Abstract: This paper is motivated by the importance of multi-sensor image fusion with specific focus on Infrared (IR) and Visible image (VI) fusion for various applications including military reconnaissance. Image fusion can be defined as the process of combining two or more source images into a single composite image with extended information content that improves visual perception or feature extraction. These images can be from different modalities like Visible camera & IR Thermal Imager. While visible images are captured by reflected radiations in the visible spectrum, the thermal images are formed from thermal radiation (IR) that may be reflected or self-emitted. A digital color camera captures the visible source image and a thermal IR camera acquires the thermal source image. In this paper, some image fusion algorithms based upon Multi-Scale Transform (MST) and region-based selection rule with consistency verification have been proposed and presented. This research includes implementation of the proposed image fusion algorithm in MATLAB along with a comparative analysis to decide the optimum number of levels for MST and the coefficient fusion rule. The results are presented, and several commonly used evaluation metrics are used to assess the suggested method's validity. Experiments show that the proposed approach is capable of producing good fusion results. While deploying our image fusion algorithm approaches, we observe several challenges from the popular image fusion methods. While high computational cost and complex processing steps of image fusion algorithms provide accurate fused results, but they also make it hard to become deployed in system and applications that require real-time operation, high flexibility and low computation ability. So, the methods presented in this paper offer good results with minimum time complexity.
Abstract: In recent years, SQL injection attacks have been identified as being prevalent against web applications. They affect network security and user data, which leads to a considerable loss of money and data every year. This paper presents the use of classification algorithms in machine learning using a method to classify the login data filtering inputs into "SQLi" or "Non-SQLi,” thus increasing the reliability and accuracy of results in terms of deciding whether an operation is an attack or a valid operation. A method as a Web-App is developed for auto-generated data replication to provide a twin of the targeted data structure. Shielding against SQLi attacks (WebAppShield) that verifies all users and prevents attackers (SQLi attacks) from entering and or accessing the database, which the machine learning module predicts as "Non-SQLi", has been developed. A special login form has been developed with a special instance of the data validation; this verification process secures the web application from its early stages. The system has been tested and validated, and up to 99% of SQLi attacks have been prevented.
Abstract: Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.
Abstract: The matrix completion problem has been studied broadly under many underlying conditions. In many real-life scenarios, we could expect elements from distinct columns or distinct positions to have a different cost. In this paper, we explore this generalization under adaptive conditions. We approach the problem under two different cost models. The first one is that entries from different columns have different observation costs, but, within the same column, each entry has a uniform cost. The second one is any two entry has different observation cost, despite being the same or different columns. We provide complexity analysis of our algorithms and provide tightness guarantees.
Abstract: The Earth's surface is constantly changing through forces of nature and human activities. Reliable, accurate, and timely change detection is critical to environmental monitoring, resource management, and planning activities. Recently, interest in deep learning algorithms, especially convolutional neural networks, has increased in the field of image change detection due to their powerful ability to extract multi-level image features automatically. However, these networks are prone to drawbacks that limit their applications, which reside in their inability to capture spatial relationships between image instances, as this necessitates a large amount of training data. As an alternative, Capsule Network has been proposed to overcome these shortcomings. Although its effectiveness in remote sensing image analysis has been experimentally verified, its application in change detection tasks remains very sparse. Motivated by its greater robustness towards improved hierarchical object representation, this study aims to apply a capsule network for PolSAR image Change Detection. The experimental results demonstrate that the proposed change detection method can yield a significantly higher detection rate compared to methods based on convolutional neural networks.
Abstract: This work describes a system that uses electromyography (EMG) signals obtained from muscle sensors and an Artificial Neural Network (ANN) for signal classification and pattern recognition that is used to control a small unmanned aerial vehicle using specific arm movements. The main objective of this endeavor is the development of an intelligent interface that allows the user to control the flight of a drone beyond direct manual control. The sensor used were the MyoWare Muscle sensor which contains two EMG electrodes used to collect signals from the posterior (extensor) and anterior (flexor) forearm, and the bicep. The collection of the raw signals from each sensor was performed using an Arduino Uno. Data processing algorithms were developed with the purpose of classifying the signals generated by the arm’s muscles when performing specific movements, namely: flexing, resting, and motion of the arm. With these arm motions roll control of the drone was achieved. MATLAB software was utilized to condition the signals and prepare them for the classification. To generate the input vector for the ANN and perform the classification, the root mean square and the standard deviation were processed for the signals from each electrode. The neuromuscular information was trained using an ANN with a single 10 neurons hidden layer to categorize the four targets. The result of the classification shows that an accuracy of 97.5% was obtained. Afterwards, classification results are used to generate the appropriate control signals from the computer to the drone through a Wi-Fi network connection. These procedures were successfully tested, where the drone responded successfully in real time to the commanded inputs.
Abstract: Health and Social care (HSc) services planning and scheduling are facing unprecedented challenges, due to the pandemic pressure and also suffer from unplanned spending that is negatively impacted by the global financial crisis. Data-driven approaches can help to improve policies, plan and design services provision schedules using algorithms that assist healthcare managers to face unexpected demands using fewer resources. The paper discusses services packing using statistical significance tests and machine learning (ML) to evaluate demands similarity and coupling. This is achieved by predicting the range of the demand (class) using ML methods such as Classification and Regression Trees (CART), Random Forests (RF), and Logistic Regression (LGR). The significance tests Chi-Squared and Student’s test are used on data over a 39 years span for which data exist for services delivered in Scotland. The demands are associated using probabilities and are parts of statistical hypotheses. These hypotheses, as their NULL part, assume that the target demand is statistically dependent on other services’ demands. This linking is checked using the data. In addition, ML methods are used to linearly predict the above target demands from the statistically found associations and extend the linear dependence of the target’s demand to independent demands forming, thus, groups of services. Statistical tests confirmed ML coupling and made the prediction statistically meaningful and proved that a target service can be matched reliably to other services while ML showed that such marked relationships can also be linear ones. Zero padding was used for missing years records and illustrated better such relationships both for limited years and for the entire span offering long-term data visualizations while limited years periods explained how well patients numbers can be related in short periods of time or that they can change over time as opposed to behaviours across more years. The prediction performance of the associations were measured using metrics such as Receiver Operating Characteristic (ROC), Area Under Curve (AUC) and Accuracy (ACC) as well as the statistical tests Chi-Squared and Student. Co-plots and comparison tables for the RF, CART, and LGR methods as well as the p-value from tests and Information Exchange (IE/MIE) measures are provided showing the relative performance of ML methods and of the statistical tests as well as the behaviour using different learning ratios. The impact of k-neighbours classification (k-NN), Cross-Correlation (CC) and C-Means (CM) first groupings was also studied over limited years and for the entire span. It was found that CART was generally behind RF and LGR but in some interesting cases, LGR reached an AUC = 0 falling below CART, while the ACC was as high as 0.912 showing that ML methods can be confused by zero-padding or by data’s irregularities or by the outliers. On average, 3 linear predictors were sufficient, LGR was found competing well RF and CART followed with the same performance at higher learning ratios. Services were packed only when a significance level (p-value) of their association coefficient was more than 0.05. Social factors relationships were observed between home care services and treatment of old people, low birth weights, alcoholism, drug abuse, and emergency admissions. The work found that different HSc services can be well packed as plans of limited duration, across various services sectors, learning configurations, as confirmed by using statistical hypotheses.
Abstract: This paper addresses the issue of automatic parameter estimation in conceptual rainfall-runoff (CRR) models. Due to threshold structures commonly occurring in CRR models, the associated mathematical optimization problems have the significant characteristic of being strongly non-differentiable. In order to face this enormous task, the resolution method proposed adopts a smoothing strategy using a special C∞ differentiable class function. The final estimation solution is obtained by solving a sequence of differentiable subproblems which gradually approach the original conceptual problem. The use of this technique, called Hyperbolic Smoothing Method (HSM), makes possible the application of the most powerful minimization algorithms, and also allows for the main difficulties presented by the original CRR problem to be overcome. A set of computational experiments is presented for the purpose of illustrating both the reliability and the efficiency of the proposed approach.
Abstract: Diabetes disease that arises from the higher glucose level due to insulin shortage or insulin opposition in the human body has become a common disease in the world. No medicine can cure it completely. However, by taking medicine, maintaining diets, and having exercises regularly, a diabetes patient can keep his glucose level within the specified limits and in this way, he/she can lead a normal life like a healthy person. But to control glucose levels, a patient needs to monitor them regularly. Various techniques are being used over the last four decades. This modern review article aims to provide a comparative study report on various blood glucose monitoring techniques in a very concise and organized manner. The review mainly emphasizes working principles, cost, technology, sensors, measurement types, measurement accuracy, advantages, and disadvantages, etc. of various techniques and then compares among each other. Besides, the use of algorithms and simulators for the growth of this technology is also presented. Finally, current research trends of this measurement technology have also been discussed.
Abstract: The paper is a comparative study of two classical vari-ants of parallel projection methods for solving the convex feasibility problem with their equivalents that involve variable weights in the construction of the solutions. We used a graphical representation of these methods for inpainting a convex area of an image in order to investigate their effectiveness in image reconstruction applications. We also presented a numerical analysis of the convergence of these four algorithms in terms of the average number of steps and execution time, in classical CPU and, alternativaly, in parallel GPU implementation.
Abstract: One of the important parts of the brain-computer interface (BCI) studies is the classification of motor imagery (MI) obtained by electroencephalography (EEG). The major goal is to provide non-muscular communication and control via assistive technologies to people with severe motor disorders so that they can communicate with the outside world. In this study, an EEG signal classification approach based on multiscale and multi-resolution transform method is presented. The proposed approach is used to decompose the EEG signal containing motor image information (right- and left-hand movement imagery). The decomposition process is performed using curvelet transform which is a multiscale and multiresolution analysis method, and the transform output was evaluated as feature data. The obtained feature set is subjected to feature selection process to obtain the most effective ones using t-test methods. SVM and k-NN algorithms are assigned for classification.
Abstract: Electroencephalography (EEG) investigations of the brain computer interfaces are based on the electrical signals resulting from neural activities in the brain. In this paper, it is offered a method for classifying motor imagery EEG signals. The suggested method classifies EEG signals into two classes using the wave atom transform, and the transform coefficients are assessed, creating the feature set. Classification is done with SVM and k-NN algorithms with and without feature selection. For feature selection t-test approaches are utilized. A test of the approach is performed on the BCI competition III dataset IIIa.
Abstract: Aflatoxins are highly poisonous and carcinogenic compounds produced by species of the genus Aspergillus spp. that can infect a variety of agricultural foods, including dried figs. Biological and environmental factors, such as population, pathogenicity and aflatoxinogenic capacity of the strains, topography, soil and climate parameters of the fig orchards are believed to have a strong effect on aflatoxin levels. Existing methods for aflatoxin detection and measurement, such as high-performance liquid chromatography (HPLC), and enzyme-linked immunosorbent assay (ELISA), can provide accurate results, but the procedures are usually time-consuming, sample-destructive and expensive. Predicting aflatoxin levels prior to crop harvest is useful for minimizing the health and financial impact of a contaminated crop. Consequently, there is interest in developing a tool that predicts aflatoxin levels based on topography and soil analysis data of fig orchards. This paper describes the development of a risk assessment tool for the contamination of aflatoxin on dried figs, based on the location and altitude of the fig orchards, the population of the fungus Aspergillus spp. in the soil, and soil parameters such as pH, saturation percentage (SP), electrical conductivity (EC), organic matter, particle size analysis (sand, silt, clay), concentration of the exchangeable cations (Ca, Mg, K, Na), extractable P and trace of elements (B, Fe, Mn, Zn and Cu), by employing machine learning methods. In particular, our proposed method integrates three machine learning techniques i.e., dimensionality reduction on the original dataset (Principal Component Analysis), metric learning (Mahalanobis Metric for Clustering) and K-nearest Neighbors learning algorithm (KNN), into an enhanced model, with mean performance equal to 85% by terms of the Pearson Correlation Coefficient (PCC) between observed and predicted values.
Abstract: Multimedia Indexing and Retrieval is generally de-signed and implemented by employing feature graphs. These graphs typically contain a significant number of nodes and edges to reflect the level of detail in feature detection. A higher level of detail increases the effectiveness of the results but also leads to more complex graph structures. However, graph-traversal-based algorithms for similarity are quite inefficient and computation intensive, espe-cially for large data structures. To deliver fast and effective retrieval, an efficient similarity algorithm, particularly for large graphs, is mandatory. Hence, in this paper, we define a graph-projection into a 2D space (Graph Code) as well as the corresponding algorithms for indexing and retrieval. We show that calculations in this space can be performed more efficiently than graph-traversals due to a simpler processing model and a high level of parallelisation. In consequence, we prove that the effectiveness of retrieval also increases substantially, as Graph Codes facilitate more levels of detail in feature fusion. Thus, Graph Codes provide a significant increase in efficiency and effectiveness (especially for Multimedia indexing and retrieval) and can be applied to images, videos, audio, and text information.
Abstract: Real-time monitoring of the supply chain conditions and procedures is a critical element for the optimal coordination and safety of the deliveries, as well as for the minimization of the delivery time and cost. Real time monitoring requires IoT data streams, which are related to the conditions of the products and the means of transport (e.g., location, temperature/humidity conditions, kinematic state, ambient light conditions, etc.). These streams are generated by battery-based IoT tracking devices, equipped with appropriate sensors, and are transmitted to a cloud-based back-end system. Proper handling and processing of the IoT data streams, using predictive and artificial intelligence algorithms, can provide significant and useful results, which can be exploited by the supply chain stakeholders in order to enhance their financial benefits, as well as the efficiency, security, transparency, coordination and sustainability of the supply chain procedures. The technology, the features and the characteristics of a complete, proprietary system, including hardware, firmware and software tools - developed in the context of a co-funded R&D program - are addressed and presented in this paper.
Abstract: Digital innovation has played a crucial role in managing smart transportation. For this, big trajectory data collected from trav-eling vehicles, such as taxis through installed global positioning sys-tem (GPS)-enabled devices can be utilized. It offers an unprecedented opportunity to trace the movements of vehicles in fine spatiotemporal granularity. This paper aims to explore big trajectory data to measure the travel efficiency of road networks using the proposed statistical travel efficiency measure (STEM) across an entire city. Further, it identifies the cause of low travel efficiency by proposed least square approximation network-based causality exploration (LANCE). Finally, the resulting data analysis reveals the causes of low travel efficiency, along with the road segments that need to be optimized to improve the traffic conditions and thus minimize the average travel time from given point A to point B in the road network. Obtained results show that our proposed approach outperforms the baseline algorithms for measuring the travel efficiency of the road network.
Abstract: One of the most significant issues as attended a lot in recent years is that of recognizing the sentiments and emotions in social media texts. The analysis of sentiments and emotions is intended to recognize the conceptual information such as the opinions, feelings, attitudes and emotions of people towards the products, services, organizations, people, topics, events and features in the written text. These indicate the greatness of the problem space. In the real world, businesses and organizations are always looking for tools to gather ideas, emotions, and directions of people about their products, services, or events related to their own. This article uses the Twitter social network, one of the most popular social networks with about 420 million active users, to extract data. Using this social network, users can share their information and opinions about personal issues, policies, products, events, etc. It can be used with appropriate classification of emotional states due to the availability of its data. In this study, supervised learning and deep neural network algorithms are used to classify the emotional states of Twitter users. The use of deep learning methods to increase the learning capacity of the model is an advantage due to the large amount of available data. Tweets collected on various topics are classified into four classes using a combination of two Bidirectional Long Short Term Memory network and a Convolutional network. The results obtained from this study with an average accuracy of 93%, show good results extracted from the proposed framework and improved accuracy compared to previous work.
Abstract: In this work, we use machine learning and data analysis techniques to predict the one-year mortality of cirrhotic patients. Data from 2,322 patients with liver cirrhosis are collected at a single medical center. Different machine learning models are applied to predict one-year mortality. A comprehensive feature space including demographic information, comorbidity, clinical procedure and laboratory tests is being analyzed. A temporal pattern mining technic called Frequent Subgraph Mining (FSM) is being used. Model for End-stage liver disease (MELD) prediction of mortality is used as a comparator. All of our models statistically significantly outperform the MELD-score model and show an average 10% improvement of the area under the curve (AUC). The FSM technic itself does not improve the model significantly, but FSM, together with a machine learning technique called an ensemble, further improves the model performance. With the abundance of data available in healthcare through electronic health records (EHR), existing predictive models can be refined to identify and treat patients at risk for higher mortality. However, due to the sparsity of the temporal information needed by FSM, the FSM model does not yield significant improvements. Our work applies modern machine learning algorithms and data analysis methods on predicting one-year mortality of cirrhotic patients and builds a model that predicts one-year mortality significantly more accurate than the MELD score. We have also tested the potential of FSM and provided a new perspective of the importance of clinical features.
Abstract: Planning the order picking lists for warehouses to achieve some operational performances is a significant challenge when the costs associated with logistics are relatively high, and it is especially important in e-commerce era. Nowadays, many order planning techniques employ supervised machine learning algorithms. However, to define features for supervised machine learning algorithms is not a simple task. Against this background, we consider whether unsupervised algorithms can enhance the planning of order-picking lists. A double zone picking approach, which is based on using clustering algorithms twice, is developed. A simplified example is given to demonstrate the merit of our approach.
Abstract: Deep reinforcement learning (deep RL) algorithms leverage the symbolic power of complex controllers by automating it by mapping sensory inputs to low-level actions. Deep RL eliminates the complex robot dynamics with minimal engineering. Deep RL provides high-risk involvement by directly implementing it in real-world scenarios and also high sensitivity towards hyperparameters. Tuning of hyperparameters on a pneumatic quadruped robot becomes very expensive through trial-and-error learning. This paper presents an automated learning control for a pneumatic quadruped robot using sample efficient deep Q learning, enabling minimal tuning and very few trials to learn the neural network. Long training hours may degrade the pneumatic cylinder due to jerk actions originated through stochastic weights. We applied this method to the pneumatic quadruped robot, which resulted in a hopping gait. In our process, we eliminated the use of a simulator and acquired a stable gait. This approach evolves so that the resultant gait matures more sturdy towards any stochastic changes in the environment. We further show that our algorithm performed very well as compared to programmed gait using robot dynamics.