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: The primary tool currently used to pre-process 10X chromium single-cell ATAC-seq data is Cell Ranger, which can take very long to run on standard datasets. To facilitate rapid pre-processing that enables reproducible workflows, we present a suite of tools called scATAK for pre-processing single-cell ATAC-seq data that is 15 to 18 times faster than Cell Ranger on mouse and human samples. Our tool can also calculate chromatin interaction potential matrices and generate open chromatin signal and interaction traces for cell groups. We use scATAK tool to explore the chromatin regulatory landscape of a healthy adult human brain and unveil cell-type specific features, and show that it provides a convenient and computational efficient approach for pre-processing single-cell ATAC-seq data.
Abstract: The utilization of electronic medical record (EMR) data to establish the disease diagnosis model has become an important research content of biomedical informatics. Deep learning can automatically extract features from the massive data, which brings about breakthroughs in the study of EMR data. The challenge is that deep learning lacks semantic knowledge, which leads to impracticability in medical science. This research proposes a method of incorporating lexical-semantic knowledge from abundant entities into a convolutional neural network (CNN) framework for pediatric disease diagnosis. Firstly, medical terms are vectorized into Lexical Semantic Vectors (LSV), which are concatenated with the embedded word vectors of word2vec to enrich the feature representation. Secondly, the semantic distribution of medical terms serves as Semantic Decision Guide (SDG) for the optimization of deep learning models. The study evaluates the performance of LSV-SDG-CNN model on four kinds of Chinese EMR datasets. Additionally, CNN, LSV-CNN, and SDG-CNN are designed as baseline models for comparison. The experimental results show that LSV-SDG-CNN model outperforms baseline models on four kinds of Chinese EMR datasets. The best configuration of the model yielded an F1 score of 86.20%. The results clearly demonstrate that CNN has been effectively guided and optimized by lexical-semantic knowledge, and LSV-SDG-CNN model improves the disease classification accuracy with a clear margin.
Abstract: E-maintenance is a relatively recent concept, generally referring to maintenance management by monitoring assets over the Internet. One of the key links in the chain of an e-maintenance system is data acquisition and transmission. Specifically for the case of a fleet of heavy-duty vehicles, where the main challenge is the diversity of the vehicles and vehicle-embedded self-diagnostic/reporting technologies, the design of the data acquisition and transmission unit is a demanding task. This is clear if one takes into account that a heavy-vehicles fleet assortment may range from vehicles with only a limited number of analog sensors monitored by dashboard light indicators and gauges to vehicles with plethora of sensors monitored by a vehicle computer producing digital reporting. The present work proposes an adaptable internet of things (IoT) sensor node that is capable of addressing this challenge. The proposed sensor node architecture is based on the increasingly popular single-board computer – expansion boards approach. In the proposed solution, the expansion boards undertake the tasks of position identification, cellular connectivity, connectivity to the vehicle computer, and connectivity to analog and digital sensors by means of a specially targeted design of expansion board. Specifically, the latter offers a number of adaptability features to cope with the diverse sensor types employed in different vehicles. In standard mode, the IoT sensor node communicates to the data center through cellular network, transmitting all digital/digitized sensor data, IoT device identity and position. Moreover, the proposed IoT sensor node offers connectivity, through WiFi and an appropriate application, to smart phones or tablets allowing the registration of additional vehicle- and driver-specific information and these data are also forwarded to the data center. All control and communication tasks of the IoT sensor node are performed by dedicated firmware.
Abstract: Shorelines are vulnerable to significant environmental impacts from oil spills. Stranded oil can cause potential short- to long-term detrimental effects along beaches that include injuries to ecosystem, socio-economic and cultural resources. In this study, a three-dimensional (3D) numerical modeling approach is developed to evaluate the fate and transport of spilled oil for hypothetical oiled shoreline cases under various combinations of beach geomorphology and environmental conditions. The developed model estimates the spatial and temporal distribution of spilled oil for the various test conditions, using the finite volume method and considering the physical transport (dispersion and advection), sinks, and sorption processes. The model includes a user-friendly interface for data input on variables such as beach properties, environmental conditions, and physical-chemical properties of spilled oil. An experimental meso-scale tank design was used to test the developed model for dissolved petroleum hydrocarbon within shorelines. The simulated results for effects of different sediment substrates, oil types, and shoreline features for the transport of spilled oil are comparable to that obtained with a commercially available model. Results show that the properties of substrates and the oil removal by shoreline effects have significant impacts on oil transport in the beach area. Sensitivity analysis, through the application of the one-step-at-a-time method (OAT), for the 3D model identified hydraulic conductivity as the most sensitive parameter. The 3D numerical model allows users to examine the behavior of oil on and within beaches, assess potential environmental impacts, and provide technical support for decisions related to shoreline clean-up operations.
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: Identification of hydrocarbon oil in remote sensing images is often the first step in monitoring oil during spill events. Most remote sensing methods adopt techniques for hydrocarbon identification to achieve detection in order to model an appropriate cleanup program. Identification on optical sensors does not only allow for detection but also for characterization and quantification. Until recently, in optical remote sensing, quantification and characterization were only potentially possible using high-resolution laboratory and airborne imaging spectrometers (hyperspectral data). Unlike multispectral, hyperspectral data are not freely available, as this data category is mainly obtained via airborne survey at present. In this research, two operational high-resolution multispectral satellites (WorldView-3 and Sentinel-2) are theoretically assessed for their suitability for hydrocarbon characterization, using the Hydrocarbon Spectra Slope model (HYSS). This method utilized the two most persistent hydrocarbon diagnostic/absorption features at 1.73 µm and 2.30 µm for hydrocarbon mapping on multispectral data. In this research, spectra measurement of seven different hydrocarbon oils (crude and refined oil) taken on 10 different substrates with the use of laboratory ASD Fieldspec were convolved to Sentinel-2 and WorldView-3 resolution, using their full width half maximum (FWHM) parameter. The resulting hydrocarbon slope values obtained from the studied samples enable clear qualitative discrimination of most hydrocarbons, despite the presence of different background substrates, particularly on WorldView-3. Due to close conformity of central wavelengths and narrow bandwidths to key hydrocarbon bands used in HYSS, the statistical significance for qualitative analysis on WorldView-3 sensors for all studied hydrocarbon oil returned with 95% confidence level (P-value ˂ 0.01), except for Diesel. Using multifactor analysis of variance (MANOVA), the discriminating power of HYSS is statistically significant for most hydrocarbon-substrate combinations on Sentinel-2 and WorldView-3 FWHM, revealing the potential of these two operational multispectral sensors as rapid response tools for hydrocarbon mapping. One notable exception is highly transmissive hydrocarbons on Sentinel-2 data due to the non-conformity of spectral bands with key hydrocarbon absorptions and the relatively coarse bandwidth (> 100 nm).
Abstract: In the design stage of a new building, the energy model of this building is often required for the analysis of the performance on energy efficiency. In practice, a certain degree of geometric simplification should be done in the establishment of building energy models, since the detailed geometric features of a real building are hard to be described perfectly in most energy simulation engine, such as ESP-r, eQuest or EnergyPlus. Actually, the detailed description is not necessary when the result with extremely high accuracy is not demanded. Therefore, this paper analyzed the relationship between the error of the simulation result from building energy models and the geometric simplification of the models. Finally, the following two parameters are selected as the indices to characterize the geometric feature of in building energy simulation: the southward projected area and total side surface area of the building. Based on the parameterization method, the simplification from an arbitrary column building to a typical shape (a cuboid) building can be made for energy modeling. The result in this study indicates that no more than 7% prediction error of annual cooling/heating load will be caused by the geometric simplification for those buildings with the ratio of southward projection length to total perimeter of the bottom of 0.25~0.35, which means this method is applicable for building performance simulation.
Abstract: Since the introduction of fractal geometry in 1970, numerous efforts have been made by architects and researchers to transfer this area of mathematical knowledge in the discipline of architecture and postmodernist discourse. The discourse of complexity and architecture is one of the most significant ongoing discourses in the discipline of architecture from the 70's until today and has generated significant styles such as deconstructivism and parametricism in architecture. During these years, several projects were designed and presented by designers and architects using fractal geometry, but due to the lack of sufficient knowledge and appropriate comprehension of the features and characteristics of this nonlinear geometry, none of the fractal-based designs have been successful and satisfying. Fractal geometry as a geometric technology has a long presence in the history of architecture. The current research attempts to identify and discover the characteristics, features, potentials and functionality of fractals despite their aesthetic aspect by examining case studies of pre-modern architecture in Asia and investigating the function of fractals.
Abstract: Wheelchair users spend long hours in a sitting position, and selecting the right cushion is highly critical in preventing pressure ulcers in that demographic. Pressure Mapping Systems (PMS) are typically used in clinical settings by therapists to identify the sitting profile and pressure points in the sitting area to select the cushion that fits the best for the users. A PMS is a flexible mat composed of arrays of distributed networks of pressure sensors. The output of the PMS systems is a color-coded image that shows the intensity of the pressure concentration. Therapists use the PMS images to compare different cushions fit for each user. This process is highly subjective and requires good visual memory for the best outcome. This paper aims to develop an image processing technique to analyze the images of PMS and provide an objective measure to assess the cushions based on their pressure distribution mappings. In this paper, we first reviewed the skeletal anatomy of the human sitting area and its relation to the PMS image. This knowledge is then used to identify the important features that must be considered in image processing. We then developed an algorithm based on those features to analyze the images and rank them according to their fit to the user's needs.
Abstract: Both daily and long-term management of a heavy-duty vehicles and construction machinery fleet is an extremely complicated and hard to solve issue. This is mainly due to the diversity of the fleet vehicles – machinery, which concerns not only the vehicle types, but also their age/efficiency, as well as the fleet volume, which is often of the order of hundreds or even thousands of vehicles/machineries. In the present paper we present “InteligentLogger”, a holistic heavy-duty fleet management system covering a wide range of diverse fleet vehicles. This is based on specifically designed hardware and software for the automated vehicle health status and operational cost monitoring, for smart maintenance. InteligentLogger is characterized by high adaptability that permits to be tailored to practically any heavy-duty vehicle/machinery (of different technologies -modern or legacy- and of dissimilar uses). Contrary to conventional logistic systems, which are characterized by raised operational costs and often errors, InteligentLogger provides a cost-effective and reliable integrated solution for the e-management and e-maintenance of the fleet members. The InteligentLogger system offers the following unique features that guarantee successful heavy-duty vehicles/machineries fleet management: (a) Recording and storage of operating data of motorized construction machinery, in a reliable way and in real time, using specifically designed Internet of Things (IoT) sensor nodes that communicate through the available network infrastructures, e.g., 3G/LTE; (b) Use on any machine, regardless of its age, in a universal way; (c) Flexibility and complete customization both in terms of data collection, integration with 3rd party systems, as well as in terms of processing and drawing conclusions; (d) Validation, error reporting & correction, as well as update of the system’s database; (e) Artificial intelligence (AI) software, for processing information in real time, identifying out-of-normal behavior and generating alerts; (f) A MicroStrategy based enterprise BI, for modeling information and producing reports, dashboards, and alerts focusing on vehicles– machinery optimal usage, as well as maintenance and scraping policies; (g) Modular structure that allows low implementation costs in the basic fully functional version, but offers scalability without requiring a complete system upgrade.
Abstract: One area of special importance for the surface-level study of heat exchangers is tubes with internal micro-fins (< 0.5 mm tall). Micro-finned surfaces are a kind of extended solid surface in which energy is exchanged with water that acts as the source or sink of energy. Significant performance gains are possible for either shell, tube, or double pipe heat exchangers if the best surfaces are identified. The parametric studies of micro-finned tubes that have appeared in the literature left some key parameters unexplored. Specifically, they ignored three-dimensional (3D) micro-fin configurations, conduction heat transfer in the fins, and conduction in the solid surface below the micro-fins. Thus, this study aimed at implementing a parametric study of 3D micro-finned tubes that considered micro-fine height and discontinuity features. A 3D conductive and convective heat-transfer simulation through coupled solid and periodic fluid domains is applied in a commercial package, ANSYS Fluent 19.1. The simulation is steady-state with turbulent water flow cooling the inner wall of a tube with micro-fins. The simulation utilizes a constant and uniform temperature on the tube outer wall. Performance is mapped for 18 different simulation cases, including a smooth tube using a realizable k-ε turbulence model at a Reynolds number of 48,928. Results compared the performance of 3D tubes with results for the similar two-dimensional (2D) one. Results showed that the micro-fine height has a greater impact on performance factors than discontinuity features in 3D micro-fin tubes. A transformed 3D micro-fin tube can enhance heat transfer, and pressure drops up to 21% and 56% compared to a 2D one, respectfully.
Abstract: Due to the concerns about the depletion of fossil fuel sources and the deteriorating environment, the attempt to investigate the production of renewable energy will play a crucial role as a potential to alleviate the dependency on mineral fuels. One particular area of interest is generation of bio-oil through sewage sludge (SS) pyrolysis. SS can be a potential candidate in contrast to other types of biomasses due to its availability and low cost. However, the presence of high molecular weight hydrocarbons and oxygenated compounds in the SS bio-oil hinders some of its fuel applications. In this context, catalytic pyrolysis is another attainable route to upgrade bio-oil quality. Among different catalysts (i.e., zeolites) studied for SS pyrolysis, activated chars (AC) are eco-friendly alternatives. The beneficial features of AC derived from SS comprise the comparatively large surface area, porosity, enriched surface functional groups and presence of a high amount of metal species that can improve the catalytic activity. Hence, a sludge-based AC catalyst was fabricated in a single-step pyrolysis reaction with NaOH as the activation agent and was compared with HZSM5 zeolite in this study. The thermal decomposition and kinetics were invested via thermogravimetric analysis (TGA) for guidance and control of pyrolysis and catalytic pyrolysis and the design of the pyrolysis setup. The results indicated that the pyrolysis and catalytic pyrolysis contain four obvious stages and the main decomposition reaction occurred in the range of 200-600 °C. Coats-Redfern method was applied in the 2nd and 3rd devolatilization stages to estimate the reaction order and activation energy (E) from the mass loss data. The average activation energy (Em) values for the reaction orders n = 1, 2 and 3 were in the range of 6.67-20.37 kJ/mol for SS; 1.51-6.87 kJ/mol for HZSM5; and 2.29-9.17 kJ/mol for AC, respectively. According to the results, AC and HZSM5 both were able to improve the reaction rate of SS pyrolysis by abridging the Em value. Moreover, to generate and examine the effect of the catalysts on the quality of bio-oil, a fixed-bed pyrolysis system was designed and implemented. The composition analysis of the produced bio-oil was carried out via gas chromatography/mass spectrometry (GC/MS). The selected SS to catalyst ratios were 1:1, 2:1 and 4:1. The optimum ratio in terms of cracking the long-chain hydrocarbons and removing oxygen-containing compounds was 1:1 for both catalysts. The upgraded bio-oils with HZSM5 and AC were in the total range of C4-C17 with around 72% in the range of C4-C9. The bio-oil from pyrolysis of SS contained 49.27% oxygenated compounds while the presence of HZSM5 and AC dropped to 7.3% and 13.02%, respectively. Meanwhile, generation of value-added chemicals such as light aromatic compounds were significantly improved in the catalytic process. Furthermore, the fabricated AC catalyst was characterized by BET, SEM-EDX, FT-IR and TGA techniques. Overall, this research demonstrated that AC is an efficient catalyst in the pyrolysis of SS and can be used as a cost-competitive catalyst in contrast to HZSM5.
Abstract: Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., entropy, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one-class classification (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, principal component analysis (PCA), kernel principal component analysis (KPCA), and autoassociative neural network (ANN) are presented and their performance are compared. It is also shown that, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 95%.
Abstract: This paper deals with the problem of using Autonomous Robotic Platforms (ARP) for the ADAS (Advanced Driver Assistance Systems) testing in automotive. There are different possibilities of the testing already in development and lately, the ARP are beginning to be used more and more widely. ARP discussed in this paper explores the hardware and software design possibilities related to the field of embedded systems. The paper focuses in its chapters on the introduction of the problem in general, then it describes the proposed prototype concept and its principles from the embedded HW and SW point of view. It talks about the key features that can be used for the innovation of these platforms (e.g., modularity, omnidirectional movement, common and non-traditional sensors used for localization, synchronization of more platforms and cars together or safety mechanisms). In the end, the future possible development of the project is discussed as well.
Abstract: Analysis of the human microbiome using metagenomic
sequencing data has demonstrated high ability in discriminating
various human diseases. Raw metagenomic sequencing data require
multiple complex and computationally heavy bioinformatics steps
prior to data analysis. Such data contain millions of short sequences
read from the fragmented DNA sequences and stored as fastq files.
Conventional processing pipelines consist in multiple steps including
quality control, filtering, alignment of sequences against genomic
catalogs (genes, species, taxonomic levels, functional pathways,
etc.). These pipelines are complex to use, time consuming and
rely on a large number of parameters that often provide variability
and impact the estimation of the microbiome elements. Training
Deep Neural Networks directly from raw sequencing data is a
promising approach to bypass some of the challenges associated with
mainstream bioinformatics pipelines. Most of these methods use the
concept of word and sentence embeddings that create a meaningful
and numerical representation of DNA sequences, while extracting
features and reducing the dimensionality of the data. In this paper
we present an end-to-end approach that classifies patients into disease
groups directly from raw metagenomic reads: metagenome2vec. This
approach is composed of four steps (i) generating a vocabulary of
k-mers and learning their numerical embeddings; (ii) learning DNA
sequence (read) embeddings; (iii) identifying the genome from which
the sequence is most likely to come and (iv) training a multiple
instance learning classifier which predicts the phenotype based on
the vector representation of the raw data. An attention mechanism
is applied in the network so that the model can be interpreted,
assigning a weight to the influence of the prediction for each genome.
Using two public real-life data-sets as well a simulated one, we
demonstrated that this original approach reaches high performance,
comparable with the state-of-the-art methods applied directly on
processed data though mainstream bioinformatics workflows. These
results are encouraging for this proof of concept work. We believe
that with further dedication, the DNN models have the potential to
surpass mainstream bioinformatics workflows in disease classification
tasks.
Abstract: Machine learning is a new and exciting area of
artificial intelligence nowadays. Machine learning is the most
valuable, time, supervised, and cost-effective approach. It is not a
narrow learning approach; it also includes a wide range of methods
and techniques that can be applied to a wide range of complex realworld
problems and time domains. Biological image classification,
adaptive testing, computer vision, natural language processing, object
detection, cancer detection, face recognition, handwriting
recognition, speech recognition, and many other applications of
machine learning are widely used in research, industry, and
government. Every day, more data are generated, and conventional
machine learning techniques are becoming obsolete as users move to
distributed and real-time operations. By providing fundamental
knowledge of machine learning tools and research opportunities in
the field, the aim of this article is to serve as both a comprehensive
overview and a guide. A diverse set of machine learning resources is
demonstrated and contrasted with the key features in this survey.
Abstract: In light of the substantial increase in end-user requirements and the incessant need of network operators to upgrade the capabilities of access networks, in this paper, the performance of the different modulation formats on eight-channels Time and Wavelength Division Multiplexing Passive Optical Network (TWDM-PON) transmission system has been examined and compared. Limitations and features of modulation formats have been determined to outline the most suitable design to enhance the data rate and transmission reach to obtain the best performance of the network. The considered modulation formats are On-Off Keying Non-Return-to-Zero (NRZ-OOK), Carrier Suppressed Return to Zero (CSRZ), Duo Binary (DB), Modified Duo Binary (MODB), Quadrature Phase Shift Keying (QPSK), and Differential Quadrature Phase Shift Keying (DQPSK). The performance has been analyzed by varying transmission distances and bit rates under different channel spacing. Furthermore, the system is evaluated in terms of minimum Bit Error Rate (BER) and Quality factor (Qf) without applying any dispersion compensation technique, or any optical amplifier. Optisystem software was used for simulation purposes.
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.