Search

A flexible pressure sensor with a rudimentary, ultra-low cost, and solvent-free fabrication process is presented in this paper. The sensor has a graphite-on-paper stacked paper structure, which deforms and restores its shape when pressure is applied and released, showing an exceptionally fast response and relaxation time of &asymp, 0.4 ms with a sensitivity of &minus, 5%/Pa. Repeatability of the sensor over 1000 cycles indicates an excellent long-term stability. The sensor demonstrated fast and reliable human touch interface, and successfully integrated into a robot gripper to detect grasping forces, showing high promise for use in robotics, human interface, and touch devices.

Flying insect detection, identification, and counting are the key components of agricultural pest management. Insect identification is also one of the most challenging tasks in agricultural image processing. With the aid of machine vision and machine learning, traditional (manual) identification and counting can be automated. To achieve this goal, a particular data acquisition device and an accurate insect recognition algorithm (model) is necessary. In this work, we propose a new embedded system-based insect trap with an OpenMV Cam H7 microcontroller board, which can be used anywhere in the field without any restrictions (AC power supply, WIFI coverage, human interaction, etc.). In addition, we also propose a deep learning-based insect-counting method where we offer solutions for problems such as the “lack of data” and “false insect detection”. By means of the proposed trap and insect-counting method, spraying (pest swarming) could then be accurately scheduled.

Attention to the environment and its problems has undergone unprecedented growth in recent years [...]

Industrial archived process data represent a convenient source of information for data-driven models, such as artificial neural network (ANN), that can be used for safety and efficiency improvement like early or even predictive fault detection and diagnosis (FDD). Nonetheless, most of the data used for model generation are representative of the process nominal states and therefore are not enough for classification problems intended to determine abnormal process conditions. This work proposes the use of techniques to augment the original real data standards, dismissing the need for experiments that could jeopardize process safety. It uses the Monte Carlo technique to artificially increase the number of model inputs coupled to the nearest neighbor search (NNS) by geometric distances to consistently classify the generated patterns in normal or faulty statuses. Finally, a radial basis function neural network is trained with the augmented data. The methodology was validated by a study case in which 3381 pulp and paper industrial data points were expanded to monitor the formation of particles in a recovery boiler. Only 5.8% of the original process data were examples of faulty conditions, but the new expanded and balanced data collection leveraged the classification performance of the neural network, allowing its future use for monitoring purpose.

Nowadays, forecasting applications are receiving unprecedent attention thanks to their capability to improve the decision-making processes by providing useful indications [...]

Although proposition of “Virtual Reality” (VR) and “Augment Reality” (AR) can be traced back to the 60s, both areas are actually blooming in recent decades. Thanks to the latest deep learning techniques, an enormous advance in computer vision research community has taken place. Since VR and AR are highly related to computer vision tasks, these areas have enjoyed the benefits as well. Yet there is no sufficient survey on such impact and new research areas arising from it. This paper mainly focuses on the latest research progress in ACM Symposium on Eye Tracking Research & Applications (ETRA) 2019, as well as several recent representative paper works. It aims to figure out the influence of deep learning techniques on latest VR/AR research. Meanwhile, new issues have popped up with the development of VR and AR technology, such as privacy and computation efficiency. This paper draws attention to such newly produced topics as well. In addition, this paper also investigates on the effect of latest VR and AR techniques on people, such as level of teamwork in collaborative tasks, assistance and treatment to patients and the disabled, etc.

Oil immersed paper insulation condition is a crucial aspect of power transformer’s life condition diagnostic. The measurement testing database collected over the years made it possible for researchers to implement classification analysis to in-service power transformer. This article presents classification analysis of transformer oil-immersed paper insulation condition. The measurements data (dielectric characteristics, dissolved gas analysis, and furanic compounds) of 149 transformers with primary voltage of 150 kV had been gathered and analyzed. The algorithm used for developing classification model is Support Vector Machine (SVM). The model has been trained and tested using different datasets. Different models have been created and the best chosen, resulting in 90.63% accuracy in predicting the oil-immersed paper insulation condition. Further implementation was executed to classify oil-paper condition of 19 Transformers which Furan data is not available. The classification results combined, reviewed, and compared to conventional assessment methods and standards, confirming that the model developed has the ability to do classification of current oil-paper condition based on Dissolved Gasses and Dielectric Characteristics.

This paper presents an overview on applications of artificial neural networks (ANNs) to robot control systems and outlines the contributions of ANNs. Adaptive neurocontrol architectures are introduced and compared to traditional adaptive control methods.

Falls are unusual actions that cause a significant health risk among older people. The growing percentage of people of old age requires urgent development of fall detection and prevention systems. The emerging technology focuses on developing such systems to improve quality of life, especially for the elderly. A fall prevention system tries to predict and reduce the risk of falls. In contrast, a fall detection system observes the fall and generates a help notification to minimize the consequences of falls. A plethora of technical and review papers exist in the literature with a primary focus on fall detection. Similarly, several studies are relatively old, with a focus on wearables only, and use statistical and threshold-based approaches with a high false alarm rate. Therefore, this paper presents the latest research trends in fall detection and prevention systems using Machine Learning (ML) algorithms. It uses recent studies and analyzes datasets, age groups, ML algorithms, sensors, and location. Additionally, it provides a detailed discussion of the current trends of fall detection and prevention systems with possible future directions. This overview can help researchers understand the current systems and propose new methodologies by improving the highlighted issues. ispartof: SENSORS vol:21 issue:15 ispartof: location:Switzerland status: published

International audience; We introduce a blind spot method to create image changes contingent on eye movements. One challenge of eye movement research is triggering display changes contingent on gaze. The eye-tracking system must capture the image of the eye, discover and track the pupil and corneal reflections to estimate the gaze position, and then transfer this data to the computer that updates the display. All of these steps introduce delays that are often difficult to predict. To avoid these issues, we describe a simple blind spot method to generate gaze contingent display manipulations without any eye-tracking system and/or display controls.

Extracting effective features from ship-radiated noise is an important way to improve the detection and recognition performance of passive sonar. Complexity features of ship-radiated noise have attracted increasing amounts of attention. However, the traditional definition of complexity based on entropy (information stored in the system) is not accurate. To this end, a new statistical complexity measure is proposed in this paper based on spectrum entropy and disequilibrium. Since the spectrum features are unique to the class of the ship, our method can distinguish different ships according to their location in the two-dimensional plane composed of complexity and spectrum entropy (CSEP). To weaken the influence of ocean ambient noise, the intrinsic time-scale decomposition (ITD) is applied to preprocess the data in this study. The effectiveness of the proposed method is validated through a classification experiment of four types of marine vessels. The recognition rate of the ITD-CSEP methodology achieved 94%, which is much higher than that of traditional feature extraction methods. Moreover, the ITD-CSEP is fast and parameter free. Hence, the method can be applied in the real time processing practical applications.

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that makes digitization of documents viable. Since the advent of deep learning, the performance of deep learning-based object detection has improved many folds. In this work, we outline and summarize the deep learning approaches for detecting graphical page objects in the document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.

The increasing demand for smart vehicles with many sensing capabilities will escalate data traffic in vehicular networks. Meanwhile, available network resources are limited. The emergence of AI implementation in vehicular network resource allocation opens the opportunity to improve resource utilization to provide more reliable services. Accordingly, many resource allocation schemes with various machine learning algorithms have been proposed to dynamically manage and allocate network resources. This survey paper presents how machine learning is leveraged in the vehicular network resource allocation strategy. We focus our study on determining its role in the mechanism. First, we provide an analysis of how authors designed their scenarios to orchestrate the resource allocation strategy. Secondly, we classify the mechanisms based on the parameters they chose when designing the algorithms. Finally, we analyze the challenges in designing a resource allocation strategy in vehicular networks using machine learning. Therefore, a thorough understanding of how machine learning algorithms are utilized to offer a dynamic resource allocation in vehicular networks is provided in this study.

Laser-induced breakdown spectroscopy (LIBS) was tested for all of the relevant issues in forensic examinations of commercial inks, including classification of pen inks on one paper type and on different paper types, determination of the deposition order of layered inks, and analysis of signatures and toners on one questioned document. The scope of this work was to determine the potential of a single LIBS setup that is compatible with portable instruments for different types of ink analysis, rather than building a very large database for inks and papers. We identified up to seven metals characteristic for the examined inks, which allowed to fully discriminate all eight black inks on one type of printing paper. When the inks were tested on ten different papers, the correct classification rates for some of them were reduced for reasons thoroughly studied and explained. The replicated tests on three crossing points, each one involving a pair of blue or black inks, were successful in five cases out of six. In the test simulating documents of forensic interest (questioned documents), LIBS was able to correctly identify the differences in three inks used for signatures on one of the three pages and the use of different printing inks on each page of the document.

In recent years, reversible data hiding (RDH) has become a research hotspot in the field of multimedia security that has aroused more and more researchers&rsquo, attention. Most of the existing RDH algorithms are aiming at continuous-tone images. For RDH in encrypted halftone images (RDH-EH), the original cover image cannot be recovered losslessly after the watermark is extracted. For some application scenarios such as medical or military images sharing, reversibility is critical. In this paper, a reversible data hiding scheme in encrypted color halftone images (RDH-ECH) is proposed. In the watermark embedding procedure, the cover image is copied into two identical images to increase redundancy. We use wet paper code to embed the watermark into the image blocks. Thus, the receiver only needs to process the image blocks by the check matrices in order to extract the watermarks. To increase embedding capacity, we embed three layers in the embedding procedure and combine the resulting images into one image for convenience of transmission. From the experimental results, it can be concluded that the original image can be restored entirely after the watermarks are extracted. Besides, for marked color halftone images, our algorithm can implement high embedding capacity and moderate visual quality.

This short paper presents the activity recognition results obtained from the CAR-CSIC team for the UCAmI’18 Cup. We propose a multi-event naive Bayes classifier for estimating 24 different activities in real-time. We use all the sensorial information provided for the competition, i.e., binary sensors fixed to everyday objects, proximity BLE-based tags, location-aware smart floor sensing and the wrist’s acceleration. The results using training data-sets of 7 days show accuracies (true positives) about 68%; however for the three extra data-sets of the competition we were able to reach a 60.5% accuracy.

The aim of this work is to develop a tool to predict some pulp properties e.g., pulp yield, Kappa number, ISO brightness (ISO 2470:2008), fiber length and fiber width, using the sapwood and heartwood proportion in the raw-material. For this purpose, Acacia melanoxylon trees were collected from four sites in Portugal. Percentage of sapwood and heartwood, area and the stem eccentricity (in N-S and E-W directions) were measured on transversal stem sections of A. melanoxylon R. Br. The relative position of the samples with respect to the total tree height was also considered as an input variable. Different configurations were tested until the maximum correlation coefficient was achieved. A classical mathematical technique (multiple linear regression) and machine learning methods (classification and regression trees, multi-layer perceptron and support vector machines) were tested. Classification and regression trees (CART) was the most accurate model for the prediction of pulp ISO brightness (R = 0.85). The other parameters could be predicted with fair results (R = 0.64–0.75) by CART. Hence, the proportion of heartwood and sapwood is a relevant parameter for pulping and pulp properties, and should be taken as a quality trait when assessing a pulpwood resource. info:eu-repo/semantics/acceptedVersion

Image fusion is a useful tool in integrating a high-resolution panchromatic image (HRPI) with a low-resolution multispectral image (LRMI) to produce a high-resolution multispectral image (HRMI). To date, many image fusion techniques have been developed to try to improve the spatial resolution of the LRMI to that of the HRPI with its spectral property reliably preserved. However, many studies have indicated that there exists a trade- off between the spatial resolution improvement and the spectral property preservation of the LRMI, and it is difficult for the existing methods to do the best in both aspects. Based on one minimization problem, this paper mathematically analyzes the tradeoff in fusing remote sensing images. In experiment, four fusion methods are evaluated through expanded spectral angle mapper (ESAM). Results clearly prove that all the tested methods have this property.

Wireless multimedia sensor networks (WMSN) have recently emerged as one of the most important technologies, driven by the powerful multimedia signal acquisition and processing abilities. Target classification is an important research issue addressed in WMSN, which has strict requirement in robustness, quickness and accuracy. This paper proposes a collaborative semi-supervised classifier learning algorithm to achieve durative online learning for support vector machine (SVM) based robust target classification. The proposed algorithm incrementally carries out the semi-supervised classifier learning process in hierarchical WMSN, with the collaboration of multiple sensor nodes in a hybrid computing paradigm. For decreasing the energy consumption and improving the performance, some metrics are introduced to evaluate the effectiveness of the samples in specific sensor nodes, and a sensor node selection strategy is also proposed to reduce the impact of inevitable missing detection and false detection. With the ant optimization routing, the learning process is implemented with the selected sensor nodes, which can decrease the energy consumption. Experimental results demonstrate that the collaborative hybrid semi-supervised classifier learning algorithm can effectively implement target classification in hierarchical WMSN. It has outstanding performance in terms of energy efficiency and time cost, which verifies the effectiveness of the sensor nodes selection and ant optimization routing.

Previous functional MRI and brain electrophysiology studies have studied the left-right differences during the tapping tasks and found that the activation of left hemisphere was more significant than that of right hemisphere. In this study, we wanted to delineate this lateralization phenomenon not only in the execution phase but also in other processing phases, such as early visual, pre-executive and post-executive phases. We have designed a finger-tapping task to delineate the left-right differences of event related potentials (ERPs) to right finger movement in sixteen right handed college students. The mean amplitudes of ERPs were analyzed to examine the left-right dominance of cortical activity in the phase of early visual process (75-120ms), pre-execution (175-260ms), execution (310-420ms) and post-execution (420-620ms). In the execution phase, ERPs at the left electrodes were significantly more pronounced than those at the right electrodes (F3 > F4, C3 > C4, P3 > P4, O1 > O2) under the situation without comparing the central electrodes (Fz, Cz, Pz, and Oz). No difference was found between left and right electrodes in other three phases except the C3 electrode still showed more dominant than C4 in the pre- and post-execution phase. In conclusion, the phenomenon of brain lateralization occur major in the execution phase. The central area also showed the lateralization in the pre- and post-execution to demonstrate its unique lateralized contributions to unilateral simple finger movements.

A valid unsupervised and multiscale segmentation of synthetic aperture radar (SAR) imagery is proposed by a combination GA-EM of the Expectation Maximization (EM) algorith with the genetic algorithm (GA). The mixture multiscale autoregressive (MMAR) model is introduced to characterize and exploit the scale-to-scale statistical variations and statistical variations in the same scale in SAR imagery due to radar speckle, and a segmentation method is given by combining the GA algorithm with the EM algorithm. This algorithm is capable of selecting the number of components of the model using the minimum description length (MDL) criterion. Our approach benefits from the properties of the Genetic and the EM algorithm by combination of both into a single procedure. The population-based stochastic search of the genetic algorithm (GA) explores the search space more thoroughly than the EM method. Therefore, our algorithm enables escaping from local optimal solutions since the algorithm becomes less sensitive to its initialization. Some experiment results are given based on our proposed approach, and compared to that of the EM algorithms. The experiments on the SAR images show that the GA-EM outperforms the EM method.

An electronic tongue comprising different numbers of electrodes was able to classify test mixtures of key odorants characteristic of bioscrubbers of livestock buildings (n-butyrate, iso-valerate, phenolate, p-cresolate, skatole and ammonium). The classification of model solutions indicates that the electronic tongue has a promising potential as an on- line sensor for characterization of odorants in livestock buildings. Back propagation artificial neural network was used for classification. The average classification rate was above 80% in all cases. A limited, but sufficient number of electrodes were selected by average classification rate and relative entropy. The sufficient number of electrodes decreased standard deviation and relative standard deviation compared to the full electrode array.

Text classification is a fundamental language task in Natural Language Processing. A variety of sequential models are capable of making good predictions, yet there is a lack of connection between language semantics and prediction results. This paper proposes a novel influence score (I-score), a greedy search algorithm, called Backward Dropping Algorithm (BDA), and a novel feature engineering technique called the “dagger technique”. First, the paper proposes to use the novel influence score (I-score) to detect and search for the important language semantics in text documents that are useful for making good predictions in text classification tasks. Next, a greedy search algorithm, called the Backward Dropping Algorithm, is proposed to handle long-term dependencies in the dataset. Moreover, the paper proposes a novel engineering technique called the “dagger technique” that fully preserves the relationship between the explanatory variable and the response variable. The proposed techniques can be further generalized into any feed-forward Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs), and any neural network. A real-world application on the Internet Movie Database (IMDB) is used and the proposed methods are applied to improve prediction performance with an 81% error reduction compared to other popular peers if I-score and “dagger technique” are not implemented.

The automated fault detection and diagnostics (AFDD) of heating, ventilation, and air conditioning (HVAC) using data mining and machine learning models have recently received substantial attention from researchers and practitioners. Various models have been developed over the years for AFDD of complete HVAC or its sub-systems. However, HVAC complexities, which partly have roots in its close coupling nature and interrelated dependencies, mean that understanding the relationship between faults and the suitability of the techniques remains an unanswered question. The literature analysis and interactive visualization of the data collected from the past implementation of AFDD models can provide useful insight to further explore this question by applying artificial intelligence (AI). Association rule mining (ARM) is deployed by this paper, using the frequent pattern (FP) growth algorithm to generate frequent fault sets for most common HVAC faults from the body of AFDD models developed in the literature to represent the status quo. A new model is developed for common HVAC faults and the techniques most frequently used to detect and diagnose them. A recommender system is developed using the ARM model to extract knowledge from the body of knowledge of HVAC data-driven AFDD in the form of rule-sets that reflect the associations. Findings of this review paper can significantly help civil and building engineers, as well as facility managers, in better management of building HVAC systems.

Precise environmental modelling of pollutants distributions represents a key factor for addresing the issue of urban air pollution. Nowadays, urban air pollution monitoring is primarily carried out by employing sparse networks of spatially distributed fixed stations. The work in this paper aims at improving the situation by utilizing machine learning models to process the outputs of multi-sensor devices that are small, cheap, albeit less reliable, thus a massive urban deployment of those devices is possible. The main contribution of the paper is the design of a mathematical model providing sensor fusion to extract the information and transform it into the desired pollutant concentrations. Multi-sensor outputs are used as input information for a particular machine learning model trained to produce the CO, NO2, and NOx concentration estimates. Several state-of-the-art machine learning methods, including original algorithms proposed by the authors, are utilized in this study: kernel methods, regularization networks, regularization networks with composite kernels, and deep neural networks. All methods are augmented with a proper hyper-parameter search to achieve the optimal performance for each model. All the methods considered achieved vital results, deep neural networks exhibited the best generalization ability, and regularization networks with product kernels achieved the best fitting of the training set.

Cryptocurrency is a new sort of asset that has emerged as a result of the advancement of financial technology and it has created a big opportunity for researches. Cryptocurrency price forecasting is difficult due to price volatility and dynamism. Around the world, there are hundreds of cryptocurrencies that are used. This paper proposes three types of recurrent neural network (RNN) algorithms used to predict the prices of three types of cryptocurrencies, namely Bitcoin (BTC), Litecoin (LTC), and Ethereum (ETH). The models show excellent predictions depending on the mean absolute percentage error (MAPE). Results obtained from these models show that the gated recurrent unit (GRU) performed better in prediction for all types of cryptocurrency than the long short-term memory (LSTM) and bidirectional LSTM (bi-LSTM) models. Therefore, it can be considered the best algorithm. GRU presents the most accurate prediction for LTC with MAPE percentages of 0.2454%, 0.8267%, and 0.2116% for BTC, ETH, and LTC, respectively. The bi-LSTM algorithm presents the lowest prediction result compared with the other two algorithms as the MAPE percentages are: 5.990%, 6.85%, and 2.332% for BTC, ETH, and LTC, respectively. Overall, the prediction models in this paper represent accurate results close to the actual prices of cryptocurrencies. The importance of having these models is that they can have significant economic ramifications by helping investors and traders to pinpoint cryptocurrency sales and purchasing. As a plan for future work, a recommendation is made to investigate other factors that might affect the prices of cryptocurrency market such as social media, tweets, and trading volume.

This paper presents an investigation of the capacity of machine learning methods (ML) to localize leakage in water distribution systems (WDS). This issue is critical because water leakage causes economic losses, damages to the surrounding infrastructures, and soil contamination. Progress in real-time monitoring of WDS and ML has created new opportunities to develop data-based methods for water leak localization. However, the managers of WDS need recommendations for the selection of the appropriate ML methods as well their practical use for leakage localization. This paper contributes to this issue through an investigation of the capacity of ML methods to localize leakage in WDS. The campus of Lille University was used as support for this research. The paper is presented as follows: First, flow and pressure data were determined using EPANET software, then, the generated data were used to investigate the capacity of six ML methods to localize water leakage. Finally, the results of the investigations were used for leakage localization from offline water flow data. The results showed excellent performance for leakage localization by the artificial neural network, logistic regression, and random forest, but there were low performances for the unsupervised methods because of overlapping clusters.

The concept of measurement uncertainty was introduced in the 1990s by the “Guide to the expression of uncertainty in measurement”, known as GUM. The word uncertainty has a lexical meaning and reflects the lack of exact knowledge or lack of complete knowledge about the value of the measurand. Thanks to the suggestions in the GUM and following the mathematical probabilistic approaches therein proposed, an uncertainty value can be found and be associated to the measured value. In the last decades, however, other methods have been proposed in the literature, which try to encompass the definitions of the GUM, thus overcoming its limitations. Some of these methods are based on the possibility theory, such as the one known as the RFV method. The aim of this paper is to briefly recall the RFV method, starting from the very beginning and the initial motivations, and summarize in a unique paper the most relevant obtained results.

In this paper, I propose a conceptual framework for law and artificial intelligence (AI) that is based on ideas derived from systems and control theory. The approach considers the relationship between the input to an AI-controlled system and the system’s output, which may affect events in the real-world. The approach aims to add to the current discussion among legal scholars and legislators on how to regulate AI, which focuses primarily on how the output, or external behavior of a system, leads to actions that may implicate the law. The goal of this paper is to show that not only is the systems output an important consideration for law and AI but so too is the relationship between the systems input to its desired output, as mediated through a feedback loop (and other control variables). In this paper, I argue that ideas derived from systems and control theory can be used to provide a conceptual framework to help understand how the law applies to AI, and particularly, to algorithmically based systems.

With the development of the Internet, network security has aroused people’s attention. It can be said that a secure network environment is a basis for the rapid and sound development of the Internet. Phishing is an essential class of cybercriminals which is a malicious act of tricking users into clicking on phishing links, stealing user information, and ultimately using user data to fake logging in with related accounts to steal funds. Network security is an iterative issue of attack and defense. The methods of phishing and the technology of phishing detection are constantly being updated. Traditional methods for identifying phishing links rely on blacklists and whitelists, but this cannot identify new phishing links. Therefore, we need to solve how to predict whether a newly emerging link is a phishing website and improve the accuracy of the prediction. With the maturity of machine learning technology, prediction has become a vital ability. This paper offers a state-of-the-art survey on methods for phishing website detection. It starts with the life cycle of phishing, introduces common anti-phishing methods, mainly focuses on the method of identifying phishing links, and has an in-depth understanding of machine learning-based solutions, including data collection, feature extraction, modeling, and evaluation performance. This paper provides a detailed comparison of various solutions for phishing website detection.

The first part of a two-part series of papers provides a survey on recent advances in Deep Reinforcement Learning (DRL) applications for solving partially observable Markov decision processes (POMDP) problems. Reinforcement Learning (RL) is an approach to simulate the human’s natural learning process, whose key is to let the agent learn by interacting with the stochastic environment. The fact that the agent has limited access to the information of the environment enables AI to be applied efficiently in most fields that require self-learning. Although efficient algorithms are being widely used, it seems essential to have an organized investigation—we can make good comparisons and choose the best structures or algorithms when applying DRL in various applications. In this overview, we introduce Markov Decision Processes (MDP) problems and Reinforcement Learning and applications of DRL for solving POMDP problems in games, robotics, and natural language processing. A follow-up paper will cover applications in transportation, communications and networking, and industries.

This paper demonstrates the differences between popular transformation-based input representations for vibration-based machine fault diagnosis. This paper highlights the dependency of different input representations on hyperparameter selection with the results of training different configurations of classical convolutional neural networks (CNNs) with three common benchmarking datasets. Raw temporal measurement, Fourier spectrum, envelope spectrum, and spectrogram input types are individually used to train CNNs. Many configurations of CNNs are trained, with variable input sizes, convolutional kernel sizes and stride. The results show that each input type favors different combinations of hyperparameters, and that each of the datasets studied yield different performance characteristics. The input sizes are found to be the most significant determiner of whether overfitting will occur. It is demonstrated that CNNs trained with spectrograms are less dependent on hyperparameter optimization over all three datasets. This paper demonstrates the wide range of performance achieved by CNNs when preprocessing method and hyperparameters are varied as well as their complex interaction, providing researchers with useful background information and a starting place for further optimization.

Machine learning (ML) is a powerful tool that delivers insights hidden in Internet of Things (IoT) data. These hybrid technologies work smartly to improve the decision-making process in different areas such as education, security, business, and the healthcare industry. ML empowers the IoT to demystify hidden patterns in bulk data for optimal prediction and recommendation systems. Healthcare has embraced IoT and ML so that automated machines make medical records, predict disease diagnoses, and, most importantly, conduct real-time monitoring of patients. Individual ML algorithms perform differently on different datasets. Due to the predictive results varying, this might impact the overall results. The variation in prediction results looms large in the clinical decision-making process. Therefore, it is essential to understand the different ML algorithms used to handle IoT data in the healthcare sector. This article highlights well-known ML algorithms for classification and prediction and demonstrates how they have been used in the healthcare sector. The aim of this paper is to present a comprehensive overview of existing ML approaches and their application in IoT medical data. In a thorough analysis, we observe that different ML prediction algorithms have various shortcomings. Depending on the type of IoT dataset, we need to choose an optimal method to predict critical healthcare data. The paper also provides some examples of IoT and machine learning to predict future healthcare system trends.

In recent years, the use of deep learning in language models has gained much attention. Some research projects claim that they can generate text that can be interpreted as human writing, enabling new possibilities in many application areas. Among the different areas related to language processing, one of the most notable in applying this type of modeling is programming languages. For years, the machine learning community has been researching this software engineering area, pursuing goals like applying different approaches to auto-complete, generate, fix, or evaluate code programmed by humans. Considering the increasing popularity of the deep learning-enabled language models approach, we found a lack of empirical papers that compare different deep learning architectures to create and use language models based on programming code. This paper compares different neural network architectures like Average Stochastic Gradient Descent (ASGD) Weight-Dropped LSTMs (AWD-LSTMs), AWD-Quasi-Recurrent Neural Networks (QRNNs), and Transformer while using transfer learning and different forms of tokenization to see how they behave in building language models using a Python dataset for code generation and filling mask tasks. Considering the results, we discuss each approach&rsquo, s different strengths and weaknesses and what gaps we found to evaluate the language models or to apply them in a real programming context.

Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS) in application areas that cannot easily be mastered with traditional control approaches, such as autonomous driving. As a consequence, the safety of machine learning became a focus area for research in recent years. Despite very considerable advances in selected areas related to machine learning safety, shortcomings were identified on holistic approaches that take an end-to-end view on the risks associated to the engineering of ML-based control systems and their certification. Applying a classic technique of safety engineering, our paper provides a comprehensive and methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and could compromise the safe operation of ML-based CPS. Identified hazards are illustrated and explained using a real-world application scenario&mdash, an autonomous shop-floor transportation vehicle. The comprehensive analysis presented in this paper is intended as a basis for future holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the focus on research onto safety hazards that are not yet adequately addressed.

Pine wilt disease causes huge economic losses to pine wood forestry because of its destructiveness and rapid spread. This paper proposes a detection and location method of pine wood nematode disease at a large scale adopting UAV (Unmanned Aerial Vehicle) remote sensing and artificial intelligence technology. The UAV remote sensing images were enhanced by computer vision tools. A Faster-RCNN (Faster Region Convolutional Neural Networks) deep learning framework based on a RPN (Region Proposal Network) network and the ResNet residual neural network were used to train the pine wilt diseased dead tree detection model. The loss function and the anchors in the RPN of the convolutional neural network were optimized. Finally, the location of pine wood nematode dead tree was conducted, which generated the geographic information on the detection results. The results show that ResNet101 performed better than VGG16 (Visual Geometry Group 16) convolutional neural network. The detection accuracy was improved and reached to about 90% after a series of optimizations to the network, meaning that the optimization methods proposed in this paper are feasible to pine wood nematode dead tree detection.

Surveys on explainable artificial intelligence (XAI) are related to biology, clinical trials, fintech management, medicine, neurorobotics, and psychology, among others. Prognostics and health management (PHM) is the discipline that links the studies of failure mechanisms to system lifecycle management. There is a need, which is still absent, to produce an analytical compilation of PHM-XAI works. In this paper, we use preferred reporting items for systematic reviews and meta-analyses (PRISMA) to present a state of the art on XAI applied to PHM of industrial assets. This work provides an overview of the trend of XAI in PHM and answers the question of accuracy versus explainability, considering the extent of human involvement, explanation assessment, and uncertainty quantification in this topic. Research articles associated with the subject, since 2015 to 2021, were selected from five databases following the PRISMA methodology, several of them related to sensors. The data were extracted from selected articles and examined obtaining diverse findings that were synthesized as follows. First, while the discipline is still young, the analysis indicates a growing acceptance of XAI in PHM. Second, XAI offers dual advantages, where it is assimilated as a tool to execute PHM tasks and explain diagnostic and anomaly detection activities, implying a real need for XAI in PHM. Third, the review shows that PHM-XAI papers provide interesting results, suggesting that the PHM performance is unaffected by the XAI. Fourth, human role, evaluation metrics, and uncertainty management are areas requiring further attention by the PHM community. Adequate assessment metrics to cater to PHM needs are requested. Finally, most case studies featured in the considered articles are based on real industrial data, and some of them are related to sensors, showing that the available PHM-XAI blends solve real-world challenges, increasing the confidence in the artificial intelligence models’ adoption in the industry.

Air pollution is a common problem for many countries around the world in the process of industrialization as well as a challenge to sustainable development. This paper has selected Chengdu-Chongqing region of China as the research object, which suffers from severe air pollution and has been actively involved in air pollution control in recent years to achieve sustainable development. Based on the historical data of 16 cities in this region from January 2015 to November 2019 on six major air pollutants, this paper has first conducted evaluation on the monthly air quality of these cities within the research period by using Principal Component Analysis and the Technique for Order Preference by Similarity to an Ideal Solution. Based on that, this paper has adopted the Long Short-Term Memory neural network model in deep learning to forecast the monthly air quality of various cities from December 2019 to November 2020. The aims of this paper are to enrich existing literature on air pollution control, and provide a novel scientific tool for design and formulation of air pollution control policies by innovatively integrating commonly used evaluation models and deep learning forecast methods. According to the research results, in terms of historical evaluation, the air quality of cities in the Chengdu-Chongqing region was generally moving in the same trend in the research period, with distinct characteristics of cyclicity and convergence. Year- on-year speaking, the effectiveness of air pollution control in various cities has shown a visible improvement trend. For example, Ya&rsquo, an&rsquo, s lowest air quality evaluation score has improved from 0.3494 in 2015 to 0.4504 in 2019, Zigong&rsquo, s lowest air quality score has also risen from 0.4160 in 2015 to 0.6429 in 2019. Based on the above historical evaluation and deep learning forecast results, this paper has proposed relevant policy recommendations for air pollution control in the Chengdu-Chongqing region.

Falling is one of the causes of accidental death of elderly people over 65 years old in Taiwan. If the fall incidents are not detected in a timely manner, it could lead to serious injury or even death of those who fell. General fall detection approaches require the users to wear sensors, which could be cumbersome for the users to put on, and misalignment of sensors could lead to erroneous readings. In this paper, we propose using computer vision and applied machine-learning algorithms to detect fall without any sensors. We applied OpenPose real-time multi-person 2D pose estimation to detect movement of a subject using two datasets of 570 &times, 30 frames recorded in five different rooms from eight different viewing angles. The system retrieves the locations of 25 joint points of the human body and detects human movement through detecting the joint point location changes. The system is able to effectively identify the joints of the human body as well as filtering ambient environmental noise for an improved accuracy. The use of joint points instead of images improves the training time effectively as well as eliminating the effects of traditional image-based approaches such as blurriness, light, and shadows. This paper uses single-view images to reduce equipment costs. We experimented with time series recurrent neural network, long- and short-term memory, and gated recurrent unit models to learn the changes in human joint points in continuous time. The experimental results show that the fall detection accuracy of the proposed model is 98.2%, which outperforms the baseline 88.9% with 9.3% improvement.

Providing fair and convenient comparisons between recommendation algorithms—where algorithms could focus on a traditional dimension (accuracy) and/or less traditional ones (e.g., novelty, diversity, serendipity, etc.)—is a key challenge in the recent developments of recommender systems. This paper focuses on novelty and presents a new, closer-to-reality model for evaluating the quality of a recommendation algorithm by reducing the popularity bias inherent in traditional training/test set evaluation frameworks, which are biased by the dominance of popular items and their inherent features. In the suggested model, each interaction has a probability of being included in the test set that randomly depends on a specific feature related to the focused dimension (novelty in this work). The goal of this paper is to reconcile, in terms of evaluation (and therefore comparison), the accuracy and novelty dimensions of recommendation algorithms, leading to a more realistic comparison of their performance. The results obtained from two well-known datasets show the evolution of the behavior of state-of-the-art ranking algorithms when novelty is progressively, and fairly, given more importance in the evaluation procedure, and could lead to potential changes in the decision processes of organizations involving recommender systems.

To realize the adaptive grasping of objects with diverse shapes and to capture the joint angles of the finger, a multi degree of freedom (DOF) adaptive finger for prosthetic hand is proposed in this paper. The fingers are designed with three joints. The maximum rotation angle of the finger joints is 90&deg, The angle at which the finger joints bend can be captured. Firstly, the prototype design, forward kinematics and force analysis of phalanges are described in detail. In order to achieve an adaptive motion pattern similar to that of the human hand, this paper investigates the optimization of the torsion spring stiffness coefficient so that the metacarpophalangeal (MCP) joints, proximal interphalangeal (PIP) joints, and distal interphalangeal (DIP) joints of the bionic finger meet a motion ratio of approximately 3:3:1. Then, in order to realize the joint angle measurement in the process of grasping an object, the mechanical-sensor integrated finger joint is designed, and the composition, angle measurement principle and measurement circuit are introduced in detail. Finally, joint angle measurement, movement law evaluation and object grasping experiments are performed to verify the validity of the designed finger. The experimental results show that the root-mean-square (RMS) of the DIP, PIP and MCP angle measurement errors are 0.36&deg, 0.59&deg, and 0.32&deg, respectively. The designed finger is able to grasp objects with different shapes stably.

The field of human activity recognition (HAR) often utilizes wearable sensors and machine learning techniques in order to identify the actions of the subject. This paper considers the activity recognition of walking and running while using a support vector machine (SVM) that was trained on principal components derived from wearable sensor data. An ablation analysis is performed in order to select the subset of sensors that yield the highest classification accuracy. The paper also compares principal components across trials to inform the similarity of the trials. Five subjects were instructed to perform standing, walking, running, and sprinting on a self-paced treadmill, and the data were recorded while using surface electromyography sensors (sEMGs), inertial measurement units (IMUs), and force plates. When all of the sensors were included, the SVM had over 90% classification accuracy using only the first three principal components of the data with the classes of stand, walk, and run/sprint (combined run and sprint class). It was found that sensors that were placed only on the lower leg produce higher accuracies than sensors placed on the upper leg. There was a small decrease in accuracy when the force plates are ablated, but the difference may not be operationally relevant. Using only accelerometers without sEMGs was shown to decrease the accuracy of the SVM.

Background. Artificial Intelligence (AI) is an advanced technology for the latest 20 years. Machine learning (ML) and deep learning (DL) are the major innovations for AI, which has been applied for multiple fields. Ophthalmology has become to be one of the most significant disciplines for human healthcare. Methodology. This study utilizes methods of text mining and bibliometric analysis to explore applications of AI to ophthalmology. 179 related articles from Web of Science (WOS) and 96 papers from China National Knowledge Infrastructure (CNKI) are explored during the period of 2000 to 2021. A descriptive analysis of major trends, journal releasing, topic mapping and quotation relationships is implemented in this paper. Leading authors, journals, institutions, nations and references in the related research are identified. Results. Findings show that the application of AI technologies in ophthalmologic diagnosis with optical coherence tomography (OCT) fundus images is the core topic for this area’s studies, especially for diabetic retinopathy (DR), aged macular degeneration (AMD) and glaucoma. It is also be predicted as the core direction over the recent years. Besides, The USA, England and China is the most competitive countries in this scientific filed. Journals of Ophthalmology, Investigative Ophthalmology and Visual Science, Eye, Acta Ophthalmologica and Scientific Reports are the top five journal related to the research area. There is a significant difference between WOS and CNKI databases pertaining to the application of Artificial Intelligence (AI) to ophthalmology, especially for the historic development, topic mapping and discipline category. Finally, the potential academic value of interdisciplinary subject of “AI in Ophthalmology” and tradition Chinese medicine (TRM) is discussed. Limitations and suggestions for the future research is indicated at the end of this paper.

Compared with traditional optical and multispectral remote sensing images, hyperspectral images have hundreds of bands that can provide the possibility of fine classification of the earth’s surface. At the same time, a hyperspectral image is an image that coexists with the spatial and spectral. It has become a hot research topic to combine the spatial spectrum information of the image to classify hyperspectral features. Based on the idea of spatial–spectral classification, this paper proposes a novel hyperspectral image classification method based on a segment forest (SF). Firstly, the first principal component of the image was extracted by the process of principal component analysis (PCA) data dimension reduction, and the data constructed the segment forest after dimension reduction to extract the non-local prior spatial information of the image. Secondly, the images’ initial classification results and probability distribution were obtained using support vector machine (SVM), and the spectral information of the images was extracted. Finally, the segment forest constructed above is used to optimize the initial classification results and obtain the final classification results. In this paper, three domestic and foreign public data sets were selected to verify the segment forest classification. SF effectively improved the classification accuracy of SVM, and the overall accuracy of Salinas was enhanced by 11.16%, WHU-Hi-HongHu by 15.89%, and XiongAn by 19.56%. Then, it was compared with six decision-level improved space spectrum classification methods, including guided filtering (GF), Markov random field (MRF), random walk (RW), minimum spanning tree (MST), MST+, and segment tree (ST). The results show that the segment forest-based hyperspectral image classification improves accuracy and efficiency compared with other algorithms, proving the algorithm’s effectiveness.

In this paper, the attitudes of experts are observed for the possible changes after taking a certain decision. The decision is taken by two persons with different fields of expertise. There is also an annotation of such changes due to the interference of a third person, which is main idea of this paper. These observations are done by developing fuzzy soft differential equations with the help of optimum fuzzy soft constants (OFSCs), which are obtained through the ranking coefficients. The ranking of alternatives is based on the coefficients, which are obtained through a decision-making process. Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is exploited to rank the alternatives, and the attitudes of resource persons are examined through phase portraits and line graphs of the respective system of differential equations. The utilization of TOPSIS is a practice of multi-criteria decision-making in the analysis of human behaviours. Dual hesitant fuzzy soft sets are taken to represent the initial data.

Apple flower detection is an important project in the apple planting stage. This paper proposes an optimized detection network model based on a generative module and pruning inference. Due to the problems of instability, non-convergence, and overfitting of convolutional neural networks in the case of insufficient samples, this paper uses a generative module and various image pre-processing methods including Cutout, CutMix, Mixup, SnapMix, and Mosaic algorithms for data augmentation. In order to solve the problem of slowing down the training and inference due to the increasing complexity of detection networks, the pruning inference proposed in this paper can automatically deactivate part of the network structure according to the different conditions, reduce the network parameters and operations, and significantly improve the network speed. The proposed model can achieve 90.01%, 98.79%, and 97.43% in precision, recall, and mAP, respectively, in detecting the apple flowers, and the inference speed can reach 29 FPS. On the YOLO-v5 model with slightly lower performance, the inference speed can reach 71 FPS by the pruning inference. These experimental results demonstrate that the model proposed in this paper can meet the needs of agricultural production.

In the last few years, intensive research has been done to enhance artificial intelligence (AI) using optimization techniques. In this paper, we present an extensive review of artificial neural networks (ANNs) based optimization algorithm techniques with some of the famous optimization techniques, e.g., genetic algorithm (GA), particle swarm optimization (PSO), artificial bee colony (ABC), and backtracking search algorithm (BSA) and some modern developed techniques, e.g., the lightning search algorithm (LSA) and whale optimization algorithm (WOA), and many more. The entire set of such techniques is classified as algorithms based on a population where the initial population is randomly created. Input parameters are initialized within the specified range, and they can provide optimal solutions. This paper emphasizes enhancing the neural network via optimization algorithms by manipulating its tuned parameters or training parameters to obtain the best structure network pattern to dissolve the problems in the best way. This paper includes some results for improving the ANN performance by PSO, GA, ABC, and BSA optimization techniques, respectively, to search for optimal parameters, e.g., the number of neurons in the hidden layers and learning rate. The obtained neural net is used for solving energy management problems in the virtual power plant system.

This paper addresses the challenge of minimizing training time for the control of Heating, Ventilation, and Air-conditioning (HVAC) systems with online Reinforcement Learning (RL). This is done by developing a novel approach to Multi-Agent Reinforcement Learning (MARL) to HVAC systems. In this paper, the environment formed by the HVAC system is formulated as a Markov Game (MG) in a general sum setting. The MARL algorithm is designed in a decentralized structure, where only relevant states are shared between agents, and actions are shared in a sequence, which are sensible from a system’s point of view. The simulation environment is a domestic house located in Denmark and designed to resemble an average house. The heat source in the house is an air-to-water heat pump, and the HVAC system is an Underfloor Heating system (UFH). The house is subjected to weather changes from a data set collected in Copenhagen in 2006, spanning the entire year except for June, July, and August, where heat is not required. It is shown that: (1) When comparing Single Agent Reinforcement Learning (SARL) and MARL, training time can be reduced by 70% for a four temperature-zone UFH system, (2) the agent can learn and generalize over seasons, (3) the cost of heating can be reduced by 19% or the equivalent to 750 kWh of electric energy per year for an average Danish domestic house compared to a traditional control method, and (4) oscillations in the room temperature can be reduced by 40% when comparing the RL control methods with a traditional control method.

Digitalization and artificial intelligence (AI) technologies in migration and mobility have incrementally expanded over recent years. Iterative approaches to AI deployment experienced a surge during 2020 and into 2021, largely due to COVID-19 forcing greater reliance on advanced digital technology to monitor, inform and respond to the pandemic. This paper critically examines the implications of intensifying digitalization and AI for migration and mobility systems for a post-COVID transnational context. First, it situates digitalization and AI in migration by analyzing its uptake throughout the Migration Cycle. Second, the article evaluates the current challenges and, opportunities to migrants and migration systems brought about by deepening digitalization due to COVID-19, finding that while these expanding technologies can bolster human rights and support international development, potential gains can and are being eroded because of design, development and implementation aspects. Through a critical review of available literature on the subject, this paper argues that recent changes brought about by COVID-19 highlight that computational advances need to incorporate human rights throughout design and development stages, extending well beyond technical feasibility. This also extends beyond tech company references to inclusivity and transparency and requires analysis of systemic risks to migration and mobility regimes arising from advances in AI and related technologies.

The segmentation of remote sensing images by deep learning technology is the main method for remote sensing image interpretation. However, the segmentation model based on a convolutional neural network cannot capture the global features very well. A transformer, whose self-attention mechanism can supply each pixel with a global feature, makes up for the deficiency of the convolutional neural network. Therefore, a multi-scale adaptive segmentation network model (MSST-Net) based on a Swin Transformer is proposed in this paper. Firstly, a Swin Transformer is used as the backbone to encode the input image. Then, the feature maps of different levels are decoded separately. Thirdly, the convolution is used for fusion, so that the network can automatically learn the weight of the decoding results of each level. Finally, we adjust the channels to obtain the final prediction map by using the convolution with a kernel of 1 × 1. By comparing this with other segmentation network models on a WHU building data set, the evaluation metrics, mIoU, F1-score and accuracy are all improved. The network model proposed in this paper is a multi-scale adaptive network model that pays more attention to the global features for remote sensing segmentation.