River flow prediction is a pivotal task in the field of water resource management during the era of rapid climate change. The highly dynamic and evolving nature of the climatic variables e.g., precipitation has a significant impact on the temporal distribution of the river discharge in recent days making the discharge forecasting even more complicated for diversified water-related issues e.g., flood prediction and irrigation planning. To predict the discharge, various physics-based numerical models are used using numerous hydrologic parameters. Extensive lab-based investigation and calibration are required to reduce the uncertainty involved in those parameters. However, in the age of data-driven predictions, several deep learning algorithms showed satisfactory performance in dealing with sequential data. In this research, Long Short-term Memory (LSTM) neural network regression model is trained using over 80 years of daily data to forecast the discharge time series up to 3 days ahead of time. The performance of the model is found satisfactory through the comparison of the predicted data with the observed data, visualization of the distribution of the errors and Root Mean Squared Error (RMSE) value of 0.09. Higher performance is achieved through the increase in the number of epochs and hyper parameter tuning. This model can be transferred to other locations with proper feature engineering and optimization to perform univariate predictive analysis and potentially be used to perform real-time river discharge prediction.

Despite a rapid rise in NBS development in recent years, the methods for evaluating NBS still have certain gaps. We propose an approach based on a combination of remote sensing data and meteorological variables to reconstruct the spatio-temporal variation of net ecosystem exchange from eddy-covariance stations. Lagrangian particle dispersion model was used for upscaling of satellite images and flux towers. We trained data-driven models based on kernel methods separately for each selected land cover class. The results suggest that the proposed approach to quantifying carbon exchange on a medium-to-large scale by blending eddy covariance flux data with moderate resolution satellite and weather data provides a set of key advantages over previously deployed methods: (1) scalability, achieved via the validation design based on a separate set of eddy covariance stations; (2) high spatial and temporal resolution due to use of the Landsat imagery; (3) robust and accurate predictions due to improved data quality control, advanced machine learning techniques, and rigorous validation. The machine learning models yielded high cross-validation results. Overall we present here globally scaled technology for the land sector based on high resolution remote sensing imagery, meteorological variables, and direct carbon flux measurements of eddy covariance flux stations.

A construction for the systems of natural and real numbers is presented in Zermelo-Fraenkel Set Thoery, that allows for simple proofs of the properties of these systems, and practical and mathematical applications. A practical application is discussed, in the form of a Simple and Linear Fast Adder (Patent Pending). Applications to finite group theory and analysis are also presented. A method is illustrated for finding the automorphisms of any finite group $G$, which consists of defining a canonical block form for finite groups. Examples are given, to illustrate the procedure for finding all groups of $n$ elements along with their automorphisms. The canonical block form of the symmetry group $\Delta_4$ is provided along with its automorphisms. The construction of natural numbers is naturally generalized to provide a simple and sound construction of the continuum with order and addition properties, and where a real number is an infinite set of natural numbers. A basic outline of analysis is proposed with a fast derivative algorithm. Under this representation, a countable sequence of real numbers is represented by a single real number. Furthermore, an infinite $\infty\times\infty$ real-valued matrix is represented with a single real number. A real function is represented by a set of real numbers, and a countable sequence of real functions is also represented by a set of real numbers. In general, mathematical objects can be represented using the smallest possible data type and these representations are calculable. In the last section, mathematical objects of all types are well assigned to tree structures in a proposed type hierarchy.

Additive manufacturing (AM) are used in several industries such as automotive, aerospace, and medical sciences. One of the most common devices used in additive manufacturing is fused deposition modeling (FDM) 3D printers. This fabrication method has different inputs that affect the quality of the parts. In this research, the bending fatigue properties of polylactic acid (PLA) biomaterial made with a 3D printer are investigated. To demonstrate the influence of printing parameters on fatigue lifetime, standard specimens with nozzle diameters of 0.2-0.6 mm, extruder temperature of 180-240°C, and print speed of 5-15 mm/s were printed. After performing fully-reversed bending fatigue tests, it was found that printed specimens at 180°C have the best fatigue lifetime in most cases. Accordingly, fatigue behavior improved by reducing the nozzle diameter. Printing at lower temperatures also improved fatigue lifetime. The printing speed affected the slope of the S-N diagram, known as the fatigue strength exponent.

The herd effect is a common phenomenon in social society. The detection of this phenomenon is of great significance in many tasks based on social network analysis such as recommendation. However, the research on social network and natural language processing seldom focuses on this issue. In this paper, we propose an unsupervised data mining method to detect herding in social networks. Taking shopping review as an example, our algorithm can identify other reviews which are affected by some previous reviews and detect a herd effect chain. From the overall perspective, the cross effects of all views form the herd effect graph. This algorithm can be widely used in various social network analysis methods through graph structure, which provides new useful features for many tasks.

Maritime ship monitoring plays an important role in maritime transportation. Fast and accurate detection of maritime ship is the key to maritime ship monitoring. The main sources of marine ship images are optical images and synthetic aperture radar (SAR) images. Different from natural images, SAR images are independent to daylight and weather conditions. Traditional ship detection methods of SAR images mainly depend on the statistical distribution of sea clutter, which leads to poor robustness. As a deep learning detector, RetinaNet can break this obstacle, and the problem of imbalance on feature level and objective level can be further solved by combining with Libra R-CNN algorithm. In this paper, we modify the feature fusion part of Libra RetinaNet by adding a bottom-up path augmentation structure to better preserve the low-level feature information, and we expand the dataset through style transfer. We evaluate our method on the publicly available SAR dataset of ship detection with complex backgrounds. The experimental results show that the improved Libra RetinaNet can effectively detect multi-scale ships through expansion of the dataset, with an average accuracy of 97.38%.

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from 8 volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides the accuracy performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. Our results indicate that the proposed method will provide the medical doctors and trainers a promising way to precisely track and understand a patient’s physical activities for better treatment.

Extensive, but remote oil and gas fields of the United States, Canada, and Russia require the construction and operation of extremely long pipelines. Global warming and local heating effects lead to rising soil temperatures and thus a reduction in the sub-grade capacity of the soils; this causes changes in the spatial positions and forms of the pipelines, consequently increasing the number of accidents. Oil operators are compelled to monitor the soil temperature along the routes of the remoted pipelines in order to be able to perform remedial measures in time. They are therefore seeking methods for the analysis of volumetric diagnostic information. To forecast soil temperatures at the different depths we propose compiling a multidimensional dataset, defining descriptive statistics; selecting uncorrelated time series; generating synthetic features; robust scaling temperature series, tuning the additive regression model to forecast soil temperatures.

Nowadays, and with the mechanization of life, speech processing has become so crucial for the interaction between humans and machines. Deep neural networks require a database with enough data for training. The more features are extracted from the speech signal, the more samples are needed to train these networks. Adequate training of these networks can be ensured when there is access to sufficient and varied data in each class. If there is not enough data; it is possible to use data augmentation methods to obtain a database with enough samples. One of the obstacles to developing speech emotion recognition systems is the Data sparsity problem in each class for neural network training. The current study has focused on making a cycle generative adversarial network for data augmentation in a system for speech emotion recognition. For each of the five emotions employed, an adversarial generating network is designed to generate data that is very similar to the main data in that class, as well as differentiate the emotions of the other classes. These networks are taught in an adversarial way to produce feature vectors like each class in the space of the main feature, and then they add to the training sets existing in the database to train the classifier network. Instead of using the common cross-entropy error to train generative adversarial networks and to remove the vanishing gradient problem, Wasserstein Divergence has been used to produce high-quality artificial samples. The suggested network has been tested to be applied for speech emotion recognition using EMODB as training, testing, and evaluating sets, and the quality of artificial data evaluated using two Support Vector Machine (SVM) and Deep Neural Network (DNN) classifiers. Moreover, it has been revealed that extracting and reproducing high-level features from acoustic features, speech emotion recognition with separating five primary emotions has been done with acceptable accuracy.

We present a new Multiple-Observations (MO) helper data scheme for secret-key binding to an SRAM PUF. This MO scheme binds a single key to multiple enrollment observations of the SRAM PUF. Performance is improved in comparison to classic schemes which generate helper data based on a single enrollment observation. The performance increase can be explained by the fact that the reliabilities of the different SRAM cells are modeled (implicitly) in the helper data. We prove that the scheme achieves secret-key capacity for any number of enrollment observations, and, therefore it is optimal. We evaluate performance of the scheme using Monte Carlo simulations, where an off-the-shelf LDPC code is used to implement the linear error-correcting code. Another scheme that models the reliabilities of the SRAM cells is the so-called Soft-Decision (SD) helper data scheme. The SD scheme considers the one-probabilities of the SRAM cells as an input, which in practice are not observable. We present a new strategy for the SD scheme that considers the binary SRAM-PUF observations as an input instead and show that the new strategy is optimal and achieves the same reconstruction performance as the MO scheme. Finally, we present a variation on the MO helper data scheme that updates the helper data sequentially after each successful reconstruction of the key. As a result, the error-correcting performance of the scheme is improved over time.

Within the framework of multiblock data analysis, a unified approach of supervised methods is discussed. It encompasses multiblock redundancy analysis (MB-RA) and multiblock partial least squares (MB-PLS) regression. Moreover, we develop new supervised strategies of multiblock data analysis, which can be seen as variants of one or the other of these two methods. They are respectively refered to as multiblock weighted redundancy analysis (MB-WRA) and multiblock weighted covariate analysis (MB-WCov). The four methods are based on the determination of latent variables associated with the various blocks of variables. They are derived from clear optimization criteria whose aim is to maximize either the sum of the covariances or the sum of squared covariances between the latent variable associated with the response block of variables and the block latent variables associated with the various explanatory blocks of variables. We also propose indices to help better interpreting the outcomes of the analyses. The methods are illustrated and compared based on simulated and real datasets.

This paper introduces a method for tunnel point cloud and BIM model integration and cross-section monitoring, providing information to analyse tunnel cross-sections and surrounding rock deformation, and support for tunnel maintenance and reconstruction. Three types of data are processed for the integration: laser scanning point cloud, BIM tunnel model and terrain model from oblique photogrammetry. An adaptive BIM modelling scheme is proposed for tunnels with alien structures. Precise spatial registration of the data sets is conducted by applying singular value decomposition (SVD) algorithm to calculate transformation parameters from the point cloud model to the BIM model. Since the tunnel central line has high-order derivability, a cross-section calculation method based on tangent vector is proposed to obtain the cross-sectional profile of tunnels at any mileage. The proposed method has been verified by applying it to a tunnel reconstruction project. The experiment results show that the tunnel point cloud and the BIM model were highly coincident after the integration. The developed program can effectively get the cross-section of the tunnel at any mileage, and correctly express the spatial relationship between the BIM tunnel, the point cloud of tunnel and the external mountainous terrain.

Contact tracing has become an indispensable tool of various extensive measures to control the spread of COVID-19 pandemic due to novel coronavirus. This essential tool helps to identify, isolate and quarantine the contacted persons of a COVID-19 patient. However, the existing contact tracing applications developed by various countries, health organizations to trace down the contacts after identifying a COVID-19 patient suffers from several security and privacy concerns. In this work, we have identified those security and privacy issues of several leading contact tracing applications and proposed a blockchain-based framework to overcome the major security and privacy challenges imposed by the applications. We have discussed the security and privacy measures that are achieved by the proposed framework to show the effectiveness against the security and privacy issues raised by the existing mobile contact tracing applications.

The purpose of this study was to detect mind-wandering experienced by pre-service teachers while learning video lecture on physics. The lecture was videotaped and consisted of a live lecture in a classroom. The lecture was about Gauss's law on physics. We investigated whether oculomotor data and eye movements could be used as a marker to indicate the learner’s mind-wandering. Each data was collected in a study in which 24 pre-service teachers (16 females and 8 males) reported self-caught mind-wandering while learning physics video lecture during30 minutes. A Tobii Pro Spectrum (sampling rate: 300Hz) was used to capture their eye-gaze during learning Gauss's law course video. After watching video lecture, we interviewed pre-service teachers about their mind-wandering experience. We first used the self-caught method to capture the mind-wandering timing of pre-service teachers while learning from video lectures. We detected more accurate mind-wandering segments by comparing fixation duration and saccade count. We investigated two types of oculomotor data (blink count, pupil size) and nine eye movements (average peak velocity of saccades; maximum peak velocity of saccades; standard deviation of peak velocity of saccades; average amplitude of saccades; maximum amplitude of saccades; total amplitude of saccades; saccade count/s; fixation duration; fixation dispersion). The result was that the blink count could not be used as a marker for mind-wandering during learning video lectures among them (oculomotor data and eye movements), unlike previous literatures. Based on the results of this study, we identified elements that can be used as mind-wandering markers while learning from video lectures that are similar to real classes, among the oculomotor data and eye movement mentioned in previous literatures. Also, we found that most participants focused on past thoughts and felt unpleasant after experiencing mind-wandering through interview analysis.

Modeling brain dynamics to better understand and control complex behaviors underlying various cognitive brain functions are of interests to engineers, mathematicians, and physicists from the last several decades. With a motivation of developing computationally efficient models of brain dynamics to use in designing control-theoretic neurostimulation strategies, we have developed a novel data-driven approach in a long short-term memory (LSTM) neural network architecture to predict the temporal dynamics of complex systems over an extended long time-horizon in future. In contrast to recent LSTM-based dynamical modeling approaches that make use of multi-layer perceptrons or linear combination layers as output layers, our architecture uses a single fully connected output layer and reversed-order sequence-to-sequence mapping to improve short time-horizon prediction accuracy and to make multi-timestep predictions of dynamical behaviors. We demonstrate the efficacy of our approach in reconstructing the regular spiking to bursting dynamics exhibited by an experimentally-validated 9-dimensional Hodgkin-Huxley model of hippocampal CA1 pyramidal neurons. Through simulations, we show that our LSTM neural network can predict the multi-time scale temporal dynamics underlying various spiking patterns with reasonable accuracy. Moreover, our results show that the predictions improve with increasing predictive time-horizon in the multi-timestep deep LSTM neural network.

Rapid technological advancements in information communication technologies have enabled water resource data collection at greater spatial and temporal scale. However, this water data is often limited to the purposes of its primary collection, and limits decisions made by stakeholders towards sustainable urban water management. This empirically focused research paper examines how water practitioners involved in strategic planning can capture additional values from integrating different water data. Furthermore, the perception of 22 urban water practitioners across Australia are presented, regarding the importance of and difficulty in using water data for strategic planning, and the necessary steps for achieving integrated water management practices. Interviewees perception revealed gaps in available water resource data (i.e. water quality, ground water, stormwater, and urban water use), and limitations of industry guidelines for operating within existing governance frameworks. Overall, the research highlights the Australian urban water sector’s perception of water data’s crucial role in representing stakeholders interest; however, changes made in water data’s collection are required for an integrated water management approach. Implications for future open water data standard are discussed.

The UNESCO World Heritage Hadrian’s Villa lies over the Colli Albani volcanic district near Rome. Magnetic, paleomagnetic, radar, and electric resistivity surveys were performed in the Plutonium–Inferi sector to detect buried buildings and outline a segment of the underground system of tunnels that link different zones of the villa. In particular, a paleomagnetic analysis of the bedrock unit allowed to accomplish an accurate geomagnetic field modelling and characterize the archaeological sources of the magnetic field anomalies. We used a computer-assisted forward modelling procedure to generate a structural model of the sources of the observed anomalies. The intrinsic ambiguity of the magnetic field modelling was reduced with the support of ground penetrating radar amplitude slices and an analysis of radar and electric resistivity profiles. The bedrock lithology in this area is an ignimbrite tuff characterized by abundant iron oxides. The high-amplitude magnetic anomalies observed in the Plutonium–Inferi area are due to strong bedrock remnant magnetization and susceptibility contrasts between topsoil infill of cavities and the surrounding tuff. The resulting magnetization model of the Plutonium–Inferi complex shows that the observed anomalies are mostly due to the presence of tunnels, skylights and a system of ditches excavated in the tuff.

In the neuroscience research field, specific for medical imaging analysis, how to mining more latent medical information from big medical data is significant for us to find the solution of diseases. In this review, we focus on neuroimaging data that is functional Magnetic Resonance Imaging (fMRI) which non-invasive techniques, it already becomes popular tools in the clinical neuroscience and functional cognitive science research. After we get fMRI data, we actually have various software and computer programming that including open source and commercial, it's very hard to choose the best software to analyze data. What's worse, it would cause final result imbalance and unstable when we combine more than software together, so that's why we want to make a pipeline to analyze data. On the other hand, with the growing of machine learning, Python has already become one of very hot and popular computer programming. In addition, it is an open source and dynamic computer programming, the communities, libraries and contributors fast increase in the recent year. Through this review, we hope that can make neuroimaging data analysis more easy, stable and uniform base the one platform system.

In the Korean construction industry, legal and institutional safety management improvements are continually being pursued. However, there was a 4.5% increase in the number of workers’ deaths at construction sites in 2017 compared to the previous year. Failure to wear safety helmets seems to be one of the major causes of the increase in accidents, and so it is necessary to develop technology to monitor whether or not safety helmets are being used. However, the approaches employed in existing technical studies on this issue have mainly involved the use of chinstrap sensors and have been limited to the problem of whether or not safety helmets are being worn. Meanwhile, improper wearing, such as when the chinstrap and harness fixing of the safety helmet are not properly tightened, has not been monitored. To remedy this shortcoming, a sensing safety helmet with a three-axis accelerometer sensor attached was developed in this study. Experiments were performed in which the sensing data were classified whether the safety helmet was being worn properly, not worn, or worn improperly during construction workers’ activities. The results verified that it is possible to differentiate among wearing status of the proposed safety helmet with a high accuracy of 97.0%

Technology development changes society and society demands new and innovative technology development. We analyze technology to understand society and technology itself. Many researches have been introduced in various fields. Most of them were about patent analysis. This is because detailed and accurate results of research and development are patented. In this paper, we study on new patent analysis method based on count data model and Bayesian regression analysis. Using count data model, we analyze the technological keywords extracted from the collected patent documents. We use the posterior distribution of Bayesian statistics to reflect the experience and knowledge of the relevant technological experts in the analysis model. Moreover, we apply the proposed model to finding sustainable technologies. Finding and developing sustainable technologies is an important activity for companies and research institutes to maintain their technological competitiveness. To illustrate how our modeling could be applied to real domain, we carry out a case study using the patent documents related to artificial intelligence.

Coordinated sets of extremely numerous digital data, on a given social or economic event, are treated by Artificial Intelligence tools to obtain reasonably accurate, valuable predictions. The same approach, applied to biomedical issues, as how to choose the right drug to completely cure a given cancer patient, does not reach satisfactory results. It is the “organized biological complexity”, which requires a different systems approach, to integrate, in an Augmented Intelligence strategy, statistical computations of digital data, network construction of “omics” findings, well-designed mathematical models and new experiments in an iterative pathway to reconstruct the “logic” beneath the “organized complexity”, as shown here for Systems Metabolomics of cancer. On this basis new diagnostic approaches, able to identify precision drug treatments, as well as new discovery strategy for more effective anti-cancer drugs are described.

Satellite remote sensing is a powerful tool to map flooded areas. In the last years, the availability of free satellite data sensibly increased in terms of type and frequency, allowing producing flood maps at low cost around the World. In this work, we propose a semi-automatic method for flood mapping, based only on free satellite images and open-source software. As case studies, we selected three flood events recently occurred in Spain and Italy. Multispectral satellite data acquired by MODIS, Proba-V, Landsat, Sentinel-2 and SAR data collected by Sentinel-1 were used to detect flooded areas using different methodologies (e.g., MNDWI; SAR backscattering variation; Supervised classification). Then, we improved and manually refined the automatic mapping using free ancillary data like DEM based water depth model and available ground truth data. For the areas affected by major floods, we also validated and compared the produced flood maps with official maps made by river authorities. We calculated flood detection performance (flood ratio) for the different datasets we used. The results show that it is necessary to take into account different factors for the choice of best satellite data, among these, the time of satellite pass with respect to the flood peak is the most important one. SAR data showed good results only for co-flood acquisitions, whereas multispectral images allowed detecting flooded areas also with the post-flood acquisition. With the support of ancillary data, it was possible to produce reliable geomorphological based flood maps in the study areas.

For automobile insurance, it has long been implied that when a policyholder made at least one claim in the prior year, the subsequent premium is likely to increase. When this happens, the policyholder may seek to switch to another insurance company to possibly avoid paying for a higher premium. In such situations, insurers may be faced with the challenges of policyholder retention by keeping premiums low in the face of competition. In this paper, we seek to find empirical evidence of possible association between policyholder switching after a claim and the associated change in premium. In accomplishing this goal, we employ the method of association rule learning, a data mining technique that has its origins in marketing for analyzing and understanding consumer purchase behavior. We apply this unique technique in two stages. In the first stage, we identify policyholder and vehicle characteristics that affect the size of the claim and resulting change in premium regardless of policy switch. In the second stage, together with policyholder and vehicle characteristics, we identify the association among the size of the claim, the level of premium increase and policy switch. This empirical process is often challenging to insurers because they are unable to observe the new premium for those policyholders who switched. However, we used a 9-year claims data for the entire Singapore automobile insurance market that allowed us to track information before and after the switch. Our results provide evidence of a strong association among the size of the claim, the level of premium increase and policy switch. We attribute this to the possible inefficiency of the insurance market because of the lack of sharing and exchange of claims history among the companies.

In this paper, we propose a simple tool to help the energy management of a large buildings stock defining clusters of buildings with the same function, setting alert thresholds for each cluster, and easily recognizing outliers. The objective is to enable a building management system to be used for detection of abnormal energy use. First, we framed the issue of energy performance indicators, and how they feed into data visualization (Data Viz) tools for a large building stock, especially for university campuses. Both for Data Viz and clustering algorithm processes, we discussed two possible approaches to choose the right number of clusters and the identification of alert thresholds and outliers, after a brief presentation of the University of Turin's building stock case study. Different Data Viz tools have been studied to apply a specific clustering algorithm, the k-means one. An explorative analysis based on the general Multidimensional detective approach by Inselberg has been performed. Two multidimensional analysis tools, the Scatter Plot Matrix and the Parallel coordinates method have been used. Secondly, the k-means clustering algorithm has been applied on the same dataset in order to test the hypothesis made during the explorative analysis. Data Viz techniques developed in this study revealed to be very useful to explore quickly and simply a large buildings' stock, identifying the worst efficient buildings and clustering them according to their distinct functions.

A lack of data reproducibility (“reproducibility crisis”) is debated across many scientific and medical disciplines. A systematic analysis of the available evidence on the reliability of scientific data revealed that, although the existence of a reproducibility crisis is widely perceived, conclusive data on the scale of the problem are lacking. Most importantly we found that, although the debate is largely focused on methodological issues, researcher conduct defines research standards and in turn data reliability. The availability of reliable methods itself does not guarantee good practice. Moreover, research is typically characterised by a lack of established methods due to its immanent novelty. Despite the crucial importance of researcher conduct, research and conclusive data on the determinants of researcher behaviour are missing. In conclusion, meta-research is urgently needed that establishes an understanding of the factors that determine researcher behaviour. This knowledge can then be used to implement and iteratively improve measures, which incentivise researchers to apply the highest standards resulting in high quality data.

At present, medical institutes generally use EMR to record patient's condition, including diagnostic information, procedures performed and treatment results. EMR has been recognized as a valuable resource for large scale analysis. However, EMR has the characteristics of diversity, incompleteness, redundancy and privacy, which make it difficult to carry out data mining and analysis directly. Therefore, it is necessary to preprocess the source data in order to improve data quality and improve the data mining results. Different types of data require different processing technologies. Most structured data commonly needs classic preprocessing technologies, including data cleansing, data integration, data transformation and data reduction. For semi-structured or unstructured data, such as medical text, containing more health information, it requires more complex and challenging processing methods. The task of information extraction for medical texts mainly includes NER (Named Entity Recognition) and RE (Relation Extraction). In this paper, we introduce the process of EMR processing, including data collection, data preprocessing, data mining, evaluation and knowledge application, analyze the current status of the key technologies, such as data preprocessing and data mining, and provide an overview of the application domains and prospects of EMR mining technologies. Finally, we summarize the existing problems in the research of EMR mining, and review the development trends.

Multi-sensor data fusion of E-tongue and E-nose can provide a more comprehensive and more accurate analysis results. However, it also brings some redundant information, it is a hot issue to reduce the feature dimension for pattern recognition. In this paper, the taste-olfactory data fusion based on E-tongue and E-nose combined with Support Vector Machine (SVM) was used to classify five different beers. First, the taste and olfactory feature information were obtained based on E-tongue and E-nose. Second, the original feature data of single system were fused, then Principal Component Analysis (PCA) was applied to extract principal components, Genetic Algorithm-Partial Least Squares (GA-PLS) was used to select the characteristic variables, 20 subsets were generated with those variables based on the best Variable Importance of Projection (VIP) score. Finally, the classification models based on SVM were established, also c and g of SVM were calculated by Grid Search (GS), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO), the classification results of all subsets were obtained. The results showed that the classification accuracy using data fusion was much higher over single E-tongue and single E-nose, and the variable selection method by VIP had the best classification performance in #12 subset coupled with GA-SVM.

With the great development of intelligent transportation systems (ITS), travel time prediction has attracted the attentions of many researchers and a large number of prediction methods have been developed. However, as an unavoidable topic, the predictability of travel time series is the basic premise for travel time prediction has received less attention than the methodology. Based on the analysis of the complexity of travel time series, this paper defines travel time predictability to express the probability of correct travel time prediction and proposes an entropy-based method to measure the upper bound of travel time predictability. Multiscale entropy is employed to quantify the complexity of travel time series, and the relationships between entropy and the upper bound of travel time predictability are presented. Empirical studies are made with vehicle trajectory data in an express road section. The effectiveness of time scales, tolerance, and series length to entropy and travel time predictability are analysis, and some valuable suggestions about the accuracy of travel time predictability are discussed. Finally, the comparisons between travel time predictability and actual prediction results from two prediction models, ARIMA and BPNN, are conducted. Experimental results demonstrate the validity and reliability of the proposed travel time predictability.

More and more works are using machine learning techniques while adopting supervisory control and data acquisition (SCADA) system for wind turbine anomaly or failure detection. While parameter selection is important for modelling a wind turbine’s health condition, only a few papers have been published focusing on this issue and in those papers interconnections among sub-components in a wind turbine are used to address this problem. However, merely the interconnections for decision making sometimes is too general to provide a parameter list considering the differences of each SCADA dataset. In this paper, a method is proposed to provide more detailed suggestions on parameter selection based on mutual information. Moreover, after proving that Copula, a multivariate probability distribution for which the marginal probability distribution of each variable is uniform is capable of simplifying the estimation of mutual information, an empirical copula based mutual information estimation method (ECMI) is introduced for an application. After that, a real SCADA dataset is adopted to test the method, and the results show the effectiveness of the ECMI in providing parameter selection suggestions when physical knowledge is not accurate enough.

For offshore wind power generation, accessibility is one of the main factors that has great impact on operation and maintenance due to constraints on weather conditions for marine transportation. This paper presents a framework to explore the accessibility of an offshore site. At first, several maintenance types are defined and taken into account. Next, a data visualization procedure is introduced to provide an insight into the distribution of access periods over time. Then, a rigorous mathematical method based on finite state Markov chain is proposed to assess the accessibility of an offshore site from the maintenance perspective. A five-year weather data of a marine site is used to demonstrate the applicability and the outcomes of the proposed method. The main findings show that the proposed framework is effective in investigating the accessibility for different time scales and is able to catch the patterns of the distribution of the access periods. Moreover, based on the developed Markov chain, the average waiting time for a certain access period can be estimated. With more information on the maintenance of an offshore wind farm, the expected production loss due to time delay can be calculated.

Disparities between fold amplitude (A) and intrusion thickness (Hsill) are critical in identifying elastic or inelastic deformation in a forced fold. However, accurate measurement of these two parameters is challenging because of the limit in separability and detectability for the seismic data. In the TZ-47 exploring area from the Tarim Basin, Northwest China, we combined wireline data and 3-D seismic data, to accurately constrain the fold amplitude and total thickness of sills that inducing the roof uplift. The measurement results show that the forced fold amplitude is 155 m and the total sill thickness is 148.4 m. When using a magma density of 2.7 g/cm3, and solid rock density of 3 g/cm3, the molten magma thickness at the time of intrusion would be 153.8 m, which is almost no difference from the forced fold amplitude. Therefore, the TZ-47 fold is a pure elastic forced fold induced by emplacement of multiple sills. Measurement solely based on seismic data may not be able to detect some thin interlayers and may result in large errors.

AbstractThe escalating impact of artificial intelligence (AI) has birthed the fascinating technology of deepfakes, capable of meticulously crafting hyper-realistic audio-visual manipulations. Within the realm of healthcare, this technology presents a double-edged sword, brimming with potential for revolutionizing various facets of care delivery while simultaneously harboring significant ethical and practical challenges. This research delves into the complex narrative surrounding AI deepfakes in healthcare, meticulously analyzing both the exciting opportunities they offer, and the inherent risks associated with their implementation.Background:Traditional healthcare practices face limitations in patient engagement, accessibility, and training efficacy. Deepfakes, with their ability to simulate real-world scenarios and interactions, emerge as a potential solution, offering personalized patient education, immersive mental health interventions, remote consultations with virtual avatars, and realistic training simulations for medical professionals.Objective:This research aims to comprehensively understand the multifaceted impact of AI deepfakes in healthcare systems. It seeks to: Identify and analyze the potential benefits of deepfakes in specific healthcare applications. Assess the ethical and practical challenges associated with deepfake implementation in healthcare settings. Propose recommendations for safe, responsible, and ethical integration of deepfakes within the healthcare system.Results/Conclusion:The research findings illuminate a landscape replete with opportunities and challenges. Deepfakes offer the potential to enhance patient education, personalize mental health interventions, facilitate remote consultations, and revolutionize medical training. However, concerns regarding misinformation, ethical breaches, data privacy, and technical limitations pose significant challenges.The conclusion emphasizes the need for a balanced approach that capitalizes on the innovative potential of deepfakes while mitigating potential harm. Collaborative efforts involving healthcare professionals, technologists, and policymakers are crucial for establishing ethical frameworks, ensuring responsible development, and harnessing the positive power of deepfakes to build a future where healthcare benefits from cutting-edge technology while prioritizing patient well-being and ethical principles.

Advanced state-of-the-art technologies, mainly computational intelligence including Machine/Deep Learning and Fuzzy Computing, through applied research, can provide added value to modern science and, in general, to entrepreneurship and the economy. Artificial intelligence is the field of computer science that attempts to model concepts such as learning, adaptability and perception to synthesize intelligent behavior in solving complex problems, utilizing elements of adaptation to the environment and philosophical reasoning. About the science of civil engineering and, in general, the construction industry, which is one of the most important in economic entrepreneurship, both in terms of the size of the workforce employed and the amount of capital invested, the penetration of artificial intelligence is possible to change industry business models, eliminate costly mistakes, reduce Jobsite injuries and generally make large-scale engineering projects more efficient. The purpose of the paper is to present the recent research on artificial intelligence methods (machine-deep learning, computer vision, natural language processing, fuzzy systems, robotics, etc.) and the corresponding related technologies related to it (extensive data analysis, blockchain, cloud computing, internet of things, augmented reality), in the fields of application of civil engineering science, including structural engineering, geotechnical engineering, hydraulics and water resources management, marine and coastal technology, transport and transportation infrastructure, planning and technical project management, critical infrastructure security and disaster mitigation..

Nowadays, technological advancement has transformed traditional vehicles into Au-tonomous Vehicles (A.V.s). In addition, in our daily lives, A.V.s play an important role since they are considered an essential component of smart cities. A.V. is an intelligent vehicle capable of main-taining safe driving by avoiding crashes caused by drivers. Unlike traditional vehicles, which are fully controlled and operated by humans, A.V.s collect information about the outside environment using sensors to ensure safe navigation. Furthermore, A.V.s reduce environmental impact because they usually use electricity to operate instead of fossil fuel, thus decreasing the greenhouse gasses. However, A.V.s could be threatened by cyberattacks, posing risks to human life. For example, re-searchers reported that Wi-Fi technology could be vulnerable to cyberattacks through Tesla and BMW AVs. Therefore, more research is needed to detect cyberattacks targeting the components of A.V.s to mitigate their negative consequences. This research will contribute to the security of A.V.s by detecting cyberattacks at the early stages. First, we inject False Data Injection (FDI) attacks into an A.V. simulation-based system developed by MathWorks. Inc. Second, we collect the dataset generated from the simulation model after integrating the cyberattack. Third, we implement an intelligent symmetrical anomaly detection method to identify FDI attacks targeting the control system of the A.V. through a compromised sensor. We use long short-term memory (LSTM) deep networks to detect FDI attacks in the early stage to ensure the stability of the operation of A.V.s. Our method classifies the collected dataset into two classifications: normal and anomaly data. The ex-perimental result shows that our proposed model's accuracy is 99.95%. To this end, the proposed model outperforms other state-of-the-art models in the same study area.

Current satellite remote sensing methods struggle to detect and map forest degradation, a critical issue as it is likely a major and growing source of carbon emissions and biodiveristy loss. TanDEM-X InSAR phase height (hϕ) is a promising variable for measuring forest disturbances, as it is closely related to mean canopy height, and thus should decrease if canopy trees are removed. However, previous research has focused on relatively flat terrain, despite the fact that much of the worlds’ remaining tropical forests are found in hilly areas, and this inevitably introduces artifacts in sideways imaging systems. In this paper, we find a relationship between hϕ and aboveground biomass change in four selectively logged plots in a hilly region of central Gabon. We show that minimising the level of multilooking in the interferometric processing chain strengthens this relationship, and that degradation estimates across steep slopes in the surrounding region are improved by selecting data from the most appropriate pass directions on a pixel-by-pixel basis. This shows that TanDEM-X InSAR can measure the magnitude of degradation, and that topographic effects can be mitigated if data from multiple SAR viewing geometries are available.

This article presents a low-cost insurance system developed for small-hold farms in disaster-prone regions, primarily using free Earth Observation (EO) data and Free Open Source Software (FOSS) – collectively termed sustainable geoinformatics - with a proprietary mobile phone app that enables verification. The study examined 30 farms in Risaralda department, Colombia. A Digital Elevation Model (12.5m pixels) from the ALOS PALSAR satellite sensor was used with a Geographical Information System (GIS) to map the terrain, drainage and geohazards of each farming district. Google Earth Engine (GEE) was used to carry out Time Series Analysis of 15 EO and weather datasets for 1998 to 2020. This analysis enabled the levels of risk from hydrometeorological hazards to be determined for each farm of the study, providing key data for the setting of insurance premiums. A parametric insurance product was piloted using GPS-tagged, time-stamped mobile phone photos to verify crop health. Key features of this insurance system are its low operational cost and rapid damage verification, relative to conventional approaches to farm insurance. It is an affordable form of insurance for small-scale farmers, with the rapid verification and payment of claims. This relatively fast, low-cost and affordable approach to insurance for small-scale farming enhances sustainable development by enabling policy-holder farmers to recover more quickly from disasters.

The article describes the results of comparison of occurence of buildings (and address points) in Poland with delimitations of land use belonging to particular classes in the CORINE Land Cover (CLC) 2018 dataset. Large discrepancies have been identified, which reach on average approx. 34% of addresses and 35% of buildings located outside class 1 (artificial surfaces), mainly on terrains of class 2 (agricultural areas). Among single-family buildings it was 37% and among new addresses (forecasted or ‘under construction’ buildings) – as much as 50%. This puts a question mark over the possibility of using CLC data with resolution of 25 ha for monitoring of spatial planning and development in Poland for purposes of the diagnosis and assessment of the scale of dispersion of built-up areas. It is worth carrying out similar analyses in other countries, known for the deconcentration processes and a relatively large share of dispersed settlement e.g. other CEE countries, Spain, Portugal, Italy.

With the increase in life expectancy and consequent aging of the world’s population, the prevalence of many neurodegenerative diseases is increasing, without concomitant improvement in diagnostics and therapeutics. These diseases share neuropathological hallmarks, including mitochondrial dysfunction. In fact, as mitochondrial alterations appear prior to neuronal cell death at an early phase of the disease onset, the study and modulation of mitochondrial alterations rise as promising strategies to predict and prevent neurotoxicity and neuronal cell death before the onset of cell viability alterations. In this work, differentiated SH-SY5Y cells were treated with the mitochondrial-targeted neurotoxicants 6-hydroxydopamine and rotenone. These compounds were used at different concentrations and for different time points to understand the similarities and differences in their mechanisms of action. To accomplishing this, data on mitochondrial parameters was acquired and analyzed using unsupervised (hierarchical clustering) and supervised (decision tree) machine learning methods. Both biochemical and computational analyses resulted in an evident distinction between the neurotoxic effects of 6-hydroxydopamine and rotenone, specifically for the highest concentrations of both compounds.

The aim of this work is to explain the behaviour of the multiresistance percentage of Pseudomona aeruginosa in some countries of Europe through a multivariate statistical analysis and machine learning validation, using data from the European Antimicrobial Resistance Surveillance System, the World Health Organization and the World Bank. First, we will use a descriptive analysis and a principal components analysis. Then, we use a k-means clustering to determine the countries and regions that are most affected by the antibiotic resistance. Second, we expand the database by adding some socioeconomic, governance and antibiotic-consumption variables. We then run a data panel regression analysis to determine some functions that relates the multiresistance percentage with those new variables. Finally, we use machine learning techniques to validate a pooling panel data case, using XGBoost and random forest algorithms. The results of the data panel analysis indicate that the most important variables for the multiresistance percentage are corruption control and the rule of law. Similar results are found with the machine learning validation analysis, where the human development index is an additional important variable for the multiresistance percentage.

(1) Background: Most patients with mycosis fungoides (MF), a form of cutaneous T-cell lym-phoma (CTCL), develop relapsed/refractory (R/R) disease following front-line systemic therapy. This report describes treatment patterns and outcomes from the subpopulation with R/R MF. (2) Methods: This observational, retrospective, cohort study analysed patient records (1984–2016) from 27 clinical sites in Eurpe. Outcomes included treatments received, response to first-, second- and third-line treatment, overall survival (OS), and progression-free survival (PFS). (3) Results: Of 104 patients with MF, 100 received second-line and 61 received third-line therapy. Median (range) times from start of first-line therapy to first R/R MF and from first to second R/R MF were 11.2 (0.3–166.5) and 13.5 (0.0–174.6) months, respectively. Second-and third-line treatment options varied and comprised systemic therapies (85% and 79% of patients, respectively), radio-therapy (32% and 34%, respectively) and topical therapies (48% and 36%, respectively). Median (95% confidence interval [CI]) OS from the diagnosis of first R/R MF was 11.5 (6.5–not reached [NR]) years and was higher with non-chemotherapy (NR) versus chemotherapy (6.5 years); es-timated median PFS (95% CI) from the time of first R/R MF was 1.3 (1.0–2.1) years. (4) Conclu-sion: High rates of R/R disease were observed after second- and third-line treatments in this re-al-world cohort, with longer median OS in patients receiving non-chemotherapy versus chemo-therapy. Following the standard management of MF and using recently approved targeted therapies can help improve patient outcomes in advanced-stage MF.

We live in the information age and, ironically, meeting the core function of journalism – i.e., to provide people access to unbiased information – has never been more difficult. This paper explores deep journalism, our data-driven Artificial Intelligence (AI) based journalism approach to study how the LinkedIn media could be useful for journalism. Specifically, we apply our deep journalism approach to LinkedIn to automatically extract and analyse big data to provide the public with information about labour markets, people’s skills and education, and businesses and industries from multi-generational perspectives. The Great Resignation and Quiet Quitting phenomena coupled with rapidly changing generational attitudes are bringing unprecedented and uncertain changes to labour markets and our economies and societies, and hence the need for journalistic investigations into these topics is highly significant. We combine big data and machine learning to create a whole machine learning pipeline and a software tool for journalism that allows discovering parameters for age dynamics in labour markets using LinkedIn data. We collect a total of 57,000 posts from LinkedIn and use it to discover 15 parameters by Latent Dirichlet Allocation algorithm (LDA) and group them into five macro-parameters, namely Generations-Specific Issues, Skills & Qualifications, Employment Sectors, Consumer Industries, and Employment Issues. The journalism approach used in this paper can automatically discover and make objective, cross-sectional, and multi-perspective information available to all. It can bring rigour to journalism by making it easy to generate information using machine learning and can make tools and information available so that anyone can uncover information about matters of public importance. This work is novel since none of the earlier works have reported such an approach and tool and leveraged it to use LinkedIn media for journalism and to discover multigenerational perspectives (parameters) for age dynamics in labour markets. The approach could be extended with additional AI tools and other media.

Automated extraction of buildings from earth observation (EO) data is important for various applications, including updating of maps, risk assessment, urban planning, policy making. Combining data from different sensors such as high-resolution multispectral (HRI) and light detection and ranging (LiDAR) has shown great potential in building extraction. Deep learning (DL) is increasingly used in multimodal data fusion and urban object extraction. However, DL-based multimodal fusion networks may underperform due to insufficient learning of “joint features” from multiple sources and oversimplified approaches to fusing multimodal features. Recently, an hybrid attention-aware fusion network (HAFNet) has been proposed for building extraction from a dataset including co-located Very-High-Resolution (VHR) optical images and Light Detection And Ranging (LiDAR) joint data. The system reported good performances thanks to the adaptivity of the attention mechanism to the features of the information content of the three streams but suffered from model overparametrization, which inevitably leads to long training times and heavy computational load. In this paper the authors propose a restructuring of the scheme, which involved replacing VGG-16-like encoders with the recently proposed EfficientNet, whose advantages counteract exactly the issues found with the HAFNet scheme. The novel configuration was tested on multiple benchmark datasets, reporting great improvements in terms of processing times, and also in terms of accuracy. The new scheme, called HAFNetE (HAFNet with EfficientNet integration), appears indeed capable of achieving good results with less parameters, translating into better computational efficiency. Based on these findings, we can conclude that, given the current advancements in single-thread schemes, the classical multi-thread HAFNet scheme could be effectively transformed by the HAFNetE scheme by replacing VGG-16 with EfficientNet blocks on each single thread. The remarkable reduction achieved in computational requirements moves the system one step closer to on-board implementation in a possible, future “urban mapping” satellite constellation.

In the last decades, climate and environmental changes have highlighted the fragility and vulnerability of the landscape, especially in mountain areas where the effects are most severe. The strategy for hazard mitigation must deploy synergistic actions based on a thorough knowledge of the territory and its phenomena to enable integrated and effective land planning and management through suitable communication tools. This study promotes the methodological setup of a Landscape Digital Twin to establish a multi-disciplinary and multi-scalar hazards overview according to a matrix framework implementable over time and space. The original contribution to the research addresses a holistic vision that combines meaningfully qualitative with quantitative approaches to generate risk maps by integrating various indicators within a multi-hazard framework from the socio-economic perspective. This contribution presents road network risk analysis by exploiting flooding and landslide scenarios. The critical road segments or nodes most vulnerable or impacted by network performance and accessibility can be identified with minimal preprocessing from credible open-source sources. The method's applicability is tested in a Piedmont Region, northern Italy case study. The integration proposed will help generate comprehensive risk analysis maps that effectively portray the interconnectedness among natural hazards, infrastructure, and socio-economic factors fostering more resilient decision-making processes.

Forest degradation is known to be widespread in the tropics, but is currently very poorly mapped, in part because there is little quantitative data on which satellite sensor characteristics and analysis methods are best at detecting it. To improve this, we used data from the Tropical Forest Degradation Experiment (FODEX) plots in the southern Peruvian Amazon, where different numbers of trees had been removed from four 1 ha forest plots, carefully inventoried by hand and Terrestrial Laser Scanning before and after the logging to give a range of biomass change (ΔAGB) values. We conducted a comparative study of six multispectral optical satellite sensors (WorldView-3, SkySat, SPOT-7, PlanetScope, Sentinel-2 and Landsat 8) at 0.3 – 30 m spatial resolution, to find the best combination of sensor and remote sensing indicator for change detection. Spectral reflectance, the Normalized Difference Vegetation Index (NDVI) and texture parameters were extracted after radiometric calibration and image preprocessing. The strength of the relationships between the change in these values and field-measured ΔAGB (computed in % ha−1) was analysed. The results demonstrate that: (a) texture measures correlates more with ΔAGB than simple spectral parameters; (b) the strongest correlations are achieved for those sensors with spatial resolutions in the intermediate range (1.5 - 10 m), with finer or coarser resolutions producing worse results, and (c) when texture is computed using a moving square window ranging between 9 - 14 m in length. Maps predicting ΔAGB showed very promising results using a NIR-derived texture parameter for 3 m resolution PlanetScope (R2 = 0.97 and RMSE = 1.80 % ha−1), followed by 1.5 m SPOT-7 (R2 = 0.74 and RMSE = 5.25 % ha−1) and 10 m Sentinel-2 (R2 = 0.71 and RMSE = 5.55 % ha−1). Texture models derived from 0.3 m WorldView-3 improved with increasing window size, with highest R2 of 0.62 and RMSE = 6.35 % ha−1 for a window of 14 m in length. The degradation in our field plots is invisible to the 30 m resolution Landsat data. Our findings imply that, at least for lowland Peru, low-medium intensity disturbance can be detected best in optical wavelengths using a texture measure derived from 3 m PlanetScope data. That such data are being collected daily, and currently released free as monthly mosaics over tropical forests as part of the Norway’s International Climate and Forest Initiative (NICFI), is excellent news for monitoring such degradation.

The land subsidence occurring in goafs after coal mining is a protracted process. The accurate prediction of long-term land subsidence in goafs relies heavily on the availability of long-term monitoring data. However, the scarcity of continuous long-term land subsidence monitoring data subsequent to the cessation of mining significantly hinders the accurate prediction of long-term land subsidence in goafs. To address this challenge, this study proposes an innovative method based on Interferometric Synthetic Aperture Radar (InSAR) for predicting long-term land subsidence of goafs following coal mining. The proposed method employs a concatenation approach that integrates multiple short-term monitoring data from different coal faces, each with distinct cessation times, into a cohesive and uniform long-term sequence by normalizing the subsidence rates. The method was verified using actual monitoring data from the Yangquan No.2 mine in Shanxi Province, China. Initially, coal faces with same shapes but varying cessation times were selected for analysis. Using InSAR monitoring data collected between June and December of 2016, the average subsidence rate corresponding to the duration after coal mining cessation of each coal face was back-calculated. Subsequently, a function relating subsidence rate to the duration after coal mining cessation was fitted to the data. Finally, the relationship between cumulative subsidence and the duration after coal mining cessation was derived by integrating the function. The results indicated that the relationship between subsidence rate and duration after coal mining cessation followed an exponential function for a given coal face, whereas the relationship between cumulative subsidence and duration after coal mining cessation conformed to the Knothe time function. Notably, after the cessation of coal mining, significant land subsidence persisted in the goaf of the Yangquan No.2 mine for a duration ranging from 5 to 10 years. The cumulative subsidence curve along the long axis of the coal face ultimately exhibited an inclined W-shape. The proposed method enables the quantitative prediction of residual land subsidence in goafs, even in cases where continuous long-term monitoring data are insufficient, thus providing valuable guidance for construction decisions above the goaf.

In economics, especially econometrics, fixed-effects are widely recognized as powerful tools for heterogeneity analysis of longitudinal data sets. However, the existing research pays more attention to such as the variable selection, parameter estimation and dimension reduction on linear relationships with too many assumptions while nonlinear relationships are ubiquitous. In this paper, an extension fixed-effects model is proposed on the curve_fit nonlinear least squares. First, with the help of expert knowledge, the series regressions between independent variables including time and dependent variable is estimated on each series data, and the parameters are estimated by curve_fit. Similarly, the coeffection between independent variables including time and dependent variable is also initially estimated on the whole panel data. Second, the distance between regressions is defined, and then the coeffect function between the series regressions is obtained on the initial co-effect with curve_fit. Third, the time-effects and individual fixed-effects for each series data in the panel data are estimated on the differences of series regressions and co-effect function. Additionally, the effectiveness of the proposed method is varified on the synthetic data.

Event data loggers are frequently used to record the date and time of tip events in tipping-bucket rain gauges. The HOBO® pendant event data logger is one such commercially-available device commonly used for this purpose. It can record the contact closure of a TBGR reed switch at a maximum timing resolution of 1 second, tied to the timing of the logger clock, which is set each time the logger is launched. These event loggers are ideal for the routine recording of rainfall. This paper addresses the issue of whether they can also be relied upon when estimating short-term intensities, for which they were not designed. New experiments show that for a series of switch closures at fixed intervals other than exact multiples of 1 s, the HOBO® logger fails to record evenly-spaced tip events. Thus, for example, with pulses at fixed 2.75 s intervals, the logger records some events as occurring at 2 s intervals, and others at 3 s intervals. The duration between logged events is correct only when the mean is calculated for a long series of logged events. In natural rainfall, tip events can occur at any time, and inter-tip times, from which intensity can be estimated, will generally not be an integral number of seconds. Consequently, particularly in intense rain, the logger behaviour just described can lead to erroneous estimates of the rainfall rate estimated from the duration of individual inter-tip times. Possible solutions are discussed.

This paper reviews the multiple roles of machine learning in improving the resilience of power grids, especially in applying new energy storage technologies. Energy storage technologies, such as compressed air energy storage, flywheel energy storage, and superconducting coil energy storage, significantly improve the power grid's ability to respond to load fluctuations and emergencies through intelligent control and optimisation of machine learning algorithms. This not only helps to optimise energy dispatch and improve the operational efficiency and flexibility of the grid but also significantly improves the stability and reliability of the grid so that it is better able to meet future challenges and needs.

Online food delivery services are rapidly growing in popularity, making customer satisfaction critical for company success in a competitive market. Accurate delivery time predictions are key to ensuring high customer satisfaction. While various methods for travel time estimation exist, effective data analysis and processing are often overlooked. This paper addresses this gap by leveraging spatial data analysis and preprocessing techniques to enhance the data quality used in Bayesian models for predicting food delivery times. We utilized the OSRM API to generate routes that accurately reflect real-world conditions. Next, we visualized these routes using various techniques to identify and examine suspicious results. Our analysis of route distribution identified two groups of outliers, leading us to establish an appropriate boundary for maximum route distance to be used in future Bayesian modelling. The spatial analysis revealed that these outliers were primarily deliveries to the outskirts or beyond the city limits. By refining the data quality through these methods, we aim to improve the accuracy of delivery time predictions, ultimately enhancing customer satisfaction.

Computational neuroscience has undergone a significant transformation in recent years, driven by the exponential growth of neural data and advancements in data science and machine learning. While traditional theoretical models remain valuable, there is a growing emphasis on integrating data-driven approaches to develop more accurate, biologically plausible, and predictive models of neural function. This shift has led to a new equilibrium in the field, where data-driven model development, machine learning techniques, and hybrid approaches that combine data and theory are increasingly prevalent. In this article, we discuss the evolving landscape of computational neuroscience, highlighting the importance of data-driven methods and the emergence of a more integrative approach that leverages both data and theory to unlock the mysteries of the brain. We also explore the implications of this shift for future research and clinical applications, emphasizing the potential for data-driven computational neuroscience to revolutionize our understanding of neural function and pave the way for new treatments for neurological disorders.

In this paper we develop and explore a methodical pipeline for swimmer localisation in outdoor environments. The developed framework is intended to be used for enhancing swimmer safety. A main issue we deal with by the proposed approach is the lack of real world training data in such outdoor environments. Natural lighting changes, dynamic water textures and possibly barely visible swimming persons are key elements to approach. We account for these difficulties by adopting an effective background removal technique with available training data. This allows us to edit swimmers into natural environment backgrounds for the use in subsequent image augmentation. We created 17 training datasets with real images, synthetic images and a mixture of both to investigate different aspects and characteristics of the proposed approach. The datasets are used to train a YOLO architecture for the possible future application in real-time detection. The trained framework is then tested and evaluated on outdoor environment imagery acquired by a safety drone to investigate and confirm the usefulness for outdoor swimmer localisation.

Since late December 2021, the Hunga Tonga-Hunga Ha'apai underwater volcano has been erupting in a series of large explosions. On Friday, January 15th, 2022, a particularly significant explosion sent a massive ash cloud high into the atmosphere. This study depicts the modeling of the volcanic ash dispersion from the event while incorporating meteorological data assimilation within the inline Weather Research and Forecasting model coupled with chemistry (WRF-Chem). Two forecast scenarios: one with only meteorology and no chemistry (OMET) and one with gas, aerosol chemistry, and no assimilation (NODA) were undertaken and compared to the third forecast impacting data assimilation to distinguish the Flux Adjusting Surface Data Assimilation System (FASDAS)'s effects. Data assimilation, a process that combines real-time observations with numerical models, plays a pivotal role in enhancing the accuracy of various scientific simulations and predictions.Analysis of different scenarios reveals that the FASDAS result in lessening of planetary boundary layer height (PBLH), downward surface shortwave flux, and 2m temperature by up to 800m, 250 W.m-2 and 6°C on the land portion, respectively, while the opposite is observed nearby the eruption site. Model validation against the observations shows that the inclusion of FASDAS nudging in WRF-Chem significantly enhances the model performance in retrieving meteorological variables. The simulations also revealed significant biases in the concentration of volcanic ash around the ash cloud. Additionally, data analysis from the Copernicus TROPOspheric Monitoring Instrument Sentinel-5 Precursor (TROPOMI-S5P) indicates that total SO2 emissions traveled west. This work demonstrates the significant contribution of data assimilation on the results of operational air quality predictions during violent volcanic eruption events.

The world has changed. New technologies, new trends, new protocols, new efficient algorithms, and systems have been used widely by civilized countries to have better and more convenient living. In this research, there have been introduced many new terms, technologies, and mechanisms. Moreover, threats, attacks, and vulnerabilities have been studied and a novel scenario has been proposed in order to overcome all these violations that have been presented in this paper. The scenario is based on a security model that has been proposed for critical sectors, such as hospitals, industries, etc., which need efficient solutions to go one step further and improve the secure and efficient living and treatment of people. The aim of this research has been to understand through research the IoT security issues and propose the appropriate solutions based on the most suitable security algorithms. The results, which have been based on the complexity, the throughput, the power consumption, the strength, and the memory usage of the algorithms studied, have been hopeful and helpful for future research and experimentation.

This paper aims to study the performance of solar collectors with various sizes under different weather conditions of different Japanese cities, i.e. Kofu city, Nagoya city and Yamagata city. The heat generated from the solar collector was used to conduct a biogas dry reforming reactor in order to produce H2 to feed a solid oxide fuel cell (SOFC). This study has revealed that the output temperature of solar collector, Tfb in April and July was higher than that in January and October irrespective of city. The optimum length of absorber (dx) of the collector was 4 m irrespective of city. It was clarified that Tfb in Yamagata city in January and October, i.e. winter and autumn is lower than that in Kofu city and Nagoya city especially, which is influenced by the tendency of a solar intensity (I) strongly, not velocity of surrounding air (ua). On the other hand, Tfb is almost the same in April and July, i.e. spring and summer, irrespective of city. The amount of produced H2 from the biogas dry reforming reactor and the power generated by SOFC using H2 in spring and summer were higher compared to the other seasons irrespective of city. This study has revealed that the highest available households number per month was 4.7 according to the investigation in this study.

AliAmbra is a project developed to explore and promote high-quality catches of the Amvrakikos Gulf GP to Artas’ wider regions. In addition, this project aimed to implement an integrated plan of action, to form a business identity with high-added value and achieve integrated business services adapted to the special characteristics of the area. The action plan for this project was to actively search for new markets, create a collective identity for the products, promote their quality and added value, engage in gastronomes and tasting exhibitions, dissemination and publicity actions, as well as enhance the quality of the products and markets based on the customer needs. The primary focus of this publication is to observe and analyze the data retrieved from various tasting exhibitions of the AliAmbra project, with a target goal of improving customer experience and product quality.

Numerous studies have been conducted in past so as to understand whether the working capital management policies of an organisation affect its performance or not. Some studies have found a positive relationship between WCM and firm performance. However, other studies have found a negative impact of WCM on firm performance. Present research work is an endeavour in this direction to find out the working capital management policies and strategies of Indian cement companies and their performances. The study employs a quantitative approach to examine whether the Indian cement companies optimally use their working capital, which is analysed by establishing the relationship between the working capital management and profitability using 11-year (2010-2021) financial data of 31 cement companies listed in Bombay Stock Exchange (BSE). The findings of the random-effects model say that only ITP is significantly negatively related to the ROA of the cement companies at a 0.01 level of significance. Similarly, APP also negatively yet poorly predicts ROA at a 0.10 level of significance the firm’s profitability is not significantly affected by ARP and CCC. Also, it has been observed that the liquidity measures CR and QR have a significant positive association with ROA. Further, the size of the industries and leverage are inversely related to ROA but the age of the firm is not significantly predicting their financial performance.

While machine learning (ML) has been quite successful in the field of structural health monitoring (SHM), its practical implementation has been limited. This is because ML model training requires data containing a variety of distinct damaged instances captured from a real structure and the experimental generation of such data is challenging. One way to tackle this issue is by generating training data through numerical simulations. However, simulated data cannot capture the bias and variance of experimental uncertainty. To overcome this problem, this work proposes a deep learning-based domain transformation method for transforming simulated data to the experimental domain. Use of this technique has been demonstrated for debonding location and size prediction of stiffened panels using a vibration-based method. The results are satisfactory for both, debonding location and size prediction. This domain transformation method can be used in any field where experimental data for training machine learning models is scarce.

The Genji firefly is a key symbol of the conservation and management of rural environments. The species lives underwater as larvae, in the soil when they pupate, and emerges on the ground as adults. Because of the large differences in habitat conditions between larvae and adults, the habitat requirements of the Genji firefly must be clarified over a wide range, from the instream to the surrounding riparian environment. In this study, we built a habitat suitability model for the Genji firefly by relating local landscape features to the number of individuals surveyed in a small river in an agricultural watershed. For habitat suitability modelling, tree-based machine learning methods, namely Random Forests (RF) and classification and regression trees (CART), are used to model species distributions and extract quantitative information on their ecological characteristics. Because the model performance on the test dataset was poor, we removed noisy absences using model outputs from the RF computation using the entire dataset. As a result, we observed improved model performance, in which there seems to be an optimal level for removing noisy absences. Variable importance and partial dependence plots were then used to visualize the relationship between the local landscape features and habitat suitability of the adult firefly. Detailed information on landscape features extracted using RF and CART is useful for a deeper understanding of the ecology of the Genji fireflies.

This paper argues that popular misrepresentation of the nature of AI has important consequences concerning how it should be regulated. Viewing AI as something that exists in itself, rather than as a set of cognitive technologies whose characteristics – physical, cognitive, and systemic – are quite different from ours (and at times from each other) leads to inefficient approaches to regulation. It limits our ability to anticipate the consequences of its foreseeable developments and social diffusion. It undermines attempts to protect ourselves from the social and political dangers it presents. After a short introduction, section 2 retraces rapidly the history of the idea that intelligence is essentially a quality, one that AI shares with human intelligence and that this resemblance trumps the differences that exist between artificial and natural cognitive systems. Section 3 reviews two approaches to the dangers of AI that reflect the illusion that AI exists in itself. Section 4 turns to the proper understanding of regulations and what is their main goal and purpose. Section 5 analyses three central characteristics of artificial cognitive systems which section six compares with corresponding characteristics of natural cognitive systems. Finally, section 7 draws some conclusions regarding how we should regulate artificial intelligence.

Hepatitis C presents a significant global health challenge, necessitating early diagnosis and precise severity classification for timely medical intervention. This study explores the application of machine learning techniques to predict the severity of hepatitis C, leveraging an extensive dataset. Our approach encompasses rigorous data preprocessing, advanced model development, and fine-tuned hyperparameter optimization to ensure accurate and reliable predictions. We evaluated four classification models: Logistic Regression, Random Forest, Gradient Boosting, and Support Vector Machine (SVM), comparing their accuracy in classifying patients. The results showed that the Random Forest and Gradient Boosting models outperformed the others with an accuracy of approximately 93.50%, demonstrating their potential in assisting Hepatitis C diagnosis. Further model enhancements through hyperparameter tuning and feature engineering can improve the precision of Hepatitis C diagnosis, contributing to better patient care.

Taiwan’s Chi Mei Medical Center has a vision of becoming a sustainable organization. They found they violated the sustainable development goal (SDG) 13 (“Climate Action”) since its workflows consume excessive tangible resources and waste much operation time. To fulfill the vision, the Chi Mei Medical Center first introduced electronic invoicing. Implementing this electronic invoicing included adopting cloud E-invoice data and creating a software robot for auditing them. This study presents this software robot and its contributions. The software robot replaces an internal auditor to log into Taiwan’s E-invoice platform, download cloud E-invoice data, and detect the inconsistency between these cloud and on-premise data. Internal auditors of the Chi Mei Medical Center only needed to confirm the detection results. They welcome this software robot since it significantly reduces their work burdens. They approved more software robots for assisting other workflows. Besides, the Chi Mei Medical Center earned profits after eliminating paper invoices. This elimination helped release less carbon. This study concludes that chasing a sustainable organization is unnecessarily equivalent to the requirement of more costs. A software robot represents the last puzzle for constructing a paperless workflow since it can resolve the resistance of existing workers to a new workflow.

Biomass gasification acquired great interest over the past decades as an effective and trustable technology to produce energy and fuels with net-zero carbon emissions. Moreover, using biomass waste as feedstock enables to recycle organic wastes and to fit the circular economy goals thus reducing the environmental impacts of waste management. Even if many studies have been already carried on, this kind of process must still be investigated and optimized with the final aim to develop industrial plants for different applications, from the hydrogen production to net-negative emission strategies. Modeling and developing of process simulations became an important tool to investigate the chemical and physical behavior of the plant, allowing to make a first raw optimization of the process and to define heat and material balances of the plant as well as to define optimal geometrical parameters with cost and time effective approaches. The present review paper focuses on the main literature models developed until now to describe biomass gasification process, and in particular on kinetic models, thermodynamic models, and computational fluid dynamic models. The aim of this study is to point out the strengths and the weakness of those models, comparing them and indicating in which situation is better to use an approach instead of another. Moreover, theoretical shortcut models and software simulations, not explicitly addressed by prior reviews, are taken into account. For researchers and designers this review provides a detailed methodology characterization as a guide to develop innovative study or project.

Background: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a complex and debilitating disease with a significant global prevalence of over 65 million individuals. It affects various systems, including the immune, neurological, gastrointestinal, and circulatory systems. Studies have shown abnormalities in immune cell types, increased inflammatory cytokines, and brain abnormalities. Further research is needed to identify consistent biomarkers and develop targeted therapies. A multidisciplinary approach is essential for diagnosing, treating, and managing this complex disease. The current study aims at employing explainable artificial intelligence (XAI) and machine learning (ML) techniques to identify discriminative metabolites for ME/CFS. Material and Methods: The present study used a metabolomics dataset of CFS patients and healthy controls, including 26 healthy controls and 26 ME/CFS patients aged 22-72. The dataset encapsulated 768 metabolites, classified into nine metabolic super-pathways: amino acids, carbohydrates, cofactors, vitamins, energy, lipids, nucleotides, peptides, and xenobiotics. Random forest-based feature selection and Bayesian Approach based-hyperparameter optimization were implemented on the target data. Four different ML algorithms [Gaussian Naive Bayes (GNB), Gradient Boosting Classifier (GBC), Logistic regression (LR) and Random Forest Classifier (RFC)] were used to classify individuals as ME/CFS patients and healthy individuals. XAI approaches were applied to clinically explain the prediction decisions of the optimum model. Performance evaluation was performed using the indices of accuracy, precision, recall, F1 score, Brier score, and AUC. Results: The metabolomics of C-glycosyltryptophan, oleoylcholine, cortisone, and 3-hydroxydecanoate were determined to be crucial for ME/CFS diagnosis. The RFC learning model outperformed GNB, GBC, and LR in ME/CFS prediction using the 1000 iteration bootstrapping method, achieving 98% accuracy, precision, recall, F1 score, 0.01 Brier score, and 99% AUC. Conclusion: RFC model proposed in this study correctly classified and evaluated ME/CFS patients through the selected biomarker candidate metabolites. The methodology combining ML and XAI can provide a clear interpretation of risk estimation for ME/CFS, helping physicians intuitively understand the impact of key metabolomics features in the model.

Social media platforms are increasingly enabling the propagation of content from groups related to drug use, thus posing risks for the wider population and, in particular, individuals who are amenable to drug use and drug addiction. The detection of drug use content on social media platforms is a priority for governments, technology companies, and drug law enforcement organizations. To counter this issue, various techniques have been developed to identify and promptly remove drug use content, while also blocking its creators from network access. In this paper, we introduce a manually annotated Twitter dataset, comprising 156,521 tweets published between 2008 and 2022, specifically compiled for the purpose of drug use detection. The dataset underwent annotation by several group of expert annotators who classified the tweets as either drug use or non-drug use. Exploratory data analysis was conducted to comprehend the dataset's characteristics. Various classification algorithms, including SVM, XGBoost, RF, NB, LSTM, and BERT were employed using the dataset. Among the traditional machine learning models, SVM utilizing term frequency-inverse document frequency features achieved the highest F1-Score (0.9017). However, BERT with textual features concatenated with numerical and categorical features in ensemble method surpassed the performance of traditional models, attaining F1-Score of 0.9112. To facilitate future research and enhance English online drug use classification accuracy, the dataset will be made publicly available.

In the recent past, China has experienced rapid urbanization as a result of diverse growth factors. In such a context, it is crucial to evaluate the expansion of urban entities in order to implement sustainable urban planning strategies in China. Since, urban entities are the spatial reflection of the concentration of human activities, the delineation of urban areas upon the boundaries of built-up surfaces has resulted from inconsistent understanding and identification of urban areas. The study has attempted to extract and evaluate the growth of urban entities in 336 prefecture cities in China mainland (2000-2020) upon a novel approach using consistent night light images. The urban entities were extracted using the light intensities of the SNPP-VIIRS-like data. After extracting urban entities, a rationality assessment was carried out comparing derived urban entities with the LandScan population product, Landsat, and road networks. Also, the results were compared with other physical extents products such as MODIS and the HE. According to the findings, urban entities are basically consistent with the LandScan, road networks, and those with the HE and MODIS. But, urban entities accurately reflect the concentration of human activities than impervious extents of MODIS and the HE. At the prefecture levels, urban entities elevated from 8082 km2 to 74,417 km2 between 2000 and 2020 showing a 10.8% growth rate. By providing a supplementary resource and guide for trustworthy urban mapping, the research will expand new research directions that address the issues of variations of NTL data brightness thresholds dynamics on regional, and global scales.

With the development of artificial intelligence technology, manipulators, as an important part of the work of intelligent robots, can replace humans to perform various complex tasks. In recent years, there have been many studies on the remote control of manipulators using various control technologies. Starting from the manufacturing materials of flexible sensors used for manipulators, this paper introduces the base materials, sensing materials, and flexible electrode materials of flexible sensors, respectively, and summarizes the performance of flexible sensors made based on the characteristics of different materials. The basic principles of dipping and coating, lithography, inkjet printing, screen printing, 3D printing and so on are introduced from the perspective of flexible sensor manufacturing process. Some different functions of sensors achieved by different structural designs, such as: tensile cracking, microchannels, etc. are also introduced. Then, from the perspective of recognition accuracy of the manipulator, two kinds of control methods based on flexible sensor by data glove control and surface EMG control are classified and introduced, and the problems existing in three aspects of flexible sensor material preparation, manufacturing process and control series design are summarized. Finally, the possible future research directions in this field are suggested.

Algorithms for machine learning have found extensive use in numerous fields and applications. One important aspect of effectively utilizing these algorithms is tuning the hyperparameters to match the specific task at hand. The selection and configuration of hyperparameters directly impact the performance of machine learning models. Achieving optimal hyperparameter settings often requires a deep understanding of the underlying models and the appropriate optimization techniques. While there are many automatic optimization techniques available, each with its own advantages and disadvantages, this article focuses on hyperparameter optimization for well-known machine learning models. It explores cutting-edge optimization methods and provides guidance on applying them to different machine learning algorithms. The article also presents real-world applications of hyperparameter optimization by conducting tests on spatial data collections for landslide susceptibility mapping. Based on the experiment's results, both Bayesian optimization and metaheuristic algorithms showed promising performance compared to baseline algorithms. For example, the metaheuristic algorithm improved the overall accuracy of the random forest model. Additionally, Bayesian algorithms, such as Gaussian processes, performed well for models like KNN and SVM. The paper thoroughly discusses the reasons behind the efficiency of these algorithms. By successfully identifying appropriate hyperparameter configurations, this research paper aims to assist researchers, spatial data analysts, and industrial users in developing machine learning models more effectively. The findings and insights provided in this paper can contribute to enhancing the performance and applicability of machine learning algorithms in various domains.

High-dimensional measurement error data are becoming more prevalent across various fields. Research on measurement error regression models has gained increasing attention due to the risk of drawing inaccurate conclusions if measurement errors are ignored. When the dimension p is larger than the sample size n, it is challenging to develop statistical inference methods for high-dimensional measurement error regression models due to the existence of bias, nonconvexity of objective function, high computational cost and many other difficulties. Over the past few years, some works have overcome the aforementioned difficulties and proposed several statistical inference methods. This paper mainly reviews the current development on estimation, hypothesis testing and variable screening methods for high-dimensional measurement error regression models and shows the theoretical results of these methods with some directions worthy of exploring for future research.

This paper proposes an approach for image data extraction and driving behavior analysis using geographic information and driving data. Information derived from geographic and global positioning systems was used for image data extraction. In addition, we used an onboard diagnostic II and a controller area network bus logger to record driving data for driving behavior analysis. Driving behavior was analyzed using sparse automatic encoders and data exploration to detect abnormal and aggressive behavior. A regression analysis was used to derive the relationship between aggressive driving behavior and road facilities. Several traffic improvements were proposed for specific intersections and roads. The results indicate that lane ratios without lane markings and with straight lane markings are important features that affect aggressive driving behaviors.

The main problem in pursuing multiple extended targets tracking is distinguishing the origins of the measurements. The association of measurements to the possible origins within the target’s extent is difficult, especially for the occlusions or the detection blind zone which cause the intermittent measurements. To solve the problem, a hierarchical network-based tracklets data association algorithm is proposed. At the low level, the min cost network flow model is used to extract possible tracklets from the divided measurement set. At the high-level, the trajectories are estimated from the tracks produced by the previous low level network. The experimental results show that the hierarchical network-based tracklets data association algorithm outperforms the JPDA and RFS-based method when the measurement is intermittently unavailable.

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process sensitive information such as personal communications and confidential documents. In this study, we propose a method for training NLP models on encrypted text data to mitigate data privacy concerns while maintaining similar performance to models trained on non-encrypted data. We demonstrate our method using two different architectures, namely Doc2Vec+XGBoost and Doc2Vec+LSTM, and evaluate the models on the 20 Newsgroups dataset. Our results indicate that both encrypted and non-encrypted models achieve comparable performance, suggesting that our encryption method is effective in preserving data privacy without sacrificing model accuracy. In order to replicate our experiments, we have provided a Colab notebook at the following address: https://t.ly/lR-TP

Soil quality is related to food security and human survival and development. In recent years, due to the acceleration of urbanization and the increase of abandoned land, land degradation occurs, poor topsoil quality. In this study, the minimum data set (MDS) was constructed through principal component analysis (PCA) to determine the indicator data set for evaluating topsoil quality in Tieling County, China. In addition, the soil quality index (SQI) was calculated to analyze the spatial distribution characteristics and influencing reasons of topsoil quality in Tieling County. The re-sults showed that MDS included total potassium (TK), Clay, zinc (Zn), soil organic matter (SOM), soil water content (SWC), cation exchange capacity (CEC), pH, and copper (Cu). The MDS indicators can well replace all indicators to evaluate the topsoil quality in the study area. The overall soil quality of Tieling County showed a trend of low in the east and high in the west, and gradually increased from the hilly area to the plain area. The evaluation results are consistent with field research, which can provide reference for other topsoil quality evaluation, and it also provide a basis for the formulation of soil quality improvement measures.

Introduction: Weighting is widely used in applied statistics especially while dealing with survey data. In recent years, multilevel modeling under complex survey designs has increased, resulting into demand for level weights. However, survey data that are accessible to the public for use usually do not contain level weights that are useful in multilevel modeling, but final survey weights that are only appropriate for single level analyses. In this paper, we demonstrate how the final survey weights can be used to estimate level weights for multilevel data analysis, and compare a model that applied level weights with one that applied the final survey weights. Methods: A framework for approximating level weights proposed by the Demographic Health Survey (DHS) program was used to estimate the level weights. Models were fitted using a multilevel mixed effects logistic regression method. Estimates from a model that applied survey weights was compared to those from a model that applied level weights. Results: Application of final survey weights instead of level weights underestimated standard errors and led to loss of precision of model estimates. Conclusions: Use of level weights produces estimates with high precision and yields correct values of standard errors hence appropriately informing inference.

In engineering practice, various types of information data are affected by many factors during the collection process. For example, information data measurement errors are caused by equipment performance and the working environment. During the transmission of detection information, the signal distortion caused by energy loss and signal interference causes unpredictable detection errors in the collected information data. Through the study of fractional calculus theory, it was found that it is suitable for studying nonlinear, non-causal, and non-stationary signals, and has the dual functions of improving detection information and enhancing signal strength. Therefore, under the influence of many factors, we applied the fractional difference algorithm to the field of information data processing. Multi-sensor detection data fusion algorithm based on the fractional partial differential equation was adopted to establish its online detection data. A multi-sensor detection data fusion algorithm based on a fractional partial differential equation is established, which effectively fuses the information data detection errors caused by various influencing factors and greatly improves the detection accuracy of information data. The effectiveness of this method is proved through its application in an experiment.

The basic constitutional freedoms and rights of a person and citizen are in principle unlimited: the full scope of their exercise is the rule, and the restriction determined by law can only be an exception based on explicit constitutional authority and the legitimate aim of the restriction determined by the Constitution. That being so, the restrictions - in addition to being based on constitutional authority and pursuing constitutional objectives - should be commensurate with the needs to achieve these objectives. This means that restrictive legal rules must be suitable for achieving the legitimate aim pursued, must not be stricter than necessary and must be balanced between the constitutionally guaranteed subjective right of the individual and the interests of society. In this scholar paper, the authors point out the economic and legal consequences of the violation of individual privacy and data protection rights caused by the public disclosure of personal data of people who, at a certain time, were obliged to self-isolate due to suspicion of Covid-19 virus infection.

In recent years, different deep learning frameworks were introduced for hyperspectral image (HSI) classification. However, the proposed network models have a higher model complexity and do not provide high classification accuracy if few-shot learning is used. This paper pre-sents an HSI classification method that combines random patches network (RPNet) and re-cursive filtering (RF) to obtain informative deep features. The proposed method first convolves image bands with random patches to extract multi-level deep RPNet features. Thereafter, the RPNet feature set is subjected to dimension reduction through principal component analysis (PCA) and the extracted components are filtered using the RF procedure. Finally, HSI spectral features and the obtained RPNet-RF features are combined to classify the HSI using a support vector machine (SVM) classifier. In order to test the performance of the proposed RPNet-RF method, some experiments were performed on three widely known datasets using a few training samples for each class and classification results were compared with those obtained by other advanced HSI classification methods adopted for small training samples. The comparison showed that the RPNet-RF classification is characterized by higher values of such evaluation metrics as overall accuracy and Kappa coefficient (https://github.com/UchaevD/RPNet-RF).

Sensor enabled big data and Artificial Intelligence platforms has the potential to address global socio-economic trends related to the livestock production sector through advances in the digitization of precision livestock farming. The increased interest in animal welfare, the likely reduction in the number of animals in relation to population growth in the coming decade and the growing demand for animal proteins pose an acute challenge to prioritizing animal welfare on the one hand while maximizing the efficiency of production systems on the other. To stimulate a sustainable, digital, and resilient recovery of the agricultural and livestock industrial sector, there is an urgent need for testing and develop new ideas and products such as wearable sensors. By validating and demonstrating a fully functional wearable sensor prototype within an operational environment on the livestock farm that includes a miniaturized animal-borne biosensor and an artificial intelligence (AI) based data acquisition and processing platform, the unmet current needs can be fulfilled. The expected quantifiable results from wearable biosensors will demonstrate that the digitization technology can perform acceptably within the performance parameters specified by the agricultural sector and under operational conditions, to measurably improve livestock productivity and health. There is a need for a multimodal, digitized, automated biosensor and health monitoring platform containing AI algorithms for optimized stress and disease prediction in farm animals. An experimental development of non-invasive wearable and wireless physiological sensor networks that can be deployed in agricultural environments would allow for real-time extraction and integration of physiological data and display on decision support dashboards for livestock workers. By testing the effectiveness of the system in generating meaningful longitudinal data for further research into physiological and behavioral characteristics of farm animals, novel insights about animal welfare can be developed. The successful implementation of the digital wearable sensor networks would provide actionable real-time information on animal health status and can be deployed directly on the livestock farm, which will strengthen the green and digital recovery of the economy due to the significant innovation potential. Continuous monitoring of animal health and physiological functioning promotes more environmentally and socially acceptable developmental pathways. Once demonstrated, the portable animal health monitoring platform will close a critical gap in digitized livestock farming and position the agricultural industry as a frontrunner in the sector of farm animal monitoring and measurement systems. The multimodal wearable sensor-driven AI approach is expected to significantly improve the effectiveness of livestock decision support systems and the selection of resilient animals for the next generation and provide predictive data for end-users in livestock farming.

As machine learning and computer vision techniques and methods continue to advance, the collection of naturalistic traffic data from video feeds is becoming more and more feasible. That is especially true for the case of bicycles, for which the collection of naturalistic data is not achievable in the traditional vehicle approach. This study describes a research effort that aims to extract naturalistic cycling data from a video dataset for use in safety and mobility applications. The used videos come from a dataset collected in a previous Virginia Tech Transportation Institute study in collaboration with SPIN in which continuous video data at a non-signalized intersection on the Virginia Tech campus was recorded. The research team applied computer vision and machine learning techniques to develop a comprehensive framework for the extraction of naturalistic cycling trajectories. In total, this study resulted in the collection and classification of 619 bicycle trajectories based on their type of interactions with other road users. The results confirm the success of the proposed methodology in relation to extracting the locations, speeds, and accelerations of the bicycles at a high level of precision. Furthermore, preliminary insights into the acceleration and speed behavior of bicyclists around motorists are determined.

Deep learning dominates automated animal activity recognition (AAR) tasks due to the high performance on large-scale datasets. However, constructing centralised data across diverse farms raises data privacy issues. Federated learning (FL) provides a distributed learning solution to train a shared model by coordinating multiple farms (clients) without sharing their private data. Whereas directly applying FL to AAR tasks often faces two challenges: client-drift during local training and gradient conflicts during global aggregation. In this study, we develop a novel FL framework called FedAAR to achieve AAR with sensor data. Specifically, we devise a prototype-guided local update module to alleviate the client-drift issue, which introduces global prototypes as shared knowledge to force clients to learn consistent features. To reduce gradient conflicts between clients, we design a gradient refinement-based aggregation module to eliminate conflicting components between client gradients during global aggregation, thereby improving the agreement between clients. Experiments are conducted on a public dataset to verify FedAAR’s effectiveness, which consists of 87,621 2-s motion data. The results demonstrate that FedAAR outperforms state-of-the-arts, with precision (75.23%), recall (75.17%), F1-score (74.70%), and accuracy (88.88%), respectively. The ablation experiments also show FedAAR’s robustness against various factors (i.e., different data sizes, communication frequency, and client numbers).

Early diagnosis, prioritization, screening, clustering and tracking of COVID-19 patients, and production of drugs and vaccines are some of the applications that have made it necessary to use a new style of technology to involve, to manage and deal with this epidemic. Strategies backed by artificial intelligence (AI) and the Internet of Things (IoT) have been undeniable to understand how the virus works and try to prevent it from spreading. Accordingly, the main aim of this survey article is to highlight the methods of ML, IoT and the integration of IoT and ML-based techniques in the applications related to COVID-19 from the diagnosis of the disease to the prediction of its outbreak. According to the main findings, IoT provided a prompt and efficient approach of following the disease spread. Most of the studies developed by ML-based techniques for handling COVID-19 based dataset provided performance criteria. The most popular performance criteria, is related to accuracy factor. It can be employed for comparing the ML-based methods with different datasets. According to the results, CNN with SVM classifier, Genetic CNN and pre-trained CNN followed by ResNet, provided highest accuracy values. On the other hand, the lowest accuracy was related to single CNN followed by XGboost and KNN methods.

By reviewing the research of development economics in recent years, five key terms of ‘innovation, coordination, green, openness and sharing’ are extracted, corresponding to the five dimensions of the New Development Concept advocated by China. Based on this, an evaluation index system of the development quality of China's fishery industry is constructed. The spatio-temporal characteristics of China's fishery industry development quality were analyzed by using the provincial panel data from 2007 to 2017. The results show that: i) China's fishery industry overall development quality continues to grow, while the variation of provincial quality is also increasing, and the contribution of innovation quality and sharing quality is increasing, becoming an important sub-dimension leading the overall development quality.ii) there is a significant spatial dependence among provincial quality, and the significance is further strengthening. The Hangzhou Bay area and Bohai Bay area have gradually become a dual-core area where the high-quality development of China's fishery industry agglomeration, and the radiation from the dual-core area to the peripheral areas may still be in the process of enhancement. The spatial and temporal distribution of China’s fishery industry development quality keeps the trend of ‘from northeast to southwest’, which is almost parallel to Hu Huanyong line. The gravity center of its distribution is close to the gravity center of Chinese population and economy, and the development quality experienced a process from relatively concentrated to dispersed and then returned to concentrated, and the development speed in the later period was higher than that in the earlier period. iii) Capital accumulation level is the dominant positive influencing factors, while government support level is the dominant negative influencing factors respectively, and both have significant spatial differentiation among provinces.

In community-based participatory projects, needs assessments are one of the first steps to identify priority areas. Access-related issues often pose significant barriers to participation for rural and remote communities, particularly Indigenous communities which have a complicated relationship with academia due to a history of exploitation and trauma. In order to bridge this gap, work with Indigenous communities requires consistent and meaningful engagement. The prominence of digital devices (i.e., smartphones) offers an unparalleled opportunity to ethically and equitably engage citizens across jurisdictions, particularly in remote communities. We propose a framework to guide needs assessments which embed digital tools in partnership with Indigenous communities. Guided by this framework, a needs assessment was conducted with a subarctic Métis community in Saskatchewan, Canada. This project is governed by a Citizen Scientist Advisory Council which includes Traditional Knowledge Keepers, Elders, and youth. An environmental scan of relevant programs, key informant interviews, and focus groups were conducted to systematically identify community priority areas. Given the timing of the needs assessment, the community identified the Coronavirus pandemic as a key priority area requiring digital initiatives. Recommendations for community-based needs assessments to conceptualize and implement digital infrastructure are put forward, with an emphasis on self-governance and data sovereignty.

Three-dimensional reconstruction plays an important role in assisting doctors and surgeons in diagnosing bone defects’ healing progress. Common three-dimensional reconstruction methods include surface and volume rendering. As the focus is on the shape of the bone, volume rendering is omitted. Many improvements have been made on surface rendering methods like Marching Cubes and Marching Tetrahedra, but not many on working towards real-time or near real-time surface rendering for large medical images, and studying the effects of different parameter settings for the improvements. Hence, in this study, an attempt towards near real-time surface rendering for large medical images is made. Different parameter values are experimented on to study their effect on reconstruction accuracy, reconstruction and rendering time, and the number of vertices and faces. The proposed improvement involving three-dimensional data smoothing with convolution kernel Gaussian size 0.5 and mesh simplification reduction factor of 0.1, is the best parameter value combination for achieving a good balance between high reconstruction accuracy, low total execution time, and a low number of vertices and faces. It has successfully increased the reconstruction accuracy by 0.0235%, decreased the total execution time by 69.81%, and decreased the number of vertices and faces by 86.57% and 86.61% respectively.

In the design and development of novel materials that have excellent mechanical properties, classification and regression methods have been diversely used across mechanical deformation simulations or experiments. The use of materials informatics methods on large data that originate in experiments or/and multiscale modeling simulations may accelerate materials discovery or develop new understanding of materials’ behavior. In this fast-growing field, we focus on reviewing advances at the intersection of data science with mechanical deformation simulations and experiments, with a particular focus on studies of metals and alloys. We discuss examples of applications, as well as identify challenges and prospects.

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 dof delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data is available. Due to the sequential nature of the data, non-linearity of the system, and correlations between parameter time series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method is capable of calculating RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

This overview study set out to compare and synthesise the findings of review studies conducted on predicting student academic performance (SAP) in higher education using educational data mining (EDM) methods, EDM algorithms and EDM tools from 2013 to June 2020. It conducted multiple searches for suitable and relevant peer-reviewed articles on two online search engines, on nine online databases, and on two online academic social networks. It, then, selected 26 eligible articles from 2,050 articles. Some of the findings of this overview study are worth mentioning. First, only 2 studies explicitly stated their precise sample sizes with maths and science as the two most mentioned subject areas. Second, 16 review studies had purposes related to either EDM techniques, EDM methods, EDM models, or EDM algorithms employed to predict SAP and student success in the higher education sector. Third, there are six commonly used typologies of input variables reported by 26 review studies, of which student demographics was the most commonly utilised variable for predicting SAP. Fourth and last, seven common EDM algorithms employed for predicting SAP were identified, of which Decision Tree emerged both as the most used algorithm and as the algorithm with the highest prediction accuracy rate for predicting SAP.

The urgent need to improve performance in the construction industry has led to the adoption of many innovative technologies. 3D laser scanners are amongst the leading technologies being used to capture and process assets or construction project data for use in various applications. Due to its nascent nature, many questions are still unanswered about 3D laser scanning, which in turn contribute to the slow adaptation of the technology. Some of these include the role of 3D laser scanners in capturing and processing raw construction project data. How accurate is the 3D laser scanner or point cloud data? How does laser scanning fit with other wider emerging technologies such as Building Information Modelling (BIM)? This study adopts a proof-of-concept approach, which in addition to answering the afore-mentioned questions, illustrates the application of the technology in practice. The study finds that the quality of the data, commonly referred to as point cloud data is still a major issue as it depends on the distance between the target object and 3D laser scanner’s station. Additionally, the quality of the data is still very dependent on data file sizes and the computational power of the processing machine. Lastly, the connection between laser scanning and BIM approaches is still weak as what can be done with a point cloud data model in a BIM environment is still very limited. The aforementioned findings reinforce existing views on the use of 3D laser scanners in capturing and processing construction project data.

The rapid evolution of Next Generation Sequencing in clinical settings and the resulting challenge of variants interpretation in the light of constantly updated information, requires robust data management systems and organized approaches to variant reinterpretation. In this paper, we present iVar: a freely available and highly customizable tool provided with a user-friendly web interface. It represents a platform for the unified management of variants identified by different sequencing technologies. iVar accepts, as input, VCF files and text annotation files and elaborates them, optimizing data organization and avoiding redundancies. Updated annotations can be periodically re-uploaded and associated to variants as historicize attributes. Data can be visualized through variant-centered and sample-centered interfaces. A customizable search functionality can be exploited to periodically check if pathogenicity related data of a variant are changed over time. Patient recontacting ensuing from variant reinterpretation is made easier by iVar through the effective identification of all patients present in the database and carrying a specific variant. We tested iVar by uploading 4171 VCF files and 1463 annotation files, obtaining a database of 4166 samples and 22569 unique variants. iVar has proven to be a useful tool with good performances for collecting and managing data from medium-throughput

Pipeline integrity is an important area of concern for the oil and gas, refining, chemical, hydrogen, carbon sequestration, and electric-power industries, due to the safety risks associated with pipeline failures. Regular monitoring, inspection, and maintenance of these facilities is therefore required for safe operation. Large standoff magnetometry (LSM) is a non-intrusive, passive magnetometer-based mea- surement technology that has shown promise in detecting defects (anomalies) in regions of elevated mechanical stresses. However, analyzing the noisy multi-sensor LSM data to clearly identify regions of anomalies is a significant challenge. This is mainly due to the high frequency of the data collection, mis-alignment between consecutive inspections and sensors, as well as the number of sensor measurements recorded. In this paper we present LSM defect identification approach based on ma- chine learning (ML). We show that this ML approach is able to successfully detect anomalous readings using a series of methods with increasing model complexity and capacity. The methods start from unsupervised learning with "point" methods and eventually increase complexity to supervised learning with sequence methods and multi-output predictions. We observe data leakage issues for some methods with randomized train/test splitting and resolve them by specific non-randomized splitting of training and validation data. We also achieve a 200x acceleration of support-vector classifier (SVC) method by porting computations from CPU to GPU leveraging the cuML RAPIDS AI library. For sequence methods, we develop a customized Convolutional Neural Network (CNN) architecture based on 1D convolutional filters to identify and characterize multiple properties of these defects. In the end, we report the scalability of the best-performing methods and compare them, for viability in field trials.

The fossil record is notorious for being incomplete and distorted, frequently conditioning the type of knowledge that can be extracted from it. In many cases, this often leads to issues when performing complex statistical analyses, such as classification tasks, predictive modelling, and variance analyses, such as those used in Geometric Morphometrics. Here different Generative Adversarial Network architectures are experimented with, testing the effects of sample size and domain dimensionality on model performance. For model evaluation, robust statistical methods were used. Each of the algorithms were observed to produce realistic data. Generative Adversarial Networks using different loss functions produced multidimensional synthetic data significantly equivalent to the original training data. Conditional Generative Adversarial Networks were not as successful. The methods proposed are likely to reduce the impact of sample size and bias on a number of statistical learning applications. While Generative Adversarial Networks are not the solution to all sample-size related issues, combined with other pre-processing steps these limitations may be overcome. This presents a valuable means of augmenting geometric morphometric datasets for greater predictive visualization.

Over the past decade, wireless communication technologies have developed significantly for intelligent applications in road transport. This paper provides an overview of telecommunications-based intelligent transport systems with a focus on ensuring system safety and resilience. In vehicle-to-everything, these problems are extremely acute due to the specifics of the operation of transport networks, which requires the use of special protection mechanisms. In this regard, it was decided to use blockchain as a system platform to support the needs of transport systems for secure information exchange. This paper describes the technological aspects of implementing blockchain technology in vehicle-to-network; the features of such technology are presented, as well as the features of their interaction.

Social media gives researchers an invaluable opportunity to gain insight into different facets of human life.Researchers put a great emphasis on categorizing the socioeconomic status (SES) of individuals to help predict various findings of interest. Forum uses, hashtags and so on are common tools of conversations grouping. On the other hand, crowdsourcing is a concept that involves gathering intelligence to group online user community based on common interest. This paper provides a mechanism to look at writings on social media and group them based on their academic background. We build upon earlier work where we analyzed online forum posts from various geographical regions in the USA and Canada and characterized the readability scores of such users. Specifically, we collected 1000 tweets from the members of the US Senate and computed the Flesch-Kincaid readability score for the Senators. Comparing the Senators’ tweets to the ones from average citizens, we note the following. 1) US Senators’ readability based on their tweets rate is much higher affirming the gap between the academic performance of US Senators and their average citizen, and 2) the immense difference among average citizen’s score compared to those of US Senators is attributed to the wide spectrum of academic attainment.

As of today, there is not any direct report yet of the degree to which missing residues exist for experimentally determined membrane protein (MP) structures, which constitute more than half of current drug targets. With a chain- and position-specific visualisation and a statistical analysis of all MP structures inside PDB (as of September 25, 2019), this article argues that the experimentally uncharted territories (EUTs, i.e., consisting of missing residues) within PDB are pluggable and should be plugged with an experimental data-driven hybrid approach, and calls for continued development of MP structural determination with less and less EUTs, in light of MPs' crucial role in biological and biomedical research, both fundamental and pharmaceutical.

As one of GEO-constellation for environmental monitoring in the next decade, Geostationary Environment Monitoring Spectrometer (GEMS) is designed to observe the Asia Pacific region to provide the information on the atmospheric chemicals, aerosol and cloud properties. For the continuous monitoring of the sensor performance after its launch in early 2020, here we suggest deep convective clouds (DCCs) as a possible target for the vicarious calibration of GEMS, the first UV/VIS hyperspectral sensor onboard a geostationary satellite. Tropospheric Monitoring Instrument (TROPOMI) and Ozone Monitoring Instrument (OMI) are used as a proxy of GEMS, and a conventional DCC detection approach applying the thermal threshold test is used for the DCC detection based on the collocations with Advance Himawari-8 Imager (AHI) onboard Himawari-8 geostationary satellite. DCCs are frequently detected over the GEMS observation area on average over 200 pixels in a single observation scene. Considering the spatial resolution of GEMS, 3.5 km×7 km which is similar to TROPOMI, and its temporal resolution (8 times a day), availability of DCCs for vicarious calibration of GEMS is expected to be sufficient. Inspection of the DCC reflectivity spectra estimated from the OMI and TROPOMI data also shows a promising result. Even though, their observation geometry and sensor characteristics are quite a different, the estimated DCC spectra agree quite a well within a known uncertainty range with comparable spectral features. When the DCC detection is further improved by applying both visible and infrared tests, the variability of DCC reflectivity from the TROPOMI data is reduced by half, from 10% to 5%. This is mainly due to the efficient screening of cold thin cirrus with the visible test and of bright warm clouds with the infrared test. The precise DCC detection is also expected to contribute to the accurate characterization of the cloud reflectivity, which will be further investigated.

The technique of obtaining information or data about any feature or object from afar, called in technical parlance as remote sensing, has proven extremely useful in diverse fields. In the ecological sphere, especially, remote sensing has enabled collection of data or information about large swaths of areas or landscapes. Even then, in remote sensing the task of identifying and monitoring of different water reservoirs has proved a tough one. This is mainly because getting correct appraisals about the spread and boundaries of the area under study and the contours of any water surfaces lodged therein becomes a factor of utmost importance. Identification of water reservoirs is rendered even tougher because of presence of cloud in satellite images, which becomes the largest source of error in identification of water surfaces. To overcome this glitch, the method of the shape matching approach for analysis of cloudy images in reference to cloud-free images of water surfaces with the help of vector data processing, is recommended. It includes the database of water bodies in vector format, which is a complex polygon structure. This analysis highlights three steps: First, the creation of vector database for the analysis; second, simplification of multi-scale vector polygon features; and third, the matching of reference and target water bodies database within defined distance tolerance. This feature matching approach provides matching of one to many and many to many features. It also gives the corrected images that are free of clouds.

The problem of real-time estimation of occupancy of buildings (number of people in various zones at every time instant) is relevant to a number of emerging applications that achieve high energy efficiency through feedback control. The measurement of CO2 concentration can be considered an important indicator that allows to define the occupation of closed and crowded spaces. Interesting cases can be school buildings and other buildings used in civil and residential (shopping centres, hospitals, etc.). This paper, starting from an experimental analysis in different classrooms of a University campus in real operating conditions, in different period of the year, proposes a possible correlation between CO2 concentration and the occupancy profile of the spaces. The acquired data are used to present some graphical correlations and to understand the most important variables or combination of them. Starting from an accurate analysis of the data, attempts are made to define a preliminary estimation method through the development of a mathematical models of occupancy dynamics in a building, which show interesting results.

The objective of this work was to investigate the use of remotely sensed vegetation indices to improve the quality of yield maps. The method was applied to the yield data of twelve cornfields from the Data Intensive Farm Management project. The results revealed the need to time shift the yield values up to three seconds to better match the sensor readings with the geographic coordinates. The residuals of the yield prediction model were used to identify points with unlikely yield values for that location, as an alternative to traditional approaches using local spatial statistics, without any assumption of spatial dependence or stationarity. The temporal and spatial distribution of the standardized coefficients for each experimental unit highlighted the presence of trends in the data. At least five out of the twelve fields presented trends that could have been induced by data collection.

In this paper the authors present a method which facilitates computationally efficient parameter estimation of dynamical systems from a continuously growing set of measurement data. It is shown that the proposed method, which utilises Sequential Monte Carlo samplers, is guaranteed to be fully parallelisable (in contrast to Markov chain Monte Carlo methods) and can be applied to a wide variety of scenarios within structural dynamics. Its ability to allow convergence of one's parameter estimates, as more data is analysed, sets it apart from other sequential methods (such as the particle filter).

The Medi-test system we developed was motivated by the large number of resources available for the medical domain, as well as the number of tests needed in this field (during and after the medical school) for evaluation, promotion, certification, etc. Generating questions to support learning and user interactivity has been an interesting and dynamic topic in NLP since the availability of e-book curricula and e-learning platforms. Current e-learning platforms offer increased support for student evaluation, with an emphasis in exploiting automation in both test generation and evaluation. In this context, our system is able to evaluate a student’s academic performance for the medical domain. Using as input medical reference texts and supported by a specially designed medical ontology, Medi-test generates different types of questionnaires for Romanian language. The evaluation includes 4 types of questions (multiple-choice, fill in the blanks, true/false and match), can have customizable length and difficulty and can be automatically graded. A recent extension of our system also allows for the generation of tests which include images. We evaluated our system with a local testing team, but also with a set of medicine students, and user satisfaction questionnaires showed that the system can be used to enhance learning.

Speech/music classification that facilitates optimized signal processing from classification results has been extensively adapted as an essential part of various electronics applications, such as multi-rate audio codecs, automatic speech recognition, and multimedia document indexing. In this paper, a new technique to improve the robustness of speech/music classifier for 3GPP enhanced voice service (EVS) using long short-term memory (LSTM) is proposed. For effective speech/music classification, feature vectors implemented with the LSTM are chosen from the features of the EVS. Experiments show that LSTM-based speech/music classification produces better results than conventional EVS under a variety of conditions and types of speech/music data.