Specific Filter Research Articles

MON-302 ADMINISTRATION OF DAPAGLIFLOZIN IN TYPE 2 DIABETES MELLITUS PATIENTS WITH CHRONIC KIDNEY DISEASE: A SYSTEMATIC REVIEW

The increasing number of diabetes mellitus has led to an increase in the incidence of chronic kidney disease (CKD). Roughly, a third of all patients with diabetes mellitus also develop CKD as the disease progresses. Dapagliflozin, a sodium-glucose cotransporter-2 (SGLT-2) inhibitor, is the latest agent used in type 2 diabetes mellitus patients. The drug lower blood sugar levels by prevent glucose reabsorption in the proximal renal tubule. Inhibition of sodium reabsorption, on the other hand, manifested as an acute reduction in glomerular filtration rate (GFR) and albuminuria. This systematic review aims to analyze the clinical impact of dapagliflozin uses in type 2 diabetes patients with CKD. Interventional studies related to dapaglifozin administration in type 2 diabetes mellitus patients with chronic kidney disease were reviewed systematically. Inaugural literature searching was finished in four scientific databases (PubMed, EbscoHost, ProQuest, and Cochrane) using specific medical subheading (MeSH) terms and filters. Articles screened and selected by three authors independently to prevent bias. Studies that were relevant included to be further reviewed using tools provided by Centre for Evidence-based Medicine (CEBM). Two related articles were included in the review. Dapagliflozin was administered in a total of 441 type 2 diabetes mellitus patients with stages 3a-4 CKD. Study period ranged between 24-weeks to 104-weeks. Investigation reveals dapagliflozin considered as safe and effective in moderate renal impairment. However, the capacity of the drug to lower blood glucose levels tend to decrease in severe impaired renal function. This review draws to the conclusion that dapagliflozin administration may not improve glycemic index in diabetes mellitus patients with severe chronic kidney disease.

Paper-based metasurface: Turning waste-paper into a solution for electromagnetic pollution

Paper-based electronics offer a simple and cost-effective means to fabricate flexible devices. Here, we report an efficient pen-on-paper approach to construct metasurfaces on paper with silver units. Further, paper-based metasurfaces are employed to shield the electromagnetic interference which create new opportunities in turning waste paper into a solution for eliminating electromagnetic pollution. Experimental measurements and simulations show that waste paper-based metasurface manufactured in this way exhibits remarkable electromagnetic shielding properties with small thickness (thickness reduced more than 90% compared with that of traditional shielding materials), which makes it an ideal candidate for specific frequency electromagnetic filters. In addition, it can be readily extended to other regions of the electromagnetic spectrum, widened the shielding band by simply scaling the silver units' sizes and utilizing appropriate three-dimensional structures. Having taken performance into consideration, production is also taken into account. Paper-based shields offer both economic and energy benefits when considered on electronic printing, in addition, environment friendly nature and pliability of paper as well as simple fabrication procedure make paper-based metasurfaces promising candidates for the future ‘green’ electronics.

Experimental Implementation and Theoretical Investigation of a Vanadium Dioxide Optical Filter for Bit Error Rate Enhancement of Enhanced Space Shift Keying Visible Light Communication Systems

Visible Light Communication (VLC) systems use light-emitting diode (LED) technology to provide high-capacity optical links. The advantages they offer, such as the high data rate and the low installation and operational cost, have identified them as a significant solution for modern networks. However, such systems are vulnerable to various exogenous factors, with the background sunlight noise having the greatest impact. In order to reduce the negative influence of the background noise effect, optical filters can be used. In this work, for the first time, a low-cost optical vanadium dioxide (VO2) optical filter has been designed and experimentally implemented based on the requirements of typical and realistic VLC systems in order to significantly increase their performance by reducing the transmittance of background noise. The functionality of the specific filter is investigated by means of its bit error rate (BER) performance estimation, taking into account its experimentally measured characteristics. Numerous results are provided in order to prove the significant performance enhancement of the VLC systems which, as it is shown, reaches almost six orders of magnitude in some cases, using the specific experimental optical filter.

Identification of Clinical Indicators of Opioid Overdose using innovative EMS software analytics.

ObjectiveTo develop a set of clinical indicators of opioid overdose using Emergency Medical Services (EMS) records that included data from Computer Aided Dispatch (CAD), ProQA systems, Electronic Patient Care Reporting (ePCR) and Hospital Medical Records.IntroductionIn North America we experience the highest rate of drug related mortality in the world. In the US, overdose is now the leading cause of death among adults under 50. Each day more than 115 people in the United States die due to an opioid overdose. The opioid overdose national crisis is rapidly evolving due to changes in drug availability and the presence of adulterated fentanyl in some areas leading to a critical need for innovative methods to identify opioid overdoses for both surveillance and intervention purposes. As an effort to strengthen our understanding of the epidemic through surveillance of Emergency Medical Services (EMS) we have developed a set of clinical indicators that identify opioid overdose within the information provided by an Electronic Patient Care Reporting (ePCR), Computer Aided Dispatch (CAD), ProQA systems and Hospital Medical Records.MethodsWe initially created a set of EMS agency specific opioid overdose filters using FirstWatch® software as part of a public health research study. Following that initial development, we have built a generic set of opioid overdose identifiers. In the initial approach we used a Zoll Data System software for ePCR and TriTech Inform CAD to define 3 set of identifiers: (T1) captured calls in which naloxone was administered and a positive clinical response was documented, (T2) had the same criteria as T1 except there was no positive response to the administration of naloxone, and (T3) consisted of calls in which one or more drug-related keywords were present within the narrative of the ePCR. Because the initial analysis was conducted in the context of a single research study, we aimed to create a more generalizable set of identifiers of opioid overdose that would function across different EMS agencies, software, and data sources. In addition, we included variables provided by Hospital Medical Records to our filtering criteria to provide a more robust and complete set of opioid overdose clinical indicators.ResultsUtilizing the EMS data sources CAD, ProQA and ePCR as well as Hospital Medical Records we have developed a set of identifiers of opioid overdose. Utilizing FirstWatch® software analytics the following variables where coded into the software: 1. CAD Data.- Chief Complaint and Opioid Overdose Keyword search; 2. ProQA.- Protocols 6, 9, 23, 31 and 32; 3. ePCR.- Primary and Secondary Impressions, Chief Complaint, Intervention of Narcan (Naloxone) Administration, Vital Signs and Opioid Overdose Keyword search; 4. Medical Records.- Patient's Admission and Discharge Diagnosis (Diagram 1). The clinical indicators obtained from this analysis where created to be utilized across different EMS specific software vendors for CAD, ProQA and ePCR systems. For the Medical Records variables a single software vendor was available to be integrated into the analysis. Nonetheless, as we used the International Statistical Classification of Diseases and Related Health Problems codes on their 10th revision (ICD-10) our determining variable codes could be generalized to other Hospital Record system if they would become available.ConclusionsCorrectly identifying an opioid overdose can a be a challenge. Its clinical features are non-specific and bystanders fear repercussions of disclosing the nature of the 911 call. Determining the correct number of opioid overdoses requires a tailored identification process. A combination of clinical determinants and incorporation of multiple EMS data sources appears to be feasible in determining opioid overdose related 911 calls.

PSY9 COST-EFFECTIVENESS ANALYSIS OF BIOLOGIC AGENTS IN THE TREATMENT OF MODERATE-TO-SEVERE PSORIASIS: A SYSTEMATIC LITERATURE REVIEW

BACKGROUND: Psoriasis is a chronic, noncommunicable disease that has a great negative impact on patients’ quality of life. Moderate-to-severe disease occurs in approximately 30% оf patients, and biologics are the main treatment option in this case. Elevated biologic treatment expenses can become a significant socioeconomic burden for both individuals and the overall health-care system. Cost-effectiveness analysis helps to determine optimal biologic treatment options that fall within the cost-effectiveness threshold. The aim of the study was to systematically review the current literature on the cost-effectiveness analysis (CEA) of existing biologics for the treatment of moderate-to-severe psoriasis, assess the articles’ quality, and summarize the main characteristics of the models, inputs and results. We used specific search strategies and filters to analyze publications in Pubmed, Cochrane library, e-library and Google Scholar. Only studies in English and Russian were included into analysis. All references within the relevant review articles were examined manually. To evaluate the quality of articles, we used Consolidated Health Economic Evaluation Reporting Standards (CHEERS) Checklist and the Quality of Health Economic Studies (QHES) instruments. Main study attributes such as the type of economic model, assumptions, effectiveness outcomes, cost measures, time horizon, and perspective, were summarized and presented in tables. Overall, twenty-two articles were included in the final review: ten of them (45%) utilized empirical economic evaluations over 12 to 54 weeks period; eight articles (36%) used Markov models with timeline from 3 years to life span. Most of these studies originated from the United States (27%) and the UK (18%). The most popular biologic agents used in the cost-effectiveness analyses were adalimumab, infiximab, ustekinumab, and etanercept. Treatment sequences with adalimumab and ustekinumab were the most cost-effective. This study provides an overview of the main characteristics of the cost-effectiveness analyses of biologic agents used to treat moderate-to-severe psoriasis.

Method of fluorescence polarization for a new alternative tool for investigation of cooking oil and lard

Testing the quality of cooking oil is very important, especially to ensure the quality and identification of other unexpected mixture of cooking oil. In this paper, the fluorescence polarisation method will be used to test the presence of lard contamination on cooking oil. Fluorescence polarization is similar to fluorescence intensity, in that it is based on the emission of light by an excited fluorophore. However, samples are excited by polarized light which is selected by specific polarizing filters. The angle of linearly polarized incoming light was adjusted by using a polarizer. The change of fluorescent polarization angle was measured by using a second polarizer (analyzer) to obtain a relation between θ-value and φ-value for all samples. The samples were various edible oils, i.e., chicken oil, lard, and canola oil. The test is carried out by measuring the change in the average polarization angle of the fluorescent light to the polarizing angle of each incoming light over the sample directly. The results of the critical angle showed that all three samples were characteristic. Chicken oil has φc = 20° with θAv = 11.28° to 13.63°, lard has φc = 40° with θAv = 7.13° to 9.51°, whereas canola oil has φc = 30° with θAv = 2.59°. These results show that the fluorescence polarization method has a good prospect for oil contamination test on cooking oil.

Label-Free Fried Starchy Matrix: Investigation by Harmonic Generation Microscopy.

An innovative methodology based on non-destructive observation by using harmonic generation microscopy is proposed for detection and location of starch granules and oil in a fried starchy matrix and topography analysis of food products. Specific fluorescent probes were used to label the main biochemical components of the starchy fried matrix, namely starch and oil. Fluorescence of starch and oil respectively stained with Safranin O and Nile red was observed from non-linear microscopy. By using sequential scanning and specific emission filters, it was possible to merge fluorescence and harmonic generation signals. Second harmonic generation (SHG) generated by starch granules was superposed with safranin fluorescence, whereas third harmonic generation (THG), not restricted to the superposition with Nile red fluorescent signal, was used to investigate the topography of the fried product. By these experiments, starch granule mapping and topography of the starchy fried product were obtained without any destructive preparation of the sample. This label-free approach using harmonic generation microscopy is a very promising methodology for microstructure investigation of a large panel of starchy food products.

A Study of Image Upsampling and Downsampling Filters

In this paper, a set of techniques used for downsampling and upsampling of 2D images is analyzed on various image datasets. The comparison takes into account a significant number of interpolation kernels, their parameters, and their algebraical form, focusing mostly on linear interpolation methods with symmetric kernels. The most suitable metrics for measuring the performance of upsampling and downsampling filters’ combinations are presented, discussing their strengths and weaknesses. A test benchmark is proposed, and the obtained results are analyzed with respect to the presented metrics, offering explanations about specific filter behaviors in general, or just in certain circumstances. In the end, a set of filters and parameters recommendations is offered based on extensive testing on carefully selected image datasets. The entire research is based on the study of a large set of research papers and on a solid discussion of the underlying signal processing theory.

A Sensorless Rotor Position Estimation Method Based on the Field Current Harmonic for an LCI-Fed EESM

In this paper, a sensorless rotor position estimation method based on the field current harmonic for a load-commutated inverter (LCI)-fed electrically excited synchronous motor (EESM) operating at zero or low speed is proposed. A detailed theoretical analysis and mathematical deduction are presented. The field current harmonic is used instead of the extra high-frequency signal injection. A reasonable harmonic frequency is selected, and a realizable field current control method is given. To simplify the complex signal processing and improve the measurement accuracy, a specific bandpass filter and a normalized quadrature phase-locked loop are designed. The phase change caused by the filters is compensated properly. The proposed approach is demonstrated through the simulation and experiment with a 15-kW LCI-fed EESM drive platform, confirming its feasibility and accuracy.

Uncertainty-Based IMU Orientation Tracking Algorithm for Dynamic Motions

With the recent technological advancement in low-cost wireless inertial motion trackers, measuring three-dimensional motion for biomechanics research becomes more facile. However, the methods of acceleration modeling in off-the-shelf filters do not hold for all movements in sports activities with significant and long-lasting accelerations. This paper presents a robust algorithm for orientation tracking in the presence of large active accelerations lasting longer than the maximum time the MEMS gyroscopes can solely keep track of the body orientation. We particularly model the uncertainty of active acceleration and take it into explicit account in an extended Kalman filter based orientation estimator for applying measurement updates accurately in dynamic motions such as sports activities. The proposed tracker also estimates the magnetic disturbances by using an uncertainty model to improve the heading estimation. Benchmarking the results with the Vicon Optical as ground truth and the MTw kit with a specific filter for body motion tracking shows the robustness of our method against variations of acceleration in different types of motion. Our tracker performs orientation estimation in real time with fast convergence during acceleration shocks and low root-mean-square error, particularly when experiencing large accelerations in periodic motions.

A tool for designing digital filters for the Hankel and Fourier transforms in potential, diffusive, and wavefield modeling

The open-source code fdesign makes it possible to design digital linear filters for the Hankel and Fourier transforms used in potential, diffusive, and wavefield modeling. Digital filters can be derived for any electromagnetic (EM) method, such as methods in the diffusive limits (direct current, controlled-source EM [CSEM]) as well as methods using higher frequency content (ground-penetrating radar [GPR], acoustic and elastic wavefields). The direct matrix inversion method is used for the derivation of the filter values, and a brute-force minimization search is carried out over the defined spacing and shifting values of the filter basis. Included or user-provided theoretical transform pairs are used for the inversion. Alternatively, one can provide layered subsurface models that will be computed with a precise quadrature method using the EM modeler empymod to generate numerical transform pairs. The comparison of the presented 201 pt filter with previously presented filters indicates that it performs better for some standard CSEM cases. The derivation of a longer 2001 pt filter for a GPR example with a 250 MHz center frequency proves that the filter method works not only for diffusive EM fields but also for wave phenomena. The presented algorithm provides a tool to create problem specific digital filters. Such purpose-built filters can be made shorter and can speed up consecutive potential, diffusive, and wavefield inversions.

Sodium Fluorescein–Guided Surgery in Peripheral Nerve Sheath Tumors: First Experience in 10 Cases of Schwannoma

The intravenous application of sodium fluorescein (SF) for brain tumor surgery goes back to the late 1940s. The development of specific fluorophore filters significantly reduced the required dosage of SF and therefore diminished possible side effects. This study investigates the application of SF in benign peripheral nerve sheath tumors (PNSTs), concentrating on its feasibility during microsurgical removal. The single-center study includes 10 consecutive schwannoma cases operated on between September 2016 and March 2017. Inclusion criteria were defined as age ≥18 years, preoperative magnetic resonance imaging with suspicion of schwannoma, and final histopathologic confirmation of schwannoma. Exclusion criteria were a history of intolerance to SF and renal insufficiency. The microsurgical part of each surgery was video recorded, and the collected material was retrospectively analyzed. Red, green, and blue values of various regions of interest set on tumor and normal nerve of each patient were evaluated using ImageJ, an open platform for scientific image analysis. Digital video analysis confirmed the intraoperative impression of increased fluorescence of the tumor in contrast with normal nerve tissue. Because the color yellow is predominantly a mixture of red and green, values of these colors were significantly increased in schwannomas compared with normal nerve tissue (P= 0.0003 and P= 0.0023, respectively). SF reveals increased fluorescence in schwannomas compared with normal nerve tissue. Intraoperative differentiation of tumor and normal nerve tissue becomes possible using a low dose of SF (0.5-1 mg/kg). No side effects occurred. Secure microsurgical preparation is feasible during application of the YELLOW 560 nm filter.

An improved optical parameter optimisation approach using Taguchi and genetic algorithm for high transmission optical filter design

High transmission optical filters require specific filter characteristics and set of optimisation methods since precision in output performance plays a vital role in such applications. In this paper, an improved genetic algorithm approach to optimise high transmission optical filter is described. High transmission of around 99% in the wavelength region of 525–575 nm without any dips in between is the main performance requirement desired. The optimisation parameters are layer thickness, refractive index and number of layers and design wavelength is 550 nm in visible region. The method integrates the Taguchi method and genetic algorithm. First, Taguchi method is used to reduce the number of design experiments and find the minimum possible number of optimised set of values that represents the quality performance of the system. Then, genetic algorithm is applied to search the optimal design parameters. The performance is determined in terms of transmittance. Three levels for each optimisation parameter were considered. The total number of design experiments to be performed (in worst case) using genetic algorithm only with three optimisation variables and three levels is approximately 33 = 27 for obtaining the best design that matches the desired performance whereas Taguchi integrated genetic method helped in finding the best matching design with 9 design experiments. The best transmission performance was obtained for 24 layers, with thickness range 10–123.75 nm and high and low refractive index of 2.1 and 1.38. This method is a very robust approach that can be used for design parameter optimisation of optical filters for high transmission applications.

A Programmable Optical Filter With Arbitrary Transmittance for Fast Spectroscopic Imaging and Spectral Data Post-Processing

Spectral reconstruction method based on narrow-band measurements has been demonstrated to achieve ultrafast spectroscopic imaging with high spatial and spectral resolution, in which multiple narrow-band images are collected by using several specific filters. Although commercially available filters can be employed in such method, filters with complex transmittance that are difficult to be fabricated typically show significant improvement in spectral reconstruction accuracy. In this study, a two dimensional programmable optical filter based on digital micromirror device (DMD) is proposed, in which its transmittance spectrum can be arbitrarily and quickly switched to realize complex transmittance. Furthermore, its flexible transmittance enables directly hardware-based spectral data post-processing, which can perform data acquisition and analysis simultaneously. Those have been evaluated by the diffuse reflectance spectra from normal and occluded skin flaps, as well as Raman spectra from live, apoptosis and necrosis leukemia cells. Our simulation results show that much higher spectral reconstruction accuracies can be achieved by the optimized filters with complex transmittance. Furthermore, the classification accuracy by using the proposed method is comparable to those achieved by conventional numerical methods. Therefore, based on the proposed programmable optical filter, fast spectroscopic imaging with high spatial and spectral resolution can be achieved for observing fast changing phenomena and even real-time target identification.

Macrocyclic host appended carbon nanotubes for selective adsorption of metal ions: combined experimental, DFT and MD studies

Crown ethers are very useful for metal ion recognition due to their nanocavity based specific ion selectivity, which on functionalization with carbon nanotubes (CNTs) can be employed as specific metal ion filters by exploiting their different interactions with metal ions.

Improved IMC-Filter Design to IMC-PI Equivalence: Application to Quadrotor

This paper proposes a method to reach the equivalence between an IMC and a PI controller regardless of the model order. To this end, the key idea consists of using a specific IMC filter that exhibits a good level of robustness and further leads to get a structure of a PI controller whatever the order of the model is. The developed procedure constitutes the main contribution of this paper. To meet given set of specifications, the controller parameters are tuned through a straightforward analytic way using the dynamics of the tracking error. Furthermore, in order to evaluate the efficiency level of this procedure, an application to control an autonomous vehicle is described and the simulation results are shown to be satisfactory.

¿Cómo se construye la noción de ciencia social latinoamericana desde Scopus? Convergencia entre ensayo y análisis categórico

The purpose of the text is to elucidate the type of writing by which the notion of social sciences is constructed in Latin America once the 21st century has begun. Through an systematic review since the Scopus platform, specific search filters were applied to fulfill the objective. Throwing in first instance 368 publications and after selecting 23 publications according to their thematic relevance in relation to articles that account for the discussion in the theoretical and epistemological construction of the notion of social sciences between 2000 and 2017, it is concluded that both the essay - understood as a theoretical discursive structure of intellectual vocational guidance -, as well as the analysis of categorical variables, are the main resources of writing and analysis, by which we can account for the discussion regarding the notion of social sciences where epistemological discussion and scientometric studies give account of a reflection of the study area.

Experiments on filtering nano-aerosols from vehicular and atmospheric pollutants under dominant diffusion using nanofiber filter

Nano-aerosols of size 100 nm and below are manifested everywhere in various urban micro-environments. In outdoor, the vehicular emission during traffic jam can release nano-aerosols with concentration above 200 million/m3 (200/cm3). Superimposed on vehicular emission are smog particles, around 10–50 nm, generated from the photochemical reaction of hydrocarbon and NOx in the presence of sunlight. These nano-aerosols, by virtue of their small sizes, can be inhaled readily into our bodies leading possibly to various chronic diseases. Air-borne viruses from influenza to epidemic viruses, which can lead to acute sickness and even death, are also in the same size range of 100 nm.Despite microfibers are being commonly used today in filters, there has been limited studies on filtration of real aerosols using microfiber filters, let alone nanofibrous filters, as most studies used simulated aerosols (e.g. sodium chloride) or test dust. Also, in standard sodium chloride test, only monodispersed aerosol size is allowed to challenge the filter. On the other hand, in reality aerosols of all sizes challenge simultaneously the filter. In this study, for the first time we have used nanofiber filter in a portable test filter set-up to filter polydispersed aerosols from the micro-environment near busy traffic area where aerosols comprise of both vehicular and atmospheric pollutants with size range between 10 and 400 nm. Real-time measurements are carried out with the portable test filter. The test results are compared to the theoretical correlation from Payet with diffusion correction at small Peclet number (Pe). We have found good comparison between test results with theoretical correlations using equivalent aerodynamic diameter for the aerosols with face velocity from 1 to 11 cm/s. A new dimensionless parameter, specific filter resistance (also established independently by Buckingham-π approach), is defined for the first time. It measures the flow drag on fibers to the amount of fibers present in the filter, the lower is the specific filter resistance the better is the filter. For our test condition, it is approximately 1.0–1.2. We have also improved the filtration efficiency of the filter by increasing the fiber basis weight by stacking up two layers of nanofibers. We have demonstrated that the efficiency increases while both the quality factor and specific filter resistance remain constant. We have also investigated the single fiber efficiency due to diffusion and found that at low velocity and low Peclet number (Pe < 10), the test results agree well with the theoretical prediction. On the other hand, at higher face velocity (>0.07 m/s) and large Peclet number (>10), there is small deviation from the theory, which is probably due to the smaller aerosols collecting by the larger aerosols upstream of the filter with an airstream consisting of polydispersed aerosol distribution challenging the filter. This has not been realized previously as tests conducted were mostly using monodispersed aerosol size distribution for which aerosol-aerosol interaction was absent.

Retrogression of correlation filters for discriminative visual object tracking

Although discriminative correlation filter-based (DCF) trackers have shown excellent performance in recent years, it still has the problem of model drift. A generic approach alleviating model drift is proposed for DCF tracking. Specific correlation filters are learned in feature channels and the combination of response maps depends on the confidence level of corresponding channels. Model drift is eliminated by allowing contaminated correlation filters to retrogress to the ones that are not influenced by impure samples. As a result, correlation filters are purified by neglecting the impure part of them. Meanwhile, both the confidence level of detection and the variant level of interframe feature space are considered during online update of correlation filters. Our approach is experimented on both OTB-50 and OTB-100 datasets. Especially on OTB-100, our approach outperforms the baseline fast discriminative scale space tracking by 6.9%, 8.1%, and 5.6% in mean distance precision, mean overlap precision, and the area-under-the-curve score, respectively. Moreover, the competitive performance is presented by comparing with other state-of-the-art tracking algorithms.

Utilizing Multilevel Features for Cloud Detection on Satellite Imagery

Cloud detection, which is defined as the pixel-wise binary classification, is significant in satellite imagery processing. In current remote sensing literature, cloud detection methods are linked to the relationships of imagery bands or based on simple image feature analysis. These methods, which only focus on low-level features, are not robust enough on the images with difficult land covers, for clouds share similar image features such as color and texture with the land covers. To solve the problem, in this paper, we propose a novel deep learning method for cloud detection on satellite imagery by utilizing multilevel image features with two major processes. The first process is to obtain the cloud probability map from the designed deep convolutional neural network, which concatenates deep neural network features from low-level to high-level. The second part of the method is to get refined cloud masks through a composite image filter technique, where the specific filter captures multilevel features of cloud structures and the surroundings of the input imagery. In the experiments, the proposed method achieves 85.38% intersection over union of cloud in the testing set which contains 100 Gaofen-1 wide field of view images and obtains satisfactory visual cloud masks, especially for those hard images. The experimental results show that utilizing multilevel features by the combination of the network with feature concatenation and the particular filter tackles the cloud detection problem with improved cloud masks.