ALBERT

Description: Volcanic ash fall-out represents a serious hazard for air and road traffic. The forecasting models used to predict its time–space evolution require information about the core characteristics of volcanic particles, such as their granulometry. Typically, such information is gained by the spot direct observation of the ash collected at the ground or by using expensive instrumentation. In this paper, a vision-based methodology aimed at the estimation of ash granulometry is presented. A dedicated image processing paradigm was developed and implemented in LabVIEW™. The methodology was validated experimentally using digital reference images resembling different operating conditions. The outcome of the assessment procedure was very encouraging, showing an accuracy of the image processing algorithm of 1.76%.

Description: Fault tolerance in IoT systems is challenging to overcome due to its complexity, dynamicity, and heterogeneity. IoT systems are typically designed and constructed in layers. Every layer has its requirements and fault tolerance strategies. However, errors in one layer can propagate and cause effects on others. Thus, it is impractical to consider a centralized fault tolerance approach for an entire system. Consequently, it is vital to consider multiple layers in order to enable collaboration and information exchange when addressing fault tolerance. The purpose of this study is to propose a multi-layer fault tolerance approach, granting interconnection among IoT system layers, allowing information exchange and collaboration in order to attain the property of dependability. Therefore, we define an event-driven framework called FaTEMa (Fault Tolerance Event Manager) that creates a dedicated fault-related communication channel in order to propagate events across the levels of the system. The implemented framework assist with error detection and continued service. Additionally, it offers extension points to support heterogeneous communication protocols and evolve new capabilities. Our empirical results show that introducing FaTEMa provided improvements to the error detection and error resolution time, consequently improving system availability. In addition, the use of Fatema provided a reliability improvement and a reduction in the number of failures produced.

Description: This study presents a 2-D lidar odometry based on an ICP (iterative closest point) variant used in a simple and straightforward platform that achieves real-time and low-drift performance. With a designated multi-scale feature extraction procedure, the lidar cloud information can be utilized at multiple levels and the speed of data association can be accelerated according to the multi-scale data structure, thereby achieving robust feature extraction and fast scan-matching algorithms. First, on a large scale, the lidar point cloud data are classified according to the curvature into two parts: smooth collection and rough collection. Then, on a small scale, noise and unstable points in the smooth or rough collection are filtered, and edge points and corner points are extracted. Then, the proposed tangent-vector-pairs based on edge and corner points are applied to evaluate the rotation term, which is significant for producing a stable solution in motion estimation. We compare our performance with two excellent open-source SLAM algorithms, Cartographer and Hector SLAM, using collected and open-access datasets in structured indoor environments. The results indicate that our method can achieve better accuracy.

Description: Voids in polymer matrix composites are one of the most common manufacturing defects, which may influence the mechanical properties and structural behavior of the final parts made of composites by various manufacturing methods. Therefore, numerous non-destructive testing (NDT) techniques were developed and applied for quality control and in-service testing of such structures. In this paper, the authors analyzed various alternatives to the reference technique, X-ray computed tomography (XCT) NDT, which is used for industrial testing of composite disks having defects in the form of the lower density areas. Different candidates, namely: vibration-based testing, infrared thermography, vibro-thermography, as well as ultrasonic testing were analyzed in terms of their sensitivity and technical feasibility. The quality of the results, the complexity of the testing procedure, time and labor consumption, and the cost of the equipment were analyzed and compared with the reference technique. Based on the conducted research the authors finally proposed a hybrid approach to quality control, using a combination of two NDT techniques–infrared thermography (for initial scanning and detection of near-surface defects) and ultrasonic testing (for a more detailed analysis of products that pass the first testing procedure). It allowed for replacing the costly XCT diagnostics with a much cheaper, but almost equally effective, alternative.

Description: For the sound field reconstruction of large conical surfaces, current statistical optimal near-field acoustic holography (SONAH) methods have relatively poor applicability and low accuracy. To overcome this problem, conical SONAH based on cylindrical SONAH is proposed in this paper. Firstly, elementary cylindrical waves are transformed into those suitable for the radiated sound field of the conical surface through cylinder-cone coordinates transformation, which forms the matrix of characteristic elementary waves in the conical spatial domain. Secondly, the sound pressure is expressed as the superposition of those characteristic elementary waves, and the superposition coefficients are solved according to the principle of superposition of wave field. Finally, the reconstructed conical pressure is expressed as a linear superposition of the holographic conical pressure. Furthermore, to overcome ill-posed problems, a regularization method combining truncated singular value decomposition (TSVD) and Tikhonov regularization is proposed. Large singular values before the truncation point of TSVD are not processed and remaining small singular values representing high-frequency noise are modified by Tikhonov regularization. Numerical and experimental case studies are carried out to validate the effectiveness of the proposed conical SONAH and the combined regularization method, which can provide reliable evidence for noise monitoring and control of mechanical systems.

Description: Lane and road marker segmentation is crucial in autonomous driving, and many related methods have been proposed in this field. However, most of them are based on single-frame prediction, which causes unstable results between frames. Some semantic multi-frame segmentation methods produce error accumulation and are not fast enough. Therefore, we propose a deep learning algorithm that takes into account the continuity information of adjacent image frames, including image sequence processing and an end-to-end trainable multi-input single-output network to jointly process the segmentation of lanes and road markers. In order to emphasize the location of the target with high probability in the adjacent frames and to refine the segmentation result of the current frame, we explicitly consider the time consistency between frames, expand the segmentation region of the previous frame, and use the optical flow of the adjacent frames to reverse the past prediction, then use it as an additional input of the network in training and reasoning, thereby improving the network’s attention to the target area of the past frame. We segmented lanes and road markers on the Baidu Apolloscape lanemark segmentation dataset and CULane dataset, and present benchmarks for different networks. The experimental results show that this method accelerates the segmentation speed of video lanes and road markers by 2.5 times, increases accuracy by 1.4%, and reduces temporal consistency by only 2.2% at most.

Description: Monitoring physical activity in medical and clinical rehabilitation, in sports environments or as a wellness indicator is helpful to measure, analyze and evaluate physiological parameters involving the correct subject’s movements. Thanks to integrated circuit (IC) technologies, wearable sensors and portable devices have expanded rapidly in monitoring physical activities in sports and tele-rehabilitation. Therefore, sensors and signal acquisition devices became essential in the tele-rehabilitation path to obtain accurate and reliable information by analyzing the acquired physiological signals. In this context, this paper provides a state-of-the-art review of the recent advances in electroencephalogram (EEG), electrocardiogram (ECG) and electromyogram (EMG) signal monitoring systems and sensors that are relevant to the field of tele-rehabilitation and health monitoring. Mostly, we focused our contribution in EMG signals to highlight its importance in rehabilitation context applications. This review focuses on analyzing the implementation of sensors and biomedical applications both in literature than in commerce. Moreover, a final review discussion about the analyzed solutions is also reported at the end of this paper to highlight the advantages of physiological monitoring systems in rehabilitation and individuate future advancements in this direction. The main contributions of this paper are (i) the presentation of interesting works in the biomedical area, mainly focusing on sensors and systems for physical rehabilitation and health monitoring between 2016 and up-to-date, and (ii) the indication of the main types of commercial sensors currently being used for biomedical applications.

Description: In this paper, we provide external image features and use the internal attention mechanism to solve the VQA problem given a dataset of textual questions and related images. Most previous models for VQA use a pair of images and questions as input. In addition, the model adopts a question-oriented attention mechanism to extract the features of the entire image and then perform feature fusion. However, the shortcoming of these models is that they cannot effectively eliminate the irrelevant features of the image. In addition, the problem-oriented attention mechanism lacks in the mining of image features, which will bring in redundant image features. In this paper, we propose a VQA model based on adversarial learning and bidirectional attention. We exploit external image features that are not related to the question to form an adversarial mechanism to boost the accuracy of the model. Target detection is performed on the image—that is, the image-oriented attention mechanism. The bidirectional attention mechanism is conducive to promoting model attention and eliminating interference. Experimental results are evaluated on benchmark datasets, and our model performs better than other models based on attention methods. In addition, the qualitative results show the attention maps on the images and leads to predicting correct answers.

Description: The signal-to-noise ratios (SNR) of ultrasonic imaging and non-destructive evaluation (NDE) applications can be greatly improved by driving each piezoelectric transducer (single or in array) with tuned HV capacitive-discharge drivers. These can deliver spikes with kW pulsed power at PRF ≈ 5000 spikes/s, achieving levels higher even than in CW high-power ultrasound: up to 5 kWpp. These conclusions are reached here by applying a new strategy proposed for the accurate modeling of own-design re-configurable HV capacitive drivers. To obtain such rigorous spike modeling, the real effects of very high levels of pulsed intensities (3–10 A) and voltages (300–700 V) were computed. Unexpected phenomena were found: intense brief pulses of driving power and probe emitted force, as well as nonlinearities in semiconductors, though their catalog data include only linear ranges. Fortunately, our piezoelectric and circuital devices working in such an intense regime have not shown serious heating problems, since the finally consumed “average” power is rather small. Intensity, power, and voltage, driving wideband transducers from our capacitive drivers, are researched here in order to drastically improve (∆ 〉〉 40 dB) their ultrasonic “net dynamic range available” (NDRA), achieving emitted forces 〉 240 Newtonspp and receiving ultrasonic signals of up to 76–205 Vpp. These measurements of ultrasonic pulsed voltages, received in NDE and Imaging, are approximately 10,000 larger than those usual today. Thus, NDRA ranges were optimized for three laboratory capacitive drivers (with six commercial transducers), which were successfully applied in the aircraft industry for imaging landing flaps in Boeing wings, despite suffering acoustic losses 〉 120 dB.

Description: Ischemic stroke is one of the leading causes of death among the aged population in the world. Experimental stroke models with rodents play a fundamental role in the investigation of the mechanism and impairment of cerebral ischemia. For its celerity and veracity, the 2,3,5-triphenyltetrazolium chloride (TTC) staining of rat brains has been extensively adopted to visualize the infarction, which is subsequently photographed for further processing. Two important tasks are to segment the brain regions and to compute the midline that separates the brain. This paper investigates automatic brain extraction and hemisphere segmentation algorithms in camera-based TTC-stained rat images. For rat brain extraction, a saliency region detection scheme on a superpixel image is exploited to extract the brain regions from the raw complicated image. Subsequently, the initial brain slices are refined using a parametric deformable model associated with color image transformation. For rat hemisphere segmentation, open curve evolution guided by the gradient vector flow in a medial subimage is developed to compute the midline. A wide variety of TTC-stained rat brain images captured by a smartphone were produced and utilized to evaluate the proposed segmentation frameworks. Experimental results on the segmentation of rat brains and cerebral hemispheres indicated that the developed schemes achieved high accuracy with average Dice scores of 92.33% and 97.15%, respectively. The established segmentation algorithms are believed to be potential and beneficial to facilitate experimental stroke study with TTC-stained rat brain images.