Standard Test Dataset Research Articles

U-track3D: Measuring, navigating, and validating dense particle trajectories in three dimensions

We describe u-track3D, a software package that extends the versatile u-track framework established in 2D to address the specific challenges of 3D particle tracking. First, we present the performance of the new package in quantifying a variety of intracellular dynamics imaged by multiple 3D microcopy platforms and on the standard 3D test dataset of the particle tracking challenge. These analyses indicate that u-track3D presents a tracking solution that is competitive to both conventional and deep-learning-based approaches. We then present the concept of dynamic region of interest (dynROI), which allows an experimenter to interact with dynamic 3D processes in 2D views amenable to visual inspection. Third, we present an estimator of trackability that automatically defines a score for every trajectory, thereby overcoming the challenges of trajectory validation by visual inspection. With these combined strategies, u-track3D provides a complete framework for unbiased studies of molecular processes in complex volumetric sequences.

Critically synchronized brain waves form an effective, robust and flexible basis for human memory and learning

The effectiveness, robustness, and flexibility of memory and learning constitute the very essence of human natural intelligence, cognition, and consciousness. However, currently accepted views on these subjects have, to date, been put forth without any basis on a true physical theory of how the brain communicates internally via its electrical signals. This lack of a solid theoretical framework has implications not only for our understanding of how the brain works, but also for wide range of computational models developed from the standard orthodox view of brain neuronal organization and brain network derived functioning based on the Hodgkin–Huxley ad-hoc circuit analogies that have produced a multitude of Artificial, Recurrent, Convolution, Spiking, etc., Neural Networks (ARCSe NNs) that have in turn led to the standard algorithms that form the basis of artificial intelligence (AI) and machine learning (ML) methods. Our hypothesis, based upon our recently developed physical model of weakly evanescent brain wave propagation (WETCOW) is that, contrary to the current orthodox model that brain neurons just integrate and fire under accompaniment of slow leaking, they can instead perform much more sophisticated tasks of efficient coherent synchronization/desynchronization guided by the collective influence of propagating nonlinear near critical brain waves, the waves that currently assumed to be nothing but inconsequential subthreshold noise. In this paper we highlight the learning and memory capabilities of our WETCOW framework and then apply it to the specific application of AI/ML and Neural Networks. We demonstrate that the learning inspired by these critically synchronized brain waves is shallow, yet its timing and accuracy outperforms deep ARCSe counterparts on standard test datasets. These results have implications for both our understanding of brain function and for the wide range of AI/ML applications.

Deep learning-based spam image filtering

Spam is some unwanted material that may be put in the form of images. While many machine learning approaches are effective at detecting textual spam, this is not true for image spam. In this paper, a new framework for identifying image spams is proposed. The images are divided into two categories: undesirable material contained in the form of images which is referred to as a spam image, whereas anything else is referred to as a ham image. Our proposed methodology is based on applying different pre-trained deep learning models, including InceptionV3, Densely Connected Convolutional Networks 121(DenseNet121), Residual Networks (ResNet50), Visual Geometry Group (VGG16) and MobileNetV2, to filter out the unwanted spam images. Different standard test datasets such as Dredze Dataset, Image Spam Hunter (ISH) Dataset and Improved Dataset are utilized in this paper for performance testing. Furthermore, transfer learning and data augmentation are employed to address the issue of a shortage of labeled data. In our implementation, the fully connected (FC) layer in the aforementioned pre-trained models is replaced with a Support Vector Machine (SVM) classifier, resulting in an improved accuracy. The obtained results reveal that ResNet50 model yields the best performance achieving 99.87% accuracy, 99.88% area under the curve (AUC), 99.98% sensitivity, 99.79% precision, 98.99% F1 score and a computational testing time of in the order of one to two seconds for the ISH dataset.

SPCM: Efficient semi-possibilistic c-means clustering algorithm

The required division and exponentiation operations needed per iteration for the possibilistic c-means (PCM) clustering algorithm complicate its implementation, especially on homomorphically-encrypted data. This paper presents a novel efficient soft clustering algorithm based on the possibilistic paradigm, termed SPCM. It aims at easing future applications of PCM to encrypted data. It reduces the required exponentiation and division operations at each iteration by restricting the membership values to an ordered set of discrete values in [0,1], resulting in a better performance in terms of runtime and several other performance indices. At each iteration, distances to the new clusters’ centers are determined, then the distances are compared to the initially computed and dynamically updated range of values, that divide the entire range of distances associated with each cluster center into intervals (bins), to assign appropriate soft memberships to objects. The required number of comparisons is O(log the number of discretization levels). Thus, the computation of centers and memberships is greatly simplified during execution. Also, the use of discrete values for memberships allows soft modification (increment or decrement) of the soft memberships of identified outliers and core objects instead of rough modification (setting to zero or one) in related algorithms. Experimental results on synthetic and standard test data sets verified the efficiency and effectiveness of the proposed algorithm. The average percent of the achieved reduction in runtime is 35% and the average percent of the achieved increase in v-measure, adjusted mutual information, and adjusted rand index is 6% on five datasets compared to PCM. The larger the dataset, the higher the reduction in runtime. Also, SPCM achieved a comparable performance with less computational complexity compared to variants of related algorithms.

Multipoint Distribution Vehicle Routing Optimization Problem considering Random Demand and Changing Load

In the distribution scenario, the using cost of vehicles is closely related to energy consumption, and the energy consumption rate of a vehicle is closely related to the size of its load. The traditional vehicle routing optimization model takes the shortest distance as the optimization goal when the customer demand is determined, while the influence of the random demand and the changing load on the energy consumption and cost of vehicles in the process of distribution is ignored. Therefore, in this paper, load varying vehicle routing problem with stochastic demands (LVGVRPSD) model is proposed with the goal of minimizing transportation energy consumption and considering the load variability and the randomness of customer demand. K-means clustering algorithm is combined with ant colony optimization (ACO) to solve the problem, and the constraint of risk probability is introduced to describe the vehicle overload problem. Examples in the standard vehicle routing problem test data set are provided and analyzed. LVGVRPSD is also compared with the traditional capacitated vehicle routing problem (CVRP) model. The case study results show that the vehicle energy consumption can be reduced by 2% in the model that considers changing load compared to the model that does not consider changing load. The results illustrate that the method of path optimization is more advantageous and reasonable in the pursuit of reducing energy consumption, when the changing load and the random demand of customer are considered.

UNLT: Urdu Natural Language Toolkit

AbstractThis study describes a Natural Language Processing (NLP) toolkit, as the first contribution of a larger project, for an under-resourced language—Urdu. In previous studies, standard NLP toolkits have been developed for English and many other languages. There is also a dire need for standard text processing tools and methods for Urdu, despite it being widely spoken in different parts of the world with a large amount of digital text being readily available. This study presents the first version of theUNLT (Urdu Natural Language Toolkit)which contains three key text processing tools required for an Urdu NLP pipeline; word tokenizer, sentence tokenizer, and part-of-speech (POS) tagger. The UNLT word tokenizer employs a morpheme matching algorithm coupled with a state-of-the-art stochasticn-gram language model with back-off and smoothing characteristics for the space omission problem. The space insertion problem for compound words is tackled using a dictionary look-up technique. The UNLT sentence tokenizer is a combination of various machine learning, rule-based, regular-expressions, and dictionary look-up techniques. Finally, the UNLT POS taggers are based on Hidden Markov Model and Maximum Entropy-based stochastic techniques. In addition, we have developed large gold standard training and testing data sets to improve and evaluate the performance of new techniques for Urdu word tokenization, sentence tokenization, and POS tagging. For comparison purposes, we have compared the proposed approaches with several methods. Our proposed UNLT, the training and testing data sets, and supporting resources are all free and publicly available for academic use.

Automatic Lyrics Transcription of Polyphonic Music With Lyrics-Chord Multi-Task Learning

Lyrics are the words that make up a song, while chords are harmonic sets of multiple notes in music. Lyrics and chords are generally essential information in music, i.e. unaccompanied singing vocals mixed with instrumental music, representing important components in polyphonic music. In a traditional lyrics transcription task, we first extract the singing vocals from the polyphonic music and then transcribe the resulting singing vocals, where the two steps are optimized independently. In this paper, we propose novel end-to-end network architectures that are designed to disentangle lyrics from chords in polyphonic music for effective lyrics transcription in a single step, where we consider chords as musical words, analogously to lexical words as lyrics intuitively. We start by studying a single-task lyrics transcriber as the reference baseline and the initial model to develop the multi-task lyrics transcription solutions. The main idea is to take advantage of chord transcription available in the training data through multi-task training to improve lyrics transcription. The experiments show that the proposed multitask lyrics transcriber significantly outperforms other competing solutions, with a word error rate (WER) of 31.82% on a standard test dataset.

Effect of stemming on text similarity for Arabic language at sentence level.

Semantic Text Similarity (STS) has several and important applications in the field of Natural Language Processing (NLP). The Aim of this study is to investigate the effect of stemming on text similarity for Arabic language at sentence level. Several Arabic light and heavy stemmers as well as lemmatization algorithms are used in this study, with a total of 10 algorithms. Standard training and testing data sets are used from SemEval-2017 international workshop for Task 1, Track 1 Arabic (ar–ar). Different features are selected to study the effect of stemming on text similarity based on different similarity measures. Traditional machine learning algorithms are used such as Support Vector Machines (SVM), Stochastic Gradient Descent (SGD) and Naïve Bayesian (NB). Compared to the original text, using the stemmed and lemmatized documents in experiments achieve enhanced Pearson correlation results. The best results attained when using Arabic light Stemmer (ARLSTem) and Farasa light stemmers, Farasa and Qalsadi Lemmatizers and Tashaphyne heavy stemmer. The best enhancement was about 7.34% in Pearson correlation. In general, stemming considerably improves the performance of sentence text similarly for Arabic language. However, some stemmers make results worse than those for original text; they are Khoja heavy stemmer and AlKhalil light stemmer.

MCFD: A Hardware-Efficient Noniterative Multicue Fusion Demosaicing Algorithm

Color demosaicing is an essential step in the camera image processing pipeline, especially on hardware platforms for real-time video applications. Though many demosaicing algorithms have been proposed in the past two decades, there remains a substantial gap between industrial needs and academic research. On one hand, industry requires a high perceptual quality, artifact-free, and low-cost demosaicing algorithm that is noniterative and small window based ready to be implemented on a hardware platform with a limited line buffer. On the other hand, academia is targeting high PSNR/SSIM, with the computation cost and line buffer receiving second priority, and often a frame buffer and iterative operation are used. The cost, large line buffer and iteration requirement make most existing demosaicing algorithms inapplicable on hardware platforms. In this paper, we introduce a novel low-cost demosaicing algorithm to narrow the gap. We keep the operation window size and computation cost as the first priority and achieve both high PSNR/SSIM and visual perceptual quality compared to previous state-of-the-art methods on standard test datasets. We fully investigate the a priori knowledge of natural scene raw images and find several key cues that are beneficial to demosaicing. Our demosaicing algorithm is a smart fusion of these useful cues. Furthermore, we solve typical demosaicing issues that occur in many traditional methods, including false color artifacts, T-section closing, and zippering artifacts. The proposed method has no learning stage, no iteration operation, a small line buffer and a limited number of parameters, so it can easily be applied to hardware platforms.

Methodology Allying Standard Penetration Test and Era-Interim Data Set for Numerical Simulations of Earth-Air Heat Exchangers

Earth-Air Heat Exchangers are devices installed on buildings to reduce electrical energy consumption with air conditioner systems. They consist of buried ducts where the air is blown and induces heat exchange with the surrounding soil. Aiming to develop a consistent numerical simulation approach to study its behavior, this research allies the usage of Standard Penetration Test (SPT) and Era-Interim as part of the computational methodology. The results indicate that the proposed methodology can be adequately adopted, allowing the soil properties assignment from SPT reports, the prescription of inlet air temperature, and soil surface temperature from ERA/Interim data.

Low light image denoising solution with contrast enhancement in curvelet domain using Gaussian mixture adaptation model

Images captured under low light are noisy and consist of unidentifiable features. Low light noise problem occurs in imaging devices because of smaller sensor size or insufficient exposure. Low light image denoising is an exacting task in many image processing applications. This paper proposes a patch-based image denoising method for low light images in the curvelet domain with contrast enhancement. Curvelet transform is a directional transform and it gives the best sparse representation for images with edges. Here the Expectation–Maximization (EM) algorithm, based on the Gaussian mixture adaptation method is performed in the curvelet domain for denoising. EM Algorithm helps in computing the Gaussian mixture model (GMM) parameters from the patches which are used in maximum a posteriori estimation to update them. GMM parameters and patches are updated periodically until a satisfactory result is achieved. Simulation is performed on standard test data set, and then extended to natural low light noisy images. The results of the proposed technique are then compared using quality metrics such as Peak Signal to Noise Ratio and Structural Similarity Index. It is observed that the use of curvelet transform in denoising process helps to restore the structural information satisfactorily.

RGSR: A two-step lossy JPG image super-resolution based on noise reduction

Single Image Super-Resolution (SISR) is a fundamental and important low-level computer vision (CV) task, yet its performance on real-world applications is not always satisfactory. Different from the previous SISR research, we focus on a specific but realistic SR issue: How can we obtain satisfied SR results from compressed JPG (C-JPG) images, which is a ubiquitous image format to greatly release storage space while missing fine details. the JPG SR task is deeply analyzed to discover the connotation. Then, we propose an effective two-step model structure named RGSR, involving two specifically designed components, i.e., JPG recovering and SR generation, instead of the perspective of noise elimination in traditional SR approaches. Besides, we further integrate the cycle loss to build a hybrid objective across scales for better SR generation. Experimental results on both of the standard test data sets and real images show that our approach achieves outstanding results and succeed in applying to practical C-JPG SR tasks.

Tyre pattern image retrieval – current status and challenges

Tyre pattern image retrieval (TPIR) is an important tool in the investigation of criminal activities and traffic accidents. Although content-based image retrieval (CBIR) has been developed for decades with abundant results, the study on TPIR which started in the 1990s has not made much progress. The lack of large standard test datasets is a crucial shortcoming which limits the research in this field. Information presented in this paper is a result of the authors’ literature research on recent academic publications and practical field investigation in the public security and transportation sectors. The state-of-the-art technologies in the field of TPIR are surveyed in detail from two aspects of tyre patterns – their low-level spatial features and high-level semantic features. Existing algorithms are examined and their pros and cons are compared and verified through experimental results. This paper also surveys the available tyre pattern datasets used in all available literature. Finally, with the considerations on technology trends in image retrieval and application requirements in TPIR, the future research directions in this field are laid out.

Super-resolution reconstruction of real infrared images acquired with unmanned aerial vehicle.

Super-resolution (SR) technology provides a far promising computational imaging approach in obtaining a high-resolution (HR) image (or image sequences) from observed multiple low-resolution (LR) images by incorporating complementary information. In this paper, a three-stage SR method is proposed to generate a HR image from infrared (IR) LR Images acquired with Unmanned Aerial Vehicle (UAV). The proposed method integrates a high-level image capturing process and a low-level SR process. In this integrated process, we incorporate UAV path optimization, sub-pixel image registration, and sparseness constraint into a computational imaging framework of a region of interest (ROI). To refine ROI complementary feathers, we design an optimal flight control scheme to acquire adequate image sequences from multi-angles. In particular, a phase correlation approach achieving reliable sub-pixel image feature matching is adapted, on the basis of which an effective sparseness regularization model is built to enhance the fine structures of the IR image. Unlike most traditional multiple-frame SR algorithms that mainly focus on signal processing and achieve good performances when using standard test datasets, the performed experiments with real-life IR sequences indicate the three-stage SR method can also deal with practical LR IR image sequences collected by UAVs. The experimental results demonstrate that the proposed method is capable of generating HR images with good performance in terms of edge preservation and detail enhancement.

Spatially and Spectrally Concatenated Neural Networks for Efficient Lossless Compression of Hyperspectral Imagery.

To achieve efficient lossless compression of hyperspectral images, we design a concatenated neural network, which is capable of extracting both spatial and spectral correlations for accurate pixel value prediction. Unlike conventional neural network based methods in the literature, the proposed neural network functions as an adaptive filter, thereby eliminating the need for pre-training using decompressed data. To meet the demand for low-complexity onboard processing, we use a shallow network with only two hidden layers for efficient feature extraction and predictive filtering. Extensive simulations on commonly used hyperspectral datasets and the standard CCSDS test datasets show that the proposed approach attains significant improvements over several other state-of-the-art methods, including standard compressors such as ESA, CCSDS-122, and CCSDS-123.

Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization

Hyperparameters are important for machine learning algorithms since they directly control the behaviors of training algorithms and have a significant effect on the performance of machine learning models. Several techniques have been developed and successfully applied for certain application domains. However, this work demands professional knowledge and expert experience. And sometimes it has to resort to the brute-force search. Therefore, if an efficient hyperparameter optimization algorithm can be developed to optimize any given machine learning method, it will greatly improve the efficiency of machine learning. In this paper, we consider building the relationship between the performance of the machine learning models and their hyperparameters by Gaussian processes. In this way, the hyperparameter tuning problem can be abstracted as an optimization problem and Bayesian optimization is used to solve the problem. Bayesian optimization is based on the Bayesian theorem. It sets a prior over the optimization function and gathers the information from the previous sample to update the posterior of the optimization function. A utility function selects the next sample point to maximize the optimization function. Several experiments were conducted on standard test datasets. Experiment results show that the proposed method can find the best hyperparameters for the widely used machine learning models, such as the random forest algorithm and the neural networks, even multi-grained cascade forest under the consideration of time cost.

Self-Tuning Possibilistic c-Means Clustering Models

The relaxation of the probabilistic constraint of the fuzzy c-means clustering model was proposed to provide robust algorithms that are insensitive to strong noise and outlier data. These goals were achieved by the possibilistic c-means (PCM) algorithm, but these advantages came together with a sensitivity to cluster prototype initialization. According to the original recommendations, the probabilistic fuzzy c-means (FCM) algorithm should be applied to establish the cluster initialization and possibilistic penalty terms for PCM. However, when FCM fails to provide valid cluster prototypes due to the presence of noise, PCM has no chance to recover and produce a fine partition. This paper proposes a two-stage c-means clustering algorithm to tackle with most problems enumerated above. In the first stage called initialization, FCM with two modifications is performed: (1) extra cluster added for noisy data; (2) extra variable and constraint added to handle clusters of various diameters. In the second stage, a modified PCM algorithm is carried out, which also contains the cluster width tuning mechanism based on which it adaptively updates the possibilistic penalty terms. The proposed algorithm has less parameters than PCM when the number of clusters is [Formula: see text]. Numerical evaluation involving synthetic and standard test data sets proved the advantages of the proposed clustering model.

Building Standard Offline Anti-phishing Dataset for Benchmarking

Anti-phishing research is one of the active research fields in information security. Due to the lack of a publicly accessible standard test dataset, most of the researchers are using their own dataset for the experiment. This makes the benchmarking across different anti-phishing techniques become challenging and inefficient. In this paper, we propose and construct a large-scale standard offline dataset that is downloadable, universal and comprehensive. In designing the dataset creation approach, major anti-phishing techniques from the literature have been thoroughly considered to identify their unique requirements. The findings of this requirement study have concluded several influencing factors that will enhance the dataset quality, which includes: the type of raw elements, source of the sample, sample size, website category, category distribution, language of the website and the support for feature extraction. These influencing factors are the core to the proposed dataset construction approach, which produced a collection of 30,000 samples of phishing and legitimate webpages with a distribution of 50 percent of each type. Thus, this dataset is useful and compatible for a wide range of anti-phishing researches in conducting the benchmarking as well as beneficial for a research to conduct a rapid proof of concept experiment. With the rapid development of anti-phishing research to counter the fast evolution of phishing attacks, the need of such dataset cannot be overemphasised. The complete dataset is available for download at http://www.fcsit.unimas.my/research/legit-phish-set. Â

Generalized Gradient Approximation Exchange Energy Functional with Near-Best Semilocal Performance.

We develop and validate a nonempirical generalized gradient approximation (GGA) exchange (X) density functional that performs as well as the SCAN (strongly constrained and appropriately normed) meta-GGA on standard thermochemistry tests. Additionally, the new functional (NCAP, nearly correct asymptotic potential) yields Kohn-Sham eigenvalues that are useful approximations of the density functional theory (DFT) ionization potential theorem values by inclusion of a systematic derivative discontinuity shift of the X potential. NCAP also enables time-dependent DFT (TD-DFT) calculations of good-quality polarizabilities, hyper-polarizabilities, and one-Fermion excited states without modification (calculated or ad hoc) of the long-range behavior of the exchange potential or other patches. NCAP is constructed by reconsidering the imposition of the asymptotic correctness of the X potential (-1/ r) as a constraint. Inclusion of derivative discontinuity and approximate integer self-interaction correction treatments along with first-principles determination of the effective second-order gradient expansion coefficient yields a major advance over our earlier correct asymptotic potential functional [CAP; J. Chem. Phys. 2015 , 142 , 054105 ]. The new functional reduces a spurious bump in the CAP atomic exchange potential and moves it to distances irrelevantly far from the nucleus (outside the tail of essentially all practical basis functions). It therefore has nearly correct atomic exchange-potential behavior out to rather large finite distances r from the nucleus but eventually goes as - c/ r with an estimated value for the constant c of around 0.3, so as to achieve other important properties of exact DFT exchange within the restrictions of the GGA form. We illustrate the results with the Ne atom optimized effective potentials and with standard molecular benchmark test data sets for thermochemical, structural, and response properties.

Image Enhancement for Inspection of Cable Images Based on Retinex Theory and Fuzzy Enhancement Method in Wavelet Domain

Inspection images of power transmission line provide vision interaction for the operator and the environmental perception for the cable inspection robot (CIR). However, inspection images are always contaminated by severe outdoor working conditions such as uneven illumination, low contrast, and speckle noise. Therefore, this paper proposes a novel method based on Retinex and fuzzy enhancement to improve the image quality of the inspection images. A modified multi-scale Retinex (MSR) is proposed to compensate the uneven illumination by processing the low frequency components after wavelet decomposition. Besides, a fuzzy enhancement method is proposed to perfect the edge information and improve contrast by processing the high frequency components. A noise reduction procedure based on soft threshold is used to avoid the noise amplification. Experiments on the self-built standard test dataset show that the algorithm can improve the image quality by 3–4 times. Compared with several other methods, the experimental results demonstrate that the proposed method can obtain better enhancement performance with more homogeneous illumination and higher contrast. Further research will focus on improving the real-time performance and parameter adaptation of the algorithm.