Precision in iterative modulation enhanced single-molecule localization microscopy

Modulation enhanced single-molecule localization microscopy (meSMLM) methods improve the localization precision by using patterned illumination to encode additional position information. Iterative meSMLM (imeSMLM) methods iteratively generate prior information on emitter positions, used to locally improve the localization precision during subsequent iterations. The Cramér-Rao lower bound cannot incorporate prior information to bound the best achievable localization precision because it requires estimators to be unbiased. By treating estimands as random variables with a known prior distribution, the Van Trees inequality (VTI) can be used to bound the best possible localization precision of imeSMLM methods. An imeSMLM method is considered, where the positions of in-plane standing-wave illumination patterns are controlled over the course of multiple iterations. Using the VTI, we analytically approximate a lower bound on the maximum localization precision of imeSMLM methods that make use of standing-wave illumination patterns. In addition, we evaluate the maximally achievable localization precision for different illumination pattern placement strategies using Monte Carlo simulations. We show that in the absence of background and under perfect modulation, the information content of signal photons increases exponentially as a function of the iteration count. However, the information increase is no longer exponential as a function of the iteration count under non-zero background, imperfect modulation, or limited mechanical resolution of the illumination positioning system. As a result, imeSMLM with two iterations reaches at most a fivefold improvement over SMLM at 8 expected background photons per pixel and 95% modulation contrast. Moreover, the information increase from imeSMLM is balanced by a reduced signal photon rate. Therefore, SMLM outperforms imeSMLM when considering an equal measurement time and illumination power per iteration. Finally, the VTI is an excellent tool for the assessment of the performance of illumination control and is therefore the method of choice for optimal design and control of imeSMLM methods.     

Hybrid convolution neural network model for a quicker detection of infested maize plants with fall armyworms using UAV-based images

Visual detection of plants diseases over a large area is time-consuming, and the results are prone to errors due to the subjective nature of human evaluations. Several automatic disease detection techniques that improve detection time and improve accuracy compared to visual methods exist, yet they are not suitable for immediate detection. In this paper, we propose a hybrid convolution neural network (CNN) model to speed up the detection of fall armyworms (faw) infested maize leaves. Specifically, the proposed system combines unmanned aerial vehicle (UAV) technology, to autonomously capture maize leaves, and a hybrid CNN model, which is based on a parallel structure specifically designed to take advantage of the benefits of both individual models, namely VGG16 and InceptionV3. We compare the performance of the proposed model in terms of accuracy and training time to four existing CNN models, namely VGG16, InceptionV3, XceptionNet, and Resnet50. The results show that compared to existing models, the proposed hybrid model reduces the training time by 16% to 44% compared to other models while exhibiting the most superior accuracy of 96.98%.     

Space partitioning strategies for indoor WLAN positioning with cascade-connected ANN structures

Position information in indoor environments can be procured using diverse approaches. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores two strategies for space partitioning when utilizing cascade-connected Artificial Neural Networks (ANNs) structures for indoor WLAN positioning. A set of cascade-connected ANN structures with different space partitioning strategies are compared mutually and to the single ANN structure. The benefits of using cascade-connected ANNs structures are shown and discussed in terms of the size of the environment, number of subspaces and partitioning strategy. The optimal cascade-connected ANN structures with space partitioning show up to 50% decrease in median error and up to 12% decrease in the average error with respect to the single ANN model. Finally, the single ANN and the optimal cascade-connected ANN model are compared against other well-known positioning techniques.     

White blood cell detection using saliency detection and CenterNet: A two-stage approach

White blood cell (WBC) detection plays a vital role in peripheral blood smear analysis. However, cell detection remains a challenging task due to multi-cell adhesion, different staining and imaging conditions. Owing to the powerful feature extraction capability of deep learning, object detection methods based on convolutional neural networks (CNNs) have been widely applied in medical image analysis. Nevertheless, the CNN training is time-consuming and inaccuracy, especially for large-scale blood smear images, where most of the images are background. To address the problem, we propose a two-stage approach that treats WBC detection as a small salient object detection task. In the first saliency detection stage, we use the Itti's visual attention model to locate the regions of interest (ROIs), based on the proposed adaptive center-surround difference (ACSD) operator. In the second WBC detection stage, the modified CenterNet model is performed on ROI sub-images to obtain a more accurate localization and classification result of each WBC. Experimental results showed that our method exceeds the performance of several existing methods on two different data sets, and achieves a state-of-the-art mAP of over 98.8%.     

Localization algorithm in wireless sensor networks based on semi-supervised manifold learning and its application

Localization of mobile nodes in wireless sensor network gets more and more important, because many applications need to locate the source of incoming measurements as precise as possible. Many previous approaches to the location-estimation problem need know the theories and experiential signal propagation model and collect a large number of labeled samples. So, these approaches are coarse localization because of the inaccurate model, and to obtain such data requires great effort. In this paper, a semi-supervised manifold learning is used to estimate the locations of mobile nodes in a wireless sensor network. The algorithm is used to compute a subspace mapping function between the signal space and the physical space by using a small amount of labeled data and a large amount of unlabeled data. This mapping function can be used online to determine the location of mobile nodes in a sensor network based on the signals received. We use independent development nodes to setup the network in metallurgical industry environment, outdoor and indoor. Experimental results show that we can achieve a higher accuracy with much less calibration effort as compared with RADAR localization systems.     

SILIC: A cross database framework for automatically extracting robust biodiversity information from soundscape recordings based on object detection and a tiny training dataset

• 1.Passive acoustic monitoring (PAM) offers many advantages comparing with other survey methods and gains an increasing use in terrestrial ecology, but the massive effort needed to extract species information from a large number of recordings limits its application. The convolutional neural network (CNN) has been demonstrated with its high performance and effectiveness in identifying sound sources automatically. However, requiring a large amount of training data still constitutes a challenge.
• 2.Object detection is used to detect multiple objects in photos or videos and is effective at detecting small objects in a complex context, such as animal sounds in a spectrogram and shows the opportunity to build a good performance model with a small training dataset. Therefore, we developed the Sound Identification and Labeling Intelligence for Creatures (SILIC), which integrates online animal sound databases, PAM databases and an object detection-based model, for extracting information on the sounds of multiple species from complex soundscape recordings.
• 3.We used the sounds of six owl species in Taiwan to demonstrate the effectiveness, efficiency and application potential of the SILIC framework. Using only 786 sound labels in 133 recordings, our model successfully identified the species' sounds from the recordings collected at five PAM stations, with a macro-average AUC of 0.89 and a mAP of 0.83. The model also provided the time and frequency information, such as the duration and bandwidth, of the sounds.
• 4.To our best knowledge, this is the first time that the object detection algorithm has been used to identify sounds of multiple wildlife species. With an online sound-labeling platform embedded and a novel data preprocessing approach (i.e., rainbow mapping) applied, the SILIC shows its good performance and high efficiency in identifying wildlife sounds and extracting robust species, time and frequency information from a massive amount of soundscape recordings based on a tiny training dataset acquired from existing animal sound databases. The SILIC can help expand the application of PAM as a tool to evaluate the state of and detect the change in biodiversity by, for example, providing high temporal resolution and continuous information on species presence across a monitoring network.

     

Echolocation of Multiple Targets in 3-D Space from a Single Emission

Using frequency-modulated echolocation sound, bat can capture a moving target in real three-dimensional (3-D) space. It is impossible to locate multiple targets in 3-D space by using only the delay time between an emission and the resultingechoes received at two points (i.e., two ears). To locate multiple targets in 3-D space requires directional information for each target. The spectrum of the echoes from nearly equidistant targets includes spectral components of both the interference between the echoes and the interference resulting from the physical process of reception at the external ear. The frequency of the spectral notch, which is the frequency corresponding to the minimum of the external ear's transfer function (EEDNF), provides a crucial cue for directional localization. In the model we present, a computational model todiscriminate multiple close targets in 3-D space utilizing echoes evoked by a single emission by distinguishing the interference of echoes from each object and the EEDNF corresponding to each target.     

Performance in three shell functions predicts the phenotypic distribution of hard‐shelled turtles

Adaptive landscapes have served as fruitful guides to evolutionary research for nearly a century. Current methods guided by landscape frameworks mostly utilize evolutionary modeling (e.g., fitting data to Ornstein–Uhlenbeck models) to make inferences about adaptive peaks. Recent alternative methods utilize known relationships between phenotypes and functional performance to derive information about adaptive landscapes; this information can then help explain the distribution of species in phenotypic space and help infer the relative importance of various functions for guiding diversification. Here, data on performance for three turtle shell functions–strength, hydrodynamic efficiency, and self‐righting ability–are used to develop a set of predicted performance optima in shell shape space. The distribution of performance optima shows significant similarity to the distribution of existing turtle species and helps explain the absence of shells in otherwise anomalously empty regions of morphospace. The method outperforms a modeling‐based approach in inferring the location of reasonable adaptive peaks and in explaining the shape of the phenotypic distributions of turtle shells. Performance surface‐based methods allow researchers to more directly connect functional performance with macroevolutionary diversification, and to explain the distribution of species (including presences and absences) across phenotypic space.     

A lightweight CNN-based model for early warning in sow oestrus sound monitoring

The reproductive performance of sows is an important indicator for evaluating the economic efficiency and production level of pigs. In this paper, we design and propose a lightweight sow oestrus detection method based on acoustic data and deep convolutional neural network (CNN) algorithms by collecting and analysing short-frequency and long-frequency sow oestrus sounds. We use visual log-mel spectrograms, which can reflect three-dimensional information, as inputs to the network model to improve the overall recognition accuracy. The improved lightweight MobileNetV3_esnet model is used to identify oestrus and nonoestrus sounds and is compared with existing algorithms. The model outperforms the other algorithms, with 97.12% precision, 97.34% recall, 97.59% F1-score, and 97.52% accuracy; the model size is 5.94 MB. Compared with traditional oestrus monitoring methods, the proposed method can more accurately boost the vocal characteristics exhibited by sows in latent oestrus, thus providing an efficient and accurate approach for use in practical applications of oestrus monitoring and early warning systems on pig farms.     

基于深度学习与多层次信息融合的药物靶标亲和力预测*

药物研发是非常重要但也十分耗费人力物力的过程。利用计算机辅助预测药物与蛋白质亲和力的方法可以极大地加快药物研发过程。药物靶标亲和力预测的关键在于对药物和蛋白质进行准确详细地信息表征。提出一种基于深度学习与多层次信息融合的药物靶标亲和力的预测模型,试图通过综合药物与蛋白质的多层次信息,来获得更好的预测表现。首先将药物表述成分子图和扩展连接指纹两种形式,分别利用图卷积神经网络模块和全连接层进行学习;其次将蛋白质序列和蛋白质K-mer特征分别输入卷积神经网络模块和全连接层来学习蛋白质潜在特征;随后将4个通道学习到的特征进行融合,再利用全连接层进行预测。在两个基准药物靶标亲和力数据集上验证了所提方法的有效性,并与其他已有模型作对比研究。结果说明提出的模型相比基准模型能得到更好的预测性能,表明提出的综合药物与蛋白质多层次信息的药物靶标亲和力预测策略是有效的。     

Adjustment for Missingness Using Auxiliary Information in Semiparametric Regression

Summary .  In this article, we study the estimation of mean response and regression coefficient in semiparametric regression problems when response variable is subject to nonrandom missingness. When the missingness is independent of the response conditional on high-dimensional auxiliary information, the parametric approach may misspecify the relationship between covariates and response while the nonparametric approach is infeasible because of the curse of dimensionality. To overcome this, we study a model-based approach to condense the auxiliary information and estimate the parameters of interest nonparametrically on the condensed covariate space. Our estimators possess the double robustness property, i.e., they are consistent whenever the model for the response given auxiliary covariates or the model for the missingness given auxiliary covariate is correct. We conduct a number of simulations to compare the numerical performance between our estimators and other existing estimators in the current missing data literature, including the propensity score approach and the inverse probability weighted estimating equation. A set of real data is used to illustrate our approach.     

Localization dominance and the effect of frequency in the Mongolian Gerbil, Meriones unguiculatus

Due to its good low-frequency hearing, the Mongolian Gerbil (Meriones unguiculatus) has become a well-established animal model for human hearing. In humans, sound localization in reverberant environments is facilitated by the precedence effect, i.e., the perceptual suppression of spatial information carried by echoes. The current study addresses the question whether gerbils are a valid animal model for such complex spatial processing. Specifically, we quantify localization dominance, i.e., the fact that in the context of precedence, only the directional information of the sound which reaches the ear first dominates the perceived position of a sound source whereas directional information of the delayed echoes is suppressed. As localization dominance is known to be stimulus-dependent, we quantified the extent to which the spectral content of transient sounds affects localization dominance in the gerbil. The results reveal that gerbils show stable localization dominance across echo delays, well comparable to humans. Moreover, localization dominance systematically decreased with increasing center frequency, which has not been demonstrated in an animal before. These findings are consistent with an important contribution of peripheral-auditory processing to perceptual localization dominance. The data show that the gerbil is an excellent model to study the neural basis of complex spatial-auditory processing.     

A Graphic Approach to Evaluate Algorithms of Secondary Structure Prediction

Abstract

Algorithms of secondary structure prediction have undergone the developments of nearly 30 years. However, the problem of how to appropriately evaluate and compare algorithms has not yet completely solved. A graphic method to evaluate algorithms of secondary structure prediction has been proposed here. Traditionally, the performance of an algorithm is evaluated by a number, i.e., accuracy of various definitions. Instead of a number, we use a graph to completely evaluate an algorithm, in which the mapping points are distributed in a three-dimensional space. Each point represents the predictive result of the secondary structure of a protein. Because the distribution of mapping points in the 3D space generally contains more information than a number or a set of numbers, it is expected that algorithms may be evaluated and compared by the proposed graphic method more objectively. Based on the point distribution, six evaluation parameters are proposed, which describe the overall performance of the algorithm evaluated. Furthermore, the graphic method is simple and intuitive. As an example of application, two advanced algorithms, i.e., the PHD and NNpredict methods, are evaluated and compared. It is shown that there is still much room for further improvement for both algorithms. It is pointed out that the accuracy for predicting either the α-helix or β-strand in proteins with higher α-helix or β-strand content, respectively, should be greatly improved for both algorithms.     

A stochastic compartment model representation of chronic disease dependence: Techniques for evaluating parameters of partially unobserved age inhomogeneous stochastic processes

Human disease states are commonly viewed in one of two ways. First, there is the clinical definition of disease as the presence or absence of a pathological condition. Second, there is the biologist's representation of disease as a point in a multivariate space of continuous physiological variables associated with suboptimal performance and survival. We present a model to represent dependency between multiple disease processes. The model is consistent with both concepts of disease and is designed to be estimated in the usual context of chronic disease information, i.e., a general lack of information about the time of disease incidence and progression. Consideration is made of the effects of individuals' differential susceptibility to disease and how these effects distinguish the disease incidence functions estimated at the individual level from those estimated for a population.     

Ecological niche modeling re‐examined: A case study with the Darwin's fox

Many previous studies have attempted to assess ecological niche modeling performance using receiver operating characteristic (ROC) approaches, even though diverse problems with this metric have been pointed out in the literature. We explored different evaluation metrics based on independent testing data using the Darwin's Fox (Lycalopex fulvipes) as a detailed case in point. Six ecological niche models (ENMs; generalized linear models, boosted regression trees, Maxent, GARP, multivariable kernel density estimation, and NicheA) were explored and tested using six evaluation metrics (partial ROC, Akaike information criterion, omission rate, cumulative binomial probability), including two novel metrics to quantify model extrapolation versus interpolation (E‐space index I) and extent of extrapolation versus Jaccard similarity (E‐space index II). Different ENMs showed diverse and mixed performance, depending on the evaluation metric used. Because ENMs performed differently according to the evaluation metric employed, model selection should be based on the data available, assumptions necessary, and the particular research question. The typical ROC AUC evaluation approach should be discontinued when only presence data are available, and evaluations in environmental dimensions should be adopted as part of the toolkit of ENM researchers. Our results suggest that selecting Maxent ENM based solely on previous reports of its performance is a questionable practice. Instead, model comparisons, including diverse algorithms and parameterizations, should be the sine qua non for every study using ecological niche modeling. ENM evaluations should be developed using metrics that assess desired model characteristics instead of single measurement of fit between model and data. The metrics proposed herein that assess model performance in environmental space (i.e., E‐space indices I and II) may complement current methods for ENM evaluation.     

Deep Convolution Neural Network Based System for Early Diagnosis of Alzheimer's Disease

ObjectivesAlzheimer's Disease (AD) is the most general type of dementia. In all leading countries, it is one of the primary reasons of death in senior citizens. Currently, it is diagnosed by calculating the MSME score and by the manual study of MRI Scan. Also, different machine learning methods are utilized for automatic diagnosis but existing has some limitations in terms of accuracy. So, main objective of this paper to include a preprocessing method before CNN model to increase the accuracy of classification.Materials and methodIn this paper, we present a deep learning-based approach for detection of Alzheimer's Disease from ADNI database of Alzheimer's disease patients, the dataset contains fMRI and PET images of Alzheimer's patients along with normal person's image. We have applied 3D to 2D conversion and resizing of images before applying VGG-16 architecture of Convolution neural network for feature extraction. Finally, for classification SVM, Linear Discriminate, K means clustering, and Decision tree classifiers are used.ResultsThe experimental result shows that the average accuracy of 99.95% is achieved for the classification of the fMRI dataset, while the average accuracy of 73.46% is achieved with the PET dataset. On comparing results on the basis of accuracy, specificity, sensitivity and on some other parameters we found that these results are better than existing methods.Conclusionsthis paper, suggested a unique way to increase the performance of CNN models by applying some preprocessing on image dataset before sending to CNN architecture for feature extraction. We applied this method on ADNI database and on comparing the accuracies with other similar approaches it shows better results.     

Signal enrichment with strain-level resolution in metagenomes using topological data analysis

Background

A metagenome is a collection of genomes, usually in a micro-environment, and sequencing a metagenomic sample en masse is a powerful means for investigating the community of the constituent microorganisms. One of the challenges is in distinguishing between similar organisms due to rampant multiple possible assignments of sequencing reads, resulting in false positive identifications. We map the problem to a topological data analysis (TDA) framework that extracts information from the geometric structure of data. Here the structure is defined by multi-way relationships between the sequencing reads using a reference database.

Results

Based primarily on the patterns of co-mapping of the reads to multiple organisms in the reference database, we use two models: one a subcomplex of a Barycentric subdivision complex and the other a Čech complex. The Barycentric subcomplex allows a natural mapping of the reads along with their coverage of organisms while the Čech complex takes simply the number of reads into account to map the problem to homology computation. Using simulated genome mixtures we show not just enrichment of signal but also microbe identification with strain-level resolution.

Conclusions

In particular, in the most refractory of cases where alternative algorithms that exploit unique reads (i.e., mapped to unique organisms) fail, we show that the TDA approach continues to show consistent performance. The Čech model that uses less information is equally effective, suggesting that even partial information when augmented with the appropriate structure is quite powerful.

     

LIMNOLOGICAL MODELLING: SIMULATION OF VERTICAL PROFILES OF TEMPERATURE,DISSOLVED OXYGEN AND NUTRIENTS. I. THEORY

SUMMARY

In a body of water, variations occur in all limnological parameters on many time and space scales. Modelling can either be specific - for a selected subset; or can attempt to simulate the gross characteristics of e.g. current, temperature, algal blooms over an annual cycle (or longer). Vertical profiles perhaps give the greatest information for assessment of water quality. For a lake in a given geographical location, the prevailing atmospheric climate (i.e. wind, rain, solar radiation) is reflected in the mean behaviour of the lake - the hydro climate. This hydroclimate is specified by a set of statistics: one for each limnological parameter; the simplest of these to model is temperature. The one-dimensional model used first to describe heat transfer is easily adapted to simulate distributions of dissolved oxygen (DO), Mn, P, N, etc. once their major sources and sinks have been identified and quantified.     

Short-term fast forecasting based on family behavior pattern recognition for small-scale users load

Household electricity consumption has been rising gradually with the improvement of living standards. Making short-term load forecasting at the small-scale users plays an increasingly important role in the future power network planning and operation. To meet the efficiency of the dispatching system and the demand of human daily power consumption, an optimal forecasting model Attention-CNN-GRU of small-scale users load at various periods of the day based on family behavior pattern recognition is proposed in this study. The low-level data information (smart meter data) is used to build the high-level model (small-scale users load). Attention mechanism and convolutional neural networks (CNN) can further enhance the prediction accuracy of gated recurrent unit (GRU) and notably shorten its prediction time. The recognition of family behavior patterns can be achieved through the users’ smart meter data, and users are aggregated into K categories. The results of optimal K category prediction under the family behavior model are summarized as the final prediction outcome. This idea framework is tested on real users’ smart meter data, and its performance is comprehensively compared with different benchmarks. The results present strong compatibility in the small-scale users load forecasting model at various periods of the day and swift short-term prediction of users load compared to other prediction models. The time is shortened by 1/4 compared with the GRU/LSTM model. Furthermore, the accuracy is improved to 92.06% (MAPE is 7.94%).