There are many machine learning approaches available and commonly used today, however, the extreme learning machine is appraised as one of the fastest and, additionally, relatively efficient models. Its main benefit is that it is very fast, which makes it suitable for integration within products that require models taking rapid decisions. Nevertheless, despite their large potential, they have not yet been exploited enough, according to the recent literature. Extreme learning machines still face several challenges that need to be addressed. The most significant downside is that the performance of the model heavily depends on the allocated weights and biases within the hidden layer. Finding its appropriate values for practical tasks represents an NP-hard continuous optimization challenge. Research proposed in this study focuses on determining optimal or near optimal weights and biases in the hidden layer for specific tasks. To address this task, a multi-swarm hybrid optimization approach has been proposed, based on three swarm intelligence meta-heuristics, namely the artificial bee colony, the firefly algorithm and the sine–cosine algorithm. The proposed method has been thoroughly validated on seven well-known classification benchmark datasets, and obtained results are compared to other already existing similar cutting-edge approaches from the recent literature. The simulation results point out that the suggested multi-swarm technique is capable to obtain better generalization performance than the rest of the approaches included in the comparative analysis in terms of accuracy, precision, recall, and f1-score indicators. Moreover, to prove that combining two algorithms is not as effective as joining three approaches, additional hybrids generated by pairing, each, two methods employed in the proposed multi-swarm approach, were also implemented and validated against four challenging datasets. The findings from these experiments also prove superior performance of the proposed multi-swarm algorithm. Sample code from devised ELM tuning framework is available on the GitHub. Full article

The demand for cost-efficient manufacturing of complex metal components has driven research for metal Additive Manufacturing (AM) such as Wire + Arc Additive Manufacturing (WAAM). WAAM enables automated, time- and material-efficient manufacturing of metal parts. To strengthen these benefits, the demand for robotically deployed in-process Non-Destructive Evaluation (NDE) has risen, aiming to replace current manually deployed inspection techniques after completion of the part. This work presents a synchronized multi-robot WAAM and NDE cell aiming to achieve (1) defect detection in-process, (2) enable possible in-process repair and (3) prevent costly scrappage or rework of completed defective builds. The deployment of the NDE during a deposition process is achieved through real-time position control of robots based on sensor input. A novel high-temperature capable, dry-coupled phased array ultrasound transducer (PAUT) roller-probe device is used for the NDE inspection. The dry-coupled sensor is tailored for coupling with an as-built high-temperature WAAM surface at an applied force and speed. The demonstration of the novel ultrasound in-process defect detection approach, presented in this paper, was performed on a titanium WAAM straight sample containing an intentionally embedded tungsten tube reflectors with an internal diameter of 1.0 mm. The ultrasound data were acquired after a pre-specified layer, in-process, employing the Full Matrix Capture (FMC) technique for subsequent post-processing using the adaptive Total Focusing Method (TFM) imaging algorithm assisted by a surface reconstruction algorithm based on the Synthetic Aperture Focusing Technique (SAFT). The presented results show a sufficient signal-to-noise ratio. Therefore, a potential for early defect detection is achieved, directly strengthening the benefits of the AM process by enabling a possible in-process repair. Full article

Event detection is an important task in the field of natural language processing, which aims to detect trigger words in a sentence and classify them into specific event types. Event detection tasks suffer from data sparsity and event instances imbalance problems in small-scale datasets. For this reason, the correlation information of event types can be used to alleviate the above problems. In this paper, we design a Hierarchical Attention Neural Network for Event Types (HANN-ET). Specifically, we select Long Short-Term Memory (LSTM) as the semantic encoder and utilize dynamic multi-pooling and the Graph Attention Network (GAT) to enrich the sentence feature. Meanwhile, we build several upper-level event type modules and employ a weighted attention aggregation mechanism to integrate these modules to obtain the correlation event type information. Each upper-level module is completed by a Neural Module Network (NMNs), event types within the same upper-level module can share information, and an attention aggregation mechanism can provide effective bias scores for the trigger word classifier. We conduct extensive experiments on the ACE2005 and the MAVEN datasets, and the results show that our approach outperforms previous state-of-the-art methods and achieves the competitive F1 scores of 78.9% on the ACE2005 dataset and 68.8% on the MAVEN dataset. Full article

This article proposes a new method of identity recognition in sanitary facilities based on electrocardiography (ECG) signals. Our team previously proposed a novel approach of invisible ECG at the thighs using polymeric electrodes, leading to the creation of a proof-of-concept system integrated into a toilet seat. In this work, a biometrics pipeline was devised, which tested four different classifiers, varying the population from 2 to 17 subjects and simulating a residential environment. However, for this approach to be industrially viable, further optimization is required, particularly regarding electrode materials that are compatible with industrial processes. As such, we also explore the use of a conductive silicone material as electrodes, aiming at the industrial-scale production of a toilet seat capable of recording ECG data, without the need for body-worn devices. A desirable aspect when using such a system is matching the recorded data with the monitored user, ideally using a minimal sensor set, further reinforcing the relevance of user identification through ECG signals collected at the thighs. Our approach was evaluated against a reference device for a population of 17 healthy and pathological individuals, covering a wide age range (24–70 years). With the silicone composite, we were able to acquire signals in 100% of the sessions, with a mean heart rate deviation between a reference system and our experimental device of 2.82 ± 1.99 beats per minute (BPM). In terms of ECG waveform morphology, the best cases showed a Pearson correlation coefficient of 0.91 ± 0.06. For biometric detection, the best classifier was the Binary Convolutional Neural Network (BCNN), with an accuracy of 100% for a population of up to four individuals. Full article

Ganoderma lucidum mushroom-mediated green synthesis of nanocrystalline titanium dioxide (TiO₂) is explored via a low-temperature (≤70 °C) wet chemical method. The role of Ganoderma lucidum mushroom extract in the reaction is to release the ganoderic acid molecules that tend to bind to the Ti⁴⁺ metal ions to form a titanium-ganoderic acid intermediate complex for obtaining TiO₂ nanocrystallites (NCs), which is quite novel, considering the recent advances in fabricated gas sensing materials. The X-ray powder diffraction, field emission scanning electron microscopy, Raman spectroscopy, and Brunauer–Emmett–Teller measurements etc., are used to characterize the crystal structure, surface morphology, and surface area of as-synthesized TiO₂ and Pd-TiO₂ sensors, respectively. The chlorine (Cl₂) gas sensing properties are investigated from a lower range of 5 ppm to a higher range of 400 ppm. In addition to excellent response–recovery time, good selectivity, constant repeatability, as well as chemical stability, the gas sensor efficiency of the as-synthesized Pd-TiO₂ NC sensor is better (136% response at 150 °C operating temperature) than the TiO₂ NC sensor (57% at 250 °C operating temperature) measured at 100 ppm (Cl₂) gas concentration, suggesting that the green synthesized Pd-TiO₂ sensor demonstrates efficient Cl₂ gas sensing properties at low operating temperatures over pristine ones. Full article

In this study, the circular Gaussian spot emitted by a laser light source is shaped into a rectangular flat-top beam to improve the scanning efficiency of a selective laser sintering scanning system. A CO₂ laser with a power of 200 W, wavelength of 10.6 μm, and spot diameter of 9 mm is shaped into a flat-top spot with a length and width of 0.5 × 0.1 mm, and the mapping function and flat-top Lorentzian function are calculated. We utilize ZEMAX to optimize the aspherical cylindrical lens of the shaping system and the cylindrical lens of the focusing system. We then calculate the energy uniformity of the flat-top line-shaped beam at distances from 500 to 535 mm and study the zoom displacement of the focusing lens system. The results indicated that the energy uniformity of the flat-top beam was greater than 80% at the distances considered, and the focusing system must precisely control the displacement of the cylindrical lens in the Y-direction to achieve precise zooming. Full article

Continuous health monitoring in a vehicle enables the earlier detection of symptoms of cardiovascular diseases. In this work, we designed flexible and thin electrodes made of polyurethane for long-term electrocardiogram (ECG) monitoring while driving. We determined the time for reliable ECG recording to evaluate the effectiveness of the electrodes. We recorded data from 19 subjects under four scenarios: rest, city, highway, and rural. The recording time was five min for rest and 15 min for the other scenarios. The total recording (950 min) is publicly available under a CC BY-ND 4.0 license. We used the simultaneous truth and performance level estimation (STAPLE) algorithm to detect the position of R-waves. Then, we derived the RR intervals to compare the estimated heart rate with the ground truth, which we obtained from ECG electrodes on the chest. We calculated the signal-to-noise ratio (SNR) and averaged it for the different scenarios. Highway had the lowest SNR (−6.69 dB) and rural had the highest (−6.80 dB). The usable time of the steering wheel was 42.46% (city), 46.67% (highway), and 47.72% (rural). This indicates that steering-wheel-based ECG recording is feasible and delivers reliable recordings from about 45.62% of the driving time. In summary, the developed electrodes allow continuous in-vehicle heart rate monitoring, and our publicly available recordings provide the opportunity to apply more sophisticated data analytics. Full article

To prevent the frequent occurrence of transmission line galloping accidents, many scholars have carried out studies. However, there are still many difficulties that have not been solved. To address the issues that have arisen during the installation of the monitoring system, a new installation technique for the galloping monitoring terminal structure has been developed, and structural design and transmission line impact have been taken into account. A method combining Kalman and Mahony complementary filtering has been shown to solve the problem of wire twisting when galloping is taken into account. The displacement is derived by double-integrating the acceleration, although the trend term has a significant impact on the integration result. To handle the trend term issue and other error effects, a method combining the least-squares method, the adaptive smoothing method, and the time-frequency domain hybrid integration approach is used. Finally, the monitoring terminal’s structural design is simulated and evaluated, and the measured amplitude is assessed on a galloping standard test bench. The difference between the measured amplitude and the laboratory standard value is less than 10%, meeting the engineering design criteria. And the galloping trajectory is identical to the test bench trajectory, which is critical for user end monitoring. Full article

Although they have been under development for years and are attracting a lot of attention, vision-based tactile sensors still have common defects—the use of such devices to infer the direction of external forces is poorly investigated, and the operating frequency is too low for them to be applied in practical scenarios. Moreover, discussion of the deformation of elastomers used in vision-based tactile sensors remains insufficient. This research focuses on analyzing the deformation of a thin elastic layer on a vision-based tactile sensor by establishing a simplified deformation model, which is cross-validated using the finite element method. Further, this model suggests a reduction in the number of markers required by a vision-based tactile sensor. In subsequent testing, a prototype HiVTac is fabricated, and it demonstrates superior accuracy to its vision-based tactile sensor counterparts in reconstructing an external force. The average error of inferring the direction of external force is 0.32${}^{\circ }$, and the root mean squared error of inferring the magnitude of the external force is 0.0098 N. The prototype was capable of working at a sampling rate of 100 Hz and a processing frequency of 1.3 kHz, even on a general PC, allowing for real-time reconstructions of not only the direction but also the magnitude of an external force. Full article

The article considers the potential applicability of C12880MA and C11708MA Hamamatsu microspectrometers, which are characterized by an extremely compact design, occupying a small volume of several cubic centimeters, in portable spectrometric equipment with spatial resolution for monitoring the optical properties of condensed scattering media. The development of methods for determining the reduced scattering and absorption spectral coefficients of radiation from various scattering materials and products allows us to speak about the possibility of real-time control of the volume concentration of optically active components included in them, for example, fat and water in dairy products. For this, it is necessary to provide sufficiently accurate spectra of diffusely reflected broadband light radiation at different distances between the points of radiation entrance and registration. The aim of the manuscript is to assess the possibility of using the considered microspectrometers in compact devices for optical diagnostics and control of the optical properties of condensed scattering media. The features of the connection diagram of these microspectrometers and the necessary methods for correcting the initially obtained spectral dependencies of diffusive reflection, which will be of interest to developers of spectral diagnostic equipment, are considered in detail. The need to eliminate the influence of the inhomogeneity of dark counts of a CMOS photodiode array is shown. The hardware functions of the C12880MA and C11708MA Hamammatsu microspectrometers, as well as the AvaSpec 2048L fiber-optic spectrometer, were experimentally measured and compared. Methods for correcting the nonlinearity of their reading scales and light characteristics, as well as improving their equivalent spectral resolution using digital Wiener filtering, are described. It is shown that the equivalent spectral resolution of C12880MA and C11708MA microspectrometers can be improved by about 40% when recording smooth spectra, subject to the condition that the resulting side oscillations are small. It is pointed out that in order to reduce the level of side oscillations in the corrected spectra with improved resolution, it is necessary to ensure the smoothness of the original spectra and a good signal-to-noise ratio. A conclusion is made about the possibility of using the considered microspectrometers in portable spectrometric equipment with careful consideration of their characteristics, the features of their switching circuit, and the necessary software. Full article

Falling is a major cause of personal injury and accidental death worldwide, in particular for the elderly. For aged care, a falling alarm system is highly demanded so that medical aid can be obtained immediately when the fall accidents happen. Previous studies on fall detection lacked practical considerations to deal with real-world situations, including the camera’s mounting angle, lighting differences between day and night, and the privacy protection for users. In our experiments, IR-depth images and thermal images were used as the input source for fall detection; as a result, detailed facial information is not captured by the system for privacy reasons, and it is invariant to the lighting conditions. Due to the different occurrence rates between fall accidents and other normal activities, supervised learning approaches may suffer from the problem of data imbalance in the training phase. Accordingly, in this study, anomaly detection is performed using unsupervised learning approaches so that the models were trained only with the normal cases while the fall accident was defined as an anomaly event. The proposed system takes sequential frames as the inputs to predict future frames based on a GAN structure, and it provides (1) multi-subject detection, (2) real-time fall detection triggered by motion, (3) a solution to the situation that subjects were occluded after falling, and (4) a denoising scheme for depth images. The experimental results show that the proposed system achieves the state-of-the-art performance and copes with the real-world cases successfully. Full article

A seismograph was designed based on Raspberry Pi. Although comprising 8 channels, the seismograph can be expanded to 16, 24, or 32 channels by using a USB interfacing with a microcontroller. In addition, by clustering more than one Raspberry Pi, the number of possible channels can be extended beyond 32. In this study, we also explored the computational intelligence of Raspberry Pi for running real-time systems and multithreaded algorithms to process raw seismic data. Also integrated into the seismograph is a Huawei MH5000-31 5G module, which provided high-speed internet real-time operations. Other hardware peripherals included a 24 bit ADS1251 analog-to-digital converter (ADC) and a STM32F407 microcontroller. Real-time data were acquired in the field for ambient noise tomography. An analysis tool called spatial autocorrelation (SPAC) was used to analyze the data, followed by inversion, which revealed the subsurface velocity of the site location. The proposed seismograph is prospective for small, medium, or commercial data acquisition. In accordance with the processing power and stability of Raspberry Pi, which were confirmed in this study, the proposed seismograph is also recommended as a template for developing high-performance computing applications, such as artificial intelligence (AI) in seismology and other related disciplines. Full article

Product defect inspections are extremely important for industrial manufacturing processes. It is necessary to develop a special inspection system for each industrial product due to their complexity and diversity. Even though high-precision 3D cameras are usually used to acquire data to inspect 3D objects, it is hard to use them in real-time defect inspection systems due to their high price and long processing time. To address these problems, we propose a product inspection system that uses five 2D cameras to capture all inspection parts of the product and a deep learning-based 2D convolutional neural network (CNN) with spatial and channel attention (SCA) mechanisms to efficiently inspect 3D ball joint socket products. Channel attention (CA) in our model detects the most relevant feature maps while spatial attention (SA) finds the most important regions in the extracted feature map of the target. To build the final SCA feature vector, we concatenated the learned feature vectors of CA and SA because they complement each other. Thus, our proposed CNN with SCA provides high inspection accuracy as well as it having the potential to detect small defects of the product. Our proposed model achieved 98% classification accuracy in the experiments and proved its efficiency on product inspection in real-time. Full article

Electrochemical impedance spectroscopy (EIS) is the golden tool for many emerging biomedical applications that describes the behavior, stability, and long-term durability of physical interfaces in a specific range of frequency. Impedance measurements of any biointerface during in vivo and clinical applications could be used for assessing long-term biopotential measurements and diagnostic purposes. In this paper, a novel approach to predicting impedance behavior is presented and consists of a dimensional reduction procedure by converting EIS data over many days of an experiment into a one-dimensional sequence of values using a novel formula called day factor (DF) and then using a long short-term memory (LSTM) network to predict the future behavior of the DF. Three neural interfaces of different material compositions with long-term in vitro aging tests were used to validate the proposed approach. The results showed good accuracy in predicting the quantitative change in the impedance behavior (i.e., higher than 75%), in addition to good prediction of the similarity between the actual and the predicted DF signals, which expresses the impedance fluctuations among soaking days. The DF approach showed a lower computational time and algorithmic complexity compared with principal component analysis (PCA) and provided the ability to involve or emphasize several important frequencies or impedance range in a more flexible way. Full article

The technologies of ultrasound detection have a wide range of applications in marine science and industrial manufacturing. With the variation of the environment, the requirements of anti-interference, miniaturization, and ultra-sensitivity are put forward. Optical microcavities are often carefully designed for a variety of ultra-sensitive detections. Using the packaged microsphere cavity, we fabricated an ultrasound sensor that can work in an underwater environment. During practical detection, the optical resonance mode of the cavity can work with real-time response accordingly. The designed structure can work in various complex environments and has advantages in the fields of precision measurement and nano-particle detection. Full article