Your search

Forecasting the daily flows of rivers is a challenging task that have a significant impact on the environment, agriculture, and people life. This paper investigates the river flow forecasting problem using two types of Deep Neural Networks (DNN) structures, Long Short-Term Memory (LSTM) and Layered Recurrent Neural Networks (L-RNN) for two rivers in the USA, Black and Gila rivers. The data sets collected for a period of seven years for Black river (six years for training and one year for testing) and four years for Gila river (three years for training and one year for testing) were used for our experiments. An order selection method based partial auto-correlation sequence was employed to determine the appropriate order for the proposed models in both cases. Mean square errors (MSE), Root mean square errors (RMSE) and Variance (VAF) were used to evaluate to developed models. The obtained results show that the proposed LSTM is able to produce an excellent model in each case study.

Image clustering presents a hot topic that researchers have chased extensively. There is always a need to a promising clustering technique due to its vital role in further image processing steps. This paper presents a compelling clustering approach for brain tumors and breast cancer in Magnetic Resonance Imaging (MRI). Driven by the superiority of nature-inspired algorithms in providing computational tools to deal with optimization problems, we propose Flower Pollination Algorithm (FPA) and Crow Search Algorithm (CSA) to present a clustering method for brain tumors and breast cancer. Evaluation clustering results of CSA and FPA were judged using two apposite criteria and compared with results of K-means, fuzzy c-means and other metaheuristics when applied to cluster the same benchmark datasets. The clustering method-based CSA and FPA yielded encouraging results, significantly outperforming those obtained by K-means and fuzzy c-means and slightly surpassed those of other metaheuristic algorithms.

Sleep is an essential part of health and longevity persons. As people grow older, the quality of their sleep becomes vital. Poor sleep quality can make negative physiological, psychological, and social impacts on the elderly population, causing a range of health problems including coronary heart disease, depression, anxiety, and loneliness. Early detection, proper diagnosis, and treatments for sleep disorders can be achieved by identifying sleep patterns through long-term sleep monitoring. Although many studies developed sleep monitoring systems by using non-invasive measures such as body temperature, pressure, or body movement signal, research is still limited to detect sleep position changes by using a depth camera. The present study is intended (1) to identify concerns on the existing sleep monitoring system based on the literature review and (2) propose to developing a non-invasive sleep monitoring system using an infrared depth camera. For the literature review, various journal/conference papers have been reviewed to understand the characteristics, tools, and algorithms of the existing sleep monitoring systems. For the system development and validation, we collected data for the sleep positions from two subjects (35 years old man and 84 years old women) during the four-hour sleep. Kinect II depth sensor was used for data collection. We found that the averaged depth data is useful measure to notify the participants’ positional changes during the sleep.

The goal of the ambient intelligence system is not only to enhance the way people communicate with the surrounding environment but also to advance safety measures and enrich human lives. In this paper, we introduce an integrated ambient intelligence system (IAmIS) to perceive the presence of people, identify them, determine their locations, and provide suitable interaction with them. The proposed framework can be applied in various application domains such as a smart house, authorisation, surveillance, crime prevention, and many others. The proposed system has five components: body detection and tracking, face recognition, controller, monitor system, and interaction modules. The system deploys RGB cameras and Kinect depth sensors to monitor human activity. The developed system is designed to be fast and reliable for indoor environments. The proposed IAmIS can interact directly with the environment or communicate with humans acting on the environment. Thus, the system behaves as an intelligent agent. The system has been deployed in our research lab and can recognise lab members and guests to the lab as well as track their movements and have interactions with them depending upon their identity and location within the lab.

The internet has changed the way that many people access written works. Books and articles, of various lengths, in several formats can be bought and accessed online, both legally and illegally. Texts in even shorter form are originating through forums, SMS, blogs, emails, and social media. Automating the process of determining the authorship of posted texts would help combat online piracy of copyrighted text and plagiarism. In addition, authorship identification could help detect fraudulent email messages from dangerous sources and combat cyberattacks by identifying authentic sources. We experiment with several machine learning algorithms on a limited set of public domain literature to identify the most efficient method of authorship identification using the least amount of samples. Different sized data sets are created by 5 predefined rounds of random sampling of 1500 word blocks on a total of 28 text books from a corpus of 7 authors. Traditional methods of authorship identification, such as Naive Bayes, Artificial Neural Network, and Support Vector Machine are implemented in addition to using a modern Deep Learning Neural Network for classification. Thirteen stylometric features are extracted ranging from character based, word based, and syntactic features. Our model consistently showed that Support Vector Machine out performs other classification methods. © 2020

Biologists and bioinformaticians heavily rely on data portals and repositories accessible through web application. While they mostly agree that the data is valuable, they find the interfaces hard to use and non-intuitive. In this paper we present a user-centered design of a database for classification and annotation for major and minor introns in various species. Our design is based on surveying and interviewing minor intron researchers and comparing the features of existing databases. In addition to its ease of use, the proposed database, Major and Minor Intron Annotation Database (MMIAD) offers high flexibility in querying and downloading subsets of information that interest the user in multiple commonly used file formats. © Proceedings of the 14th IADIS International Conference Interfaces and Human Computer Interaction 2020, IHCI 2020 and Proceedings of the 13th IADIS International Conference Game and Entertainment Technologies 2020, GET 2020 - Part of the 14th Multi Conference on Computer Science and Information Systems, MCCSIS 2020. All rights reserved.

Adult content on the Internet may be accessed by children with only a few keystrokes. While separate child-safe accounts may be established, a better approach could be incorporating automatic age estimation capability into the browser. We envision a safer browsing experience by implementing child-safe browsers combined with Internet content rating similar to the film industry. Before such a browser is created it was necessary to test the age estimation module to see whether acceptable error rates are possible. We created an Android application for collecting biometric touch data, specifically tapping data. We arranged with an elementary school, a middle school, a high school, and a university and collected samples from 262 user sessions (ages 5 to 61). From the tapping data, feature vectors were constructed, which were used to train and test 14 regressors and classifiers. Results for regression show the best mean absolute errors of 3.451 and 3.027 years, respectively, for phones and tablets. Results for classification show the best accuracies of 73.63% and 82.28%, respectively, for phones and tablets. These results demonstrate that age estimation, and hence, a child-safe browser, is feasible, and is a worthwhile objective. © 2020 IEEE.

Traditional keyboards remain the input device of choice for typing-heavy environments. When attached to sensitive data, security is a major concern. To continuously authenticate users in these environments, use of keystroke dynamics can be a preferred choice. An integral part of user enrollment in a keystroke based continuous authentication system is the writing instruction (prompt) given to the users, to use as a basis for their improvised writing. There are many prompts possible, and they directly impact the performance of authentication systems. Hence, prompts should be designed carefully, and with purpose. In this paper, we bridge the gap between cognitive psychology and computer science and attempt to influence the mental state of the users to acquire a better authentication performance. We compare two kinds of writing prompts, creative and factual, for generating reference samples. In addition, we perform two robustness tests: robustness to dissimilar writing style (e.g., creative reference and factual test) and robustness to surface (e.g., hard surface reference and soft surface test). We collect data from thirty participants in four weekly sessions. We experiment with three features: key interval, key press, and key hold latencies. We use Relative (R) measure to generate the match score between the reference and test samples. Results show that creative writing consistently performs better than the factual one. Both writing prompts perform well with dissimilar style in testing, i.e., continuous authentication is found robust to writing style. Also, we find that the surface (hard or soft) used in testing need not match that used for the reference, thus continuous authentication is also surface robust. © 2020 IEEE.

The cyber-behavioral biometric modalities such as keystroke dynamics, mouse dynamics, and touch screen dynamics have come under attacks of different forms in recent days. To address these attacks and other security issues, we present a novel concept of using smartwatch sensor data to continuously verify users in cyberspace and show its potential to be a new standalone cyber-behavioral biometric modality. For our experiments, smartwatch gyroscope and accelerometer data collected from 49 subjects while typing in desktop computer have been considered. We implemented six pattern matching classifiers to compare each verification attempt against the user profile. Experimental results comprising of 282, 240 classification attempts show significantly high True Positive (TP) rates and extremely low False Positive (FP) rates with the highest achieved TP rate of 87.2% and lowest FP rate of 0.2%. With this level of accuracy and natural resiliency to attacks comes with physical biometric property as such in hand movement, we opine that smartwatch movement dynamics, besides being a new biometric trait, can be a solution to the security loopholes in existing cyber-behavioral biometric modalities for continuous verification. © 2020 IEEE.

In this paper, we provide a consistent, inexpensive, and easy to use graphical user interface (GUI) smart phone application named Sleep Apnea Screener (SAS) that can diagnosis Obstructive Sleep Apnea (OSA) based on demographic data such as: gender, age, height, BMI, neck circumference, waist, etc., allowing a tentative diagnosis of OSA without the need for overnight tests. The developed smart phone application can diagnosis sleep apnea using a model trained with 620 samples collected from a sleep center in Corpus Christi, TX. Two machine learning classifiers (i.e., Logistic Regression (LR) and Support Vector Machine (SVM)) were used to diagnosis OSA. Our preliminary results show that at-home OSA screening is indeed possible, and that our application is effective method for covering large numbers of undiagnosed cases.

Roads should always be in a reliable con-dition and maintained regularly. One of the problems that should be maintained well is the pavement cracks problem. This a challenging problem that faces road engineers, since maintaining roads in a stable condition is needed for both drivers and pedestrians. Many meth-ods have been proposed to handle this problem to save time and cost. In this paper, we proposed a two-stage method to detect pavement cracks based on Principal Component Analysis (PCA) and Convolutional Neural Network (CNN) to solve this classification problem. We employed a Principal Component Analysis (PCA) method to extract the most significant features with a di˙erent number of PCA components. The proposed approach was trained using a Mendeley Asphalt Crack dataset, which contains 400 images of road cracks with a 480×480 resolution. The obtained results show how PCA helped in speeding up the learning process of CNN.

In urban planning and transportation management, the centrality characteristics of urban streets are vital measures to consider. Centrality can help in understanding the structural properties of dense traffic networks that affect both human life and activity in cities. Many cities classify urban streets to provide stakeholders with a group of street guidelines for possible new rehabilitation such as sidewalks, curbs, and setbacks. Transportation research always considers street networks as a connection between different urban areas. The street functionality classification defines the role of each element of the urban street network (USN). Some potential factors such as land use mix, accessible service, design goal, and administrators’ policies can affect the movement pattern of urban travelers. In this study, nine centrality measures are used to classify the urban roads in four cities evaluating the structural importance of street segments. In our work, a Stacked Denoising Autoencoder (SDAE) predicts a street’s functionality, then logistic regression is used as a classifier. Our proposed classifier can differentiate between four different classes adopted from the U.S. Department of Transportation (USDT): principal arterial road, minor arterial road, collector road, and local road. The SDAE-based model showed that regular grid configurations with repeated patterns are more influential in forming the functionality of road networks compared to those with less regularity in their spatial structure.

Weaknesses in smartphone security pose a severe privacy threat to users. Currently, smartphones are secured through methods such as passwords, fingerprint scanners, and facial recognition cameras. To explore new methods and strengthen smartphone security, we developed a capacitive swipe based user authentication and identification technique. Swipe is a gesture that a user performs throughout the usage of a smartphone. Our methodology focuses on using the capacitive touchscreen to capture the user's swipe. While the user swipes, a series of capacitive frames are captured for each swipe. We developed an algorithm to process this series of capacitive frames pertaining to the swipe. While different swipes may contain different numbers of capacitive frames, our algorithm normalizes the frames by constructing the same number of frames for every swipe. After applying the algorithm, we transform the normalized frames into gray scale images. We apply principal component analysis (PCA) to these images to extract principal components, which are then used as features to authenticate/identify the user. We tested random forest (RF) and support vector machine (SVM) algorithms as classifiers. For authentication, the performance of SVM (tested with left swipes) was more promising than RF, yielding a maximum accuracy of 79.88% with an FAR and FRR of 15.84% and 50%, respectively. SVM (tested with right swipes) produced our maximum identification accuracy at 57.81% along with an FAR and FRR of 0.60% and 42.18%, respectively. © 2020 IEEE.

Image creation and retention are growing at an exponential rate. Individuals produce more images today than ever in history and often these images contain family. In this paper, we develop a framework to detect or identify family in a face image dataset. The ability to identify family in a dataset of images could have a critical impact on finding lost and vulnerable children, identifying terror suspects, social media interactions, and other practical applications. We evaluated our framework by performing experiments on two facial image datasets, the Y-Face and KinFaceW, comprising 37 and 920 images, respectively. We tested two feature extraction techniques, namely PCA and HOG, and three machine learning algorithms, namely K-Means, agglomerative hierarchical clustering, and K nearest neighbors. We achieved promising results with a maximum detection rate of 94.59% using K-Means, 89.18% with agglomerative clustering, and 77.42% using K-nearest neighbors. © 2020 World Scientific Publishing Company.

Ozone is a toxic gas with massive distinct chemical components from oxygen. Breathing ozone in the air can cause severe effects on human health, especially people who have asthma. It can cause long-lasting damage to the lungs and heart attacks and might lead to death. Forecasting the ozone concentration levels and related pollutant attribute is critical for developing sophisticated environment safety policies. In this paper, we present three artificial neural network (ANN) models to forecast the daily ozone (O3), coarse particulate matter (PM10), and particulate matter (PM2.5) concentrations in a highly polluted city in the Republic of China. The proposed models are (1) recurrent multilayer perceptron (RMLP), (2) recurrent fuzzy neural network (RFNN), and (3) hybridization of RFNN and grey wolf optimizer (GWO), which are referred to as RMLP-ANN, RFNN, and RFNN-GWO models, respectively. The performance of the proposed models is compared with other conventional models previously reported in the literature. The comparative results showed that the proposed models presented outstanding performance. The RFNN-GWO model revealed superior results in the modeling of O3, PM10, and PM2.5 compared with the RMLP-ANN and RFNN models. © 2020, Springer Nature B.V.

Retweeting is an important way of information propagation on Twitter. In this paper, we investigate the sentiment correlation between regular tweets and retweets. We anticipate our investigation sheds a light on how the sentiment of regular tweets impacts the retweets of different sentiments. We propose a method for measuring the sentiment of tweets. We categorize the Twitter users into different groups by different norms, which are the follower count, the betweenness connectivity, a combination of follower count and betweenness centrality,and the amount of tweets. Then, we calculate the sentiment correlation for different groups to examine the influential factors for retweeting a message with a certain sentiment.We find that the users with higher betweenness centrality and higher tweets amount tend to exhibit a higher sentiment correlation. The users with medium-level followers_count show the highest sentiment correlation compared to the low-level and high-level followers_count. After combining the two factors of followers_count and betweenness centrality, we discover that specifically at low-level betweenness centrality the users with medium-level followers_count have the highest sentiment correlation. Our last observation is that the difference for correlation coefficients exists between different types of users. Our study on the sentiment correlation provides instructional information for modeling information propagation in human society. © 2020, Springer-Verlag GmbH Austria, part of Springer Nature.

Alzheimer's Disease (AD) is a neurodegenerative disease that causes complications with thinking capability, memory and behavior. AD is a major public health problem among the elderly in developed and developing countries. With the growth of AD around the world, there is a need to further expand our understanding of the roles different clinical measurements can have in the diagnosis of AD. In this work, we propose a machine learning-based technique to distinguish control subjects with no cognitive impairments, AD subjects, and subjects with mild cognitive impairment (MCI), often seen as precursors of AD. We utilized several machine learning (ML) techniques and found that Gradient Boosting Decision Trees achieved the highest performance above 84% classification accuracy. Also, we determined the importance of the features (clinical biomarkers) contributing to the proposed multi-class classification system. Further investigation on the biomarkers will pave the way to introduce better treatment plan for AD patients. © 2020 The authors and IOS Press.

This work proposes a new approach in addressing Economic Load Dispatch (ELD) optimization problem in power unit systems using nature-inspired metaheuristics search algorithms. Solving such a problem requires a degree of maximization of the economic pact of a power network system, where this is possible with some existing population-based metaheuristic search algorithms. The key issue to be handled here is how to maximize the economic benevolence of a power network under a variety of operational constraints, taking into account the reduction in the generated fuel cost as well as the aggregate power loss in the transmission power network system. Some nature-inspired metaheuristics will be explored. Meanwhile, we shall focus our attention on a newly developed nature-inspired search algorithm, referred to as the Crow Search Algorithm or CSA for short, as well as the Differential Evolution (DE) that is commonly known as a metaheuristic. The CSA emerged to light by simulating the intelligent flocking behavior of crows. The practicability of the proposed approach-based CSA was conducted to common types of power generators, including three and six buses (nodes) in addition to the IEEE 30-bus standard system. The results of the presented approaches were compared to other results developed using existing nature-inspired metaheuristic algorithms like particle swarm optimization and genetic algorithms and also compared to traditional approaches such as quadratic programming method. The results reported here support that CSA has achieved an outstanding performance in solving the problem of ELD in power systems, demonstrating their good optimization capabilities through arriving at a combination of power loads that consummate the constraints of the ELD problem while simultaneously lessening the entire fuel cost. The experimental results also showed that the CSA solutions were capable of maximizing the reliability of the power supplied to the customers, and also reducing both the generated power cost and the loss of power in the transmission power systems.