This research article is aimed at improving the efficiency of a computer vision system that uses image processing for detecting cracks. Images are prone to noise when captured using drones or under various lighting conditions. To analyze this, the images were gathered under various conditions. To address the noise issue and to classify the cracks based on the severity level, a novel technique is proposed using a pixel-intensity resemblance measurement (PIRM) rule. Using PIRM, the noisy images and noiseless images were classified. Then, the noise was filtered using a median filter. The cracks were detected using VGG-16, ResNet-50 and InceptionResNet-V2 models. Once the crack was detected, the images were then segregated using a crack risk-analysis algorithm. Based on the severity level of the crack, an alert can be given to the authorized person to take the necessary action to avoid major accidents. The proposed technique achieved a 6% improvement without PIRM and a 10% improvement with the PIRM rule for the VGG-16 model. Similarly, it showed 3 and 10% for ResNet-50, 2 and 3% for Inception ResNet and a 9 and 10% increment for the Xception model. When the images were corrupted from a single noise alone, 95.6% accuracy was achieved using the ResNet-50 model for Gaussian noise, 99.65% accuracy was achieved through Inception ResNet-v2 for Poisson noise, and 99.95% accuracy was achieved by the Xception model for speckle noise. Full article

The direct tactile assessment of surface textures during palpation is an essential component of open surgery that is impeded in minimally invasive and robot-assisted surgery. When indirectly palpating with a surgical instrument, the structural vibrations from this interaction contain tactile information that can be extracted and analysed. This study investigates the influence of the parameters contact angle $\alpha$ and velocity $\overrightarrow{v}$ on the vibro-acoustic signals from this indirect palpation. A 7-DOF robotic arm, a standard surgical instrument, and a vibration measurement system were used to palpate three different materials with varying $\alpha$ and $\overrightarrow{v}$. The signals were processed based on continuous wavelet transformation. They showed material-specific signatures in the time–frequency domain that retained their general characteristic for varying $\alpha$ and $\overrightarrow{v}$. Energy-related and statistical features were extracted, and supervised classification was performed, where the testing data comprised only signals acquired with different palpation parameters than for training data. The classifiers support vector machine and k-nearest neighbours provided $99.67\%$ and $96.00\%$ accuracy for the differentiation of the materials. The results indicate the robustness of the features against variations in the palpation parameters. This is a prerequisite for an application in minimally invasive surgery but needs to be confirmed in realistic experiments with biological tissues. Full article

The vertical component magnetic field signal in the ground–airborne frequency domain electromagnetic (GAFDEM) method is detected by the air coil sensor, which is parallel to the ground. Unfortunately, the air coil sensor has low sensitivity in the low-frequency band, making it challenging to detect effective low-frequency signals and causing low accuracy and large error for interpreted deep apparent resistivity in actual detection. This work develops an optimized weight magnetic core coil sensor for GAFDEM. The cupped flux concentrator is used in the sensor to reduce the weight of the sensor while maintaining the magnetic gathering capacity of the core coil. The winding of the core coil is optimized to resemble the shape of a rugby ball, taking full advantage of the magnetic gathering capacity at the core center. Laboratory and field experiment results show that the developed optimized weight magnetic core coil sensor for the GAFDEM method is highly sensitive in the low-frequency band. Therefore, the detection results at depth are more accurate compared with those obtained using existing air coil sensors. Full article

Lung cancer is a high-risk disease that causes mortality worldwide; nevertheless, lung nodules are the main manifestation that can help to diagnose lung cancer at an early stage, lowering the workload of radiologists and boosting the rate of diagnosis. Artificial intelligence-based neural networks are promising technologies for automatically detecting lung nodules employing patient monitoring data acquired from sensor technology through an Internet-of-Things (IoT)-based patient monitoring system. However, the standard neural networks rely on manually acquired features, which reduces the effectiveness of detection. In this paper, we provide a novel IoT-enabled healthcare monitoring platform and an improved grey-wolf optimization (IGWO)-based deep convulution neural network (DCNN) model for lung cancer detection. The Tasmanian Devil Optimization (TDO) algorithm is utilized to select the most pertinent features for diagnosing lung nodules, and the convergence rate of the standard grey wolf optimization (GWO) algorithm is modified, resulting in an improved GWO algorithm. Consequently, an IGWO-based DCNN is trained on the optimal features obtained from the IoT platform, and the findings are saved in the cloud for the doctor’s judgment. The model is built on an Android platform with DCNN-enabled Python libraries, and the findings are evaluated against cutting-edge lung cancer detection models. Full article

This study proposes an electrocardiogram (ECG) signal stitching scheme to detect arrhythmias in drivers during driving. When the ECG is measured through the steering wheel during driving, the data are always exposed to noise caused by vehicle vibrations, bumpy road conditions, and the driver’s steering wheel gripping force. The proposed scheme extracts stable ECG signals and transforms them into full 10 s ECG signals to classify arrhythmias using convolutional neural networks (CNN). Before the ECG stitching algorithm is applied, data preprocessing is performed. To extract the cycle from the collected ECG data, the R peaks are found and the TP interval segmentation is applied. An abnormal P peak is very difficult to find. Therefore, this study also introduces a P peak estimation method. Finally, 4 × 2.5 s ECG segments are collected. To classify arrhythmias with stitched ECG data, each time series’ ECG signal is transformed via the continuous wavelet transform (CWT) and short-time Fourier transform (STFT), and transfer learning is performed for classification using CNNs. Finally, the parameters of the networks that provide the best performance are investigated. According to the classification accuracy, GoogleNet with the CWT image set shows the best results. The classification accuracy is 82.39% for the stitched ECG data, while it is 88.99% for the original ECG data. Full article

Terminal neurological conditions can affect millions of people worldwide and hinder them from doing their daily tasks and movements normally. Brain computer interface (BCI) is the best hope for many individuals with motor deficiencies. It will help many patients interact with the outside world and handle their daily tasks without assistance. Therefore, machine learning-based BCI systems have emerged as non-invasive techniques for reading out signals from the brain and interpreting them into commands to help those people to perform diverse limb motor tasks. This paper proposes an innovative and improved machine learning-based BCI system that analyzes EEG signals obtained from motor imagery to distinguish among various limb motor tasks based on BCI competition III dataset IVa. The proposed framework pipeline for EEG signal processing performs the following major steps. The first step uses a meta-heuristic optimization technique, called the whale optimization algorithm (WOA), to select the optimal features for discriminating between neural activity patterns. The pipeline then uses machine learning models such as LDA, k-NN, DT, RF, and LR to analyze the chosen features to enhance the precision of EEG signal analysis. The proposed BCI system, which merges the WOA as a feature selection method and the optimized k-NN classification model, demonstrated an overall accuracy of 98.6%, outperforming other machine learning models and previous techniques on the BCI competition III dataset IVa. Additionally, the EEG feature contribution in the ML classification model is reported using Explainable AI (XAI) tools, which provide insights into the individual contributions of the features in the predictions made by the model. By incorporating XAI techniques, the results of this study offer greater transparency and understanding of the relationship between the EEG features and the model’s predictions. The proposed method shows potential levels for better use in controlling diverse limb motor tasks to help people with limb impairments and support them while enhancing their quality of life. Full article

While machine translation for spoken language has advanced significantly, research on sign language translation (SLT) for deaf individuals remains limited. Obtaining annotations, such as gloss, can be expensive and time-consuming. To address these challenges, we propose a new sign language video-processing method for SLT without gloss annotations. Our approach leverages the signer’s skeleton points to identify their movements and help build a robust model resilient to background noise. We also introduce a keypoint normalization process that preserves the signer’s movements while accounting for variations in body length. Furthermore, we propose a stochastic frame selection technique to prioritize frames to minimize video information loss. Based on the attention-based model, our approach demonstrates effectiveness through quantitative experiments on various metrics using German and Korean sign language datasets without glosses. Full article

Wearable Heart Rate monitors are used in sports to provide physiological insights into athletes’ well-being and performance. Their unobtrusive nature and ability to provide reliable heart rate measurements facilitate the estimation of cardiorespiratory fitness of athletes, as quantified by maximum consumption of oxygen uptake. Previous studies have employed data-driven models which use heart rate information to estimate the cardiorespiratory fitness of athletes. This signifies the physiological relevance of heart rate and heart rate variability for the estimation of maximal oxygen uptake. In this work, the heart rate variability features that were extracted from both exercise and recovery segments were fed to three different Machine Learning models to estimate maximal oxygen uptake of 856 athletes performing Graded Exercise Testing. A total of 101 features from exercise and 30 features from recovery segments were given as input to three feature selection methods to avoid overfitting of the models and to obtain relevant features. This resulted in the increase of model’s accuracy by 5.7% for exercise and 4.3% for recovery. Further, post-modelling analysis was performed to remove the deviant points in two cases, initially in both training and testing and then only in training set, using k-Nearest Neighbour. In the former case, the removal of deviant points led to a reduction of 19.3% and 18.0% in overall estimation error for exercise and recovery, respectively. In the latter case, which mimicked the real-world scenario, the average R value of the models was observed to be 0.72 and 0.70 for exercise and recovery, respectively. From the above experimental approach, the utility of heart rate variability to estimate maximal oxygen uptake of large population of athletes was validated. Additionally, the proposed work contributes to the utility of cardiorespiratory fitness assessment of athletes through wearable heart rate monitors. Full article

Accurately detecting early developmental stages of insect pests (larvae) from off-the-shelf stereo camera sensor data using deep learning holds several benefits for farmers, from simple robot configuration to early neutralization of this less agile but more disastrous stage. Machine vision technology has advanced from bulk spraying to precise dosage to directly rubbing on the infected crops. However, these solutions primarily focus on adult pests and post-infestation stages. This study suggested using a front-pointing red-green-blue (RGB) stereo camera mounted on a robot to identify pest larvae using deep learning. The camera feeds data into our deep-learning algorithms experimented on eight ImageNet pre-trained models. The combination of the insect classifier and the detector replicates the peripheral and foveal line-of-sight vision on our custom pest larvae dataset, respectively. This enables a trade-off between the robot’s smooth operation and localization precision in the pest captured, as it first appeared in the farsighted section. Consequently, the nearsighted part utilizes our faster region-based convolutional neural network-based pest detector to localize precisely. Simulating the employed robot dynamics using CoppeliaSim and MATLAB/SIMULINK with the deep-learning toolbox demonstrated the excellent feasibility of the proposed system. Our deep-learning classifier and detector exhibited 99% and 0.84 accuracy and a mean average precision, respectively. Full article

The monitoring of airborne pollen has received much attention over the last decade, as the prevalence of pollen-induced allergies is constantly increasing. Today, the most common technique to identify airborne pollen species and to monitor their concentrations is based on manual analysis. Here, we present a new, low-cost, real-time optical pollen sensor, called Beenose, that automatically counts and identifies pollen grains by performing measurements at multiple scattering angles. We describe the data pre-processing steps and discuss the various statistical and machine learning methods that have been implemented to distinguish different pollen species. The analysis is based on a set of 12 pollen species, several of which were selected for their allergic potency. Our results show that Beenose can provide a consistent clustering of the pollen species based on their size properties, and that pollen particles can be separated from non-pollen ones. More importantly, 9 out of 12 pollen species were correctly identified with a prediction score exceeding 78%. Classification errors occur for species with similar optical behaviour, suggesting that other parameters should be considered to provide even more robust pollen identification. Full article

In order to complete this set of three companion papers, in this last, we focus our attention on environmental monitoring by taking advantage of photonic technologies. After reporting on some configurations useful for high precision agriculture, we explore the problems connected with soil water content measurement and landslide early warning. Then, we concentrate on a new generation of seismic sensors useful in both terrestrial and under water contests. Finally, we discuss a number of optical fiber sensors for use in radiation environments. Full article

A challenging problem in millimeter wave (mmWave) communications for the fifth generation of cellular communications and beyond (5G/B5G) is the beam selection problem. This is due to severe attenuation and penetration losses that are inherent in the mmWave band. Thus, the beam selection problem for mmWave links in a vehicular scenario can be solved as an exhaustive search among all candidate beam pairs. However, this approach cannot be assuredly completed within short contact times. On the other hand, machine learning (ML) has the potential to significantly advance 5G/B5G technology, as evidenced by the growing complexity of constructing cellular networks. In this work, we perform a comparative study of using different ML methods to solve the beam selection problem. We use a common dataset for this scenario found in the literature. We increase the accuracy of these results by approximately 30%. Moreover, we extend the given dataset by producing additional synthetic data. We apply ensemble learning techniques and obtain results with about 94% accuracy. The novelty of our work lies in the fact that we improve the existing dataset by adding more synthetic data and by designing a custom ensemble learning method for the problem at hand. Full article

A core endeavour in current affective computing and social signal processing research is the construction of datasets embedding suitable ground truths to foster machine learning methods. This practice brings up hitherto overlooked intricacies. In this paper, we consider causal factors potentially arising when human raters evaluate the affect fluctuations of subjects involved in dyadic interactions and subsequently categorise them in terms of social participation traits. To gauge such factors, we propose an emulator as a statistical approximation of the human rater, and we first discuss the motivations and the rationale behind the approach.The emulator is laid down in the next section as a phenomenological model where the core affect stochastic dynamics as perceived by the rater are captured through an Ornstein–Uhlenbeck process; its parameters are then exploited to infer potential causal effects in the attribution of social traits. Following that, by resorting to a publicly available dataset, the adequacy of the model is evaluated in terms of both human raters’ emulation and machine learning predictive capabilities. We then present the results, which are followed by a general discussion concerning findings and their implications, together with advantages and potential applications of the approach. Full article

This paper proposes a feature fusion algorithm for solving the path planning problem of multiple unmanned aerial vehicles (UAVs) using GPS and communication denial conditions. Due to the blockage of GPS and communication, UAVs cannot obtain the precise position of a target, which leads to the failure of path planning algorithms. This paper proposes a feature fusion proximal policy optimization (FF-PPO) algorithm based on deep reinforcement learning (DRL); the algorithm can fuse image recognition information with the original image, realizing the multi-UAV path planning algorithm without an accurate target location. In addition, the FF-PPO algorithm adopts an independent policy for multi-UAV communication denial environments, which enables the distributed control of UAVs such that multi-UAVs can realize the cooperative path planning task without communication. The success rate of our proposed algorithm can reach more than 90% in the multi-UAV cooperative path planning task. Finally, the feasibility of the algorithm is verified by simulations and hardware. Full article

We report a high-resolution fiber optic temperature sensor system based on an air-filled Fabry–Pérot (FP) cavity, whose spectral fringes shift due to a precise pressure variation in the cavity. The absolute temperature can be deduced from the spectral shift and the pressure variation. For fabrication, a fused-silica tube is spliced with a single-mode fiber at one end and a side-hole fiber at the other to form the FP cavity. The pressure in the cavity can be changed by passing air through the side-hole fiber, causing the spectral shift. We analyzed the effect of sensor wavelength resolution and pressure fluctuation on the temperature measurement resolution. A computer-controlled pressure system and sensor interrogation system were developed with miniaturized instruments for the system operation. Experimental results show that the sensor had a high wavelength resolution (<0.2 pm) with minimal pressure fluctuation (~$0.015$ kPa), resulting in high-resolution ($\pm 0.32 ℃$) temperature measurement. It shows good stability from the thermal cycle testing with the maximum testing temperature reaching $800 ℃$. Full article