Search

The power system frequency fluctuations could be captured by digital recordings and extracted to compare with a reference database for forensic timestamp verification. It is known as the Electric Network Frequency (ENF) criterion, enabled by the properties of random fluctuations and intra-grid consistency. In essence, this is a task of matching a short random sequence within a long reference, whose accuracy is mainly concerned with whether this match could be uniquely correct. In this paper, we comprehensively analyze the factors affecting the reliability of ENF matching, including the length of test recording, length of reference, temporal resolution, and Signal-to-Noise Ratio (SNR). For synthetic analysis, we incorporate the first-order AutoRegressive (AR) ENF model and propose an efficient Time-Frequency Domain noisy ENF synthesis method. Then, the reliability analysis schemes for both synthetic and real-world data are respectively proposed. Through a comprehensive study, we quantitatively reveal that while the SNR is an important external factor to determine whether timestamp verification is viable, the length of test recording is the most important inherent factor, followed by the length of reference. However, the temporal resolution has little impact on performance. Finally, a practical workflow of the ENF-based audio timestamp verification system is proposed, incorporating the discovered results.

Electroencephalographic (EEG) source imaging (ESI) is a powerful method for studying brain functions and surgical resection of epileptic foci. However, accurately estimating the location and extent of brain sources remains challenging due to noise and background interference in EEG signals. To reconstruct extended brain sources, we propose a new ESI method called Variation Sparse Source Imaging based on Generalized Gaussian Distribution (VSSI-GGD). VSSI-GGD uses the generalized Gaussian prior as a sparse constraint on the spatial variation domain and embeds it into the Bayesian framework for source estimation. Using a variational technique, we approximate the intractable true posterior with a Gaussian density. Through convex analysis, the Bayesian inference problem is transformed entirely into a series of regularized ${L}_{{2}{p}}$ -norm ( ${0} < {p} < {1}$ ) optimization problems, which are efficiently solved with the ADMM algorithm. Imaging results of numerical simulations and human experimental dataset analysis reveal the superior performance of VSSI-GGD, which provides higher spatial resolution with clear boundaries compared to benchmark algorithms. VSSI-GGD can potentially serve as an effective and robust spatiotemporal EEG source imaging method. The source code of VSSI-GGD is available at https://github.com/Mashirops/VSSI-GGD.git.

Superior fiber quality is one of the most important objectives in cotton breeding. To detect the genetic basis underlying fiber quality, an F2 population containing 413 plants was constructed by crossing Jifeng 914 and Jifeng 173, both of which have superior fiber quality, with Jifeng 173 being better. Five fiber quality traits were investigated in the F2, F2:3, F2:4, and F2:5 populations. Quantitative trait loci (QTL) mapping was conducted based on a high-density genetic map containing 11,488 single nucleotide polymorphisms (SNPs) and spanning 4202.12 cM in length. Transgressive segregation patterns and complex correlations in the five tested traits were observed. A total of 108 QTLs were found, including 13 major effect QTLs that contributed more than 10% toward phenotypic variation (PV) and 9 stable QTLs that could be repeatedly mapped in different generations. Chromosome A7 contained 12 QTL, ranking the first. No QTL was found on chromosomes D1 and D11. Two QTLs could be repeatedly detected in three populations, including qFL-D3-2 in F2, F2:4, and F2:5 with 9.18–21.45% of PV and qFS-A11-1 in F2:3, F2:4, and F2:5 with 6.05–10.41% of PV. Another seven stable QTLs could be detected in two populations, including four major effect QTLs: qFL-A12-3, qFS-D10-2, qMC-D6-2, and qMC-D8-1. Fourteen QTL-overlapping regions were found, which might explain the complex correlations among the five phenotypic traits. Four regions on chromosome A11, D3, D6, and D10 covered by both stable and major effect QTLs are promising for further fine mapping. The genomic regions of the two QTLs detected in three populations and the four major effect QTLs contain 810 genes. Gene functional analysis revealed that the annotated genes are mainly involved in protein binding and metabolic pathways. Fifteen candidate genes in the qFL-D3-2 region are highly expressed in fiber or ovules during fiber initiation, elongation, secondary cell wall thickening, or maturation stages. qRT-PCR revealed that Ghir_D03G005440.1 and Ghir_D03G011310.1 may play a role in promoting fiber initiation, while Ghir_D03G006470.1 may be beneficial for promoting fiber elongation. This study provides more information for revealing the molecular genetic basis underlying cotton fiber quality.

Abstract In recent years, convolutional neural networks (CNNs) have been applied successfully in many fields. However, these deep neural models are still considered as “black box” for most tasks. One of the fundamental issues underlying this problem is understanding which features are most influential in image recognition tasks and how CNNs process these features. It is widely believed that CNN models combine low‐level features to form complex shapes until the object can be readily classified, however, several recent studies have argued that texture features are more important than other features. In this paper, we assume that the importance of certain features varies depending on specific tasks, that is, specific tasks exhibit feature bias. We designed two classification tasks based on human intuition to train deep neural models to identify the anticipated biases. We designed experiments comprising many tasks to test these biases in the Res Net and Dense Net models. From the results, we conclude that (1) the combined effect of certain features is typically far more influential than any single feature; (2) in different tasks, neural models can perform different biases, that is, we can design a specific task to make a neural model biased towards a specific anticipated feature.

Understanding the genetic basis of the node of the first fruiting branch (NFFB) improves early-maturity cotton breeding. Here we report QTL mapping on 200 F2 plants and derivative F2:3 and F2:4 populations by genotyping by sequencing (GBS). BC1F2 population was constructed by backcrossing one F2:4 line with the maternal parent JF914 and used for BSA-seq for further QTL mapping. A total of 1,305,642 SNPs were developed between the parents by GBS, and 2,907,790 SNPs were detected by BSA-seq. A high-density genetic map was constructed containing 11,488 SNPs and spanning 4,202.12 cM in length. A total of 13 QTL were mapped in the 3 tested populations. JF914 conferred favorable alleles for 11 QTL, and JF173 conferred favorable alleles for the other 2 QTL. Two stable QTL were repeatedly mapped in F2:3 and F2:4, including qNFFB-D3-1 and qNFFB-D6-1. Only qNFFB-D3-1 contributed more than 10% of the phenotypic variation. This QTL covered about 24.7 Mb (17,130,008–41,839,226 bp) on chromosome D3. Two regions on D3 (41,779,195–41,836,120 bp, 41,836,768–41,872,287 bp) were found by BSA-seq and covered about 92.4 Kb. This 92.4 Kb region overlapped with the stable QTL qNFFB-D3-1 and contained 8 annotated genes. By qRT-PCR, Ghir_D03G012430 showed a lower expression level from the 1- to 2-leaf stage and a higher expression level from the 3- to 6-leaf stage in the buds of JF173 than that of JF914. Ghir_D03G012390 reached the highest level at the 3- and 5-leaf stages in the buds of JF173 and JF914, respectively. As JF173 has lower NFFB and more early maturity than JF914, these two genes might be important in cell division and differentiation during NFFB formation in the seedling stage. The results of this study will facilitate a better understanding of the genetic basis of NFFB and benefit cotton molecular breeding for improving earliness traits.

Abstract Relation extraction between entity pairs is an increasingly critical area in natural language processing. Recently, the pre‐trained bidirectional encoder representation from transformer (BERT) performs excellently on the text classification or sequence labelling tasks. Here, the high‐level syntactic features that consider the dependency between each word and the target entities into the pre‐trained language models are incorporated. Our model also utilizes the intermediate layers of BERT to acquire different levels of semantic information and designs multi‐granularity features for final relation classification. Our model offers a momentous improvement over the published methods for the relation extraction on the widely used data sets.

A dense heterogeneous cellular network can effectively increase the system capacity and enhance the network coverage. It is a key technology for the new generation of the mobile communication system. The dense deployment of small base stations not only improves the quality of network service, but also brings about a significant increase in network energy consumption. This paper mainly studies the energy efficiency optimization of the Macro-Femto heterogeneous cellular network. Considering the dynamic random changes of the access users in the network, the sleep process of the Femto Base Stations (FBSs) is modeled as a Semi-Markov Decision Process (SMDP) model in order to save the network energy consumption. And further, this paper gives the dynamic sleep algorithm of the FBS based on the value iteration. The simulation results show that the proposed SMDP-based adaptive sleep strategy of the FBS can effectively reduce the network energy consumption.

Remote sensing scene classification is a fundamental responsibility of earth observation, aiming at identifying information granular for land cover classification. The multi-granular land use for multi-source remotely sensed image categories is now a principal task in remote sensing data augmentation and data selection. Understanding image representations are meaningful for the scene classification task. Training deep learning model-based approaches has to do with scene classification and brings about fantastic achievement. At the same time, these high-level approaches are computationally expensive and time–consuming. This paper introduces multi-granularity Neural Network Encoding architecture base on InceptionV3, InceptionReseNetV2, VGG16, and DenseNet201 architecture into remote sensing scene classification. To improve performance and to solve intra-class variation for multi-class scene issues remote sensing dataset. By using pre-trained CNN, activation function and ensemble learning have been adopting. InceptionV3 and VGG16 are used to extract features. InceptionResNetV2 use for fine-tuning, which consists of unfreezing the entre model and retraining the new data with a lower learning rate. The proposed fine-tune whole pre-trained model produces better results of test set up to 97.84 % than features extracted by InceptionResNetV2. Also, we use DCNNs ensemble average and weighted average to achieve better outcomes for 97.36% and 99.10%. In our experiments, we attempted to fine-tune the deep convolutional neural networks (DCNNs) training method for remote sensing scene classification on two public datasets UCM, SIRI-WHU, and one dataset I collected through the google earth engine from East Africa Community Countries (EACC) within nine classes within total 2112 labeled images. The results indicate that our proposed fine-tuning of the pre-trained model with few epochs and less computational time increases accuracy.

Earth’s drylands are expected to expand due to climate change, but how this will affect vegetation remains unclear. Here the authors use models to show that despite expansion, primary productivity in drylands is likely to increase through the 21st Century.

Atmospheric diffusion is one of the factors affecting local air quality, dominating the evolution of air pollution episodes. Previous work has emphasized the unfavorable diffusion conditions in the Sichuan Basin resulting from its complex terrain. However, the recent spatiotemporal variation in atmospheric diffusion conditions in the basin and their effects on local air quality remain unclear. Based on the wind speed, boundary layer height, vertical potential temperature difference of ERA5 analysis, two independent metrics containing information on horizontal and vertical diffusion ability, i.e., ventilation coefficient (VE) and the air stagnant conditions (ASI), are involved to indicate wintertime atmospheric diffusion conditions in the basin. Both VE and ASI reveal a decrease tendency of atmospheric diffusion condition from the northwestern portion of the basin to the southeast. In terms of the long-term variation in diffusion conditions, VE showed a broader increasing trend from 1979 to 2019, with a distinct increase in the western region. In contrast, the occurrence of air stagnation events has declined −3∼−6%/decade in the basin, more significantly over the western basin. Both the increase in VE and the decrease in air stagnation frequency indicate the improvement of atmospheric diffusion conditions in the Sichuan Basin from 1979 to 2019, which mitigates the effects of air pollutant emissions to some extent. The enhancement of diffusion conditions is due to the improvement of vertical diffusion conditions. The lowest seasonal PM2.5 concentrations occur in the northwestern basin, where VE is highest and ASI is lowest. Atmospheric diffusion conditions can explain approximately 25–50% of the interannual variation in PM2.5 concentrations in Chengdu.

Species distribution models are widely used in conservation biology and invasive biology. MaxEnt models are the most widely used models among the existing modeling tools. In the MaxEnt modeling process, the default parameters are used most often to build the model. However, these models tend to be overfit. Aiming at this problem, this study uses an optimized MaxEnt model to analyze the impact of past, present and future climate on the distributions of Codonopsis pilosula, an economic species, to provide a theoretical basis for its introduction and cultivation. Based on 264 distribution records and eight environmental variables, the potential distribution areas of C. pilosula in the last interglacial, middle Holocene and current periods and 2050 and 2070 were simulated. Combined with the percentage contribution, permutation importance, and jackknife test, the environmental factors affecting the suitable distribution area of this species were discussed. The results show that the parameters of the optimal model are: the regularization multiplier is 1.5, and the feature combination is LQHP (linear, quadratic, hinge, product). The main temperature factors affecting the distribution of C. pilosula are the annual mean temperature, mean diurnal range, and isothermality. The main precipitation factors are the precipitation seasonality, precipitation in the wettest quarter, and precipitation in the driest quarter, among which the annual average temperature contributes the most to the distribution area of this species. With climate warming, the suitable area of C. pilosula exhibits a northward expansion trend. It is estimated that in 2070, the suitable area of this species will expand to its maximum, reaching 2.5108 million square kilometers. The highly suitable areas of C. pilosula are mainly in Sichuan, Gansu, Shaanxi, Shanxi, and Henan Provinces. Our findings can be used to provide theoretical support related to avoiding the blind introduction of C. pilosula.

Learning label noise is gaining increasing attention from a variety of disciplines, particularly in supervised machine learning for classification tasks. The k nearest neighbors (kNN) classifier is often used as a natural way to edit the training sets due to its sensitivity to label noise. However, the kNN-based editor may remove too many instances if not designed to take care of the label noise. In addition, the one-sided nearest neighbor (NN) rule is unconvincing, as it just considers the nearest neighbors from the perspective of the query sample. In this paper, we propose an ensemble and iterative recovery strategy-based kGNN method (EIRS-kGNN) to edit data with label noise. EIRS-kGNN first uses the general nearest neighbors (GNN) to expand the one-sided NN rule to a binary-sided NN rule, taking the neighborhood of the queried samples into account. Then, it ensembles the prediction results of a finite set of ks in the kGNN to prudently judge the noise levels for each sample. Finally, two loops, i.e., the inner loop and the outer loop, are leveraged to iteratively detect label noise. A frequency indicator is derived from the iterative processes to guide the mixture approaches, including relabeling and removing, to deal with the detected label noise. The goal of EIRS-kGNN is to recover the distribution of the data set as if it were not corrupted. Experimental results on both synthetic data sets and UCI benchmarks, including binary data sets and multi-class data sets, demonstrate the effectiveness of the proposed EIRS-kGNN method.

The deep convolutional neural networks (DCNN) require large number of training data to avoid overfitting, which makes it unsuitable for processing small-scale image datasets. The transfer learning using DCNN (TCNN) reuses pre-trained layers to generate a mid-level image representation so that the optimization of more than millions CNN parameters can be avoided. By this way, overfitting problem in small-scale data can be alleviated. However, although now many public DCNNs have been trained and can be reused, the existing TCNNs are formed by only a single pre-trained DCNN structure and cannot make full use of multiple structures of pre-trained DCNNs. At the same time, the existing ensemble CNNs have not enough good representation ability. To address this problem, we combine the conventional ideas of ensemble CNNs and propose three ensemble TCNNs (TECNN). They are the voting method based on the combination of all TCNNs, the PickOver method by finding the optimal combination, and weighted method by finding weighted combination. Different from the existing ensemble CNNs, the proposed methods do not need to retrain the component CNNs and generate ensemble transferring representations by transferring the pre-trained mid-level parameters. The mathematical models of those three methods are also provided. Their versions of using fine-tuning are also compared in the experiments. In addition, we replace the Softmax classifier with ensemble linear classifiers in the full-connection layer. They outperform the current state of the art algorithms on Caltech ImageNet and some internet image data. All this research has released as an open source library called Transferring Image Ensemble Representations using Deep Convolutional Neural Networks (TECNN). The source codes and relevant datasets in different versions are available from: http://www.cquptshuyinxia.com/TECNN.html.

There are many algorithms for solving complex problems in supervised manner. However, unsupervised tasks are more common in real scenarios. Inspired by the idea of granular computing and the characteristics of human cognitive process, this paper proposes a complex tasks decomposition mechanism based on Density Peaks Clustering (DPC) to address complex tasks with an unsupervised process, which simulates the multi-granular observation and analysis of human being. Firstly, the DPC algorithm is modified to nullify its essential defects such as the difficulty of locating correct clustering centers and classifying them accurately. Then, the improved DPC algorithm is used to construct the initial decomposition solving space with multi-granularity theory. We also define subtask centers set and the granulation rules to guide the multi-granularity decomposing procedure. These rules are further used to decompose the solving space from coarse granules to the optimal fine granules with a convergent and automated process. Furthermore, comprehensive experiments are presented to verify the applicability and veracity of our proposed method in community-detection tasks with several benchmark complex social networks. The results show that our method outperforms other four state-of-the-art approaches.

Satellite-based rapid sweeping screening of localized PM2.5 hotspots at fine-scale local neighborhood levels is highly desirable. This motivated us to develop a random forest–convolutional neural network–local contrast normalization (RF–CNN–LCN) pipeline that detects local PM2.5 hotspots at a 300 m resolution using satellite imagery and meteorological information. The RF–CNN joint model in the pipeline uses three meteorological variables and daily 3 m/pixel resolution PlanetScope satellite imagery to generate daily 300 m ground-level PM2.5 estimates. The downstream LCN processes the estimated PM2.5 maps to reveal local PM2.5 hotspots. The RF–CNN joint model achieved a low normalized root mean square error for PM2.5 of within ~31% and normalized mean absolute error of within ~19% on the holdout samples in both Delhi and Beijing. The RF–CNN–LCN pipeline reasonably predicts urban PM2.5 local hotspots and coolspots by capturing both the main intra-urban spatial trends in PM2.5 and the local variations in PM2.5 with urban landscape, with local hotspots relating to compact urban spatial structures and coolspots being open areas and green spaces. Based on 20 sampled representative neighborhoods in Delhi, our pipeline revealed an annual average 9.2 ± 4.0 μg m−3 difference in PM2.5 between the local hotspots and coolspots within the same community. In some cases, the differences were much larger; for example, at the Indian Gandhi International Airport, the increase was 20.3 μg m−3 from the coolest spot (the residential area immediately outside the airport) to the hottest spot (airport runway). This work provides a possible means of automatically identifying local PM2.5 hotspots at 300 m in heavily polluted megacities and highlights the potential existence of substantial health inequalities in long-term outdoor PM2.5 exposures even within the same local neighborhoods between local hotspots and coolspots.

It is a basic task to measure the similarity between two uncertain concepts in many real-life artificial intelligence applications, such as image retrieval, collaborative filtering, public opinion guidance, and so on. As an important cognitive computing model, cloud model has been used in many fields of artificial intelligence. It can realise the bidirectional cognitive transformation between qualitative concept and quantitative data based on the theory of probability and fuzzy set. The similarity measure of two uncertain concepts is a fundamental issue in cloud model theory. Popular similarity measure methods of cloud model are surveyed in this study. Their limitations are analysed in detail. Some related future research topics are proposed.

In recent years, electroencephalogram (EEG) signals have been used as a biometric modality, and EEG-based biometric systems have received increasing attention. However, due to the sensitive nature of EEG signals, the extraction of identity information through processing techniques may lead to some loss in the extracted identity information. This may impact the distinctiveness between subjects in the system. In this context, we propose a new self-relative evaluation framework for EEG-based biometric systems. The proposed framework aims at selecting a more accurate identity information when the biometric system is open to the enrollment of novel subjects. The experiments were conducted on publicly available EEG datasets collected from 108 subjects in a resting state with closed eyes. The results show that the openness condition is useful for selecting more accurate identity information.

Current passive sensors fail to accurately identify cloud phase, thus largely limiting the quantification of radiative contributions and precipitation of different cloud phases over the Tibet Plateau (TP), especially for the mixed-phase and supercooled water clouds. By combining the 4 years of (January 2007–December 2010) cloud phase (2B-CLDCLASS-LIDAR), radiative fluxes (2B-FLXHR-LIDAR), and precipitation (2C-PRECIP-COLUMN) products from CloudSat, this study systematically quantifies the radiative contribution of cloud phases and precipitation over the TP. Statistical results indicate that the ice cloud frequently occurs during the cold season, while mixed-phase cloud fraction is more frequent during the warm season. In addition, liquid clouds exhibit a weak seasonal variation, and the relative cloud fraction is very low, but supercooled water cloud has a larger cloud distribution (the value reaches about 0.24) than those of warm water clouds in the eastern part of the TP during the warm season. Within the atmosphere, the ice cloud has the largest radiative contribution during the cold season, the mixed-phase cloud is the second most important cloud phase for the cloud radiative contribution during the warm season, and supercooled water clouds’ contribution is particularly important during the cold season. In particular, the precipitation frequency over the TP is mainly dominated by the ice and mixed-phase clouds and is larger over the southeastern part of the TP during the warm season.

Cross-domain recommendation is a promising solution in recommendation systems by using relatively rich information from the source domain to improve the recommendation accuracy of the target domain. Most of the existing methods consider the rating information of users in different domains, the label information of users and items and the review information of users on items. However, they do not effectively use the latent sentiment information to find the accurate mapping of latent features in reviews between domains. User reviews usually include user’s subjective views, which can reflect the user’s preferences and sentiment tendencies to various attributes of the items. Therefore, in order to solve the cold-start problem in the recommendation process, this paper proposes a cross-domain recommendation algorithm (CDR-SAFM) based on sentiment analysis and latent feature mapping by combining the sentiment information implicit in user reviews in different domains. Different from previous sentiment research, this paper divides sentiment into three categories based on three-way decision ideas—namely, positive, negative and neutral—by conducting sentiment analysis on user review information. Furthermore, the Latent Dirichlet Allocation (LDA) is used to model the user’s semantic orientation to generate the latent sentiment review features. Moreover, the Multilayer Perceptron (MLP) is used to obtain the cross domain non-linear mapping function to transfer the user’s sentiment review features. Finally, this paper proves the effectiveness of the proposed CDR-SAFM framework by comparing it with existing recommendation algorithms in a cross-domain scenario on the Amazon dataset.

Approximation computation is a critical step in rough sets theory used in knowledge discovery and other related tasks. In practical applications, an information system often evolves over time by the variation of attributes or objects. Effectively computing approximations is vital in data mining. Dominance-based rough set approach can handle information with preference-ordered attribute domain, but it is not able to handle the situation of data missing. Confidential Dominance-based Rough Set Approach (CDRSA) is introduced to process Incomplete Ordered Decision System (IODS). This paper focuses on incremental updating approximations under dynamic environment in IODS. With the CDRSA, the principles of incremental updating approximations are discussed while the variation of attribute sets or the union of subsets of objects and the corresponding incremental algorithms are developed. Comparative experiments on data sets of UCI and results show that the proposed incremental approaches can improve the performance of updating approximations effectively by a significant shortening of the computational time.