm known as generalized normal distribution optimization(GNDO)supported by the conversion of the normal distribution to a binary one using the arctangent transfer function to convert the continuous values into binary values.Further,a novel restarting strategy(RS)is proposed to preserve the diversity among the solutions within the population by identifying the solutions that exceed a specific distance from the best-so-far and replace them with the others created using an effective updating scheme.This strategy is integrated with GNDO to propose another binary variant having a high ability to preserve the diversity of the solutions for avoiding becoming stuck in local minima and accelerating convergence,namely improved GNDO(IGNDO).The proposed GNDO and IGNDO algorithms are extensively compared with seven state-of-the-art algorithms to verify their performance on thirteen medical instances taken from the UCI repository.IGNDO is shown to be superior in terms of fitness value and classification accuracy and competitive with the others in terms of the selected features.Since the principal goal in solving the FS problem is to find the appropriate subset of features that maximize classification accuracy,IGNDO is considered the best.

Mesozoic Volcanic-Intrusive Complexes in the Coastal Area of Southeastern Zhejiang Province: Their Features, Petrogenesis and Distribution Pattern

On the basis of previous studies and by means of field geological, remote sensing, petrographical,mineralogical, petrochemical and geochemical investigations, the authors studied the temporal-spatial distribu-tion of the regional structures, volcanic structures and products of volcanic activity in the coastal area ofsoutheastern Zhejiang. On the basis and through a systematic comparison of the products of magmatism in thearea, it is considered that there exists a compsite volcanic structural belt composed of linear and circular struc-tures and it has been demonstrated that there exist volcanic intrusive complexes--'trinity' composed of vol-canic, subvolcanic and plutonic rocks. It is suggested that the volcanic intrusive complexes in the area belong tothe typical syntexis series and that its materials were derived from a mixed source of crust and mantle.

Statistical study on the spatial - temporal distribution features of the arctic sea ice extent

On the basis of the arctic monthly mean sea ice extent data set during 1953-1984, the arctic region is divided into eight subregions,and the analyses of empirical orthogonal functions, power spectrum and maximum entropy spectrum are made to indentify the major spatial and temporal features of the sea ice fluctuations within 32-year period. And then, a brief appropriate physical explanation is tentatively suggested. The results show that both seasonal and non-seasonal variations of the sea ice extent are remarkable, and iis mean annual peripheral positions as well as their interannu-al shifting amplitudes are quite different among all subregions. These features are primarily affected by solar radiation, o-cean circulation, sea surface temperature and maritime-continental contrast, while the non-seasonal variations are most possibly affected by the cosmic-geophysical factors such as earth pole shife, earth rotation oscillation and solar activity.

DDoS Attack Detection in Cloud Computing Based on Ensemble Feature Selection and Deep Learning

Intrusion Detection System(IDS)in the cloud Computing(CC)environment has received paramount interest over the last few years.Among the latest approaches,Deep Learning(DL)-based IDS methods allow the discovery of attacks with the highest performance.In the CC environment,Distributed Denial of Service(DDoS)attacks are widespread.The cloud services will be rendered unavailable to legitimate end-users as a consequence of the overwhelming network traffic,resulting in financial losses.Although various researchers have proposed many detection techniques,there are possible obstacles in terms of detection performance due to the use of insignificant traffic features.Therefore,in this paper,a hybrid deep learning mode based on hybridizing Convolutional Neural Network(CNN)with Long-Short-Term Memory(LSTM)is used due to its robustness and efficiency in detecting normal and attack traffic.Besides,the ensemble feature selection,mutualization aggregation between Particle Swarm Optimizer(PSO),Grey Wolf Optimizer(PSO),Krill Hird(KH),andWhale Optimization Algorithm(WOA),is used to select the most important features that would influence the detection performance in detecting DDoS attack in CC.A benchmark dataset proposed by the Canadian Institute of Cybersecurity(CIC),called CICIDS 2017 is used to evaluate the proposed IDS.The results revealed that the proposed IDS outperforms the state-of-the-art IDSs,as it achieved 97.9%,98.3%,97.9%,98.1%,respectively.As a result,the proposed IDS achieves the requirements of getting high security,automatic,efficient,and self-decision detection of DDoS attacks.

Adaptive Kernel Firefly Algorithm Based Feature Selection and Q-Learner Machine Learning Models in Cloud

CC’s(Cloud Computing)networks are distributed and dynamic as signals appear/disappear or lose significance.MLTs(Machine learning Techniques)train datasets which sometime are inadequate in terms of sample for inferring information.A dynamic strategy,DevMLOps(Development Machine Learning Operations)used in automatic selections and tunings of MLTs result in significant performance differences.But,the scheme has many disadvantages including continuity in training,more samples and training time in feature selections and increased classification execution times.RFEs(Recursive Feature Eliminations)are computationally very expensive in its operations as it traverses through each feature without considering correlations between them.This problem can be overcome by the use of Wrappers as they select better features by accounting for test and train datasets.The aim of this paper is to use DevQLMLOps for automated tuning and selections based on orchestrations and messaging between containers.The proposed AKFA(Adaptive Kernel Firefly Algorithm)is for selecting features for CNM(Cloud Network Monitoring)operations.AKFA methodology is demonstrated using CNSD(Cloud Network Security Dataset)with satisfactory results in the performance metrics like precision,recall,F-measure and accuracy used.

Wireless distributed computing for cyclostationary feature detection

Recently, wireless distributed computing （WDC） concept has emerged promising manifolds improvements to current wireless technotogies. Despite the various expected benefits of this concept, significant drawbacks were addressed in the open literature. One of WDC key challenges is the impact of wireless channel quality on the load of distributed computations. Therefore, this research investigates the wireless channel impact on WDC performance when the tatter is applied to spectrum sensing in cognitive radio （CR） technology. However, a trade- off is found between accuracy and computational complexity in spectrum sensing approaches. Increasing these approaches accuracy is accompanied by an increase in computational complexity. This results in greater power consumption and processing time. A novel WDC scheme for cyclostationary feature detection spectrum sensing approach is proposed in this paper and thoroughly investigated. The benefits of the proposed scheme are firstly presented. Then, the impact of the wireless channel of the proposed scheme is addressed considering two scenarios. In the first scenario, workload matrices are distributed over the wireless channel