Abstract: Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.
Abstract: As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.
Abstract: The COVID-19 pandemic is unprecedented in terms of its global reach and economic impacts. Historically, investment in infrastructure development projects has been touted to boost the economic growth of a nation. The State and Local governments responsible for delivering infrastructure assets work under tight budgets. Therefore, it is important to understand which infrastructure projects have the highest potential of boosting economic growth in the post-pandemic era. This paper presents relationships between infrastructure projects and economic growth. Statistical relationships between investment in different types of infrastructure projects (transit, water and wastewater, highways, power, manufacturing etc.) and indicators of economic growth are presented using historic data between 2002 and 2020 from the U.S. Census Bureau and U.S. Bureau of Economic Analysis (BEA). The outcome of the paper is the comparison of statistical correlations between investment in different types of infrastructure projects and indicators of economic growth. The comparison of the statistical correlations is useful in ranking the types of infrastructure projects based on their ability to influence economic prosperity. Therefore, investment in the infrastructures with the higher rank will have a better chance of boosting the economic growth. Once, the ranks are derived, they can be used by the decision-makers in infrastructure investment related decision-making process.
Abstract: An effective emergency response to accidents with chemical, biological, radiological, nuclear, or explosive materials (CBRNE) that represent highly dynamic situations needs immediate actions within limited time, information and resources. The aim of the study is to provide the foundation for division of unsafe area into risk zones according to the impact of hazardous parameters (heat radiation, thermal dose, overpressure, chemical concentrations). A decision on the boundary values for three risk zones is based on the vulnerability analysis that covered a variety of accident scenarios containing the release of a toxic or flammable substance which either evaporates, ignites and/or explodes. Critical values are selected for the boundary definition of the Red, Orange and Yellow risk zones upon the examination of harmful effects that are likely to cause injuries of varying severity to people and different levels of damage to structures. The obtained results provide the basis for creating a comprehensive real-time risk map for a decision support at CBRNE operations.
Abstract: In agricultural production and breeding, implementing automatic picking robot in orchard farming to reduce human labour and error is challenging. The core function of it is automatic identification based on machine vision. This paper focuses on apple detection and counting in orchards and implements several deep learning methods. Extensive datasets are used and a semi-automatic annotation method is proposed. The proposed deep learning models are in state-of-the-art YOLO family. In view of the essence of the models with various backbones, a multi-dimensional comparison in details is made in terms of counting accuracy, mAP and model memory, laying the foundation for realising automatic precision agriculture.
Abstract: Detecting subjectively biased statements is a vital task. This is because this kind of bias, when present in the text or other forms of information dissemination media such as news, social media, scientific texts, and encyclopedias, can weaken trust in the information and stir conflicts amongst consumers. Subjective bias detection is also critical for many Natural Language Processing (NLP) tasks like sentiment analysis, opinion identification, and bias neutralization. Having a system that can adequately detect subjectivity in text will boost research in the above-mentioned areas significantly. It can also come in handy for platforms like Wikipedia, where the use of neutral language is of importance. The goal of this work is to identify the subjectively biased language in text on a sentence level. With machine learning, we can solve complex AI problems, making it a good fit for the problem of subjective bias detection. A key step in this approach is to train a classifier based on BERT (Bidirectional Encoder Representations from Transformers) as upstream model. BERT by itself can be used as a classifier; however, in this study, we use BERT as data preprocessor as well as an embedding generator for a Bi-LSTM (Bidirectional Long Short-Term Memory) network incorporated with attention mechanism. This approach produces a deeper and better classifier. We evaluate the effectiveness of our model using the Wiki Neutrality Corpus (WNC), which was compiled from Wikipedia edits that removed various biased instances from sentences as a benchmark dataset, with which we also compare our model to existing approaches. Experimental analysis indicates an improved performance, as our model achieved state-of-the-art accuracy in detecting subjective bias. This study focuses on the English language, but the model can be fine-tuned to accommodate other languages.
Abstract: The COVID-19 dataset is obtained by extracting weather, longitude, latitude, ISO3666, cases and death of coronavirus patients across the globe. The data were extracted for a period of eight day choosing uniform time within the specified period. Then mapping of cases and deaths with reverence to continents were obtained. Bayesian Geostastical modelling was carried out on the dataset. The study found out that countries in the tropical region suffered less deaths/attacks compared to countries in the temperate region, this is due to high temperature in the tropical region.
Abstract: Edgeworth approximation is one of the most important statistical methods that has a considered contribution in the reduction of the sum of standard deviation of the independent variables’ coefficients in a Quantile Regression Model. This model estimates the conditional median or other quantiles. In this paper, we have applied approximating statistical methods in an economical problem. We have created and generated a quantile regression model to see how the profit gained is connected with the realized sales of the cosmetic products in a real data, taken from a local business. The Linear Regression of the generated profit and the realized sales was not free of autocorrelation and heteroscedasticity, so this is the reason that we have used this model instead of Linear Regression. Our aim is to analyze in more details the relation between the variables taken into study: the profit and the finalized sales and how to minimize the standard errors of the independent variable involved in this study, the level of realized sales. The statistical methods that we have applied in our work are Edgeworth Approximation for Independent and Identical distributed (IID) cases, Bootstrap version of the Model and the Edgeworth approximation for Bootstrap Quantile Regression Model. The graphics and the results that we have presented here identify the best approximating model of our study.
Abstract: The COVID-19 causes a worldwide crisis and has an impact in every dimension of the economy. Organizations with the ability to adapt to new developments and which innovate solutions for the disrupted world during and after the Corona crises have the opportunity to not only survive the crisis but rather to use new trends to implement new business models and gain advantage. In this context, startups seem to have better opportunities to manage the Corona crisis through their innovation-based nature. The main result of this paper is the understanding that by applying a startup orientated innovation (SOCI) strategy, established companies can be motivated to meet the challenge of COVID-19 in a similar way like startups. This result can be achieved by describing the role of innovation and a SOCI strategy as helpful methods for organizations to meet the coming challenges during and after the COVID-19 epidemics. In addition to this, this paper presents a practical application of SOCI through the PANDA approach of the Fresenius University of Applied Sciences in Germany and discuss it in the context of COVID-19 as an exemplary successful real-world implementation of SOCI strategy.
Abstract: Phosphorus is an essential nutrient for plant life which is most frequently found as phosphate in water. Once phosphate is found in abundance in surface water, a series of adverse effects on an ecosystem can be initiated. Therefore, a portable and reliable method is needed to monitor the phosphate concentrations in the field. In this paper, an inexpensive dip strip device with the ascorbic acid/antimony reagent dried on blotting paper along with wet chemistry is developed for the detection of low concentrations of phosphate in water. Ammonium molybdate and sulfuric acid are separately stored in liquid form so as to improve significantly the lifetime of the device and enhance the reproducibility of the device’s performance. The limit of detection and quantification for the optimized device are 0.134 ppm and 0.472 ppm for phosphate in water, respectively. The device’s shelf life, storage conditions, and limit of detection are superior to what has been previously reported for the paper-based phosphate detection devices.
Abstract: The forensic use of handwriting depends on the analysis, comparison, and evaluation decisions made by forensic document examiners. When using biometric technology in forensic applications, it is necessary to compute Likelihood Ratio (LR) for quantifying strength of evidence under two competing hypotheses, namely the prosecution and the defense hypotheses wherein a set of assumptions and methods for a given data set will be made. It is therefore important to know how repeatable and reproducible our estimated LR is. This paper evaluated the accuracy and reproducibility of examiners' decisions. Confidence interval for the estimated LR were presented so as not get an incorrect estimate that will be used to deliver wrong judgment in the court of Law. The estimate of LR is fundamentally a Bayesian concept and we used two LR estimators, namely Logistic Regression (LoR) and Kernel Density Estimator (KDE) for this paper. The repeatability evaluation was carried out by retesting the initial experiment after an interval of six months to observe whether examiners would repeat their decisions for the estimated LR. The experimental results, which are based on handwriting dataset, show that LR has different confidence intervals which therefore implies that LR cannot be estimated with the same certainty everywhere. Though the LoR performed better than the KDE when tested using the same dataset, the two LR estimators investigated showed a consistent region in which LR value can be estimated confidently. These two findings advance our understanding of LR when used in computing the strength of evidence in handwriting using forensics.
Abstract: Among different droplet manipulations, controlled droplet-splitting is of great significance due to its ability to increase throughput and operational capability. Furthermore, unequal droplet-splitting can provide greater flexibility and a wider range of dilution factors. In this study, we developed two-dimensional, time-dependent complex fluid dynamics simulations to model droplet formation in a flow focusing device, followed by splitting in a Y-shaped junction with sub-channels of unequal widths. From the results obtained from the numerical study, we correlated the diameters of the droplets in the sub-channels to the Weber number, thereby demarcating the droplet splitting and non-splitting regimes.
Abstract: To improve the registration accuracy of a source point cloud and template point cloud when the initial relative deflection angle is too large, a PointNetLK algorithm combined with an oriented bounding box (PointNetLK-OBB) is proposed. In this algorithm, the OBB of a 3D point cloud is used to represent the macro feature of source and template point clouds. Under the guidance of the iterative closest point algorithm, the OBB of the source and template point clouds is aligned, and a mirror symmetry effect is produced between them. According to the fitting degree of the source and template point clouds, the mirror symmetry plane is detected, and the optimal rotation and translation of the source point cloud is obtained to complete the 3D point cloud registration task. To verify the effectiveness of the proposed algorithm, a comparative experiment was performed using the publicly available ModelNet40 dataset. The experimental results demonstrate that, compared with PointNetLK, PointNetLK-OBB improves the registration accuracy of the source and template point clouds when the initial relative deflection angle is too large, and the sensitivity of the initial relative position between the source point cloud and template point cloud is reduced. The primary contribution of this paper is the use of PointNetLK to avoid the non-convex problem of traditional point cloud registration and leveraging the regularity of the OBB to avoid the local optimization problem in the PointNetLK context.
Abstract: One of the issues that arises with microscale lab-on-a-chip technology is that the laminar flow within the microchannels limits the mixing of fluids. To combat this, micromixers have been introduced as a means to try and incorporate turbulence into the flow to better aid the mixing process. This study presents an electroosmotic micromixer that balances vortex generation and degeneration with the inlet flow velocity to greatly increase the mixing efficiency. A comprehensive parametric study was performed to evaluate the role of the relevant parameters on the mixing efficiency. It was observed that the suggested micromixer is perfectly suited for biological applications due to its low pressure drop (below 10 Pa) and low shear rate. The proposed micromixer with optimized working parameters is able to attain a mixing efficiency of 95% in a span of 0.5 seconds using a frequency of 10 Hz, a voltage of 0.7 V, and an inlet velocity of 0.366 mm/s.
Abstract: There is an increasing interest in introducing computational thinking at an early age. Computational thinking, like mathematical thinking, engineering thinking, and scientific thinking, is a kind of analytical thinking. Learning computational thinking skills is not only to improve technological literacy, but also allows learners to equip with practicable skills such as problem-solving skills. As people realize the importance of computational thinking, the field of educational technology faces a problem: how to choose appropriate tools and activities to help students develop computational thinking skills. Robots are gradually becoming a popular teaching tool, as robots provide a tangible way for young children to access to technology, and controlling a robot through programming offers them opportunities to engage in developing computational thinking. This study explores whether the introduction of flowcharts into the robotics programming courses can help children convert natural language into a programming language more easily, and then to better cultivate their computational thinking skills. An experimental study was adopted with a sample of children ages six to seven (N = 16) participated, and a one-meter-tall humanoid robot was used as the teaching tool. Results show that children can master basic programming concepts through robotic courses. Children's computational thinking has been significantly improved. Besides, results suggest that flowcharts do have an impact on young children’s computational thinking skills development, but it only has a significant effect on the "sequencing" and "correspondence" skills. Overall, the study demonstrates that the humanoid robot and flowcharts have qualities that foster young children to learn programming and develop computational thinking skills.
Abstract: Predicting the actual cost and duration in construction projects concern a continuous and existing problem for the construction sector. This paper addresses this problem with modern methods and data available from past public construction projects. 39 bridge projects, constructed in Greece, with a similar type of available data were examined. Considering each project’s attributes with the actual cost and the actual duration, correlation analysis is performed and the most appropriate predictive project variables are defined. Additionally, the most efficient subgroup of variables is selected with the use of the WEKA application, through its attribute selection function. The selected variables are used as input neurons for neural network models through correlation analysis. For constructing neural network models, the application FANN Tool is used. The optimum neural network model, for predicting the actual cost, produced a mean squared error with a value of 3.84886e-05 and it was based on the budgeted cost and the quantity of deck concrete. The optimum neural network model, for predicting the actual duration, produced a mean squared error with a value of 5.89463e-05 and it also was based on the budgeted cost and the amount of deck concrete.
Abstract: The aim of this experimental and numerical study is to analyze the effects of acoustic streaming generated by 40 kHz ultrasonic waves on heat transfer in forced convection, with and without 40 PPI aluminum metal foam. Preliminary dynamic and thermal studies were done with COMSOL Multiphase, to see heat transfer enhancement degree by inserting a 40PPI metal foam (10 × 2 × 3 cm) on a heat sink, after having determined experimentally its permeability and Forchheimer's coefficient. The results obtained numerically are in accordance with those obtained experimentally, with an enhancement factor of 205% for a velocity of 0.4 m/s compared to an empty channel. The influence of 40 kHz ultrasound on heat transfer was also tested with and without metallic foam. Results show a remarkable increase in Nusselt number in an empty channel with an enhancement factor of 37,5%, while no influence of ultrasound on heat transfer in metal foam presence.
Abstract: Based on a convenience sample of 2,092 participants from across all 50 states of the United States, a survey was conducted to explore Americans’ mask-wearing behaviors during COVID-19 according to their political convictions, religious beliefs, and ethnic cultures from late July to early September, 2020. The purpose of the study is to provide evidential support for government policymaking so as to drive up more effective public policies by taking into consideration the variance in these social factors. It was found that the respondents’ party affiliation or preference, religious belief, and ethnicity, in addition to their health condition, gender, level of concern of contracting COVID-19, all affected their mask-wearing habits both in March, the initial coronavirus outbreak stage, and in August, when mask-wearing had been made mandatory by state governments. The study concludes that pandemic awareness campaigns must be run among all citizens, especially among African Americans, Muslims, and Republicans, who have the lowest rates of wearing masks, in order to protect themselves and others. It is recommended that complementary cognitive bias awareness programs should be implemented in non-Black and non-Muslim communities to eliminate social concerns that deter them from wearing masks.
Abstract: It is an established fact that organizations across the globe consider employees as their assets and try to advance their well-being. However, the local firms of developing countries are mostly profit oriented and do not have much concern about their employees’ engagement or commitment. Like other developing countries, the local organizations of Pakistan are also less concerned about the well-being of their employees. Especially public sector organizations lack concern regarding engagement, satisfaction or commitment of the employees. Therefore, this study aimed at investigating the impact of job recognition and job motivation on organizational commitment in the mediation role of employee engagement. The data were collected from land record officers of board of revenue, Punjab, Pakistan. Structured questionnaire was used to collect data through physically visiting land record officers and also through the internet. A total of 318 land record officers’ responses were finalized to perform data analysis. The data were analyzed through confirmatory factor analysis and structural equation modeling technique. The findings revealed that job recognition and job motivation have direct as well as indirect positive and significant impact on organizational commitment. The limitations, practical implications and future research indications are also explained.
Abstract: Magnetic nanoparticles (MNPs) are widely used to facilitate magnetic particle imaging (MPI) which has the potential to become the leading diagnostic instrument for biomedical imaging. This comparative study assesses the effects of changing iron content and excitation frequency on point-spread function (PSF) representing the effect of magnetization reversal. PSF is quantified by features of interest for MPI: i.e., drive field amplitude and full-width-at-half-maximum (FWHM). A superparamagnetic quantifier (SPaQ) is used to assess differential magnetic susceptibility of two commercially available MNPs: Synomag®-D50 and Synomag®-D70. For both MNPs, the signal output depends on increase in drive field frequency and amount of iron-oxide, which might be hampering the sensitivity of MPI systems that perform on higher frequencies. Nevertheless, there is a clear potential of Synomag®-D for a stable MPI resolution, especially in case of 70 nm version, that is independent of either drive field frequency or amount of iron-oxide.