Set Of Filters Research Articles

Automatic Classification of Images with Skin Cancer Using Artificial Intelligence

Skin cancer is the most common malignant neoplasty in the world, it is a public health problem, which has increased in recent years due to environmental changes, different lifestyles, sun exposure, among others. One way to detect skin cancer is by analyzing medical images, analyzing these images can get the detection of any abnormalities. In this paper, several block programming models are implemented with classifiers for the recognition of medical images of skin cancer. Preprocessing, manipulation, and computer vision to extract the relevant characteristics of the images are the starting point for obtaining appropriate classification values. The main objective of this project is to perform the analysis of a set of classification techniques, as well as to verify that combination of image processing operations and classification tools provide better performance compared to the classification values of the original images. Images of three kinds of skin cancer type were used: melanocytic nevi, melanoma, and benign lesions similar to keratosis. Each category contains 200 images. The images were subjected to a set of filters, to later use different classification algorithms. 6 types of filters and 5 different classification techniques were implemented. The results obtained allow us to see the feasibility of the proposed method.

Filter group delays equalization for 2D discrete wavelet transform applications

This paper presents a new approach to perform near-perfect image reconstruction for an online/real-time two-dimensional discrete wavelet transform (2D-DWT) analysis/synthesis applications, such as image enhancement, compression, and watermarking. The proposed new model is based on equalizing the cumulative filter group delays over all calculation paths by inserting appropriate delays. This model has been implemented in MATLAB/SIMULINK and compared to the default model using six wavelet-based filter sets and two dyadic decomposition/reconstructed levels. Peak signal-to-noise ratios (PSNRs) of images reconstructed by the proposed equalized model present an improvement of more than 60 dB, compared to those of images reconstructed by the default model.

A Parameterized Model for Differential Galaxy Counts at Any Wavelength

Abstract Certain astronomy problems, such as the probabilistic cross-matching algorithms of Wilson & Naylor, require descriptions of galaxy counts as a function of brightness in many different filter sets, for which we often lack dedicated observations. With this motivation in mind, I present a simple model for calculating differential galaxy counts for an arbitrary bandpass or wavelength. The model uses a double Schechter function to describe the number density of galaxies as a function of absolute magnitude, including redshift-driven galaxy evolution, for both “blue” and “red” galaxy types. Collating previously derived values for the parameterization of the evolving Schechter function— M 0 * , ϕ 0 * , P, Q, and α—I fit the dependencies of these parameters as a function of wavelength, allowing for the tabulation of differential galaxy counts in a new filter for which observations are unavailable. Finally, I briefly compare the model with some differential galaxy counts obtained from the literature.

On the Black-Box Challenge for Fraud Detection Using Machine Learning (I): Linear Models and Informative Feature Selection

Artificial intelligence (AI) is rapidly shaping the global financial market and its services due to the great competence that it has shown for analysis and modeling in many disciplines. What is especially remarkable is the potential that these techniques could offer to the challenging reality of credit fraud detection (CFD); but it is not easy, even for financial institutions, to keep in strict compliance with non-discriminatory and data protection regulations while extracting all the potential that these powerful new tools can provide to them. This reality effectively restricts nearly all possible AI applications to simple and easy to trace neural networks, preventing more advanced and modern techniques from being applied. The aim of this work was to create a reliable, unbiased, and interpretable methodology to automatically evaluate CFD risk. Therefore, we propose a novel methodology to address the mentioned complexity when applying machine learning (ML) to the CFD problem that uses state-of-the-art algorithms capable of quantifying the information of the variables and their relationships. This approach offers a new form of interpretability to cope with this multifaceted situation. Applied first is a recent published feature selection technique, the informative variable identifier (IVI), which is capable of distinguishing among informative, redundant, and noisy variables. Second, a set of innovative recurrent filters defined in this work are applied, which aim to minimize the training-data bias, namely, the recurrent feature filter (RFF) and the maximally-informative feature filter (MIFF). Finally, the output is classified by using compelling ML techniques, such as gradient boosting, support vector machine, linear discriminant analysis, and linear regression. These defined models were applied both to a synthetic database, for better descriptive modeling and fine tuning, and then to a real database. Our results confirm that our proposal yields valuable interpretability by identifying the informative features’ weights that link original variables with final objectives. Informative features were living beyond one’s means, lack or absence of a transaction trail, and unexpected overdrafts, which are consistent with other published works. Furthermore, we obtained 76% accuracy in CFD, which represents an improvement of more than 4% in the real databases compared to other published works. We conclude that with the use of the presented methodology, we do not only reduce dimensionality, but also improve the accuracy, and trace relationships among input and output features, bringing transparency to the ML reasoning process. The results obtained here were used as a starting point for the companion paper which reports on our extending the interpretability to nonlinear ML architectures.

Optimized spectral filter design enables more accurate estimation of oxygen saturation in spectral imaging.

Oxygen saturation (SO2) in tissue is a crucially important physiological parameter with ubiquitous clinical utility in diagnosis, treatment, and monitoring, as well as widespread use as an invaluable preclinical research tool. Multispectral imaging can be used to visualize SO2 non-invasively, non-destructively and without contact in real-time using narrow spectral filter sets, but typically, these spectral filter sets are poorly suited to a specific clinical task, application, or tissue type. In this work, we demonstrate the merit of optimizing spectral filter sets for more accurate estimation of SO2. Using tissue modelling and simulated multispectral imaging, we demonstrate filter optimization reduces the root-mean-square-error (RMSE) in estimating SO2 by up to 37% compared with evenly spaced filters. Moreover, we demonstrate up to a 79% decrease in RMSE for optimized filter sets compared with filter sets chosen to minimize mutual information. Wider adoption of this approach will result in more effective multispectral imaging systems that can address specific clinical needs and consequently, more widespread adoption of multispectral imaging technologies in disease diagnosis and treatment.

A filter-based Raman spectrometer for non-invasive imaging of atmospheric water vapor.

A new instrument was designed and developed to map the spatial distribution of water vapor concentration in the atmosphere. The high spatial resolution, sensitivity, and accuracy of the instrument enable new studies of the role of turbulence on clouds and aerosols in small-scale laboratory environments. The instrument exploits Raman scattering in a multi-pass laser configuration by using a set of narrow bandpass filters and a pair of charge coupled device imaging cameras in the 90° scattering geometry. The absolute concentration of water vapor was inferred from measured ratios of H2O and N2 vibrational Raman transitions. We have measured the number densities of water molecules in the atmosphere as low as 3.5 × 1017 cm-3, with an accuracy better than 20% and as high as 7.0 × 1017 cm-3 during minutes long observations. These measurements were taken within an imaging region 6cm in diameter, with a per-pixel resolution 2.60mm wide by 0.16mm tall and 1mm deep.

Field Evaluation of Transmit Diversity Code Filter Sets in ATSC 3.0 Single Frequency Networks

Advanced Television Systems Committee (ATSC) 3.0, a recently developed terrestrial broadcasting standard, supports a Single Frequency Network (SFN), which extends service coverage and enhances received field strength without additional frequency resources. In SFN, multiple transmitters emit identical ATSC 3.0 broadcasting signals, which may cause constructive or destructive interference on a receiver side. The worst situation occurs when two signals from different transmitters are received with the opposite phase and similar power within a sample time, causing the cancellation of the received signal. In order to prevent such signal cancellation, ATSC 3.0 adopted transmitter diversity code filter sets (TDCFS), which is a frequency domain pre-distortion scheme to minimize cross-correlation among multiple transmitter signals in SFN. This paper sets up an ATSC 3.0 SFN consisting of two transmitter sites, transmitting high definition (HD) for mobile service and 4K ultra high definition (UHD) for fixed service. Layered division multiplexing (LDM) and time division multiplexing (TDM) are used to simulcast the two services with different robustness in the same radio frequency (RF) channel. Then, performance is evaluated using a threshold of visibility (ToV) and a successful reception rate. The time and frequency channel responses are changed at the same reception area when TDCFS is applied so the results show that reception performance is improved in the worst situation in SFN.

Real-Time Tracking Algorithm for Aerial Vehicles Using Improved Convolutional Neural Network and Transfer Learning

To address the poor image feature extraction ability, excessive tracking time, and low accuracy of traditional real-time algorithms for aerial tracking of vehicle traffic, a real-time tracking algorithm using improved convolutional neural network (CNN) and transfer learning was proposed herein. In this algorithm, first, the aerial vehicle images are matched with sample images for the image offset calibration. Second, the CNN parameters are initialized by constructing a filter set, and transfer learning is employed to construct a CNN pre-training model. Third, a deep convolution feature extraction structure map is designed to extract the depth features of images. Finally, based on the depth features, the target vehicle motion model is established, the similarity between the target and candidate models is calculated, and the real-time tracking of aerial vehicles is completed. The results show that the image correction accuracy of the proposed algorithm is as high as 92%. The algorithm yields satisfactory results in terms of feature extraction and calculation accuracy. Moreover, it has a small overall error, the average tracking time required by it is only 22.8 s, and its false negative rate is as low as 0.4%. Therefore, the proposed algorithm has considerable potential practical application.

Inexpensive multispectral imaging device

Multi/hyperspectral imaging is an important technique to obtain color data and spectral monitoring. It is a precise remote sensing technique that includes two or more bands in the visible and invisible spectrum. This study demonstrates the design and construction of a low-cost, multispectral imaging system using a single linear array sensor and a varifocal lens coupled to individual spectral band-pass filters. The system allows the automated data acquisition of raw spectral data for seven spectral bands, each with different wavelengths. The raw data are visualized in real-time to generate images of spectral bands to obtain the desired spectral information on the computer graphical screen. Sensor arrays with spectral responsivity between 0.3 and 1.05 μm and motorized filter disks with a linear guide are used for acquiring data from specific wavelengths. Axis movement of the imaging device is achieved by a linear guide for spatial monitoring. Seven different bands are scanned and transferred to the computer via motorized band-pass filter sets with the imaging device. The multispectral imaging device has high accuracy with a 0.9936 linear correlation coefficient (r2) and averaged noise of the total system is below 1% (0.7%). Although the present configuration uses seven spectral bands including visible and narrow bandpass optical filters to obtain multispectral information from an object, the system is designed to have a replaceable and selectable motorized rotating filter, easily remounted, and adjusted up to forty spectral bands with 20 nm full width at half maximum (FWHM).

Using multi-channel detector for simultaneous hyperspectral and flim imaging in strongly scattering media

We describe a method that allows imaging in scattering media, such as biological tissues, and perform multiplexed hyperspectral and FLIM analysis of these images. This method is based on a set of transmission filters placed in front of wide area 4-channel detector in the emission path of a fluorescence microscope. The special transmission filters with sin-cos or linear spectral profiles were used to resolve the emission wavelength in every pixel of an image. The set of filters are used to obtain the spectral phasor of the transmitted light, which is enough to perform spectral deconvolution over a broad wavelength range.

The effect of arrangement in multi-cyclone filters on performance and the uniformity of fluid and particle flow distribution

In this research, a design algorithm of a multi-cyclone filter box based on available volume is proposed. The influence of arranging cyclones in the box and the uniformity of fluid and particle flow distribution is also studied. After introducing domain physics, used governing equations are expressed. Grid generation and validation of the numerical solution are then examined. Design of the quantity, diameter, and performance parameters of the cyclone in the filter set is performed by presenting an algorithm. This study shows that adding only 10% to the volume of the filter box reduces the pressure drop by 40 to 50%. For filters consisting of many cyclones, the optimized arrangement of cyclones next to each other is introduced which can improve the standard deviation of flow distributions by 27.5%. Increasing the inlet flow rate can make the distribution of larger diameter particles among cyclones non-uniform by up to 85%.

Hybrid Symmetrical Uncertainty and Reference Set Harmony Search Algorithm for Gene Selection Problem

Selecting the most miniature possible set of genes from microarray datasets for clinical diagnosis and prediction is one of the most challenging machine learning tasks. A robust gene selection technique is required to identify the most significant subset of genes by removing spurious or non-predictive genes from the original dataset without sacrificing or reducing classification accuracy. Numerous studies have attempted to address this issue by implementing either a filter or a wrapper. Although the filter approaches are computationally efficient, they are completely independent of the induction algorithm. On the other hand, wrapper approaches outperform filter approaches but are computationally more expensive. Therefore, this study proposes an enhanced gene selection method that uses a hybrid technique that combines the Symmetrical Uncertainty (SU) filter and Reference Set Harmony Search Algorithm (RSHSA) wrapper method, known as SU-RSHSA. The framework to develop the proposed SU-RSHSA includes numerous stages: (1) investigate a novel gene selection method based on the HSA and will then determine appropriate values for the HSA’s parameters, (2) enhance the construction process of the initial harmony memory while satisfying the diversity of the solution by embedding a reference set within the HSA (RSHSA), and (3) investigates the effect of integrating Symmetrical Uncertainty (SU) as a filter and RSHSA as a wrapper (SU-RSHSA) to maximize classification accuracy by leveraging their respective advantages. The results demonstrate that the SU-RSHSA outperforms the original HSA and SU-HSA in terms of classification accuracy, a small number of selected relevant genes, and reduced computational time. More importantly, the proposed SU-RSHSA gene selection method effectively generates a small subset of salient genes with high classification accuracy.

3MRS: An Effective Coarse-to-Fine Matching Method for Multimodal Remote Sensing Imagery

The fusion of image data from multiple sensors is crucial for many applications. However, there are significant nonlinear intensity deformations between images from different kinds of sensors, leading to matching failure. To address this need, this paper proposes an effective coarse-to-fine matching method for multimodal remote sensing images (3MRS). In the coarse matching stage, feature points are first detected on a maximum moment map calculated with a phase congruency model. Then, feature description is conducted using an index map constructed by finding the index of the maximum value in all orientations of convolved images obtained using a set of log-Gabor filters. At last, several matches are built through image matching and outlier removal, which can be used to estimate a reliable affine transformation model between the images. In the stage of fine matching, we develop a novel template matching method based on the log-Gabor convolution image sequence and match the template features with a 3D phase correlation matching strategy, given that the initial correspondences are achieved with the estimated transformation. Results show that compared with SIFT, and three state-of-the-art methods designed for multimodal image matching, PSO-SIFT, HAPCG, and RIFT, only 3MRS successfully matched all six types of multimodal remote sensing image pairs: optical–optical, optical–infrared, optical–depth, optical–map, optical–SAR, and day–night, with each including ten different image pairs. On average, the number of correct matches (NCM) of 3MRS was 164.47, 123.91, 4.88, and 4.33 times that of SIFT, PSO-SIFT, HAPCG, and RIFT for the successfully matched image pairs of each method. In terms of accuracy, the root-mean-square error of correct matches for 3MRS, SIFT, PSO-SIFT, HAPCG, and RIFT are 1.47, 1.98, 1.79, 2.83, and 2.45 pixels, respectively, revealing that 3MRS got the highest accuracy. Even though the total running time of 3MRS was the longest, the efficiency for obtaining one correct match is the highest considering the most significant number of matches. The source code of 3MRS and the experimental datasets and detailed results are publicly available.

Statistical stegdetectors performance by message re-embedding

State-of-the-art stegdetectors for digital images are based on pre-processing (calibration) of analyzed image for increasing stego-to-cover ratio. In most cases, the calibration is realized by image processing with enormous set of high-pass filters to obtain good estimation of cover image from the stego one. Nevertheless, the efficiency of this approach significantly depends on careful selection of filters for reliably extraction of cover image alterations that are specific for each embedding method. The selection is non-trivial and laborious operation that is realized today by training of convolutional neural networks, such as Ye-Net, SR-Net to name but a few. The paper is devoted to performance analysis of alternative approach to image calibration, namely message re-embedding into analyzed image. The considered method is aimed to increasing stego-to-cover ratio by amplification of cover image alterations caused by message hiding. The analysis was performed on ALASKA and VISION datasets by usage of stegdetector based on SPAM model of covers. Messages were re-embedded according to state-of-the-art adaptive methods HUGO, S-UNIWARD, MG and MiPOD. Proposed approach allows significantly (up to 20%) decreasing detection error even in case of low payload of cover image (less than 10%) where modern stegdetectors are ineffective.

The study and analysis of using CMY color filter arrays for 0.8 um CMOS image sensors

Digital color cameras detect scenes through color filter array (CFA) of mosaic patterns. Among existing filter arrays in commercial CMOS image sensors (CIS), the CMY color filter set is one that is a more desirable choice for low-illuminating conditions. However, these color filters generally suffered from lower color fidelity than their counterpart RGB color filters. Nevertheless, the overall CIS performance were affected not only by the pigments used for color filters but also by the detailed structure designs and CFA arrangement of the pixel itself, we tends to explore the best combination for both the color filter materials and the pixel designs that will improve CIS performance for low light conditions that will have applications in astrophotography, low phototoxicity bioimaging, as well as general photography during dawn and dusk.

Kronecker Product Multichannel Linear Filtering for Adaptive Weighted Prediction Error-Based Speech Dereverberation

Reverberation, whichis caused by late reflections, impairs not only speech quality but also intelligibility. Consequently, dereverberation, a process to mitigate the impact of reverberation, has attracted significant research interests. Numerous approaches have been developed in the literature, among which the weighted-prediction-error (WPE) one has demonstrated promising potential for reducing or eliminating reverberation. The WPE method has been well studied and several variants have been developed. The adaptive one, called adaptive WPE (AWPE) method, has been widely investigated for use in real applications as it can deal with reverberation in time-varying acoustic environments. However, the computational complexity of AWPE is high, which may be a problem for its implementation in real-time systems. This paper presents some new insights into AWPE-based speech dereverberation by introducing the concepts of Kronecker product and partially time-varying filtering. It then develops two algorithms for dereverberation with lower complexity than AWPE. The significant contributions of this work are as follows. First, we propose a Kronecker product filtering framework for speech dereverberation, where the linear prediction filter is formulated as the Kronecker product of two sets of shorter filters. Second, we propose a partially time-varying Kronecker product filter for dereverberation. Instead of estimating the entire linear prediction filter as in the conventional method, the proposed one only needs to update part of the filter. The proposed approaches can significantly reduce the computational complexity without sacrificing dereverberation performance as compared to AWPE. Simulation results validate the theoretical analysis and justify the advantages of the new methods.

МОДЕРНІЗАЦІЯ АСТРОНОМІЧНОГО КОМПЛЕКСУ СПОСТЕРЕЖНОЇ СТАНЦІЇ ЛІСНИКИ

The Lisnyky observation station (international code 585) is actively used for observations of small bodies and for educational purpose. The station operates two telescopes AZT-8 (D=700 mm, F=2830 mm, D/F=1:4) and AZT-14 (D=480 mm, F=7715 mm, D/F=1:16). They have an outdated design and need to be modernized to meet the modern requirements of observational astronomy. The world practice of modernizing optical telescopes is reduced, as a rule, to installing new modern light receivers, changing the optical system, improving optical characteristics by aluminizing mirrors. Light receivers are now CCD image sensors, the use of which allows you to significantly increase the penetrating power (to observe fainter objects) and the temporal and spatial resolution of telescopes. Modern light receivers are equipped with automatic filter units with various sets of astronomical filters. Different sets of light receivers are used for different tasks of observational astronomy. The concept of modernization of the observation complex based on the AZT-14 and AZT-8 telescopes was developed according to these modern requirements. A new Moravian C4-16000ES CMOS camera (4096 × 4096 pixels, 9 × 9 μm) with a UBVRI light filter unit of the Johnson-Cousins photometric system was installed at the main focus of the AZT-8 telescope in 2021. In this version, the telescope is used to monitor small bodies and search for new comets and asteroids, photometric and positional observations of comets, observations of active galactic nuclei. An optical reducer (4.5 times reduction focal length) with a block of broadband light filters BVRI light filters was developed and manufactured for the AZT-14 telescope in order to increase the field of view on the CCD array, reduce the size of star images and increase the light power of the telescope. A new block of 8 comet narrowband filters, which is used with the Apogee Alta U47 CCD camera, was designed and manufactured for observations of comets. An electronic control system, which includes the following main electronic components: a light filter position sensor board, an electronic board, a stable frequency generator, a stepper motor driver, a controller for controlling all electronic components and for communication with a personal computer, was developed and manufactured for control the unit.

A simple method of UV stray light correction for field spectrometers in Ground Validation Sites

Field spectrometers are widely applied in ground validation sites for remote sensing. However, the control of stray light is one of the most important factors to ensure accurate measurements, since the spectral distribution of target source differs significantly from the laboratory calibration source. Here, a simple UV stray light correction method for continuously distributed wide-spectrum light sources was established by using a set of bandpass filters. This analysis enabled a simple, low-cost method for correcting for the observed straylight.

TRACKING THE DYNAMICS OF LECTURER RATING INDICATORS TO ENSURE THE QUALITY OF HIGHER EDUCATION

The importance of the role of the lecturer in ensuring the quality of higher education cannot be denied. The system of internal quality assurance provides for the availability of developed and published criteria, rules, and procedures for the evaluation of academic and research staff, as well as their annual review by European standards, the Law of Ukraine "On Higher Education", recommendations of the National Agency for Higher Education Quality Assurance. Borys Grinchenko Kyiv University has developed a lecturer rating system "E-portfolio", one of the components of the information and educational environment, to form the qualitative composition of the scientific and pedagogical staff. To analyze the activities of the academic staff and all departments of Grinchenko University, several types of reports were presented in the "E-portfolio" system, which can be built according to such criteria as the main activities, rating points, structural units, positions, academic rank, degree, etc. For several years, only built-in statistics were used to analyze the activities of lecturers and units, but there was a need to monitor more detailed dynamics of all indicators. Modern business intelligence tools were analyzed for the development of visualization. It was decided to use the Power BI business intelligence tool, which will allow you to have a complete picture of the lecturer's performance by all the necessary criteria. The article presents an analytical report of Power BI based on the "Star Scheme" model. Thanks to the created "Measures" and standard functions of pivot tables, it became possible to visualize the input rating data and create details and filters for more convenient viewing and data analysis. After completing all the settings of visualization and filters, the report was published using the Power BI report server tool in the public domain. The use of this tool allows the top managers of the university to have a holistic picture of the results in the performance of employees and departments, as well as to determine the priorities of activities, to make fair decisions when extending contracts, which fully and unconditionally contributes to ensuring the quality of higher education.

Noise Reduction Methods for Charge Stability Diagrams of Double Quantum Dots

Operating semiconductor quantum dots as quantum bits requires isolating single electrons by adjusting gate voltages. The transitions of electrons to and from the dots appear as a honeycomb-like pattern in recorded charge stability diagrams (CSDs). Thus, detecting the pattern is essential to tune a double dot, but manual tuning is seriously time-consuming. However, automation of this process is difficult because the transitions’ contrast is often low, and noise and background disorder potential shifts disturb the CSDs. Therefore, the signal-to-noise ratio needs to be increased to improve the detection of the line pattern. For this purpose, we evaluate a representative set of edge-preserving smoothing filters and compare them both quantitatively and qualitatively by suitable metrics and visual assessment. We generate artificial data to use full-reference metrics for the evaluation procedure and to optimize the filter parameters. Based on the results of this article, the methods attain a moderate to good amount of noise reduction and structure improvement dependent on the different CSD qualities. In conclusion, we suggest introducing the block-matching and three-dimensional transform-domain filter into the automated tuning processing pipeline. If the data are corrupted by significant amounts of random telegraph noise, the bilateral filter and the rolling guidance filter are also good choices.