Abstract: Prevent abuse and illegal activities in a given area of the sea is a very difficult and expensive task. Artificial intelligence offers the possibility to implement new methods to identify the vessel class type from the kinematic features of the vessel itself. The task strictly depends on the quality of the data. This paper explores the application of a deep Long Short-Term Memory model by using AIS flow only with a relatively low quality. The proposed model reaches high accuracy on detecting nine vessel classes representing the most common vessel types in the Ionian-Adriatic Sea. The model has been applied during the Adriatic-Ionian trial period of the international EU ANDROMEDA H2020 project to identify vessels performing behaviours far from the expected one, depending on the declared type.
Abstract: In-situ testing is preferred to evaluate the liquefaction potential in cohesionless soils due to high disturbance during sampling. Although new in-situ methods with high accuracy have been developed, standard penetration test, the simplest and the oldest in-situ test, is still used due to the profusion of the recorded data. This paper reviews the Iranian standard of evaluating liquefaction potential in soils (codes 525) and compares the liquefaction assessment methods based on standard penetration test (SPT) results on cohesionless soil in this standard with the international standards. To this, methods for assessing liquefaction potential are compared with what is presented in standard 525. It is found that although the procedure used in Iranian standard of evaluating the potential of liquefaction has not been updated according to the new findings, it is a conservative procedure.
Abstract: In the design stage of a new building, the energy model of this building is often required for the analysis of the performance on energy efficiency. In practice, a certain degree of geometric simplification should be done in the establishment of building energy models, since the detailed geometric features of a real building are hard to be described perfectly in most energy simulation engine, such as ESP-r, eQuest or EnergyPlus. Actually, the detailed description is not necessary when the result with extremely high accuracy is not demanded. Therefore, this paper analyzed the relationship between the error of the simulation result from building energy models and the geometric simplification of the models. Finally, the following two parameters are selected as the indices to characterize the geometric feature of in building energy simulation: the southward projected area and total side surface area of the building. Based on the parameterization method, the simplification from an arbitrary column building to a typical shape (a cuboid) building can be made for energy modeling. The result in this study indicates that no more than 7% prediction error of annual cooling/heating load will be caused by the geometric simplification for those buildings with the ratio of southward projection length to total perimeter of the bottom of 0.25~0.35, which means this method is applicable for building performance simulation.
Abstract: During COVID-19, the depression rate has increased dramatically. Young adults are most vulnerable to the mental health effects of the pandemic. Lower-income families have a higher ratio to be diagnosed with depression than the general population, but less access to clinics. This research aims to achieve early depression detection at low cost, large scale, and high accuracy with an interdisciplinary approach by incorporating clinical practices defined by American Psychiatric Association (APA) as well as multimodal AI framework. The proposed approach detected the nine depression symptoms with Natural Language Processing sentiment analysis and a symptom-based Lexicon uniquely designed for young adults. The experiments were conducted on the multimedia survey results from adolescents and young adults and unbiased Twitter communications. The result was further aggregated with the facial emotional cues analyzed by the Convolutional Neural Network on the multimedia survey videos. Five experiments each conducted on 10k data entries reached consistent results with an average accuracy of 88.31%, higher than the existing natural language analysis models. This approach can reach 300+ million daily active Twitter users and is highly accessible by low-income populations to promote early depression detection to raise awareness in adolescents and young adults and reveal complementary cues to assist clinical depression diagnosis.
Abstract: As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.
Abstract: To improve the registration accuracy of a source point cloud and template point cloud when the initial relative deflection angle is too large, a PointNetLK algorithm combined with an oriented bounding box (PointNetLK-OBB) is proposed. In this algorithm, the OBB of a 3D point cloud is used to represent the macro feature of source and template point clouds. Under the guidance of the iterative closest point algorithm, the OBB of the source and template point clouds is aligned, and a mirror symmetry effect is produced between them. According to the fitting degree of the source and template point clouds, the mirror symmetry plane is detected, and the optimal rotation and translation of the source point cloud is obtained to complete the 3D point cloud registration task. To verify the effectiveness of the proposed algorithm, a comparative experiment was performed using the publicly available ModelNet40 dataset. The experimental results demonstrate that, compared with PointNetLK, PointNetLK-OBB improves the registration accuracy of the source and template point clouds when the initial relative deflection angle is too large, and the sensitivity of the initial relative position between the source point cloud and template point cloud is reduced. The primary contribution of this paper is the use of PointNetLK to avoid the non-convex problem of traditional point cloud registration and leveraging the regularity of the OBB to avoid the local optimization problem in the PointNetLK context.
Abstract: It is necessary to test to see if optical devices such as camera, night vision devices are working properly. Therefore, a precision biaxial rotary system (gimbal) is required for mounting Unit Under Test, UUT. The Gimbal systems can be utilized for precise positioning of the UUT; hence, optical test can be performed with high accuracy. The weight of UUT, which is placed outside the axis of rotation, causes an off-axis moment to the mounting armature. The off-axis moment can act against the direction of movement for some orientation, thus the electrical motor, which rotates the gimbal axis, has to apply higher level of torque to guide and stabilize the system. Moreover, UUT and its mounting fixture to the gimbal can be changed, which causes change in applied resistance moment to the gimbals electrical motor. In this study, a preloaded spring is added to the gimbal system for minimizing applied off axis moment with the help of four bar mechanism. Two different possible methods for preloading spring are introduced and system optimization is performed to eliminate all moment which is created by off axis weight.
Abstract: Biosensors play a significant role in the healthcare
sectors, scientific and technological progress. Developing electrodes
that are easy to manufacture and deliver better electrochemical
performance is advantageous for diagnostics and biosensing. They
can be implemented extensively in various analytical tasks such as
drug discovery, food safety, medical diagnostics, process controls,
security and defence, in addition to environmental monitoring.
Development of biosensors aims to create high-performance
electrochemical electrodes for diagnostics and biosensing. A
biosensor is a device that inspects the biological and chemical
reactions generated by the biological sample. A biosensor carries
out biological detection via a linked transducer and transmits the
biological response into an electrical signal; stability, selectivity,
and sensitivity are the dynamic and static characteristics that affect
and dictate the quality and performance of biosensors. In this
research, a developed experimental study for laser scribing technique
for graphene oxide inside a vacuum chamber for processing of
graphene oxide is presented. The processing of graphene oxide (GO)
was achieved using the laser scribing technique. The effect of the
laser scribing on the reduction of GO was investigated under two
conditions: atmosphere and vacuum. GO solvent was coated onto a
LightScribe DVD. The laser scribing technique was applied to reduce
GO layers to generate rGO. The micro-details for the morphological
structures of rGO and GO were visualised using scanning electron
microscopy (SEM) and Raman spectroscopy so that they could
be examined. The first electrode was a traditional graphene-based
electrode model, made under normal atmospheric conditions, whereas
the second model was a developed graphene electrode fabricated
under a vacuum state using a vacuum chamber. The purpose was
to control the vacuum conditions, such as the air pressure and the
temperature during the fabrication process. The parameters to be
assessed include the layer thickness and the continuous environment.
Results presented show high accuracy and repeatability achieving low
cost productivity.
Abstract: Research in predictive maintenance modeling has improved in the recent years to predict failures and needed maintenance with high accuracy, saving cost and improving manufacturing efficiency. However, classic prediction models provide little valuable insight towards the most important features contributing to the failure. By analyzing and quantifying feature importance in predictive maintenance models, cost saving can be optimized based on business goals. First, multiple classifiers are evaluated with cross-validation to predict the multi-class of failures. Second, predictive performance with features provided by different feature selection algorithms are further analyzed. Third, features selected by different algorithms are ranked and combined based on their predictive power. Finally, linear explainer SHAP (SHapley Additive exPlanations) is applied to interpret classifier behavior and provide further insight towards the specific roles of features in both local predictions and global model behavior. The results of the experiments suggest that certain features play dominant roles in predictive models while others have significantly less impact on the overall performance. Moreover, for multi-class prediction of machine failures, the most important features vary with type of machine failures. The results may lead to improved productivity and cost saving by prioritizing sensor deployment, data collection, and data processing of more important features over less importance features.
Abstract: With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.
Abstract: Recent development of AI and edge computing plays a critical role to capture meaningful events such as detection of an unattended bag. One of the core problems is re-identification across multiple CCTVs. Immediately following the detection of a meaningful event is to track and trace the objects related to the event. In an extensive environment, the challenge becomes severe when the number of CCTVs increases substantially, imposing difficulties in achieving high accuracy while maintaining real-time performance. The algorithm that re-identifies cross-boundary objects for extensive tracking is referred to Extensive Re-Identification, which emphasizes the issues related to the complexity behind a great number of CCTVs. The Spatial-Temporal Awareness approach challenges the conventional thinking and concept of operations which is labor intensive and time consuming. The ability to perform Extensive Re-Identification through a multi-sensory network provides the next-level insights – creating value beyond traditional risk management.
Abstract: Acoustic Emission (AE) is one of the most effective non-destructive tests that can be used to detect the defect process as it is occurring. AE techniques can be used to monitor a wide range of structures and materials such as metals, non-metals and combinations of these when load is applied. The current work investigates the effectiveness and accuracy of TOA method in AE tests involving reinforced composite concrete-mortar structures. A series of experimental tests were performed using the Hsu-Neilson (H-N) source to study 2-D location accuracy using this method on concrete-mortar (400×400 mm) specimens. Four AE sensors (R3I – resonant frequency 30 kHz) were mounted to the mortar surface and six sources were performed at each point of preselected locations on the upper surface of the mortar. Results show that the TOA method can be used effectively to locate signals on composite concrete/mortar specimen and has high accuracy.
Abstract: Thermogravimetry has been popularized as a thermal characterization technique since the 1950s. It aims at investigating the weight loss against both reaction time and temperature, whilst being able to characterize the evolved gases from the volatile components of the organic material being tested using an appropriate hyphenated analytical technique. In an effort to characterize and identify the reclaimed waste from an unsanitary landfill site, this approach was initiated. Solid waste (SW) reclaimed from an active landfill site in the State of Kuwait was collected and prepared for characterization in accordance with international protocols. The SW was segregated and its major components were identified after washing and air drying. Shredding and cryomilling was conducted on the plastic solid waste (PSW) component to yield a material that is representative for further testing and characterization. The material was subjected to five heating rates (b) with minimal repeatable weight for high accuracy thermogravimetric analysis (TGA) following the recommendation of the International Confederation for Thermal Analysis and Calorimetry (ICTAC). The TGA yielded thermograms that showed an off-set from typical behavior of commercial grade resin which was attributed to contact of material with soil and thermal/photo-degradation.
Abstract: Certain systems can function well only if they recognize the sound environment as humans do. In this research, we focus on sound classification by adopting a convolutional neural network and aim to develop a method that automatically classifies various environmental sounds. Although the neural network is a powerful technique, the performance depends on the type of input data. Therefore, we propose an approach via a slice bispectrogram, which is a third-order spectrogram and is a slice version of the amplitude for the short-time bispectrum. This paper explains the slice bispectrogram and discusses the effectiveness of the derived method by evaluating the experimental results using the ESC‑50 sound dataset. As a result, the proposed scheme gives high accuracy and stability. Furthermore, some relationship between the accuracy and non-Gaussianity of sound signals was confirmed.
Abstract: Prediction of wall shear stress in a rectangular channel, with non-homogeneous roughness distribution, was studied. Estimation of shear stress is an important subject in hydraulic engineering, since it affects the flow structure directly. In this study, the Genetic Algorithm Artificial (GAA) neural network is introduced as a hybrid methodology of the Artificial Neural Network (ANN) and modified Genetic Algorithm (GA) combination. This GAA method was employed to predict the wall shear stress. Various input combinations and transfer functions were considered to find the most appropriate GAA model. The results show that the proposed GAA method could predict the wall shear stress of open channels with high accuracy, by Root Mean Square Error (RMSE) of 0.064 in the test dataset. Thus, using GAA provides an accurate and practical simple-to-use equation.
Abstract: The neural network quantization is highly desired
procedure to perform before running neural networks on mobile
devices. Quantization without fine-tuning leads to accuracy drop of
the model, whereas commonly used training with quantization is done
on the full set of the labeled data and therefore is both time- and
resource-consuming. Real life applications require simplification and
acceleration of quantization procedure that will maintain accuracy of
full-precision neural network, especially for modern mobile neural
network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with
quantization procedure by introducing the trained scale factors for
discretization thresholds that are separate for each filter. Using the
proposed technique, we quantize the modern mobile architectures of
neural networks with the set of train data of only ∼ 10% of the
total ImageNet 2012 sample. Such reduction of train dataset size and
small number of trainable parameters allow to fine-tune the network
for several hours while maintaining the high accuracy of quantized
model (accuracy drop was less than 0.5%). Ready-for-use models and
code are available in the GitHub repository.
Abstract: Accurate prediction of NOx emission is a continuous challenge in the field of diesel engine-out emission modeling. Performing experiments for each conditions and scenario cost significant amount of money and man hours, therefore model-based development strategy has been implemented in order to solve that issue. NOx formation is highly dependent on the burn gas temperature and the O2 concentration inside the cylinder. The current empirical models are developed by calibrating the parameters representing the engine operating conditions with respect to the measured NOx. This makes the prediction of purely empirical models limited to the region where it has been calibrated. An alternative solution to that is presented in this paper, which focus on the utilization of in-cylinder combustion parameters to form a predictive semi-empirical NOx model. The result of this work is shown by developing a fast and predictive NOx model by using the physical parameters and empirical correlation. The model is developed based on the steady state data collected at entire operating region of the engine and the predictive combustion model, which is developed in Gamma Technology (GT)-Power by using Direct Injected (DI)-Pulse combustion object. In this approach, temperature in both burned and unburnt zone is considered during the combustion period i.e. from Intake Valve Closing (IVC) to Exhaust Valve Opening (EVO). Also, the oxygen concentration consumed in burnt zone and trapped fuel mass is also considered while developing the reported model. Several statistical methods are used to construct the model, including individual machine learning methods and ensemble machine learning methods. A detailed validation of the model on multiple diesel engines is reported in this work. Substantial numbers of cases are tested for different engine configurations over a large span of speed and load points. Different sweeps of operating conditions such as Exhaust Gas Recirculation (EGR), injection timing and Variable Valve Timing (VVT) are also considered for the validation. Model shows a very good predictability and robustness at both sea level and altitude condition with different ambient conditions. The various advantages such as high accuracy and robustness at different operating conditions, low computational time and lower number of data points requires for the calibration establishes the platform where the model-based approach can be used for the engine calibration and development process. Moreover, the focus of this work is towards establishing a framework for the future model development for other various targets such as soot, Combustion Noise Level (CNL), NO2/NOx ratio etc.
Abstract: Ultra-high-performance fiber reinforced concrete (UHPFRC) is a specially formulated cement-based composite characterized with an ultra-high compressive strength (fc’ = 240 MPa) and a low water-cement ratio (W/B= 0.2). With such material characteristics, UHPFRC is favored for the design and constructions of structures required high structural performance and slender geometries. Unlike conventional concrete, the structural performance of members manufactured with UHPFRC has not yet been fully studied, particularly, for UHPFRC columns with high slenderness. In this study, the behaviors of slender UHPFRC columns under concentric or eccentric load will be investigated both experimentally and numerically. Four slender UHPFRC columns were tested under eccentric loads with eccentricities, of 0 mm, 35 mm, 50 mm, and 85 mm, respectively, and one UHPFRC beam was tested under four-point bending. Finite element (FE) analysis was conducted with concrete damage plasticity (CDP) modulus to simulating the load-middle height or middle span deflection relationships and damage patterns of all UHPFRC members. Simulated results were compared against the experimental results and observation to gain the confidence of FE model, and this model was further extended to conduct parametric studies, which aim to investigate the effects of slenderness regarding failure modes and load-moment interaction relationships. Experimental results showed that the load bearing capacities of the slender columns reduced with an increase in eccentricity. Comparisons between load-middle height and middle span deflection relationships as well as damage patterns of all UHPFRC members obtained both experimentally and numerically demonstrated high accuracy of the FE simulations. Based on the available FE model, the following parametric study indicated that a further increase in the slenderness of column resulted in significant decreases in the load-bearing capacities, ductility index, and flexural bending capacities.
Abstract: This research presents the three-dimensional mechanical characteristics of a commercial gas diffusion layer by experiment and simulation results. Although the mechanical performance of gas diffusion layers has attracted much attention, its reliability and accuracy are still a major challenge. With the help of simulation analysis methods, it is beneficial to the gas diffusion layer’s extensive commercial development and the overall stress analysis of proton electrolyte membrane fuel cells during its pre-production design period. Therefore, in this paper, a three-dimensional constitutive model of a commercial gas diffusion layer, including its material stiffness matrix parameters, is developed and coded, in the user-defined material model of a commercial finite element method software for simulation. Then, the model is validated by comparing experimental results as well as simulation outcomes. As a result, both the experimental data and simulation results show a good agreement with each other, with high accuracy.
Abstract: Driven by the demand of intelligent monitoring in
rehabilitation centers or hospitals, a high accuracy real-time location
system based on UWB (ultra-wideband) technology was proposed.
The system measures precise location of a specific person, traces his
movement and visualizes his trajectory on the screen for doctors or
administrators. Therefore, doctors could view the position of the
patient at any time and find them immediately and exactly when
something emergent happens. In our design process, different
algorithms were discussed, and their errors were analyzed. In addition,
we discussed about a , simple but effective way of correcting the
antenna delay error, which turned out to be effective. By choosing the
best algorithm and correcting errors with corresponding methods, the
system attained a good accuracy. Experiments indicated that the
ranging error of the system is lower than 7 cm, the locating error is
lower than 20 cm, and the refresh rate exceeds 5 times per second. In
future works, by embedding the system in wearable IoT (Internet of
Things) devices, it could provide not only physical parameters, but
also the activity status of the patient, which would help doctors a lot in
performing healthcare.