Search

Due to digitalization, small and medium-sized enterprises (SMEs) have significantly enhanced their efficiency and productivity in the past few years. The process to automate SME transaction execution is getting highly multifaceted as the number of stakeholders of SMEs is connecting, accessing, exchanging, adding, and changing the transactional executions. The balanced lifecycle of SMEs requires partnership exchanges, financial management, manufacturing, and productivity stabilities, along with privacy and security. Interoperability platform issue is another critical challenging aspect while designing and managing a secure distributed Peer-to-Peer industrial development environment for SMEs. However, till now, it is hard to maintain operations of SMEs' integrity, transparency, reliability, provenance, availability, and trustworthiness between two different enterprises due to the current nature of centralized server-based infrastructure. This paper bridges these problems and proposes a novel and secure framework with a standardized process hierarchy/lifecycle for distributed SMEs using collaborative techniques of blockchain, the internet of things (IoT), and artificial intelligence (AI) with machine learning (ML). A blockchain with IoT-enabled permissionless network structure is designed called "B-SMEs" that provides solutions to cross-chain platforms. In this, B-SMEs address the lightweight stakeholder authentication problems as well. For that purpose, three different chain codes are deployed. It handles participating SMEs' registration, day-to-day information management and exchange between nodes, and analysis of partnership exchange-related transaction details before being preserved on the blockchain immutable storage. Whereas AI-enabled ML-based artificial neural networks are utilized, the aim is to handle and optimize day-to-day numbers of SME transactions; so that the proposed B-SMEs consume fewer resources in terms of computational power, network bandwidth, and preservation-related issues during the complete process of SMEs service deliverance. The simulation results present highlight the benefits of B-SMEs, increases the rate of ledger management and optimization while exchanging information between different chains, which is up to 17.3%, and reduces the consumption of the system's computational resources down to 9.13%. Thus, only 14.11% and 7.9% of B-SME's transactions use network bandwidth and storage capabilities compared to the current mechanism of SMEs, respectively. [ABSTRACT FROM AUTHOR]

Recent decades have witnessed the growing importance of human motion detection systems based on artificial intelligence (AI). The growing interest in human motion detection systems is the advantages of automation in the monitoring of patients remotely and giving warnings to doctors promptly. Currently, wearable devices are frequently used for human motion detection systems. However, such devices have several limitations, such as the elderly not wearing devices due to lack of comfort or forgetfulness and/or battery limitations. To overcome the problems of wearable devices, we propose an AI-driven human motion detection system (deep learning-based system) using channel state information (CSI) extracted from Radio Frequency (RF) signals. The main contribution of this paper is to improve the performance of the deep learning models through techniques, including structure modification and dimension reduction of the original data. In this work, We firstly collected the CSI data with the center frequency 5.32 GHz and implemented the structure of the basic deep learning network in our previous work. After that, we changed the basic deep learning network by increasing the depth, increasing the width, adapting some advanced network structures, and reducing dimensions. After finishing those modifications, we observed the results and analyzed how to further improve the deep learning performance of this contactless AI-enabled human motion detection system. It can be found that reducing the dimension of the original data can work better than modifying the structure of the deep learning model. [ABSTRACT FROM AUTHOR]

Nations worldwide are mobilizing to harness the power of Artificial Intelligence (AI) given its massive potential to shape global competitiveness over the coming decades. Using a dataset of 2.2 million AI papers, we study inter-city citations, collaborations, and talent migrations to uncover dependencies between Eastern and Western cities worldwide. Beijing emerges as a clear outlier, as it has been the most impactful city since 2007, the most productive since 2002, and the one housing the largest number of AI scientists since 1995. Our analysis also reveals that Western cities cite each other far more frequently than expected by chance, East–East collaborations are far more common than East–West or West–West collaborations, and migration of AI scientists mostly takes place from one Eastern city to another. We then propose a measure that quantifies each city's role in bridging East and West. Beijing's role surpasses that of all other cities combined, making it the central gateway through which knowledge and talent flow from one side to the other. We also track the center of mass of AI research by weighing each city's geographic location by its impact, productivity, and AI workforce. The center of mass has moved thousands of kilometers eastward over the past three decades, with Beijing's pull increasing each year. These findings highlight the eastward shift in the tides of global AI research, and the growing role of the Chinese capital as a hub connecting researchers across the globe. [ABSTRACT FROM AUTHOR]

The saturated hydraulic conductivity, ksat, is a crucial variable to describe the hydromechanical behavior of soils. The value of ksat of lateritic soils that are typically found in tropical regions is highly affected by the soil's structure, void ratio, and fine particle aggregation. As a result, the determination of ksat in the field or in the laboratory is complex and involves greater variability, depending on the type of test and on the spatial location of sampling. This paper presents a study of ksat values of lateritic soils, analyzing them using Statistic, Multilayer Perceptron Artificial Neural Networks (ANN) and Decision Trees (CHAID). This study aims to support decision-making regarding the type of test and depth chosen for sampling in laterite soils and understanding the factors influencing the permeability of such soils. An extensive literature review on the ksat values of lateritic soils was performed, providing data for the establishment of a database comprise of 722 registries. According to agronomic and geotechnical soil classifications, the Brazilian lateritic soils presents a "moderate" hydraulic conductivity. A significant variation of permeability values along the depth was identified, particularly for depths between 0.1 and 0.2 m. Regarding the importance of testing variables, the ANN indicated a high dependency on the type of test. The decision tree divided field test and laboratory test automatically, inferring the relevance of the type of test to the determination of ksat. [ABSTRACT FROM AUTHOR]

Osteoporosis (OP) is characterized by diminished bone mass and deteriorating bone structure that increases the chance of fractures in the spine, hips, and wrists. In this paper, a novel data processing method of artificial intelligence (AI) is used for evaluating, predicting, and classifying OP risk factors in clinical data of men and women separately. Additionally, artificial intelligence was used to suggest the most appropriate sports programs for treatment. Data was obtained from dual-energy x-ray absorption scanning center of Ayatollah Kashani, Milad, and Khatam al-Anbia hospitals in Tehran, Iran. The subjects included 1224 men and women. Models were developed using decision tree, random forest (RF), k-nearest neighbor, support vector machine, gradient boosting (GB), Extra trees, Ada Boost (AB), and artificial neural network multilayer perceptron analysis to predict osteoporosis and to recommend sports programs. Data was divided into training (80%) and test dataset (20%). The results were obtained on a 20% test dataset. Area under receiver operating characteristic curve (AUROC) was used to compare the performance of the models. To predict healthy individuals, osteopenia and osteoporosis, the FR algorithm with AUROC 0.91 performed best in men and the GB algorithm with AUROC 0.95 performed best in women compared to other classification algorithms. Prediction of RF algorithm in women and men with AUROC 0.96 and 0.99, respectively, showed the highest performance in diagnosing the type of exercise for healthy individuals and those with osteopenia and OP. Eight AI algorithms were developed and compared to accurately predict osteoporosis risk factors and classify individuals into three categories: healthy, osteopenia, and OP. In addition, the AI algorithms were developed to recommend the most appropriate sports programs as part of treatment. Applying the AI algorithms in a clinical setting could help primary care providers classify patients with osteoporosis and improve treatment by recommending appropriate exercise programs. [ABSTRACT FROM AUTHOR]

In recent years, with the advance of Artificial Intelligence, automatic music composition has been demonstrated. However, there are many music genres and music instruments. For a same piece of music, different music instruments would produce different effects. Invented some 2500 years ago, Guzheng is one of the oldest music instruments in China and the world. It has distinct timbres and patterns that cannot be duplicated by other music instruments. Therefore, it is interesting to see whether AI can compose Guzheng music or alike. In this paper we present a method that can automatically compose and play Guzheng music. First, we collect a number of existing Guzheng music pieces and convert them into Music Instrument Digital Interface format. Second, we use these data to train a Long Short-Term Memory (LSTM) network and use the trained network to generate new Guzheng music pieces. Next, we use the Reinforcement Learning to optimize the LSTM network by adding special Guzheng playing techniques. Comparing to the existing AI methods, such as LSTM and Generative Adversary Network, our new method is more effective in capturing the characteristics of Guzheng music. According to the evaluations from skilled Guzheng players and general audiences, our Guzheng music is very close to the real Guzheng music. The presented method can also be used to automatically compose the music of other Chinese music instruments. [ABSTRACT FROM AUTHOR]

The quantification of microstructural properties to optimize battery design and performance, to maintain product quality, or to track the degradation of LIBs remains expensive and slow when performed through currently used characterization approaches. In this paper, a convolution neural network-based deep learning approach (CNN) is reported to infer electrode microstructural properties from the inexpensive, easy to measure cell voltage versus capacity data. The developed framework combines two CNN models to balance the bias and variance of the overall predictions. As an example application, the method was demonstrated against porous electrode theory-generated voltage versus capacity plots. For the graphite|LiMn 2 O 4 chemistry, each voltage curve was parameterized as a function of the cathode microstructure tortuosity and area density, delivering CNN predictions of Bruggeman's exponent and shape factor with 0.97 R 2 score within 2 s each, enabling to distinguish between different types of particle morphologies, anisotropies, and particle alignments. The developed neural network model can readily accelerate the processing-properties-performance and degradation characteristics of the existing and emerging LIB chemistries. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence, path planning of Autonomous Mobile Robot (AMR) has been a research hotspot in recent years. This paper proposes the improved A* algorithm combined with the greedy algorithm for a multi-objective path planning strategy. Firstly, the evaluation function is improved to make the convergence of A* algorithm faster. Secondly, the unnecessary nodes of the A* algorithm are removed, meanwhile only the necessary inflection points are retained for path planning. Thirdly, the improved A* algorithm combined with the greedy algorithm is applied to multi-objective point planning. Finally, path planning is performed for five target nodes in a warehouse environment to compare path lengths, turn angles and other parameters. The simulation results show that the proposed algorithm is smoother and the path length is reduced by about 5%. The results show that the proposed method can reduce a certain path length. [ABSTRACT FROM AUTHOR]

This work focuses on facial processing, which refers to artificial intelligence (AI) systems that take facial images or videos as input data and perform some AI-driven processing to obtain higher-level information (e.g. a person's identity, emotions, demographic attributes) or newly generated imagery (e.g. with modified facial attributes). Facial processing tasks, such as face detection, face identification, facial expression recognition or facial attribute manipulation, are generally studied as separate research fields and without considering a particular scenario, context of use or intended purpose. This paper studies the field of facial processing in a holistic manner. It establishes the landscape of key computational tasks, applications and industrial players in the field in order to identify the 60 most relevant applications adopted for real-world uses. These applications are analysed in the context of the new proposal of the European Commission for harmonised rules on AI (the AI Act) and the 7 requirements for Trustworthy AI defined by the European High Level Expert Group on AI. More particularly, we assess the risk level conveyed by each application according to the AI Act and reflect on current research, technical and societal challenges towards trustworthy facial processing systems. [ABSTRACT FROM AUTHOR]

In the field of artificial intelligence, a large number of promising tools, such as condition-based maintenance, are available for large internal combustion engines. The cylinder liner, which is a key engine component, is subject to defects due to the manufacturing process. In addition, the cylinder liner straightforwardly affects the usage and safety of the internal combustion engine. Currently, the detection of cylinder liner quality mainly depends on manual human detection. However, this type of detection is destructive, time-consuming, and expensive. In this paper, a new cylinder liner defect database is proposed. The goal of this research is to develop a nondestructive yet reliable method for quantifying the surface condition of the cylinder liner. For this purpose, we propose a transformer method with a block division and mask mechanism on our newly collected cylinder liner defect database to automatically detect defects. Specifically, we first use a local defect dataset to train the transformer network. With a hierarchical-level architecture and attention mechanism, multi-level and discriminative feature are obtained. Then, we combine the transformer network with the block division method to detect defects in 64 local regions, and merge their results for the high-resolution image. The block division method can be used to resolve the difficulty of the in detecting the small defect. Finally, we design a mask to suppress the influence of noise. All methods allow us to achieve higher accuracy results than state-of-the-art algorithms. Additionally, we show the baseline results on the new database. [ABSTRACT FROM AUTHOR]

Big Data analytics and Artificial Intelligence (AI) technologies have become the focus of recent research due to the large amount of data. Dimensionality reduction techniques are recognized as an important step in these analyses. The multidimensional nature of Quality of Experience (QoE) is based on a set of Influence Factors (IFs) whose dimensionality is preferable to be higher due to better QoE prediction. As a consequence, dimensionality issues occur in QoE prediction models. This paper gives an overview of the used dimensionality reduction technique in QoE modeling and proposes modification and use of Active Subspaces Method (ASM) for dimensionality reduction. Proposed modified ASM (mASM) uses variance/standard deviation as a measure of function variability. A straightforward benefit of proposed modification is the possibility of its application in cases when discrete or categorical IFs are included. Application of modified ASM is not restricted to QoE modeling only. Obtained results show that QoE function is mostly flat for small variations of input IFs which is an additional motive to propose a modification of the standard version of ASM. This study proposes several metrics that can be used to compare different dimensionality reduction approaches. We prove that the percentage of function variability described by an appropriate linear combination(s) of input IFs is always greater or equal to the percentage that corresponds to the selection of input IF(s) when the reduction degree is the same. Thus, the proposed method and metrics are useful when optimizing the number of IFs for QoE prediction and a better understanding of IFs space in terms of QoE. [ABSTRACT FROM AUTHOR]

Herbarium specimens are dried plants mounted onto paper. They are used by a limited number of researchers, such as plant taxonomists, as a source of information on morphology and distribution. Recently, digitised herbarium specimens have begun to be used in comprehensive research to address broader issues. However, some specimens have been misidentified, and if used, there is a risk of drawing incorrect conclusions. In this study, we successfully developed a system for identifying taxon names with high accuracy using an image recognition system. We developed a system with an accuracy of 96.4% using 500,554 specimen images of 2171 plant taxa (2064 species, 9 subspecies, 88 varieties, and 10 forms in 192 families) that grow in Japan. We clarified where the artificial intelligence is looking to make decisions, and which taxa is being misidentified. As the system can be applied to digitalised images worldwide, it is useful for selecting and correcting misidentified herbarium specimens. [ABSTRACT FROM AUTHOR]

The low-cost 'THz Torch' wireless link technology is still in its infancy. Until very recently, inherent limitations with available hardware has resulted in a modest operational figure of merit performance (Range × Bit Rate). However, a breakthrough was reported here by the authors, with the introduction of 'Cognitive Demodulation'. This bypassed the thermal time constant constraints normally associated with both the thermal emitter and sensor; allowing step-change increases in both Range and Bit Rate with direct electronic modulation. This paper concentrates on advancements to the bit error rate (BER) performance. Here, separate techniques are introduced to the demodulation software that, when combined, result in enhanced Cognitive Demodulation. A factor of more than 100 improvement in BER was demonstrated within the laboratory and approximately a 60-fold improvement in a non-laboratory environment; both at the maximum Range and Bit Rate of 2 m and 125 bps, respectively, demonstrated recently. Moreover, demodulation speed is increased by almost a factor of 10,000; allowing for real-time demodulation while easing future computational hardware requirements. In addition to these software advancements, the paper demonstrates important improvements in hardware that has brought the technology out of the laboratory, with field trials being performed within an office corridor. [ABSTRACT FROM AUTHOR]

Smart textiles are novel solutions for remote healthcare monitoring which involve non-invasive sensors-integrated clothing. Polymer optical fiber (POF) sensors have attractive features for smart textile technology, and combined with Artificial Intelligence (AI) algorithms increase the potential of intelligent decision-making. This paper presents the development of a fully portable photonic smart garment with 30 multiplexed POF sensors combined with AI algorithms to evaluate the system ability on the activity classification of multiple subjects. Six daily activities are evaluated: standing, sitting, squatting, up-and-down arms, walking and running. A k-nearest neighbors classifier is employed and results from 10 trials of all volunteers presented an accuracy of 94.00 (0.14)%. To achieve an optimal amount of sensors, the principal component analysis is used for one volunteer and results showed an accuracy of 98.14 (0.31)% using 10 sensors, 1.82% lower than using 30 sensors. Cadence and breathing rate were estimated and compared to the data from an inertial measurement unit located on the garment back and the highest error was 2.22%. Shoulder flexion/extension was also evaluated. The proposed approach presented feasibility for activity recognition and movement-related parameters extraction, leading to a system fully optimized, including the number of sensors and wireless communication, for Healthcare 4.0. [ABSTRACT FROM AUTHOR]

As the demand for health grows, the increase in medical waste generation is gradually outstripping the load. In this paper, we propose a deep learning approach for identification and classification of medical waste. Deep learning is currently the most popular technique in image classification, but its need for large amounts of data limits its usage. In this scenario, we propose a deep learning-based classification method, in which ResNeXt is a suitable deep neural network for practical implementation, followed by transfer learning methods to improve classification results. We pay special attention to the problem of medical waste classification, which needs to be solved urgently in the current environmental protection context. We applied the technique to 3480 images and succeeded in correctly identifying 8 kinds of medical waste with an accuracy of 97.2%; the average F1-score of five-fold cross-validation was 97.2%. This study provided a deep learning-based method for automatic detection and classification of 8 kinds of medical waste with high accuracy and average precision. We believe that the power of artificial intelligence could be harnessed in products that would facilitate medical waste classification and could become widely available throughout China. [ABSTRACT FROM AUTHOR]

Networked-Control Systems (NCSs), a type of cyber-physical systems, consist of tightly integrated computing, communication and control technologies. While being very flexible environments, they are vulnerable to computing and networking attacks. Recent NCSs hacking incidents had major impact. They call for more research on cyber-physical security. Fears about the use of quantum computing to break current cryptosystems make matters worse. While the quantum threat motivated the creation of new disciplines to handle the issue, such as post-quantum cryptography, other fields have overlooked the existence of quantum-enabled adversaries. This is the case of cyber-physical defense research, a distinct but complementary discipline to cyber-physical protection. Cyber-physical defense refers to the capability to detect and react in response to cyber-physical attacks. Concretely, it involves the integration of mechanisms to identify adverse events and prepare response plans, during and after incidents occur. In this paper, we assume that the eventually available quantum computer will provide an advantage to adversaries against defenders, unless they also adopt this technology. We envision the necessity for a paradigm shift, where an increase of adversarial resources because of quantum supremacy does not translate into a higher likelihood of disruptions. Consistently with current system design practices in other areas, such as the use of artificial intelligence for the reinforcement of attack detection tools, we outline a vision for next generation cyber-physical defense layers leveraging ideas from quantum computing and machine learning. Through an example, we show that defenders of NCSs can learn and improve their strategies to anticipate and recover from attacks. [ABSTRACT FROM AUTHOR]

The barriers for the development of continuous monitoring of Suspended Sediment Concentration (SSC) in channels/rivers include costs and technological gaps but this paper shows that a solution is feasible by: (i) using readily available high-resolution images; (ii) transforming the images into image analytics to form a modelling dataset; and (iii) constructing predictive models by learning inherent correlation between observed SSC values and their image analytics. High-resolution images were taken of water containing a series of SSC values using an exploratory flume. Machine learning is processed by dividing the dataset into training and testing sets and the paper uses the following models: Generalized Linear Machine (GLM) and Distributed Random Forest (DRF). Results show that each model is capable of reliable predictions but the errors at higher SSC are not fully explained by modelling alone. Here we offer sufficient evidence for the feasibility of a continuous SSC monitoring capability in channels before the next phase of the study with the goal of producing practice guidelines. [ABSTRACT FROM AUTHOR]

In the present paper, we aimed to determine the influence of various non-pharmaceutical interventions (NPIs) enforced during the first wave of COVID-19 across countries on the spreading rate of COVID-19 during the second wave. For this purpose, we took into account national-level climatic, environmental, clinical, health, economic, pollution, social, and demographic factors. We estimated the growth of the first and second wave across countries by fitting a logistic model to daily-reported case numbers, up to the first and second epidemic peaks. We estimated the basic and effective (second wave) reproduction numbers across countries. Next, we used a random forest algorithm to study the association between the growth rate of the second wave and NPIs as well as pre-existing country-specific characteristics. Lastly, we compared the growth rate of the first and second waves of COVID-19. The top three factors associated with the growth of the second wave were body mass index, the number of days that the government sets restrictions on requiring facial coverings outside the home at all times, and restrictions on gatherings of 10 people or less. Artificial intelligence techniques can help scholars as well as decision and policy-makers estimate the effectiveness of public health policies, and implement "smart" interventions, which are as efficacious as stringent ones. [ABSTRACT FROM AUTHOR]

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this context, counterfactual explanations that synthesize small, interpretable changes to a given query while producing desired changes in model predictions have become popular. This under-constrained, inverse problem is vulnerable to introducing irrelevant feature manipulations, particularly when the model's predictions are not well-calibrated. Hence, in this paper, we propose the TraCE (training calibration-based explainers) technique, which utilizes a novel uncertainty-based interval calibration strategy for reliably synthesizing counterfactuals. Given the wide-spread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, to detect shortcuts, and to infer relationships between patient attributes and disease severity. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence, big data classification technology provides the advantageous help for the medicine auxiliary diagnosis research. While due to the different conditions in the different sample collection, the medical big data is often imbalanced. The class-imbalance problem has been reported as a serious obstacle to the classification performance of many standard learning algorithms. SMOTE algorithm could be used to generate sample points randomly to improve imbalance rate, but its application is affected by the marginalization generation and blindness of parameter selection. Focusing on this problem, an improved SMOTE algorithm based on Normal distribution is proposed in this paper, so that the new sample points are distributed closer to the center of the minority sample with a higher probability to avoid the marginalization of the expanded data. Experiments show that the classification effect is better when use proposed algorithm to expand the imbalanced dataset of Pima, WDBC, WPBC, Ionosphere and Breast-cancer-wisconsin than the original SMOTE algorithm. In addition, the parameter selection of the proposed algorithm is analyzed and it is found that the classification effect is the best when the distribution characteristics of the original data was maintained best by selecting appropriate parameters in our designed experiments. [ABSTRACT FROM AUTHOR]

The combination of biological neurology and memristive theory has greatly promoted the development of neuromorphic computing. To build a large-scale artificial intelligence alert system, the exploration of bionic synapses compatible with standard processes has become an urgent problem to be solved in the next step. In response to the above application requirements, this paper proposes a volatile avalanche diode threshold switching (VADTS) that is fully compatible with standard semiconductor technology to simulate the various functions of the synapse. Technology computer-aided design device-level simulation can verify the bionic principle of VADTS. The function of VADTS's bionic synapse was verified by the experimental test platform. The results show that under the action of the excitation signal (11.25 V), the device can continuously change from a high-resistance state to a low-resistance state. When the excitation signal is lower than the threshold, VADTS presents a "no adaptation" state of nerve synapses. When the excitation signal is higher than the threshold and changes continuously, the current changes along with the amplitude of the excitation signal, similar to the "sensitization" state of the nerve synapse. [ABSTRACT FROM AUTHOR]

This paper is focused on the application and performance of artificial intelligence in the numerical modeling of nanofluid flows. Suspension of metallic nanoparticles in the fluids has shown potential in heat transfer enhancement of the based fluids. There are many numerical studies for the investigation of thermal and hydrodynamic characteristics of nanofluids. However, the optimization of the computational fluid dynamics (CFD) modeling by an artificial intelligence (AI) algorithm is not considered in any study. The CFD is a powerful technique from an accuracy point of view. However, it could be time and cost-consuming, especially in large-scale and complicated problems. It is expected that the machine learning technique of the AI algorithms could improve such CFD drawbacks by patterning the CFD data. Once the AI finds the CFD pattern intelligently, there is no need for CFD calculations. The particle swarm optimization-based fuzzy inference system (PSOFIS) is considered in this study to predict the velocity profile of Al2O3/water turbulent flow in a heated pipe. One of the challenging problems in CFD modeling is the lost data for a specific boundary condition. For example, the CFD data are available for wall heat fluxes of 75, 85, 105, and 125 w/m2, but there is no data for the wall heat flux of 95 w/m2. So, the PSOFIS learns the available CFD data, and it predicts the velocity profile for where the data is not available (i.e., wall heat flux of 95 w/m2). The intelligence of PSOFIS is checked by the coefficient of determination (R2 pattern) for different values of accept ratio (AR) and inertia weight damping ratio (IWDR). The best intelligence is obtained for the AR and IWDR of 0.7 and 0.99, respectively. At this condition, the velocity profile predicted by both CFD and PSOFIS is compatible. As the performance of the PSOFIS, for learning time of 268 s, the prediction of the CFD data lost was negligible (~ 1 s). In contrast, the CFD calculation takes around 600 s for each simulation. [ABSTRACT FROM AUTHOR]

Content addressable memory (CAM) for search and match operations demands high speed and low power for near real-time decision-making across many critical domains. Resistive RAM (RRAM)-based in-memory computing has high potential in realizing an efficient static CAM for artificial intelligence tasks, especially on resource-constrained platforms. This paper presents an XNOR-based RRAM-CAM with a time-domain analog adder for efficient winning class computation. The CAM compares two operands, one voltage and the second one resistance, and outputs a voltage proportional to the similarity between the input query and the pre-stored patterns. Processing the summation of the output similarity voltages in the time-domain helps avoid voltage saturation, variation, and noise dominating the analog voltage-based computing. After that, to determine the winning class among the multiple classes, a digital realization is utilized to consider the class with the longest pulse width as the winning class. As a demonstrator, hyperdimensional computing for efficient MNIST classification is considered. The proposed design uses 65 nm CMOS foundry technology and realistic data for RRAM with total area of 0.0077 mm2, consumes 13.6 pJ of energy per 1 k query within 10 ns clock cycle. It shows a reduction of ~ 31 × in area and ~ 3 × in energy consumption compared to fully digital ASIC implementation using 65 nm foundry technology. The proposed design exhibits a remarkable reduction in area and energy compared to two of the state-of-the-art RRAM designs. [ABSTRACT FROM AUTHOR]

Healthcare using body sensor data has been getting huge research attentions by a wide range of researchers because of its good practical applications such as smart health care systems. For instance, smart wearable sensor-based behavior recognition system can observe elderly people in a smart eldercare environment to improve their lifestyle and can also help them by warning about forthcoming unprecedented events such as falls or other health risk, to prolong their independent life. Although there are many ways of using distinguished sensors to observe behavior of people, wearable sensors mostly provide reliable data in this regard to monitor the individual's functionality and lifestyle. In this paper, we propose a body sensor-based activity modeling and recognition system using time-sequential information-based deep Neural Structured Learning (NSL), a promising deep learning algorithm. First, we obtain data from multiple wearable sensors while the subjects conduct several daily activities. Once the data is collected, the time-sequential information then go through some statistical feature processing. Furthermore, kernel-based discriminant analysis (KDA) is applied to see the better clustering of the features from different activity classes by minimizing inner-class scatterings while maximizing inter-class scatterings of the samples. The robust time-sequential features are then applied with Neural Structured Learning (NSL) based on Long Short-Term Memory (LSTM), for activity modeling. The proposed approach achieved around 99% recall rate on a public dataset. It is also compared to existing different conventional machine learning methods such as typical Deep Belief Network (DBN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) where they yielded the maximum recall rate of 94%. Furthermore, a fast and efficient explainable Artificial Intelligence (XAI) algorithm, Local Interpretable Model-Agnostic Explanations (LIME) is used to explain and check the machine learning decisions. The robust activity recognition system can be adopted for understanding peoples' behavior in their daily life in different environments such as homes, clinics, and offices. [ABSTRACT FROM AUTHOR]

This paper proposes a data augmentation method based on artificial intelligence (AI) to obtain sound level spectrum as predicting the spatial and temporal data of time-resolved three-dimensional Particle Tracking Velocimetry (4D PTV) data. A 4D PTV has used to measure flow characteristics of three side mirror models adopting the Shake-The-Box (STB) algorithm with four high-speed cameras on a robotic arm for measuring industrial scale. Helium filled soap bubbles are used as tracers in the wind tunnel experiment to characterize flow structures around automobile side mirror models. Full volumetric velocity fields and evolution of vortex structures are obtained and analyzed. Instantaneous pressure fields are deduced by solving a Poisson equation based on the 4D PTV data. To predict spatial and temporal data of velocity field, artificial intelligence (AI)-based data prediction method has applied. Adaptive Neural Fuzzy Inference System (ANFIS) based machine learning algorithm works well to find 4D missing data behind the automobile side mirror model. Using the ANFIS model, power spectrum of velocity fluctuations and sound level spectrum of pressure fluctuations are successfully obtained to assess flow and noise characteristics of three different side mirror models. [ABSTRACT FROM AUTHOR]

Current seismic processing workflows in the oil and gas industry involve several interactions between different experts to optimize the overall data quality in various tasks, such as noise attenuation, velocity analysis and horizon picking. While many machine learning-based approaches have been proposed to support each of those steps, most of them disregard expert interactions to guide the overall optimization. This paper presents geocycles, a cyclic learning approach that mimics this iterative process, which can be applied to different pre-stack seismic processing tasks. Our method refactor these processes considering training, testing, and evaluation sub-tasks, which allow the selection of samples for greedy sequential processes targeting an overall optimum quality for very large seismic datasets. We present encouraging results showing that a cyclic structure and efficient quality metrics improved overall outcomes in up to 128% for two different seismic processing tasks in comparison to a 1-cycle machine learning approach. [ABSTRACT FROM AUTHOR]

In the last 20 years, terrorism has led to hundreds of thousands of deaths and massive economic, political, and humanitarian crises in several regions of the world. Using real-world data on attacks occurred in Afghanistan and Iraq from 2001 to 2018, we propose the use of temporal meta-graphs and deep learning to forecast future terrorist targets. Focusing on three event dimensions, i.e., employed weapons, deployed tactics and chosen targets, meta-graphs map the connections among temporally close attacks, capturing their operational similarities and dependencies. From these temporal meta-graphs, we derive 2-day-based time series that measure the centrality of each feature within each dimension over time. Formulating the problem in the context of the strategic behavior of terrorist actors, these multivariate temporal sequences are then utilized to learn what target types are at the highest risk of being chosen. The paper makes two contributions. First, it demonstrates that engineering the feature space via temporal meta-graphs produces richer knowledge than shallow time-series that only rely on frequency of feature occurrences. Second, the performed experiments reveal that bi-directional LSTM networks achieve superior forecasting performance compared to other algorithms, calling for future research aiming at fully discovering the potential of artificial intelligence to counter terrorist violence. [ABSTRACT FROM AUTHOR]

We introduce a new approach for finding high accuracy, free and closed-form expressions for the gravitational waves emitted by binary black hole collisions from ab initio models. More precisely, our expressions are built from numerical surrogate models based on supercomputer simulations of the Einstein equations, which have been shown to be essentially indistinguishable from each other. Distinct aspects of our approach are that: (i) representations of the gravitational waves can be explicitly written in a few lines, (ii) these representations are free-form yet still fast to search for and validate and (iii) there are no underlying physical approximations in the underlying model. The key strategy is combining techniques from Artificial Intelligence and Reduced Order Modeling for parameterized systems. Namely, symbolic regression through genetic programming combined with sparse representations in parameter space and the time domain using Reduced Basis and the Empirical Interpolation Method enabling fast free-form symbolic searches and large-scale a posteriori validations. As a proof of concept we present our results for the collision of two black holes, initially without spin, and with an initial separation corresponding to 25–31 gravitational wave cycles before merger. The minimum overlap, compared to ground truth solutions, is 99%. That is, 1% difference between our closed-form expressions and supercomputer simulations; this is considered for gravitational (GW) science more than the minimum required due to experimental numerical errors which otherwise dominate. This paper aims to contribute to the field of GWs in particular and Artificial Intelligence in general. [ABSTRACT FROM AUTHOR]

The paper presents quantum model of subjective text perception based on binary cognitive distinctions corresponding to words of natural language. The result of perception is quantum cognitive state represented by vector in the qubit Hilbert space. Complex-valued structure of the quantum state space extends the standard vector-based approach to semantics, allowing to account for subjective dimension of human perception in which the result is constrained, but not fully predetermined by input information. In the case of two distinctions, the perception model generates a two-qubit state, entanglement of which quantifies semantic connection between the corresponding words. This two-distinction perception case is realized in the algorithm for detection and measurement of semantic connectivity between pairs of words. The algorithm is experimentally tested with positive results. The developed approach to cognitive modeling unifies neurophysiological, linguistic, and psychological descriptions in a mathematical and conceptual structure of quantum theory, extending horizons of machine intelligence. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is the most common type of dementia. Its diagnosis and progression detection have been intensively studied. Nevertheless, research studies often have little effect on clinical practice mainly due to the following reasons: (1) Most studies depend mainly on a single modality, especially neuroimaging; (2) diagnosis and progression detection are usually studied separately as two independent problems; and (3) current studies concentrate mainly on optimizing the performance of complex machine learning models, while disregarding their explainability. As a result, physicians struggle to interpret these models, and feel it is hard to trust them. In this paper, we carefully develop an accurate and interpretable AD diagnosis and progression detection model. This model provides physicians with accurate decisions along with a set of explanations for every decision. Specifically, the model integrates 11 modalities of 1048 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) real-world dataset: 294 cognitively normal, 254 stable mild cognitive impairment (MCI), 232 progressive MCI, and 268 AD. It is actually a two-layer model with random forest (RF) as classifier algorithm. In the first layer, the model carries out a multi-class classification for the early diagnosis of AD patients. In the second layer, the model applies binary classification to detect possible MCI-to-AD progression within three years from a baseline diagnosis. The performance of the model is optimized with key markers selected from a large set of biological and clinical measures. Regarding explainability, we provide, for each layer, global and instance-based explanations of the RF classifier by using the SHapley Additive exPlanations (SHAP) feature attribution framework. In addition, we implement 22 explainers based on decision trees and fuzzy rule-based systems to provide complementary justifications for every RF decision in each layer. Furthermore, these explanations are represented in natural language form to help physicians understand the predictions. The designed model achieves a cross-validation accuracy of 93.95% and an F1-score of 93.94% in the first layer, while it achieves a cross-validation accuracy of 87.08% and an F1-Score of 87.09% in the second layer. The resulting system is not only accurate, but also trustworthy, accountable, and medically applicable, thanks to the provided explanations which are broadly consistent with each other and with the AD medical literature. The proposed system can help to enhance the clinical understanding of AD diagnosis and progression processes by providing detailed insights into the effect of different modalities on the disease risk. [ABSTRACT FROM AUTHOR]

Compared to the abilities of the animal brain, many Artificial Intelligence systems have limitations which emphasise the need for a Brain-Inspired Artificial Intelligence paradigm. This paper proposes a novel Brain-Inspired Spiking Neural Network (BI-SNN) model for incremental learning of spike sequences. BI-SNN maps spiking activity from input channels into a high dimensional source-space which enhances the evolution of polychronising spiking neural populations. We applied the BI-SNN to predict muscle activity and kinematics from electroencephalography signals during upper limb functional movements. The BI-SNN extends our previously proposed eSPANNet computational model by integrating it with the 'NeuCube' brain-inspired SNN architecture. We show that BI-SNN can successfully predict continuous muscle activity and kinematics of upper-limb. The experimental results confirmed that the BI-SNN resulted in strongly correlated population activity and demonstrated the feasibility for real-time prediction. In contrast to the majority of Brain–Computer Interfaces (BCIs) that constitute a 'black box', BI-SNN provide quantitative and visual feedback about the related brain activity. This study is one of the first attempts to examine the feasibility of finding neural correlates of muscle activity and kinematics from electroencephalography using a brain-inspired computational paradigm. The findings suggest that BI-SNN is a better neural decoder for non-invasive BCI. [ABSTRACT FROM AUTHOR]

In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from the National Genomics Data Center repository, separating the genome of different virus strains from the Coronavirus family with 98.73% accuracy. The network's behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are validated on samples from the National Center for Biotechnology Information and Global Initiative on Sharing All Influenza Data repositories, and are proven to be able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n = 6 previously tested positive), delivering a sensitivity similar to routine diagnostic methods, and 100% specificity. The proposed methodology has a substantial added value over existing methods, as it is able to both automatically identify promising primer sets for a virus from a limited amount of data, and deliver effective results in a minimal amount of time. Considering the possibility of future pandemics, these characteristics are invaluable to promptly create specific detection methods for diagnostics. [ABSTRACT FROM AUTHOR]

Heat transfer augmentation of the nanofluids is still an attractive concept for researchers due to rising demands for designing efficient heat transfer fluids. However, the pressure loss arisen from the suspension of nanoparticles in liquid is known as a drawback for developing such novel fluids. Therefore, prediction of the nanofluid pressure, especially in internal flows, has been focused on studies. Computational fluid dynamics (CFD) is a commonly used approach for such a prediction of fluid flow. The CFD tools are perfect and precise in prediction of the fluid flow parameters. But they might be time-consuming and expensive, especially for complex models such as 3-dimension modeling and turbulent flow. In addition, the CFD could just predict the pressure, and it is disabled for finding the relationship of such variables. This study is intended to show the performance of the artificial intelligence (AI) algorithm as an auxiliary method for cooperation with the CFD. The turbulent flow of Cu/water nanofluid warming up in a pipe is considered as a sample of a physical phenomenon. The AI algorithm learns the CFD results. Then, the relation between the CFD results is discovered by the AI algorithm. For this purpose, the adaptive network-based fuzzy inference system (ANFIS) is adopted as AI tool. The intelligence condition of the ANFIS is checked by benchmarking the CFD results. The paper outcomes indicated that the ANFIS intelligence is met by employing gauss2mf in the model as the membership function and x, y, and z coordinates, the nanoparticle volume fraction, and the temperature as the inputs. The pressure predicted by the ANFIS at this condition is the same as that predicted by the CFD. The artificial intelligence of ANFIS could find the relation of the nanofluid pressure to the nanoparticle fraction and the temperature. The CFD simulation took much more time (90–110 min) than the total time of the learning and the prediction of the ANFIS (369 s). The CFD modeling was done on a workstation computer, while the ANFIS method was run on a normal desktop. [ABSTRACT FROM AUTHOR]

In the current research paper a novel hybrid model combining first-principle and artificial intelligence (AI) was developed for simulation of a chemical reactor. We study a 2-dimensional reactor with heating sources inside it by using computational fluid dynamics (CFD). The type of considered reactor is bubble column reactor (BCR) in which a two-phase system is created. Results from CFD were analyzed in two different stages. The first stage, which is the learning stage, takes advantage of the swarm intelligence of the ant colony. The second stage results from the first stage, and in this stage, the predictions are according to the previous stage. This stage is related to the fuzzy logic system, and the ant colony optimization learning framework is build-up this part of the model. Ants movements or swarm intelligence of ants lead to the optimization of physical, chemical, or any kind of processes in nature. From point to point optimization, we can access a kind of group optimization, meaning that a group of data is studied and optimized. In the current study, the swarm intelligence of ants was used to learn the data from CFD in different parts of the BCR. The learning was also used to map the input and output data and find out the complex connection between the parameters. The results from mapping the input and output data show the full learning framework. By using the AI framework, the learning process was transferred into the fuzzy logic process through membership function specifications; therefore, the fuzzy logic system could predict a group of data. The results from the swarm intelligence of ants and fuzzy logic suitably adapt to CFD results. Also, the ant colony optimization fuzzy inference system (ACOFIS) model is employed to predict the temperature distribution in the reactor based on the CFD results. The results indicated that instead of solving Navier–Stokes equations and complex solving procedures, the swarm intelligence could be used to predict a process. For better comparisons and assessment of the ACOFIS model, this model is compared with the genetic algorithm fuzzy inference system (GAFIS) and Particle swarm optimization fuzzy inference system (PSOFIS) method with regards to model accuracy, pattern recognition, and prediction capability. All models are at a similar level of accuracy and prediction ability, and the prediction time for all models is less than one second. The results show that the model's accuracy with low computational learning time can be achieved with the high number of CIR (0.5) when the number of inputs ≥ 4. However, this finding is vice versa, when the number of inputs < 4. In this case, the CIR number should be 0.2 to achieve the best accuracy of the model. This finding could also highlight the importance of sensitivity analysis of tuning parameters to achieve an accurate model with a cost-effective computational run. [ABSTRACT FROM AUTHOR]

Bubbly flow behavior simulation in two-phase chemical reactors such bubble column type reactors is widely employed for chemical industry purposes. The computational fluid dynamics (CFD) approach has been employed by engineers and researchers for modeling these types of chemical reactors. In spite of the CFD robustness for simulating transport phenomena and chemical reactions in these reactors, this approach has been known as expensive for modeling such turbulent complex flows. Artificial intelligence (AI) algorithm of the adaptive network-based fuzzy inference system (ANFIS) are largely understood and utilized for the CFD approach optimization. In this hybrid approach, the CFD findings are learned by AI algorithms like ANFIS to save computational time and expenses. Once the pattern of the CFD results have been captured by the AI model, this hybrid model can be then used for process simulation and optimization. As such, there is no need for further simulations of new conditions. The objective of this paper is to obviate the need for expensive CFD computations for two-phase flows in chemical reactors via coupling CFD data to an AI algorithm, i.e., differential evolution based fuzzy inference system (DEFIS). To do so, air velocity as the output and the values of the x, and y coordinates, water velocity, and time step as the inputs are inputted the AI model for learning the flow pattern. The effects of cross over as the DE parameter and also the number of inputs on the best intelligence are investigated. Indeed, DEFIS correlates the air velocity to the nodes coordinates, time, and liquid velocity and then after the CFD modeling could be replaced with the simple correlation. For the first time, a comparison is made between the ANFIS and the DEFIS performances in terms of the prediction capability of the gas (air) velocity. The results released that both ANFIS and DEFIS could accurately predict the CFD pattern. The prediction times of both methods were obtained to be equal. However, the learning time of the DEFIS was fourfold of ANFIS. [ABSTRACT FROM AUTHOR]

Artificial intelligence has recently made a disruptive impact in medical imaging by successfully automatizing expert-level diagnostic tasks. However, replicating human-made decisions may inherently be biased by the fallible and dogmatic nature of human experts, in addition to requiring prohibitive amounts of training data. In this paper, we introduce an unsupervised deep learning architecture particularly designed for OCT representations for unbiased, purely data-driven biomarker discovery. We developed artificial intelligence technology that provides biomarker candidates without any restricting input or domain knowledge beyond raw images. Analyzing 54,900 retinal optical coherence tomography (OCT) volume scans of 1094 patients with age-related macular degeneration, we generated a vocabulary of 20 local and global markers capturing characteristic retinal patterns. The resulting markers were validated by linking them with clinical outcomes (visual acuity, lesion activity and retinal morphology) using correlation and machine learning regression. The newly identified features correlated well with specific biomarkers traditionally used in clinical practice (r up to 0.73), and outperformed them in correlating with visual acuity ( R 2 = 0.46 compared to R 2 = 0.29 for conventional markers), despite representing an enormous compression of OCT imaging data (67 million voxels to 20 features). In addition, our method also discovered hitherto unknown, clinically relevant biomarker candidates. The presented deep learning approach identified known as well as novel medical imaging biomarkers without any prior domain knowledge. Similar approaches may be worthwhile across other medical imaging fields. [ABSTRACT FROM AUTHOR]

There are growing interests in the use of robots in collaborative environments with humans or other intelligent machines. Sensing the environment for which the robot is operating can be done in many ways, generally guided by skin-like sensors. Some of the skins are inspired by natural sensing in humans or other species. As humans, we use many of our senses, such as version, hearing, smell, and touch, to move around by avoiding colliding with other humans or objects. Different from humans, many other mammals also use whiskers as an additional sensor to help navigate around. In this paper, we demonstrate a touchless capacitive imaging-based sensor in the situation where the obstacles are in close vicinity to the robot. The proposed imaging system can sense the changes in areas near to the skin-like sensors by measuring the capacitances between the array of electrodes. A 4D sensing approach has been developed with the spatiotemporal Total Variation algorithm. The 4D operational mode gives sensors the time awareness that allows for dynamical responses and hence the better control of the robots. Several experiments are conducted to show the skin-like behaviour of this sensor by simulating various scenarios. The sensor shows the excellent ability to detect an object in its vicinity, where the depth is close to half of the planar sensor array size. [ABSTRACT FROM AUTHOR]

In this paper we present a unified framework for extreme learning machines and reservoir computing (echo state networks), which can be physically implemented using a single nonlinear neuron subject to delayed feedback. The reservoir is built within the delay-line, employing a number of "virtual" neurons. These virtual neurons receive random projections from the input layer containing the information to be processed. One key advantage of this approach is that it can be implemented efficiently in hardware. We show that the reservoir computing implementation, in this case optoelectronic, is also capable to realize extreme learning machines, demonstrating the unified framework for both schemes in software as well as in hardware. [ABSTRACT FROM AUTHOR]

Thyroid nodules are common, and their investigation is very important to exclude the possibility of cancer. The increase in blood vessels of malignant tumours may be related to local temperature augmentation detectable on the skin surface. The objective of this paper is to evaluate the feasibility of Infrared Thermography for cancer identification. For this purpose, two studies were performed. One used numerical modelling to simulate regional metabolic temperature propagation to evaluate whether a nodule is perceptible on the skin surface. A second study considered thyroid nodule identification by using convolutional neural networks (CNNs). First, variations in nodular size and fat thickness were investigated, showing that the fat layer has an important role in regional heat transfer. In the second study, the training process achieved accuracy of 96% for in-sample and 95% for validation. In the testing phase, 92% accuracy, 100% precision and 80% recall were achieved. Thus, the presented studies suggest the feasibility of using Infrared Thermography with the CNN Artificial Intelligence technique as additional information in the investigation of thyroid nodules for patients without a very thick subcutaneous fat layer. [ABSTRACT FROM AUTHOR]

The development of artificial intelligence has led researchers to study the ethical principles that should guide machine behavior. The challenge in building machine morality based on people's moral decisions, however, is accounting for the biases in human moral decision-making. In seven studies, this paper investigates how people's personal perspectives and decision-making modes affect their decisions in the moral dilemmas faced by autonomous vehicles. Moreover, it determines the variations in people's moral decisions that can be attributed to the situational factors of the dilemmas. The reported studies demonstrate that people's moral decisions, regardless of the presented dilemma, are biased by their decision-making mode and personal perspective. Under intuitive moral decisions, participants shift more towards a deontological doctrine by sacrificing the passenger instead of the pedestrian. In addition, once the personal perspective is made salient participants preserve the lives of that perspective, i.e. the passenger shifts towards sacrificing the pedestrian, and vice versa. These biases in people's moral decisions underline the social challenge in the design of a universal moral code for autonomous vehicles. We discuss the implications of our findings and provide directions for future research. [ABSTRACT FROM AUTHOR]