We propose a deep-learning approach for the joint MIMO detection and channel decoding problem. Conventional MIMO receivers adopt a model-based approach for MIMO detection and channel decoding in linear or iterative manners. However, due to the complex MIMO signal model, the optimal solution to the joint MIMO detection and channel decoding problem (i.e., the maximum likelihood decoding of the transmitted codewords from the received MIMO signals) is computationally infeasible. As a practical measure, the current model-based MIMO receivers all use suboptimal MIMO decoding methods with affordable computational complexities. This work applies the latest advances in deep learning for the design of MIMO receivers. In particular, we leverage deep neural networks (DNN) with supervised training to solve the joint MIMO detection and channel decoding problem. We show that DNN can be trained to give much better decoding performance than conventional MIMO receivers do. Our simulations show that a DNN implementation consisting of seven hidden layers can outperform conventional model-based linear or iterative receivers. This performance improvement points to a new direction for future MIMO receiver design.

Complementary Metal-Oxide-Semiconductor (CMOS) is a typical image sensor that has a wide range of applications. However, considering the limitations of the weather condition and hardware cost, it is hard to capture high-resolution images by CMOS sensor. Recently, Super-Resolution (SR) techniques for image restoration has been gaining attentions due to its excellent performance. Under the powerful learning ability, Generative Adversarial Networks (GANs) have been proved to achieve great success. In this paper, we propose the Advanced Generative Adversarial Networks (AGAN) to efficiently correct these issues; 1) we design a Laplacian pyramid framework as pre-trained module, which is beneficial to provide multi-scale features for our input. 2) at each feature block, a convolutional skip-connections network, which may contain some latent information, is significant for generative model to reconstruct a plausible-looking image; 3) considering that edge details usually play an important role in image generation, a novel perceptual loss function is defined to train and seek optimal parameters. It is effective to achieve excellent and compelling quality captured by CMOS sensor. Quantitative and qualitative evaluations have been demonstrated that our algorithm not only fully takes advantage of Convolutional Neural Networks (CNNs) to improve the image quality, but also performs better than previous GAN algorithms for super-resolution task.

Geologists employ high-spatial-resolution (HR) remote sensing (RS) data for many diverse applications as they effectively reflect detailed geological information, enabling high-quality and efficient geological surveys. Applications of HR RS data to geological and related fields have grown recently. By analyzing these applications, we can better understand the results of previous studies and more effectively use the latest data and methods to efficiently extract key geological information. HR optical remote sensing data are widely used in geological hazard assessment, seismic monitoring, mineral exploitation, glacier monitoring, and mineral information extraction due to high accuracy and clear object features. Compared with optical satellite images, synthetic-aperture radar (SAR) images are stereoscopic and exhibit clear relief, strong performance, and good detection of terrain, landforms, and other information. SAR images have been applied to seismic mechanism research, volcanic monitoring, topographic deformation, and fault analysis. Furthermore, a multi-standard maturity analysis of the geological applications of HR images using literature from the Science Citation Index reveals that optical remote sensing data are superior to radar data for mining, geological disaster, lithologic, and volcanic applications, but inferior for earthquake, glacial, and fault applications. Therefore, geological remote sensing research needs to be truly multidisciplinary or interdisciplinary, ensuring more detailed and efficient surveys through cross-linking with other disciplines. Moreover, the recent application of deep learning technology to remote sensing data extraction has improved automatic processing and data analysis capabilities.

In this work, the decennial experience of Policumbent student team at Politecnico di Torino is summarized by focusing on the acquired knowledge in design of Human Powered Vehicles (HPVs) and on soft skills developed by both students and staff. Policumbent was funded by the authors at the end of 2008 in order to gather engineering students interested in design and construction of HPVs. In the last decade, the team has grown from 10 up to 50 students enrolled per year, exploring a range of HPV design for sports and mobility. Even when focusing on sport vehicles and extreme HPVs for speed record, such kind of projects allows students to familiarize with important concepts related to sustainable mobility: the amount of resistive forces and dissipated power, the role of vehicle weight and the impact of acceleration on the overall energetic balance as far as fundamental concepts about energy consumption, efficiency and emissions of the ``human engine'' in comparison with other kind of engines. By touching with hands such topics in the framework of a ``human-centred'' design project, the students have opportunity to develop awareness about the impact of design choices on sustainability of any kind of vehicle for transportation. Also, the paper retraces the team evolution path by focusing on a thorough analysis of what factors contributed to the success of this project.

Stemborer pests contribute to significant maize crop yield loses incurred by the smallholder famers in Ethiopia. The problem requires requires concerted effort to learn and adopt new innovations to find a long lasting solution. In this study, the on-farm implementation of the push-pull technology (PPT) was used as a platform for interaction and enhancing the social learning among the stakeholders in the maize growing Woredas of Bako Tibe, Jimma Arjo and Yayu in the Oromia region. The main stakeholders were the smallholder maize farmers, researchers and the extension staffs. The study took place between August 2014 to May 2015. The PPT is a biological based strategy addresses the stemborer pest problem in maize crop. Under the strategy, maize crop is intercropped with a stemborer moth repellent fodder legume, Desmodium (the push) together with an attractant trap plant, Napier/Brachiaria grass (the pull) planted around maize-legume intercrop. The study was implemented based on the transdisciplinary action research approach and qualitative data collected during focus group discussions, key informant interviews, stakeholder workshops, participant observations and on-farm PPT demonstrations. The findings show that, the involvement of different stakeholders in joint PPT activities in an interactive environment is an innovation in itself. It creates opportunities for the stakeholders’ empowerment as well as deliberating on the contributions from each other to overcome uncertainties about the technology and create new knowledge. The intercropping strategy of maize with Desmodium and Napier/Brachiaria is used to reintroduce the traditional mixed cropping system of smallholder agriculture as strategy for control of pests.

This paper addresses the development of knowledge and assessment-centered learning approaches within a reflective learning framework in a first year physics class in a university faculty. The quality of students’ reflections was scored using a Self-reporting Reflective Learning Appraisal Questionnaire at the end of each learning approach. The results showed the differences between the approaches based on reflections on the learning control through self-knowledge, by connecting experience and knowledge, as well as through self-reflection and self-regulation. Assessment-centered activities fundamentally help students identify aspects of their attitudes towards, as well as regulate, their sustainability learning education.

This paper presents a new adaptive and optimal algorithm for the trajectory tracking control of a quadrotor using iterative learning algorithm (ILA) and enumerative learning algorithm. Ordinarily the ILA, as an adaptive method, can perform well with PID control to improve the controller’s performance for a nonlinear system. Quadrotors are considered as non-linear and unstable systems which the use of an adaptive and optimal controller can increase its stability and decrease error level. In this method, a PID controller is proposed for the outer and inner control loops of a quadrotor and the ILA is used to adapt PID control gains. Subsequently, an enumerative learning algorithm is used to optimize the learning rates of the ILA. For this purpose, at first, the dynamic model of the quadrotor is acquired. After that, the structure of the inner and outer control loops is defined. In the end, the simulation results for the trajectory tracking control of a quadrotor are demonstrated. Through simulation, it is concluded that as time increases, the performance of the suggested control method in trajectory tracking control becomes better and better and error signals convergence to zero.

Horses’ ability to adapt to new environments and to acquire new information plays an important role in handling and training. Social learning in particular would be very adaptive for horses as it enables them to flexibly adapt to new environments. In the context of horse handling, social learning from humans has been rarely investigated but could help to facilitate management practices. We assessed the impact of human demonstration on spatial problem-solving abilities in horses using a detour task. In this task, a bucket with a food reward was placed behind a double-detour barrier and horses (n = 16) received a human demonstration or no demonstration. Horses were allocated to two test groups of 8 horses each, which experienced the two treatments in a counterbalanced order. We found that horses did not solve the detour task faster with human demonstration. However, both test groups improved rapidly over trials. Our results suggest that horses prefer to use individual rather than social information when being confronted with a spatial problem-solving task.

This research assess the effects of training program based on the usage of the digital learning objects in teaching practice at the Northern Borders University staff. E Assessment through the tablets and smart phones and the teachers’ attitudes towards such way of evaluation is the major objective of this study as the researcher expects that the assessment mechanism in the university through utilization of tablets and smart phones and its application will inevitably bring in a systematic improvement in the assessment and evaluation process of the curricula. Moreover, making use of the e learning objects in training will make a significant change in e training program of the university. Hence, the researcher has chosen voluntary random samples from the university teaching staff (men\women) from various different faculties (medicine, medical sciences, science, education and arts, business administration, home economics, and science and literature). These samples included 300 members of the teaching staff. In a group of 20 to 25 members, a personal training was conducted regarding the usage of tablets and smart phones and its applications in the assessment process. Each group participated by producing a complete e-assessment for their students in the Northern Borders University and by the e learning system i.e. Blackboard and Question Mark. The research also depends on the semi-experimental design of multiple groups and on testing the groups’ pre and post achievement tests. In addition, the research identifies the level of the university teaching staff in using the tablets and the smartphones and its applications in the assessment process by the note card that the individuals have during the test.

Genealogy contributes to learning by developing critical thinking skills. A review of three classics of genealogical literature, matched against modern tutors, confirmed that the validation and evaluation of information and the management of hypotheses have long been the core skills for family historians. A consultation with 100 genealogists revealed a preference for task orientated learning, often alone, in a self-contained environment. Reference to learning theory suggested that Genealogical Studies could be usefully offered to under achieving students in general education who respond to these conditions.

The problem of event detection in general noisy signals arises in many applications; usually, either a functional form for the event is available, or a previous annotated sample with instances of the event that can be used to train a classification algorithm. There are situations, however, where neither functional forms nor annotated samples are available; then it is necessary to apply other strategies to separate and characterize events. In this work, we analyze 15 minute-long samples of an acoustic signal, and are interested in separating sections, or segments, of the signal which are likely to contain significative events. For that, we apply a sequential algorithm with the only assumption that an event alters the energy of the signal. The algorithm is entirely based on Bayesian methods.

In this paper, we tackle air quality forecasting by using machine learning approaches to predict the hourly concentration of air pollutants (e.g., Ozone, PM_2.5 and Sulfur Dioxide). Machine learning, as one of the most popular techniques, is able to efficiently train a model on big data by using large-scale optimization algorithms. Although there exists some works applying machine learning to air quality prediction, most of the prior studies are restricted to small scale data and simply train standard regression models (linear or non-linear) to predict the hourly air pollution concentration. In this work, we propose refined models to predict the hourly air pollution concentration based on meteorological data of previous days by formulating the prediction of 24 hours as a multi-task learning problem. It enables us to select a good model with different regularization techniques. We propose a useful regularization by enforcing the prediction models of consecutive hours to be close to each other, and compare with several typical regularizations for multi-task learning including standard Frobenius norm regularization, nuclear norm regularization, ℓ_2,1 norm regularization. Our experiments show the proposed formulations and regularization achieve better performance than existing standard regression models and existing regularizations.

Abstract: The future of transportation is being reshaped by autonomous vehicles (AVs), which promise to revolutionize road safety, accessibility, and environmental sustainability. Central to their evolution are advancements in artificial intelligence (AI), which enable real-time perception, decision-making, and control. This paper explores the future trajectory of AI in AVs, highlighting innovative AI paradigms such as explainable AI, federated learning, and adaptive regulatory frameworks. It delves into the development of sophisticated perception algorithms for environmental understanding, advanced decision-making systems employing reinforcement learning and deep neural networks, and precise control mechanisms through predictive modeling and optimization. By addressing current challenges, including regulatory hurdles and the complexity of AI algorithms, this paper provides a comprehensive outlook on the potential and implications of AV technology. It envisions a future where AI-driven AVs are seamlessly integrated into society, offering profound insights into their impact on transportation and societal dynamics.

The location and number data of individual fruit trees are critical for planting area investigation, fruit yield prediction, and smart orchard management and planning. These data are conventionally obtained through manual investigation and statistics with time-consuming and laborious effort. Object detection models in deep learning used widely in computer vision could provide an opportunity for accurate detection of individual fruit trees, which is essential for rapidly obtaining the data and reducing human operations errors. This study proposes an approach to detecting individual fruit trees and mapping their spatial distribution by integrating deep learning with unmanned aerial vehicle (UAV) remote sensing. UAV remote sensing collected high-resolution true-color images of fruit trees in the experimental pomelo tree orchards in Meizhou city, South China. An image dataset of deep learning samples of individual pomelo trees (IPTs) was constructed through visual interpretation and field investigation based on the fruit tree images captured by UAV remote sensing. Four different scales of YOLOv5 (YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) for object detection were selected to train, validate, and test on the image dataset of pomelo trees. The results show that the average precision (AP@0.5) of the four YOLOv5 models for validation reach 87.8%, 88.5%, 89.1%, and 90.7%, respectively. The larger the model scale, the higher the average accuracy of the detection result of validation. It suggests that YOLOv5x is a preferred high-accuracy model among the YOLOv5 family and is suitable to realize the detection of IPTs. The number of the IPTs in the study area was counted using YOLOv5x, and their spatial distribution map was made using the non-maximum suppression method and ArcGIS software. This study will provide primary data and technical support for smart orchard management in Meizhou city and other fruit-producing areas.

Cloud data centers play a vital role in modern computing infrastructure, offering scalable resources for diverse applications. However, managing costs and resources efficiently in these centers has become a crucial concern due to the exponential growth of cloud computing. User applications exhibit complex behavior, leading to fluctuations in system performance and increased power usage. To tackle these obstacles, we propose the consolidation of virtual machines (VMs) to optimize resource utilization and reduce operational costs. This paper introduces a novel algorithm, leveraging the Modified Artificial Feeding Birds Algorithm (ModAFBA), to manage cost optimally in cloud data centers by reducing power usage while meeting service level agreements (SLAs). The ModAFBA algorithm, inspired by bird foraging behavior, dynamically adjusts solutions based on environmental changes. Comprehensive experimental evaluation demonstrates the superiority of the proposed algorithm in terms of power usage, migration count, and SLA compliance. Through this research, we aim to advance cost management and resource optimization in cloud data centers, providing a valuable tool for cloud service providers to enhance infrastructure efficiency and achieve cost savings.

In this study, I will present some documentary evidence that Carlos Drummond de Andrade’s poem “A Máquina do Mundo” [The Machine of the World] (1949) was based on prior reflections contained in a forgotten newspaper article entitled “Poesia e Pesadelo” [Poetry and Nightmare] (1949). In that article, Drummond critically analyzed some of the theses of Stephen Spender's essay “What Is Modern in Modern Poetry” (1948), which had just been published in The Tiger's Eye magazine. As soon as he read Spender's text, Drummond wrote “Poetry and Nightmare” and began to elaborate a narrative poem whose protagonist would be a machine. All the documentary evidence indicates that Drummond took Spender's lessons as touchstones for the elaboration of the narrative and allegorical structure of “The Machine of the World.” According to the interpretation I am proposing here, Drummond, in writing the machine poem, put into practice at least six lessons drawn from Spender’s essay, namely: 1) the modern poet must represent the tension between the external machinelike landscape and the landscape of the inner world of the creative imagination; 2) he must also represent the machinelike, ugly, and urban world around him in a beautiful and poetic way; 3) he must avoid the misconceptions of excessive utopian visionarism, as well as creeping realism; 4) he must reject the imperative of political engagement, whose principle of action states that poetry has a transformative mission in society; 5) he must free himself from the obsession with free verse as the only form of modern poetry and start using the traditional fixed forms; 6) he must understand machines as poetic symbols of human passions, and not just as exotic objects foreign to human reality. My conclusion is that, after reading Spender’s essay, Drummond changed his aesthetic and philosophical understanding of what defines the essence of modern poetry, both in terms of form and content.

Digital machine intelligence has evolved from its inception in the form of computation of numbers to AI, which is centered around performing cognitive tasks that humans can perform, such as predictive reasoning or complex calculations. The state of the art includes tasks that are easily described by a list of formal, mathematical rules or a sequence of event-driven actions such as modeling, simulation, business workflows, interaction with devices, etc., and also tasks that are easy to do “intuitively”, but are hard to describe formally or as a sequence of event-driven actions such as recognizing spoken words or faces. While these tasks are impressive, they fall short in applying common sense reasoning to new situations, filling in information gaps, or understanding and applying unspoken rules or norms. Human intelligence uses both associative memory and event-driven transaction history to make sense of what they are observing fast enough to do something about it while they are still observing it. In addition to this cognitive ability, all bio-logical systems exhibit autopoiesis and self-regulation. In this paper, we demonstrate how machine intelligence can be enhanced to include both associative memory and event-driven transaction history to create a new class of knowledge-based assistants to augment human intelligence. The digital assistants use global knowledge derived from the Large Language Models to bridge the knowledge gap between various participants interacting with each other. We use the general theory of information and schema-based knowledge representation to create the memory and history of various transactions involved in the interactions.

Using the potent tools of information geometry (IG), the current research analyses the information geometrics of the five-dimensional HTBFC Manifold. By enabling a unique revolutionary analysis for the performance of Human-Trust Based Feedback Control (HTBFC), the integration of information geometry into HTBFC facilitates the relativistic analysis of the five-dimensional HTBFC manifold. Both the two- and three-dimensional manifold subcases are investigated. This work provides a ground-breaking approach to IG unification of Human- Machine Interactions (HMIs). Some potential applications of HTBFC to robotics are presented.Conclusions are provided, along with some emerging open problems and recommendations for future research.

A land cover map of two arctic catchments, nearby the Abisko Scientific Research Station, was obtained from a classification of a Sentinel-2 satellite image and a ground survey performed in July 2022. The two contiguous catchments, Miellajokka and Stordalen, are covered by various ecotypes, from boreal forest to alpine tundra and peatland. Two classification algorithms, support vector machine and random forest, were tested and gave very similar results. The percentage of correctly classified pixels was over 88% in both cases. The developed workflow relies solely on open source software and acquired ground observations. Space organization was directed by the altitude as demonstrated by the intersection of the land cover with the topography. Comparison between this new land cover map and previous ones based on data acquired between 2008 and 2011 shows some trends of vegetation cover evolution in response to climate change in the considered area. This land cover map is key input data for permafrost modeling, and hence for the quantification of climate change impacts in the studied area.

Intracortical microelectrode arrays (MEAs) can be used in a range of applications, from basic neuroscience research to providing an intimate interface with the brain as part of a Brain-Computer Interface (BCI) system aimed to restore function for people living with neurological disorders or injuries. Unfortunately, MEAs tend to fail prematurely, leading to a loss in functionality for many applications. An important contributing factor in MEA failure is oxidative stress resulting from chronically inflammatory-activated microglia and macrophages releasing reactive oxygen species (ROS) around the implant site. Antioxidants offer a means for mitigating oxidative stress and improving tissue health and MEA performance. Here, we investigate using the clinically available antioxidant dimethyl fumarate (DMF) to reduce the neuroinflammatory response and improve MEA performance in a rat MEA model. Daily treatment of DMF for 16 weeks resulted in a significant improvement in the recording capabilities of MEA devices during the sub-chronic (Weeks 5-11) phase (42% active electrode yield vs. 35% for control). However, these sub-chronic improvements were lost in the chronic implantation phase, as a more exacerbated neuroinflammatory response occurs in DMF-treated animals by 16 weeks post-implantation. Yet, neuroinflammation was indiscriminate between treatment and control groups during the sub-chronic phase. Although worse for chronic use, a temporary improvement (<12 weeks) in MEA performance is meaningful. Providing short-term improvement to MEA devices using DMF can allow for improved use for limited-duration studies. Further efforts should be taken to explore the mechanism behind a worsened neuroinflammatory response at the 16-week time point for DMF-treated animals to assess its usefulness to specific applications.

Vegetation classifications on large geographic scales are necessary to inform conservation decisions and monitor keystone, invasive, and endangered species. These classifications are often effectively achieved by applying models to imaging spectroscopy, a type of remote sensing, data, but such undertakings are often limited in spatial extent. Here we provide accurate, high-resolution spatial data on the keystone species Metrosideros polymorpha, a highly polymorphic tree species distributed across bioclimatic zones and environmental gradients on Hawai'i island, using airborne imaging spectroscopy and LiDAR. We compare two tree species classification techniques, support vector machine (SVM) and spectral mixture analysis (SMA), to assess their ability to map M. polymorpha over 28,000 square kilometers where differences in topography, background vegetation, sun angle relative to the aircraft, and day of data collection, among others, challenge accurate classification. To capture spatial variability in model performance, we applied gaussian process classification (GPC) to estimate the spatial probability density of M. polymorpha occurrence using only training sample locations. We found that, while SVM and SMA models exhibit similar raw score accuracy over the test set (96.0% and 93.4%, respectively), SVM better reproduces the spatial distribution of M. polymorpha than SMA. We developed a final 2 m x 2 m M. polymorpha presence dataset and a 30 m x 30 m M. polymorpha density dataset using SVM classifications that have been made publicly available for use in conservation applications. Accurate, large-scale species classifications are achievable, but metrics for model performance assessments must account for spatial variation of model accuracy.

The increasing prevalence of depression worldwide requires more effectiveness in therapy approaches and a molecular understanding of antidepressants mode of action. We carried out untargeted metabolomics of the prefrontal cortex of rats exposed to chronic social isolation (CSIS), a rat model of depression, and/or fluoxetine treatment using liquid chromatography-high resolution mass spectrometry. The behavioral phenotype was assessed by the forced swim test. To analyze metabolomics data, univariate and multivariate analysis and biomarker capacity assessment using the classical receiver operating characteristic (ROC) curve were used. Support vector machine-linear kernel (SVM-LK), as a machine-learning algorithm was performed for binary classification. Upregulated myo-inositol following CSIS may represent a potential marker of depressive phenotype. Effective fluoxetine treatment reversed depressive-like behavior and increased sedoheptulose 7-phosphate, hypotaurine, and acetyl-L-carnitine contents, which were identified as potential markers. We identified 4 or 10 marker candidates with ROC curve greater than 0.9 for CSIS or fluoxetine effectiveness designation. SVM-LK has given accuracy of 61.50%, or 93.30%, and 7 or 25 predictive metabolites for CSIS vs. control and fluoxetine-treated CSIS vs. CSIS classification. Overall, metabolic fingerprints combined with ROC curve and SVM-LK may represent a new approach to identifying potential markers or predicting metabolites for group designation or classification.

Sense element engagement theory explains how neural networks produce cortical prosthetic vision. A major prediction of the theory can be tested by developing a device which is expected to enable perception of continuous forms in altered visual geometries. The research reported here completes several essential steps in developing this device: (1) replication of simulations that are consistent with the theory using the NEST simulator, which can also be used for full-scale network emulation by a neuromorphic computer; (2) testing whether results consistent with the theory survive increasing the scale and duration of simulations; (3) establishing a method that uses numbers of spikes produced by network neurons to report the number of phosphenes produced by cortical stimulation; and (4) simulating essential functions of the prosthetic device. NEST simulations replicated early results and increasing their scale and duration produced results consistent with the theory. A decision function created using multinomial logistic regression correctly classified the expected number of phosphenes for 2080 spike number distributions for each of three sets of data, half of which arise from simulations expected to yield continuous visual forms on an altered visual geometry. A process for modulating electrical stimulation amplitude based on intermittent population recordings that is predicted to produce continuous visual forms was successfully simulated. The classification function developed using logistic regression will be used to tune this process as the scale of simulations is further increased.

Lumbar support exoskeletons with active and passive actuators are currently the cutting-edge technology for preventing back injuries in workers while lifting heavy objects. However, many challenges still exist in both types of exoskeletons, including rigid actuators, risks of human-robot interaction, high battery consumption, bulky design, and limited assistance. In this paper, the design of a compact, lightweight energy storage device combined with rotary series elastic (ES-RSEA) is proposed for use in a lumbar support exoskeleton to increase the level of assistance and exploit the human bioenergy during the two stages of the lifting task. ES takes the responsibility to store and release passive mechanical energy while RSEA provides excellent compliance and prevents injury from the human body's undesired movement. The experimental tests on the spiral spring showed excellent linear characteristics (above 99%) with an actual spring stiffness of 9.96 Nm/rad. The results demonstrate that ES-RSEA can provide maximum torque assistance in the ascent phase with 66.6 Nm while generating nearly 21 Nm of spring torque during descent without turning on the DC motor. Ultimately, the proposed design can maximize the energy storage of human energy, exploit the biomechanics of lifting tasks, and reduce the burden on human effort to perform lifting tasks.

To achieve the near zero emission of wastewater in the flue gas desulfurization (FGD) system in coal-fired power plant and better utilize the exhaust heat from flue gas, a feasible technology of spraying FGD wastewater in the flue duct for evaporation is discussed in the present study. A full-scale influencing factor investigation on the wastewater droplet evaporation performance is established under the Eulerian-Lagrangian model numerically. The dominant factors, including the characters of wastewater droplets, flue gas and the spray nozzles were analyzed under different conditions, respectively. Considering the multiple factors and conditions in the process, a Least-Square support vector machine (LSSVM) model is introduced to predict the evaporation rate based on the numerical results. Conclusions are made that the flue gas temperature and droplet diameter are of great importance in the evaporation process. The spray direction of droplet parallel with the flue gas flow direction is profitable for the dispersion of droplet, resulting the maximal evaporation rate. A double-nozzle arrangement optimized with relatively small flow rate is recommended. The LSSVM model can accurately predict the evaporation rate using the numerical results with different conditions.

Fault diagnosis of the gearbox is a decisive part of the modern industry to find the many gearbox defects like gear tooth crack, chipped or broken, etc. But sometimes, the nonstationary properties of vibration signal and low energy of minimal faults make this procedure very challenging. Previously, many types of techniques have been developed for gearbox condition monitoring. But most of the methods are dealing with conventional techniques of the gearbox condition monitoring, such as time-domain analysis or frequency domain analysis. Most of the conventional methods are not suitable for the nonstationary vibration signal. Thus, this paper presents a novel gearbox fault diagnosis technique using conditional temporal moments and an optimizable support vector machine (SVM). This work also presents an integrated features extraction technique based on the standard features, i.e., statistical and spectral features with the combinations of moment features. The impact of the four conditional temporal moments of each gearbox condition is also presented. This work shows that the proposed method successfully classifies and categorizes the gearbox faults at an early stage.

The study takes into account different classes of tunnel boring machines (TBMs), with the aim of identifying correlation models which are meant to estimate, at a preliminary design phase, the construction time of a tunnel and to evaluate the mechanical and operational parameters of the TBMs, starting from the knowledge of the tunnel length and/or the excavation diameter. To achieve this goal, first of all a database was created, thanks to the collection of the most meaningful technical parameters from a large number of tunnels; afterward, it was statistically analysed through Microsoft Excel. In a first phase, forecasting models were identified for the three types of machines investigated, separately for compact rocks (open TBM) and fractured rocks (single and double shield TBM). Then, the mechanical parameters collected through the database were analysed, with the aim of obtaining models that take into account, in addition to the type of TBM, the geological aspect, and the type of rock characterising the rock mass. Finally, the validation of the study was proposed in a real case, represented by the Moncenisio base tunnel, a work included in the new Turin–Lyon connection line. The estimated values were compared with the real ones, in order to verify the accuracy of the experimental models identified.

This work presents an alternative to harnessing wind energy with an Electromagnetic Frequency Regulator (EFR) coupled to a hydrostatic transmission and associated with a horizontal axis wind turbine, a bidirectional frequency inverter and a secondary energy source, in a hybridized system. The hydrostatic transmision is composed by a fixed displacement axial piston pump and a variable displacement, swash plate, axial piston motor. Feedback linearization was used as a technique to control the motor geometric displacement, and a prediction algorithm for the steady state rotations of the armature and the electromagnetic field has been developed. A 5\,kW project was simulated on a Scilab platform, with combinations of constant or variable load, and constant or variable wind speed. The results indicated that the system was able to supply the generator load, adapting to fluctuations in wind speed. The possibility of storing wind energy through the inverter has also been proven. The system can accumulate energy in batteries during the fastest wind regimes, to use it when the turbine power is lower than the load.

Dayaoshan, as an important metal ore producing area in China, is faced with the dilemma of resource depletion due to long-term exploitation. In this paper, remote sensing method is used to circle the favorable metallogenic areas and find new ore points for Gulong. Firstly, vegetation interference bas been removed by using mixed pixel decomposition method with hyperplane and genetic algorithm (GA) optimization; then, altered mineral distribution information has been extracted based on principal component analysis (PCA) and support vector machine (SVM) method; Thirdly, the favorable areas of gold mining in Gulong has been delineated by using ant colony algorithm (ACA) optimization SVM model to remove false altered minerals; Lastly, field survey verified that the extracted alteration mineralization information is correct and effective. The results show that the mineral alteration extraction method proposed in this paper has certain guiding significance for metallogenic prediction by remote sensing.

Freeway travelling time is affected by many factors including traffic volume, adverse weather, accident, traffic control and so on. We employ the multiple source data-mining method to analyze freeway travelling time. We collected toll data, weather data, traffic accident disposal logs and other historical data of freeway G5513 in Hunan province, China. Using Support Vector Machine (SVM), we proposed the travelling time model based on these databases. The new SVM model can simulate the nonlinear relationship between travelling time and those factors. In order to improve the precision of the SVM model, we applied Artificial Fish Swarm algorithm to optimize the SVM model parameters, which include the kernel parameter σ, non-sensitive loss function parameter ε, and penalty parameter C. We compared the new optimized SVM model with Back Propagation (BP) neural network and common SVM model, using the historical data collected from freeway G5513. The results show that the accuracy of the optimized SVM model is 17.27% and 16.44% higher than those of the BP neural network model and the common SVM model respectively.

Abstract: This review addresses the complexities of type 1 diabetes (T1D)and its associated complications, with a par-ticular focus on diabetic retinopathy (DR). This review outlines the progression from non-proliferative to proliferative diabetic retinopathy and diabetic macular edema, highlighting the role of dysglycemia in the pathogenesis of these conditions. A significant portion of the review is devoted to technological advances in diabetes management, particu-larly the use of Hybrid Closed Loop systems (HCLS) and to the potential of open-source HCLS systems, which could be easily adapted to different patiens’needs using big data analytics and machine learning. Personalized HCLS algorithms that integrate factors such as patient lifestyle, dietary habits, and hormonal variations are highlighted as critical to reducing the incidence of diabetes-related complications and improving patient outcomes.

Self-sustained learning (SSL) is considered a crucial factor in promoting students’ long-term learning and development in a sustainable society. To deepen the understanding of SSL, especially in the context of learning English as a second language, the current study examined the influence of intercultural communicative skills, language mindset, and positive L2 self on SSL in English learning among 1,238 college students in China. The results showed that students not only had a strong language mindset, positive L2 self, and intercultural communicative skills but also scored higher in long-term self-sustained English learning. Findings from the Structural Equation Modeling indicated that both language mindset and intercultural communicative skills positively predicted positive L2 self and self-sustained English learning. Furthermore, language mindset and intercultural communicative skills had an indirect impact on self-sustained English learning through positive L2 self. These findings suggest that to promote English learners’ SSL, instructors should help facilitate students’ intercultural communicative skills and foster a growth language mindset, as well as positive language learning beliefs.

Solid-phase joining is a technique used to fuse two materials by applying heat and pressure, causing plastic deformation without reaching the melting point. This method is applicable for similar and dissimilar materials, including metals, polymers, and ceramics, without the need for filler material. Among the various methods, Friction Stir Welding (FSW) is preferred for joining dissimilar materials due to its solid-state process, which enhances mechanical properties, metallurgical compatibility, and reduces distortion. FSW is particularly effective for materials with significant differences in melting points. The current project focuses on assessing the strength and mechanical properties of FSW joints between aluminum and polymer-based composites. FSW was selected for its ability to produce fine-grained, strong welds free from fusion-related defects such as porosity and cracks. Applications in sectors like automotive, aerospace, and shipbuilding are explored, with impact, hardness, and tensile tests conducted to evaluate joint performance. This comprehensive study includes literature review, fabrication, testing, and tool design to ensure a thorough understanding of dissimilar joint properties.

This paper investigates the application of Graph Neural Networks (GNNs) in solving the facility location decision problem. By adapting the learning objectives and structure of GNNs, this research bridges the gap between traditional optimization approaches and modern machine learning techniques. The proposed method demonstrates improved decision-making capabilities, providing promising results for facility location optimization. Additionally, potential future research directions are outlined, highlighting areas where GNNs can further enhance decision-making processes in complex supply chain networks. Hybrid GNN and Mixed Integer Programming solutions have been proposed.

This paper reviews recent works related to applications of reinforcement learning in power system optimal control problems. Based on an extensive analysis of works in the recent literature, we attempt to better understand what is the gap between reinforcement learning methods that rely on complete or incomplete information about the model dynamics, and data-driven reinforcement learning approaches. More specifically we ask how such models change based on the application or the algorithm, what are the currently open theoretical and numerical challenges in each of the leading applications, and which reinforcement-based control strategies will rise in the following years. The reviewed research works are divided to ``model-based'' methods and ``model-free'' methods, in order to highlight the current developments and trends within each of these two groups. The optimal control problems reviewed are energy markets, grid stability and control, energy management in buildings, electrical vehicles and energy storage.

In this study, we introduce an innovative framework for multimodal learning that leverages enhanced fusion gate units within gated neural network architectures. The proposed Fusion Gate Unit (FGU) serves as a pivotal component in neural network designs, aiming to derive a comprehensive intermediate representation by amalgamating data from diverse modalities. The FGU is adept at determining the extent to which each modality influences the unit's activation through the utilization of multiplicative gating mechanisms. We conducted evaluations on a multilabel genre classification task for movies, utilizing both plot summaries and poster images as input modalities. The results demonstrate that the FGU significantly elevates the macro F-score compared to single-modality approaches and surpasses existing fusion techniques, including mixture of experts models. Additionally, we present the MM-IMDb dataset alongside this publication, which, to our knowledge, represents the most extensive publicly accessible multimodal dataset for movie genre prediction to date. This dataset is expected to facilitate further research and development in the field of multimodal information processing.

Plant diseases not only cause economic losses, but they also pose a health risk. In this regard, aflatoxins are linked to the development of some type of liver cancer, especially the hepatocellular carcinoma. Aflatoxins are usually produced by the fungi Aspergillus flavus and Parsiticus in figs, and their identification is usually carried out using invasive and complex methods or by visual inspection at an advanced stage. Given that Spain is one of the main producers of figs and Extremadura is the leading region in the country, it is necessary to explore alternative ways of detecting the presence of aflatoxins in figs and preventing them from entering the food chain. The aim of this research is to address the early detection of Aspergillus flavus fungus using non-invasive techniques with the aid of hyperspectral imaging and the application of artificial intelligence techniques, in particular deep learning. The images were taken after inoculation of the microtoxin using 3 different concentrations, related to three different classes and healthy figs (healthy controls). The analysis of the hyperspectral images was performed at the pixel level. Firstly, a full connected neural network was used to analyse the spectral signature associated with each pixel; second, the wavelet transform was applied to each spectral signature. The resulting images are fed to a convolutional neural network. The hyperparameters of the proposed models were adjusted based on the parameter tuning process also performed. The results are promising, with 83% accuracy, 82.75% recall and 83.25% F1-measure for the single neural network, and 77.25% accuracy, recall and F1 for the convolution neural network.

High-precision, ultra-thin angular detectable imaging upon a single pixel holds significant promise for light field detection and reconstruction, thereby catalyzing advancements in machine vision and interaction technology. Traditional light-direction angle sensors relying on optical components like gratings and lenses face inherent constraints from diffraction limits in achieving device miniaturization. Recently, angle sensors via coupled double nanowires have demonstrated prowess in attaining high-precision angle perception of incident light at sub-wavelength device scales, which may herald a novel design paradigm for ultra-compact angle sensors. However, the current approach to measure the three-dimensional (3D) incident light direction is unstable. In this paper, we propose a flexible segmented concentric nanorings structure capable of discerning the 3D light-direction based on its sensitivity character to both elevation (θ) and azimuth (ϕ) angles at a micrometer device scale. Through deep learning (DL) analysis and prediction, our simulations reveal that for angle scanning with a step size of 1o, the device can still achieve a detection range of 0∼360o for azimuth and 45o∼90o for elevation, with an average accuracy of 0.19o, and DL can further solve some data aliasing problems to expand the sensing range. Our design broadens the angle sensing dimension based on mutual resonance coupling among nanorings segments, and through waveguide implementation or sensor array arrangements, the detection range can be flexibly adjusted to accommodate diverse application scenarios.

The design of school environments plays a pivotal role in promoting student wellness, mindfulness, and socio-emotional learning (SEL). This article explores the integration of Environment Behaviour Studies (EBS) concepts into school design to enhance students' overall well-being and academic success. It highlights the importance of indoor environmental quality, ergonomic and flexible learning spaces, and biophilic design in fostering a healthy and engaging learning atmosphere. Additionally, the article delves into the creation of mindfulness spaces, sensory-friendly environments, and the use of colour and aesthetics to support emotional regulation and mental health. By examining case studies of successful implementations, the article underscores best practices for designing schools that promote positive social interactions, ensure safety, and reflect community values. Ultimately, this comprehensive approach to school design aims to nurture holistic development, support socio-emotional learning, and prepare students for lifelong success.

Two-dimensional ultrasound (2D US) is commonly used in clinical settings for its cost-effectiveness and non-invasiveness, but it is limited by spatial orientation and operator dependency. Three-dimensional ultrasound (3D US) overcomes these limitations by adding a third dimension and enhancing integration with other imaging modalities. Advances in deep learning (DL) have further propelled the viability of freehand image-based 3D reconstruction, broadening clinical applications in intraoperative and point-of-care (POC) settings. This review evaluates state-of-the-art freehand 3D US reconstruction methods that eliminate the need for external tracking devices, focusing on experimental setups, data acquisition strategies, and reconstruction methodologies. PubMed, Scopus, and IEEE Xplore were searched for studies since 2014 following PRISMA guidelines, excluding those using additional imaging or tracking systems other than inertial measurement units (IMUs). Fourteen eligible studies were analyzed, showing a shift from traditional speckle decorrelation towards DL-based methods, particularly Convolutional Neural Networks (CNNs). Variability in datasets and evaluation methods hindered a comprehensive quantitative comparison, but notable accuracy improvements were observed with IMUs and integration of contextual and temporal information within CNNs. These advancements enhance freehand 3D US reconstruction feasibility, though variability limits definitive conclusions about the most effective methods. Future research should focus on improving precision in complex trajectories and adaptability across clinical scenarios.

In addressing the multifaceted problem of multiple-input multiple-output (MIMO) detection in wireless communication systems, this work highlights the pressing need for enhanced detection reliability under variable channel conditions and MIMO antenna configurations. We propose a novel method that sets a new standard for deep unfolding approaches to MIMO detection by integrating the iterative conjugate gradient method with Tikhonov regularization, combining the adaptability of modern deep learning techniques with the robustness of classical regularization. Unlike conventional techniques, our strategy treats the regularization parameter of Tikhonov regularization as well as step size values and search direction coefficients of conjugate gradient (CG) method as trainable parameters within the deep learning framework, allowing for dynamic modification according to channel conditions and MIMO antenna configurations. Detection performance is significantly improved by the proposed approach in variety of conditions. In different MIMO settings, the suggested method consistently shows better bit error rate (BER) and normalized minimum mean square error (NMSE) performance. Across a range of MIMO configurations and channel conditions, the proposed method exhibits significantly lower BER and NMSE values than well-known techniques such as DetNet and CG. The proposed method has superior performance over CG and other model-oriented methods, especially in small number of iterations. Consequently, the simulation results demonstrate the flexibility of the proposed approach, making it a viable choice for MIMO systems with a range of antenna configurations and different channnel conditions.

Ultrasound imaging is a vital imaging tool in musculoskeletal medicine, with the number of publications on ultrasound-guided surgery increasing in recent years. However, ultrasound imaging has drawbacks, such as operator dependency and image obscurity. Artificial Intelligence (AI) and Deep Learning (DL), a subset of AI, can address these issues. DL methods, including segmentation, detection, and localization of target tissues and medical instruments, potentially allow physicians and surgeons to perform ultrasound-guided procedures more accurately and efficiently. This review summarizes recent advances in ultrasound-guided procedures for musculoskeletal diseases and provides a comprehensive overview of the utilization of AI/DL in ultrasound for musculoskeletal medicine, particularly focusing on ultrasound-guided surgery.

The joint extraction of entities and relations is a critical task in information extraction, and its performance directly affects the performance of downstream tasks. However, existing joint extraction models based on deep learning exhibit weak processing capabilities for the phenomenon of multiple pronunciations of one character and multiple characters of one pronunciation when processing Chinese texts, resulting in performance loss. To address these issues, this paper introduces part-of-speech (POS) and pinyin features to aid the model in learning semantic features that are more contextually appropriate. A Chinese Joint Entity and Relation Extraction Model based on Progressive Contrastive Learning and Heterogeneous Feature Fusion is proposed (CJE-PCHF). During model training, an interactive fusion network based on progressive contrastive learning is employed to learn the dependencies between pinyin, POS, and semantic features. This guides the model in heterogeneous feature fusion, capturing higher-order semantic associations between heterogeneous features. On the commonly used DuIE evaluation dataset for joint extraction, this model achieved a significant improvement, with the F1 score increasing by 5.4% compared to the benchmark model CasRel.

This paper presents a methodology based on deep learning models and metaheuristic algorithms for the optimization of airfoils for the design of aircraft wings with large endurance. The use of AZTLI-NN (a neural network with an architecture composed of a multilayer perceptron and a variational autoencoder) is implemented for the prediction of graphs of the aerodynamic coefficients of the airfoil as a function of the angle of attack. This neural network presents good predictions of the aerodynamic coefficients, similar to the coefficients obtained with computational fluid dynamics simulations. AZTLI-NN in combination of metaheuristic algorithms and the CST profile parameterization method show excellent performance in single-objective and multi-objective profile optimization tasks.

Coffee is one of the most valuable agricultural products worldwide, and it is crucial to have efficient tools to obtain reliable information about production. This study aims to estimate coffee plantation production using segmentation and deep learning techniques in RGB images. Photographs of coffee plants were taken in Tabaconas, San Ignacio-Cajamarca, to create a dataset of crops during the harvest stage. The images were segmented to detect coffee fruits. A deep learning method was developed with YOLOv5 to detect the fruits and OpenCV to count them. The results showed that YOLOv5 achieved an accuracy of 97.25%, a recall of 95.77%, and an F1-Score of 96.37%, demonstrating high reliability in detecting coffee fruits. The average detection time per image was 17.9 seconds. The metrics were evaluated using a confusion matrix, highlighting the model's good performance. In conclusion, segmentation and deep learning techniques, along with counting algorithms developed with OpenCV, proved effective for estimating coffee production. This approach provides a valuable tool for farmers, improving crop management and facilitating decision-making in precision agriculture.

The National Institute of Health Stroke Scale (NIHSS) is used worldwide to classify stroke severity as ‘mild’, ‘moderate’ or ‘severe’ based on neurological impairment. Yet stroke survivors argue that the classification of ‘mild’ does not represent the holistic experience and impact of stroke on their daily lives. In this observational cohort study, we aimed to identify different types of impairment among stroke survivors classified as mild. We used mild stroke survivors’ data from the START longitudinal stroke cohort (n=73) with measures related to sensorimotor, cognition, depression, functional disability, physical activity, work and social adjustment over 12 months. Given the multi-source, multi-granular and unlabelled nature of data, we utilised a structure-adapting, unsupervised machine learning approach, the Growing Self-organising Map (GSOM) algorithm to generate distinct clinical profiles. These diverse impairment profiles revealed that mild stroke survivors experience varying degrees of impairment and impact (cognitive, depression, physical activity, work/social adjustment) at different time points, despite the uniformity implied by their NIHSS-classified ‘mild’ stroke. This emphasises the necessity of creating a holistic and comprehensive representation of mild stroke survivors’ needs over the first-year post-stroke to improve rehabilitation and post-stroke care.

As split learning (SL) becomes popular for addressing data privacy and resource limitation issues in edge model training process, it is crucial to pre-validate whether the extensive use of wireless and computing resources in SL can achieve the expected training latency and convergence. While digital twin network (DTN) can potentially estimate network strategy performance in pre-validation environments, they are still in their infancy for SL tasks, facing challenges like unknown non-i.i.d. data distributions, inaccurate channel states, and misreport resource availability across devices. To address these challenges, this paper proposes a TransNeural algorithm for DTN pre-validation environment to estimate SL latency and convergence. First, the TransNeural algorithm integrates transformers to efficiently model data similarities between different devices, considering different data distributions and device participate sequence greatly influence SL training convergence. Second, it leverages neural network to automatically establish the complex relationships between SL latency and convergence with data distributions, wireless and computing resources, dataset sizes, and training iterations. Deviations in user reports are also accounted for in the estimation process. Simulations show that the TransNeural algorithm improves latency estimation accuracy by 13.44% and convergence estimation accuracy by 116.74% compared to traditional equation-based methods.

There are clear signs that the COVID-19 pandemic has had a straining impact on the higher education sector in South Africa and the far reaches of the world. This chapter examines (Science, Technology, Engineering, Mathematics) STEM lecturers’ experiences with digital assessments and perspectives on the continuity of digital transformation in the higher education sector in the post-COVID-19 era at one of South Africa’s rural universities. In 2022, a survey of ten (10) lecturers was conducted and the reports were also consulted by four (4) e-learning practitioners to obtain their views on the use of online learning and contact courses in the post-pandemic period. A qualitative research approach was used to understand the puzzling issues faced by STEM lecturers at a previously disadvantaged institution in Limpopo Province. The results of this study show that there is a puzzling conundrum that hinders the integration of effective online learning. Furthermore, online education as the new normal in the post-COVID-19 era seems unattainable due to extremely complex and difficult-to-understand mathematical symbols. Software and tools proved to be limitations in terms of establishing an interactive learning environment for students and lecturers on online learning platforms. Lecturers’ use of learning and teaching platforms deteriorated due to numerous unknown challenges, but also the tightening of COVID-19 restrictions. Furthermore, the results showed that science and mathematics lecturers believe that contact learning remains irreplaceable across generations and eras as some are not technology enthusiasts. This paper recommends that the lack of technological systems as well as technological resistance and reluctance to adopt transformative pedagogy and innovative practices, should not be viewed as a thorny issue to end the dominance of online education in STEM courses. Keywords: connectivism, Learning Management Systems, affordances, technological resistance, Moodle, transformative pedagogy

Named Entity Recognition (NER) serves as a fundamental and pivotal stage in the development of various knowledge-based support systems, including knowledge retrieval and question answering systems. In the domain of pig diseases, Chinese NER models encounter several challenges such as the scarcity of annotated data, domain-specific vocabulary, diverse entity categories, and ambiguous entity boundaries.To address these challenges, a corpus, labeled datasets and a lexicon specific to pig diseases for Chinese named entity recognition were constructed. Subsequently, a Pig Disease Chinese Named Entity Recognition (PDCNER) model was proposed. The model integrates external lexicon knowledge of pig disease by employing Lexicon-enhanced BERT and enhance feature representation by incorporating contrastive learning. Experimental results show that the model achieved the best recognition results, with a precision of 86.92%, a recall of 85.08%, and an F1-score of 85.99% respectively. Furthermore, the model exhibits robustness and generalizability across few-shot and publicly available datasets. Experimental results illustrate the proposed model could effectively identify Chinese named entities of pig diseases, outperforming several existing baseline methods. Moreover, the proposed model can be extended to other animal disease domains, such as chicken and cattle, thereby facilitating seamless adaptation for named entity identification across diverse contexts.

In order to shorten the detection time and improve the average precision on embedded devices, A lightweight and high accuracy model is proposed for passion fruit in complex environments (backlight, occlusion, overlap, sunny, cloudy, rainy). Firstly, replacing the backbone network of YOLOv5 with a lightweight GhostNet model reduces the number of parameters and computation while improving detection speed. Secondly, a new feature branch is added to the GhostNet network, and the feature fusion layer in the neck network is reconstructed to effectively combine the lower-level and higher-level features, which not only improves the accuracy of the model but also maintains its lightweight. Finally, the knowledge distillation methods are used to transfer the knowledge from the more capable teacher model to the less capable student model, which significantly improving the detection accuracy. The improved model is denoted as G-YOLO-NK. The average accuracy of the G-YOLO-NK network is 96.00%, which is 1.00% higher than the original YOLOv5s model. Furthermore, the improved model size is 7.14MB, reduced to half of the original model, and the real-time detection frame rate is 11.25 FPS on the Jetson Nano. Compared to the state-of-the-art model, the proposed model outperforms them in terms of average precision and detection performance. The present work provides an effective model for real-time detection of passion fruits in complex orchard scenes, which can provide valuable technical support for the development of orchard picking robots and greatly improve the intelligence level of orchards.

The detection accuracy of bridge superficial defect using the deep neural network approach decreases significantly under light variation and weak texture condition. To address these issues, an enhanced intelligent detection method based on the YOLOv8 deep neural network is proposed in this study. Firstly, multi-branch coordinate attention (MBCA) is proposed to improve the accuracy of coordinate positioning by introducing a global perception module in coordinate attention mechanism. Furthermore, a deformable convolution based on MBCA is developed to improve the adaptability for complex feature shapes. Lastly, the deformable convolutional network-attention-YOLO (DAC-YOLO) detection algorithm is formed by replacing the deep C2F structure in the YOLOv8 architecture with deformable convolution. A supervised dataset consisting of 4794 bridge surface damage images is employed to verify the proposed method, and results show that it achieves improvements of 2.0% and 3.4% in mAP and R. Meanwhile, the model complexity decreases by 1.2G, increasing the detection speed by 3.5/f·s-1.

Digital twin technology is revolutionizing traditional manufacturing paradigms. In modern manufacturing systems, digital twin technology is fraught with challenges due to the scarcity of labeled data. Specifically, existing supervised machine learning algorithms, with their reliance on voluminous training data, find their applicability constrained in real-world production settings. This paper introduces an unsupervised 3D reconstruction approach tailored for industrial applications, aimed at bridging the data void in creating digital twin models. Our proposed model, by ingesting high-resolution 2D images, autonomously reconstructs precise 3D digital twin models without the need for manual annotations or prior knowledge. Through comparisons with multiple baseline models, we demonstrate the superiority of our method in terms of accuracy, speed, and generalization capabilities. This research not only offers an efficient approach to industrial 3D reconstruction but also paves the way for the widespread adoption of digital twin technology in manufacturing.

In high-risk railway construction, personal protective equipment monitoring is critical but challenging due to small and frequently obstructed targets. We propose YOLO-EA, an innovative model that enhances safety measure detection by integrating ECA into its backbone's convolutional layers, improving discernment of minuscule objects like hardhats. YOLO-EA further refines target recognition under occlusion by replacing GIoU with EIoU loss. YOLO-EA's effectiveness was empirically substantiated using a dataset derived from real-world railway construction site surveillance footage. It outperforms YOLOv5, achieving 98.9% precision and 94.7% recall, up 2.5% and 0.5% respectively, while maintaining real-time performance at 70.774 fps. This highly efficient and precise YOLO-EA holds great promise for practical application in intricate construction scenarios, enforcing stringent safety compliance during complex railway construction projects.

This study investigated how different gamification elements in mobile apps influence users' basic psychological needs (autonomy, competence, relatedness) and subsequent engagement outcomes. Survey data was analyzed using PLS-SEM. Social gamification elements enhanced autonomy and competence needs, while immersive elements boosted autonomy and relatedness. Achievement/progression components increased competence and relatedness perceptions. Interestingly, personal traits did not significantly impact psychological needs. Crucially, satisfying autonomy and relatedness predicted higher user satisfaction and continued usage intentions, highlighting their importance for sustained engagement. Competence influenced satisfaction but not continuance intention. The findings demonstrate the motivational roles of distinct gamification features in fostering need-supportive experiences. Designers should incorporate varied social, immersive, and achievement components to address users' psychological requirements holistically. Prioritizing autonomy and relatedness support appears vital for achieving enjoyable, self-motivated, and persistent user engagement across gamified systems and domains. The study provides actionable insights for optimizing motivational affordances through psychologically-informed gamification implementations.

Multimedia resources, such as instructional videos, are currently enjoying a certain popularity in training programmes for medical and dental students. The major challenge is to create such resources that have quality content and are acceptable to students. We investigated the opinions of a sample of 551 students from 4 medical universities in Romania in order to identify the characteristics of the instructional videos that students prefer and we comparatively analysed these characteristics according to gender, age group, but also according to their general preferences for using Internet services. We used univariate (hypothesis testing) and multivariate (Two-Step Clustering) data analysis techniques and revealed three clusters of students, primarily determined by perceptions of the visual appearance of instructional videos. The structure of the clusters by gender and age group is relatively similar, but we recorded differences between them associated with students' expressed preferences for certain Internet services compared to others. Students who prefer instructional videos to contain images used only for aesthetic purposes, to fill in breaks, use Internet services mainly for communication, while students who prefer in videos the use of already drawn explanatory diagrams are slightly younger than the others and use Internet services mainly for information and communication.

The intricate relationship between Gray-Level Co-occurrence Matrix (GLCM) metrics and machine learning model performance underscores the need for rigorous dataset evaluation and selection protocols to ensure the reliability and generalizability of classification outcomes. This study involved a thorough examination of selected publicly available plant diseases datasets, with an emphasis on how well they performed as measured by GLCM metrics. After first classifying the datasets according to their GLCM metrics, dataset_2 (D2) and dataset_5 (D5) were found, respectively, to be the best-performing dataset in all GLCM analyses. The same datasets were then used to train deep learning models, and their classification performances were assessed. A noteworthy association was observed between the results of training deep learning models and the performance ratings derived from GLCM studies. More specifically, dataset_2 (D2) performed best in both GLCM analysis and deep learning model performance, indicating a strong correlation between the accuracy of classification and the textural qualities that GLCM captured. In the context of plant disease identification, in particular, these results highlight the significance of clearly defined dataset selection criteria in deep learning applications. Scholars can improve the accuracy and dependability of deep learning models for diagnosing plant diseases by giving preference to datasets with favorable GLCM metrics. The research also emphasizes the importance of texture features being taken into account in addition to conventional image features, highlighting the necessity of transparency and rigor in dataset selection procedures.

In this paper we present the exploration of indoor positioning technologies for UAVs, and navigation techniques for path planning and obstacle avoidance. The objective is to perform warehouse inventory tasks using a drone to search for barcodes or markers to identify the objects. For the indoor positioning techniques, we employ Visual-Inertial Odometry (VIO), Ultra-Wideband (UWB), AprilTag fiducial markers, and Simultaneous Localization and Mapping (SLAM). These algorithms encompass global positioning, local positioning, and pre-mapping positioning, comparing the merits and drawbacks of various techniques and trajectories. In UAV navigation, we combine SLAM-based RTAB-Map indoor mapping and navigation path planning of the ROS for indoor environments. This system enables precise drone positioning indoors and utilizes global and local path planners to generate flight paths that avoid dynamic, static, unknown, and known obstacles, demonstrating high practicality and feasibility. To achieve the warehouse inventory inspection, a reinforcement learning approach is proposed to recognize the markers by adjusting the UAV's viewpoint. We address several main problems in inventory management, including efficiently planning paths while ensuring a certain level of detection rate. Two reinforcement learning techniques, AC (Actor-Critic) and PPO (Proximal Policy Optimization), are implemented based on AprilTag identification. Testing is performed in both simulated and real-world environments, and the effectiveness of the proposed method is validated.Code is available at https://github.com/kellen080/Navigation and https://github.com/kellen080/Indoor\_Positioning.

In this paper we propose a module that uses features learned by a deep convolutional neural network to infer areas of corrosion and segment pixels to corrosion areas of inspection interest. Our segmentation module is based on eigen tree decomposition and information based decision criteria. To interrogate performance we use several state-of-the-art deep learning architectures and compare to our approach. The results indicate that our method produces better results in terms of accuracy and precision, whilst maintaining good (f-score) significance over the entire dataset.

Identification and segmentation of rock particles is very important in geology, mining, engineering construction, and environmental monitoring. Traditional methods for recognizing the rock particle characteristics are time-consuming, labor-intensive, and limited by the geographical scope of the sampling sites, which makes it more difficult to represent the spatial distribution of the rock particles accurately. Recent advancements in deep learning techniques offer promising solutions to automate this process. This study aims at utilizing state-of-the-art (SOTA) Mask R-CNN deep learning algorithm from the Detectron2 framework, to capture global features of rocks that will enable the recognition of rock particles more efficiently, just from having the rock images. These images are subject to image processing techniques such as a Gaussian filter, to denoise and smoothen the image, and an Illumination Adaptive Transformer (IAT) framework, to adjust the lighting exposure; all of which add to improve the quality of the image dataset. Afterward, the Mask R-CNN and Detectron2 models are utilized in training the images using transfer learning. Experimental results from evaluating the performance of the proposed algorithms showcase the effectiveness of the approach, thereby highlighting its potential to revolutionize rock particle segmentation across various domains.

Amid escalating urbanization, devising rational commercial space layouts is a critical challenge. Leveraging machine learning, this study uses a Back-propagation (BP) neural network to optimize commercial spaces in Weinan City's central urban area. The results indicate an increased number of commercial facilities with a trend of multi-centered agglomeration and outward expansion. Based on these findings, we propose a strategic framework for rational commercial space development emphasizing aggregation centers, development axes, and spatial guidelines. This strategy provides valuable insights for urban planners in small and medium-sized cities in the Yellow River Basin and metropolitan areas, ultimately showcasing the power of machine learning in enhancing urban planning.

The IEEE 802.11ah standard is introduced to address the growing scale of Internet of Things (IoT) applications. To reduce contention and enhance energy efficiency within the system, the restricted access window (RAW) mechanism is introduced at the medium access control (MAC) layer to manage the significant number of stations accessing the network. However, the RAW parameters need to be appropriately determined to achieve optimal network performance. In this paper, we optimize the configuration of RAW parameters in the IEEE 802.11ah-based IoT network. We analyze and propose an RAW parameters optimization problem with the objective of improving network throughput and formulate it as a Markov decision process. To cope with the complex and dynamic network conditions, we propose a proximal policy optimization (PPO)-based deep reinforcement learning (DRL) algorithm to find the optimal RAW parameters. We construct network environments with periodic and random traffic in the NS-3 simulator to validate the performance of the proposed PPO-based RAW parameters optimization algorithm. Simulation results reveal that using the PPO-based DRL algorithm, optimal RAW parameters can be obtained under different network conditions, thereby significantly improving network throughput.

This study extends the CGAN-based MODIS cloud vertical-profile (64×64-scene, about 70km width×15km height) retrieval technique developed by Leinonen et al. (2019) [1] to construct seamless 3D cloud fields for the MODIS granules [2]. Firstly, the accuracy and spatial continuity of the Leinonen et al. [1] retrievals are statistically evaluated. Then, according to the characteristics of the retrieval error, a spatially overlapping-scene ensemble generation method and a bi-directional Ensemble Binning Probability Fusion (CGAN-BEBPF) technique are developed, which improves the CGAN retrieval accuracy and support to construct seamless 3D clouds. The CGAN-BEBPF technique involves three steps: cloud masking, intensity scaling, and optimal value selection. It ensures adequate coverage of the low reflectivity areas while preserving the high reflectivity cloud cores. The technique is applied to retrieve the 3D cloud fields of Typhoon Chaba and a multi-cell convective system. The cloud structures of the CGAN-BEBPF results are highly consistent with the ground-based radar observations. It can retrieve weak clouds at the top levels of convective storms and hurricanes that were missed by ground-based radars and fill the gaps of the ground-based radar lower-level PPI scan. Overall, CGAN-BEBPF can be automated to retrieve the rich informative 3D structures of typhoons and severe convective systems over the oceans along the MODIS swath, which certainly presents great value for improving maritime and near-shore typhoons and convection prediction and other cloud-sensitive applications.

This study was to identify clinical cancer biomarkers for recurrent gastric cancer survivors using artificial intel-ligence. From a hospital-based cancer registry database in Taiwan, the datasets of the incidence of recurrence and clinical risk features were included in 2476 gastric cancer survivors. We benchmarked Random forest with MLP, C4.5, AdaBoost, and Bagging algorithms on metrics and leveraged synthetic minority oversampling technique (SMOTE) for imbalanced dataset issues, cost-sensitive learning for risk assessment, and SHapley Additive ex-Planations (SHAP) for feature importance analysis in this study. Our proposed Random forest outperformed the other models with an accuracy of 87.9%, a recall rate of 90.5%, an accuracy rate of 86% and F1 of 88.2% on re-current category by a 10-fold cross-validation in a balanced dataset. We identified clinical features of recurrent gastric cancer, which are the top five features, stage, number of regional lymph node involvement, Helicobacter pylori, BMI(body mass index), and gender, which significantly affect the prediction model's output, are worth paying attention to in the following causal effect analysis. Using an artificial intelligence model, the risk factors for recurrent gastric cancer could be identified and cost-effectively ranked according to their feature importance. In addition, they should be crucial clinical features to provide physicians with the knowledge to screen high-risk patients in gastric cancer survivors as well.

The research of object classification and part segmentation is a hot topic in computer vision. A considerable number of studies have been carried out about deep learning on 3D point clouds. However,it is challenging to achieve effective feature learning due to sparsity of point clouds. Recently, a variety of Transformers have been adopted to improve point cloud processing and display great potential. Nevertheless, large numbers of Transformer layers tend to incur huge computational and memory costs. PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks, this does not mean that PointNet++ has no potential.Thus, this paper offer two major contributions that significantly improve PointNet++ performance. Firstly, we introduce a novel contextual feature extraction (CFE) block that significantly enhances the feature extraction capabilities of PointNet++ networks. Secondly, to further enhance feature fusion, we seamlessly integrate a mutual learning (ML) block into the network architecture. By embedding these two innovative blocks within each layer of the network, we not only enrich the network's functionality but also impart it with greater robustness and adaptability. The specific experiments were conducted on the S3DIS (6-fold cross-validation) and Modelnet40 datasets with 86.5% and 92.7% accuracy, respectively, which proved that our model is comparable or even better than most existing methods for classification and segmentation tasks.

This paper addresses challenges and solutions in urban development and infrastructure resilience, particularly in the context of Japan's rapidly urbanizing landscape. It explores the integration of smart city concepts to combat land subsidence and liquefaction, phenomena highlighted by the 2011 Great East Japan Earthquake. Using advanced technologies such as smart sensing and predictive analytics through kriging and ensemble learning, the study aims to improve the accuracy of geotechnical investigations and urban planning. By analyzing data from 433 geotechnical surveys in Setagaya, Tokyo, it develops predictive models to accurately determine the depth of bearing layers critical to urban infrastructure. The results demonstrate the superiority of ensemble learning in predicting the depth of bearing layers, with significant implications for smart city development and the sustainability of urban environments. This interdisciplinary approach not only seeks to mitigate risks associated with geological disturbances, but also promotes sustainable urban growth that prioritizes safety and prosperity. Through advanced technology and comprehensive research, the study underscores the potential of smart cities to address urban complexities and ensure a resilient, sustainable future.

This study introduces SkinLiTE, a lightweight supervised contrastive learning model, tailored to enhance the detection and typification of skin lesions in dermoscopic images. The core of SkinLiTE lies in its unique integration of supervised and contrastive learning approaches, which leverages labeled data to learn generalizable representations. This approach is particularly adept at handling the complexities and imbalances inherent in skin lesions datasets. The methodology encompasses a two-phase learning process. In the first phase, SkinLiTE utilizes an encoder network and a projection head to transform and project dermoscopic images into a feature space where contrastive loss is applied, focusing on minimizing intra-class variations while maximizing inter-class differences. The second phase freezes the encoder's weights, leveraging the learned representations for classification through a series of dense and dropout layers. The model was evaluated using three datasets from Skin Cancer ISIC 2019-2020, covering a wide range of skin conditions. SkinLiTE demonstrated superior performance across various metrics—accuracy, AUC , and F1 score—particularly when compared with traditional supervised learning models. Notably, SkinLiTE achieved an accuracy of 0.9087 using AugMix augmentation for binary classification of skin lesions. It also showed comparable results with the state-of-the-art approaches of ISIC challenge without relying on external data, underscoring its efficacy and efficiency. The results highlight the potential of SkinLiTE as a significant step forward in the field of dermatological AI, offering a robust, efficient, and accurate tool for skin lesion detection and classification. Its lightweight architecture and ability to handle imbalanced datasets make it particularly suited for integration into Internet of Medical Things environments, paving the way for enhanced remote patient monitoring and diagnostic capabilities. This research contributes to the evolving landscape of AI in healthcare, demonstrating the impact of innovative learning methodologies in medical image analysis.

Evolutionary algorithms and swarm intelligence algorithms find applicability in reinforcement learning of neural networks due to their independence from gradient-based methods. To achieve successful training of neural networks using these algorithms, careful considerations must be made to select appropriate algorithms due to the availability of various algorithmic variations. In Part1, 2 and 3, the author previously reported experimental evaluations on Evolution Strategy, Genetic Algorithm, and Differential Evolution for reinforcement learning of neural networks, utilizing the Acrobot control task. This article constitutes Part4 of the series of comparative research. In this study, Particle Swarm Optimization is adopted as an instance of major swarm intelligence algorithms. The experimental result shows that PSO performed worse than all of DE, GA and ES. The difference between PSO and DE was statistically significant (p<.01). In addition, PSO exhibited lower capability in exploring solutions in high-dimensional search spaces than DE, GA, and ES did. A larger swarm size compensated for the weakness of PSO in global exploration, thus making itself more beneficial than a larger number of swarm search iterations.

Classifying network flow subsequences in an Industrial IoT gateway is an effective method for identifying Industrial IoT faults. This paper proposes a subsequence classification algorithm SSGBUL-IKNN based on unsupervised learning encoding to address the problem of low classification accuracy. Firstly, we built a network module based on unsupervised learning to encode the flow sequence of the Industrial IoT gateway. In the encoding module, a subsequence calibration algorithm controls the increasing error during the coding process. Then, the specific fault type is obtained through an improved KNN classification algorithm based on the indication distance source from the integrated coding sequences converted by multi-dimensional network flow sequences. The test result on three Industrial IoT datasets of a sewage treatment plant shows that the accuracy of SSGBUL-IKNN in this paper exceeds 92%, significantly higher than the algorithm DTW and TSF. It reaches the classification requirements of Industrial IoT fault diagnosis.

In the dynamic landscape of modern education, characterized by an increasingly active involvement of IT technologies in learning, the imperative to transfer to students the skills necessary to integrate Artificial Intelligence (AI) into the process represents an important goal. This paper presents a novel framework for knowledge transfer, diverging from traditional programming language-centric approaches by integrating PSoC 6 microcontroller technology. This framework establishes a cyclical learning cycle encompassing theoretical fundamentals and practical experimentation, fostering AI literacy at the edge. Through a structured combination of theoretical instruction and hands-on experimentation, students develop proficiency in understanding and harnessing AI capabilities. Emphasizing critical thinking, problem-solving, and creativity, this approach equips students with the tools to navigate the complexities of real-world AI applications effectively. By leveraging PSoC 6 as an educational tool, a new generation of individuals is efficiently cultivated with essential AI skills. These individuals are adept at leveraging AI technologies to address societal challenges and drive innovation, thereby contributing to long-term sustainability initiatives. Specific strategies for experiential learning, curriculum recommendations, and results of knowledge application are presented, aimed at preparing students to excel in a future where AI will be omnipresent and indispensable.

Recently, interest in STEM education has grown among researchers and educators, also considering the skills required to address the challenges of the 21st century. Supporting learning in STEM subjects is an open challenge, especially during secondary education, which is reflected in the implementation of innovative pedagogical practices, including approaches focused on Game-Based Learning (GBL). This study analyzed the main issues addressed by research on game-based educational approaches applied to STEM teaching and learning in secondary school and their evolving trends. A text analysis of abstracts published in the past decade was conducted using T-lab software. The “Word Analysis” function was used for preliminary visual mapping; then the “Specificity Analysis” and “Thematic Analysis of Elementary Contexts” functions were applied to explore changes in research directions and to map the themes covered by the most recent studies. The results showed that the implementation of games in STEM disciplines is a promising area of inquiry. A shift in research directions also emerged, currently more focused on studying how GBL can foster engagement and the emotional component of learning. Adapting to rapidly changing technology and integrating essential skills such as coding and computational thinking are additional challenges that the research community is facing.

The strong competition in the automotive industry has required manufacturers to implement lean production, both with methods and techniques specific to Industry 4.0. At the same time, universities must provide graduates with specific skills for applying these new production methods and techniques. In this context, a Lean Learning Factory was developed in the Pitesti University Center, which allows students to learn, experiment, and research, in an environment similar to that of enterprises, the new Lean Manufacturing methods and techniques, and Industry 4.0. The research presented in this study had as its objective identifying the minimum number of repetitions necessary to train operators who serve two differently organized workstations, one classic, the other including digital techniques, but on which the same assembly operation is performed. Several indicators were considered in the analysis, such as the number of errors, the number of stops, the effective duration of the work cycle, and the percentage ratio between the standard duration of cyclical activities and the effective duration of the work cycle. The evolution of these indicators was mathematically modelled by regression functions, using the least squares method. The obtained results also highlight the usefulness of applying the DOJO method as a Lean manufacturing-specific learning technique and the efficiency of implementing digital techniques in work organization.

Existing studies often lack a systematic solution for Unmanned Aerial Vehicles (UAV) inspection system, which hinders their widespread application in crack detection. To enhance its practicality, this study proposes a formal and systematic framework for UAV inspection systems, specifically designed for automatic crack detection and pavement distress evaluation. The framework integrates UAV data acquisition, deep learning based crack identification, and road damage assessment in a comprehensive and orderly manner. Firstly, the flight control strategy is presented, and road crack data is collected using the DJI Mini 2 UAV imagery, establishing a high-quality UAV crack image datasets with ground truth information. Secondly, a validation and comparison study is conducted to enhance the automatic crack detection capability and provide an appropriate deployment scheme for UAV inspection systems. This study develops automatic crack detection models based on mainstream deep learning algorithms(namely, Faster-RCNN, YOLOv5s, YOLOv7-tiny, and YOLOv8s) in urban road scenarios. The results demonstrate that the Faster-RCNN algorithm achieves the highest accuracy and is suitable for online data collection of UAV and offline inspection at work stations. Meanwhile, the YOLO models, while slightly lower in accuracy, are the fastest algorithm and are suitable for lightweight deployment of UAV with online collection and real-time inspection. Quantitative measurement methods for road cracks are presented to assess road damage, which will enhance the application of UAV inspection systems and provide factual evidence for maintenance decisions made by road authorities.

In this review paper, we discuss the use of BERT, one of the most well-liked deep learning-based language models. The model's operation mechanism, key areas of applicability to text analytics tasks, comparisons with related models for each activity, and a description of certain proprietary models are all covered in this work. The data from several dozen original scientific studies that have been published in the last few years and have garnered the greatest interest from the scientific community were systematized in order to prepare this review. All researchers and students who wish to learn about the most recent developments in the field of natural language text analysis may find this survey helpful. Bidirectional Encoder Representations from Transformers, or BERT for short, is the subject of a thorough investigation that we present. The area of natural language processing holds significant importance in the creation of intelligent systems. To do a variety of activities, one must comprehend the sentence's correct meaning in order to produce the desired result. Computers have a hard time understanding languages because of how context constantly changes. The main challenge in natural language processing tasks is getting computers to understand text context, and BERT is seen as a revolution in this regard. It picks up the language and its meaning in a manner that is quite similar to how the human brain processes meaning from sentences. Its capacity to identify a word from both the left and right contexts of a sentence makes it special. A new era in the perception and comprehension of natural languages has been ushered in with the development of BERT, which could help computers understand natural languages more fully. This study aims to provide readers with a deeper knowledge of the BERT language model and how it is applied to different NLP tasks.

Federated learning trains a neural network model using the client's data to maintain the benefits of centralized model training, while maintaining the privacy. However, if the client data are not independently and identically distributed (non-IID) because of different environments, the accuracy of the model may suffer from client drift during training owing to discrepancies in each client's data. This study proposes a personalized federated learning algorithm based on the concept of multitask learning to divide each client model into two layers: a feature extraction layer and a category prediction layer. The feature extraction layer maps the input data to a low-dimensional feature vector space. Furthermore, the parameters of the neural network are aggregated with those of other clients using an adaptive method. The category prediction layer maps low-dimensional feature vectors to the label sample space, with its parameters remaining unaffected by other clients to maintain client uniqueness. The proposed personalized federated learning method produces faster learning model convergence rates and higher accuracy rates for the non-IID datasets in our experiments.

The accurate and timely assessment of lymph node involvement is paramount in the management of patients with malignant tumors, owing to its direct correlation with cancer staging, therapeutic strategy formulation, and prognostication. Dual-energy computed tomography (DECT), as a burgeoning imaging modality, has shown promising results in the diagnosis and prediction of preoperative metastatic lymph nodes in recent years. This article aims to explore the application of DECT in identifying metastatic lymph nodes (LNs) across various cancer types, including but not limited to thyroid carcinoma (focusing on papillary thyroid carcinoma), lung cancer, and colorectal cancer. Through this narrative review, we aim to elucidate the clinical relevance and utility of DECT in the detection and predictive assessment of lymph node metastasis in malignant tumors, thereby contributing to the broader academic discourse in oncologic radiology and diagnostic precision.

Scaffoldings play a critical role as temporary structures in supporting construction processes. Accidents at construction sites frequently stem from issues related to scaffoldings, including insufficient support caused by deviations from the construction design, insecure rod connections, or absence of cross bracing, which result in uneven loading and potential collapse, leading to casualties. In this study, we introduce a deep-learning-based, augmented reality (AR)-enabled system called scaffolding assembly deficiency detection system (SADDS) to assist field inspectors in identifying deficiencies in scaffolding assemblies. Inspectors have the flexibility to utilize SADDS through various devices, such as video cameras, mobile phones, or AR goggles (i.e., Microsoft HoloLens 2), for automated detection of deficiencies in scaffolding assemblies. The training test yielded satisfactory results, with a mean average precision of 0.89 and individual precision values of 0.96, 0.82, 0.90, and 0.89 for “qualified” frames and frames with the “missing cross-tie rod,” “missing lower-tie rod,” and “missing footboard” deficiencies, respectively. Field tests conducted at two construction sites demonstrated improved system performance compared to that in the training test. However, these field tests also revealed certain limitations of the SADDS system.

The COVID-19 pandemic necessitated a profound shift to online education, impacting students across various educational levels. This research, drawing from a comprehensive survey of 1,000,000 students, delves into the surge in demand for online education during the pandemic and its potential enduring implications. The study scrutinizes factors steering this transition, the perceived effectiveness of online education, challenges encountered by students, and their anticipated preferences for the future. Results unveil nuanced perspectives among K-12, undergraduate, and postgraduate students, with safety, flexibility, and accessibility emerging as pivotal influencers. The findings offer valuable insights into challenges faced and future preferences, enlightening educational stakeholders about the dynamic needs of students and contributing to the ongoing evolution of the post-pandemic educational landscape.

The author previously reported an experimental result of evolutionary reinforcement learning of neural network controllers for the pendulum task. In the previous work, a conventional multilayer perceptron was employed in which connection weights were real numbers. In this study, the author experimentally applies an evolutionary algorithm to the reinforcement training of binary neural networks. In both studies, the same task and the same evolutionary algorithm are utilized, i.e. the pendulum control problem and Evolution Strategy respectively. The only differences lie in the memory size per connection weight and the model size of the neural network. The findings from this study are (1) the performance of the binary MLP with 32 hidden units was inferior to that of the real-valued MLP with 16 hidden units; however, this difference was not statistically significant (p >.05); (2) the trained binary MLP successfully swung the pendulum swiftly into an inverted position and maintained its stability after inversion, as the real-valued MLP had done; and (3) the memory size required to record the binary MLP with 32 hidden units is 3.1% or 6.2% of the memory size required to record the real-valued MLP with 16 hidden units.

In this study, we present a federated learning approach that combines a multi-branch network and the Oort client selection algorithm to improve the performance of federated learning systems. This method successfully addresses the significant issue of non-iid data, a challenge not adequately tackled by the commonly used MFedAvg method. Additionally, one of the key innovations of this research is the introduction of uniformity, a metric that quantifies the disparity in training time amongst participants in a federated learning setup. This novel concept not only aids in identifying stragglers but also provides valuable insights into assessing the fairness and efficiency of the system. Experimental results underscore the merits of the integrated multi-branch network with the Oort client selection algorithm and highlight the crucial role of uniformity in designing and evaluating federated learning systems.

Background: Genome-wide association studies (GWAS) have shed light on various complex diseases and traits, by detecting more than 400,000 associated genetic loci. This number is expected to drastically increase because of the use of novel artificial intelligence methods offering new ways to study the effects of variants. Deep learning using artificial neural networks (ANN) is a sub-field of artificial intelligence, which simulates how the human brain learns. We aimed at assessing the potential of deep learning in human genetic studies of Alzheimer’s Disease (AD) and how these compare to the traditional statistical methods used in GWAS, by simultaneously testing the two approaches on the same dataset, while discovering new genetic loci associated to AD. Methods: To address this aim, phenotypic and genome-wide SNP data from the UK Biobank was analysed on a binary outcome, AD diagnosis, in two different data balance options, of one-to-one and one-to-two case-control datasets, using 2,764 cases vs 2,764 controls and 5,528 controls respectively matched on gender, age, ethnicity, PC1-20 and genotyping array. Genetic data handling and GWAS were performed using PLINK, whereas neural networks were trained using GenNet, a new ANN tool, with the same datasets, separated into training (60%), validation (20%) and test (20%) sets. Neural network layers were determined using biological knowledge, by annotating SNPs to genes and genes to AD related pathways, using ANNOVAR annotations followed by GeneSCF and KEGG. Results: Significant associations were detected between four SNPs linked to two different genes and AD for the 1 to 1 case-control study design and six SNPs linked to four different genes for the 1 to 2 case-control study design by using PLINK. All identified regions have been previously associated to AD. GenNet identified twelve SNPs on seven genes to be associated with AD, all with biological plausibility, achieving an AUC of 0.80 when using three biologically determined layers and 0.73 when using two layers at the neural networks. No common top SNPs were identified between the machine learning and GWAS models. Conclusion: This is one of the first studies attempting to compare the traditional GWAS to more sophisticated state-of-art methods for understanding the genetic architecture of complex phenotypes using the same dataset. More systematic comparisons with such approaches on real data are needed to enable best practises for machine learning in the analysis of genome-wide genetic data.

Audio classification using deep learning models, essential for applications like voice assistants and music analysis, faces challenges when deployed on edge devices due to their limited computational resources and memory. Achieving a balance between performance, efficiency, and accuracy is a significant obstacle in optimizing these models for such constrained environments. In this investigation, we evaluate diverse deep learning architectures, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for audio classification tasks on the ESC 50, UrbanSound8k, and Audio Set datasets. Our empirical findings indicate that Mel Spectrograms outperform raw audio data, attributing this enhancement to their synergistic alignment with advanced image classification algorithms and their congruence with human auditory perception. To address the constraints of model size, we apply model compression techniques, notably magnitude pruning, Taylor Pruning, and 8-bit quantization. The research demonstrates that a hybrid pruned model achieves a commendable accuracy rate of 89 percent, which, although marginally lower than the 92 percent accuracy of the uncompressed CNN, strikingly illustrates an equilibrium between efficiency and performance. Subsequently, we deploy the optimized model on Raspberry Pi 4 and NVIDIA Jetson Nano platforms for audio classification tasks. These findings highlight the significant potential of model compression strategies in enabling effective deep learning applications on resource-limited devices, with minimal compromise on accuracy.

Capsizing accidents are regarded as marine accidents with a high rate of casualties per accident. Approximately 89% of all such accidents occur in small ships (vessels with gross tonnage less than 10 tons). Stability calculations are critical for assessing the risk of capsizing incidents and evaluating a ship's seaworthiness. Despite the high frequency of capsizing accidents involving small ships, they are generally exempt from adhering to stability regulations, thus remaining systemically exposed to the risk of capsizing. Moreover, the absence of essential design documents complicates direct ship stability calculations. This study utilizes hull form feature data—obtained from the general arrangement of small ships—as input for a deep learning model. The model is structured as a multilayer neural network and aims to infer hydrostatic curves, which is required data for stability calculations.

The rapid expansion of social media and instant messaging applications, such as WhatsApp, has transformed how individuals and organizations communicate and engage. This think piece explores the potential of integrating WhatsApp as a customer relationship management (w-CRM) tool within the education sector to foster and sustain long-term relationships among students, teaching staff, and non-teaching staff. By leveraging real-time features and the widespread use of WhatsApp, educational institutions can create a more interactive and dynamic learning environment, benefiting all stakeholders involved. The literature highlights the importance of establishing clear frameworks for mutual engagement and interaction and the potential of w-CRM to improve communication between students' families and educational institutions. There are potential risks associated with the pervasive use of WhatsApp, and call for future research to explore strategies for mitigating these risks while maximizing the benefits of w-CRM in the education sector. Longitudinal studies are recommended to evaluate the long-term impact of w-CRM on stakeholder relationships, student outcomes, and overall institutional performance.

Due to the recent trend of unmanned economy, retail stores have gradually reduced their service and cashier manpower. The retail product recognition becomes one of key issues for unmanned shopping. Although the success of deep neural networks has made object recognition feasible in a variety of applications, it still struggles to perform well on a large number of classes of retail products. In this paper, we propose an improved ensemble learning-based approach for retail product recognition. In the proposed approach, the object classification network is first improved through feature extraction and block attention. An ensemble model is then built by integrating multiple network models and using loss selection as model weights. In the experiments, the feasibility of our ensemble learning-based approach has been evaluated through many production items. The results demonstrate the effectiveness of the proposed approach compared with previous retail product recognition methods.

Academic researchers publish their work in various formats, such as papers, patents, and research reports, on different academic sites. When searching for a particular researcher's work, it can be challenging to pinpoint the right individual, especially when there are multiple researchers with the same name. In order to handle this issue, we propose a name disambiguation scheme of researchers with the same name based on heterogeneous academic sites. The proposed scheme collects and integrates research results from these varied academic sites, focusing on attributes crucial for disambiguation. It then employs clustering techniques to identify individuals who share the same name. Additionally, the proposed rule-based algorithm name disambiguation method and the existing deep learning-based identification method. This approach allows for the selection of the most accurate disambiguation scheme, taking into account the metadata available in the academic sites, using a multiclass classification approach. To demonstrate the effectiveness of the proposed method, we conduct various performance evaluations, measuring accuracy, recall, and the F1-measure, highlighting the scheme's superior performance in the name disambiguation.

Embracing innovative digital technologies within educational systems is essential for overcoming challenges in modern learning environments, especially in the post-COVID-19 era. Teaching sustainability management in higher education institutions with innovative digital tools plays a fundamental role in the transition toward sustainable societies. Suitable game design elements play a significant role in facilitating sustainable learning. This study explored the effectiveness of incorporating business simulation games with project-based learning (PBL) in a flipped classroom setting. This approach was adopted within the context of a university cross-border e-commerce course to prepare students for acquiring 21st -century skills as higher-order thinking skills in a rapidly changing educational landscape. A quasi-experimental method was employed, involving a total of 60 university students from China's Zhejiang Province. Participants completed an online questionnaire designed to assess their learning engagement across three dimensions (cognitive, emotional, and behavioral) as well as their higher-order thinking skills (problem-solving, critical thinking, and creativity). The results show that the business simulation games combined with flipped classroom learning had a significantly positive impact on students’ learning outcomes, enhancing their problem-solving, critical thinking, and creative capabilities. Importantly, this approach also improved student engagement and promoted sustainable practices by applying real-life scenarios in an interactive environment. We conclude that business simulation games integrated with project-based learning (PBL) in flipped classroom settings represent a valuable educational approach. This approach not only enhances learning engagement but also fosters the development of higher-order thinking skills, encouraging students to adopt sustainable learning practices.

Generative AI has gained enormous interest nowadays due to new applications like chatGPT, DALL E, Stable Difussion and Deep Fake. Particularly DALL E, Stable Difussion and others (Adobe Firefly, ImagineArt...) are able to create images from a text prompt and are also able to recreate real photographs. Due to this fact, intense research has arisen to create new image forensics applications able to distinguish between real captured images and videos and artificial ones. Detecting forgeries made with Deep Fake is one of the most researched issues. This paper is about another kind of forgery detection. The purpose of this research aims to detect photo realistic AI created images versus real photos coming from a physical camera. For this purpose, techniques that perform a pixel level feature extraction are used. First one is Photo Response Non-Uniformity (PRNU). PRNU is a special noise due to imperfections on the camera sensor that is used for source camera identification. The underlying idea is that AI images will have a different PRNU pattern. Second one is Error level analysis (ELA). This is other type of feature extraction traditionally used for detecting image editions. In fact, ELA is being used nowadays by photographers to detect manually AI created images. Both kinds of features are used to train Convolutional Neural Networks to differentiate between AI images and real photographs. Good results are obtained achieving accuracy rates over 95%. Both extraction methods are carefully assessed by computing precision/recall and F1-score measurements.

Global Earth Observation (EO) is becoming increasingly important in understanding and addressing critical aspects of life on our planet about environmental issues, natural disasters, sustainable development and others. EO plays a key role in making informed decisions on applying or reforming land use, responding to disasters, shaping climate adaptation policies etc. EO is also becoming a useful tool for helping professionals make the most profitable decisions, e.g., in real estate or the investment sector. Finding similarities in landscapes may provide useful information regarding applying contiguous policies, taking alike decisions or learning from best practices on events and happenings that have already occurred in similar landscapes in the past. However, current applications of similar landscape retrieval are limited by moderate performance and the need for time-consuming and costly annotations. We propose splitting the similar landscape retrieval task into a set of smaller tasks that aim at identifying individual concepts inherent to satellite images. Our approach relies on several models trained with Unsupervised Representation Learning (URL) on Google Earth images to identify these concepts. We show the efficacy of matching individual concepts for tackling the task of retrieving similar landscape(s) to a user-selected satellite image with a proof-of-concept application of the proposed approach on the geographical territory of the Republic of Cyprus. Our results demonstrate the efficacy of breaking up the landscape similarity task into individual concepts closely related to remote sensing instead of trying to capture all concepts and image semantics with a single model like a single RGB semantics model.

Deep networks-based hashing has gained significant popularity in recent years, particularly in the field of image retrieval. However, most existing methods only focus on extracting semantic information from the final layer, disregarding valuable structural information that contains important semantic details crucial for effective hash learning. To address this limitation and improve image retrieval accuracy, we propose a novel deep hashing method called Deep Supervised Hashing by Fusing Multiscale Deep Features (DSHFMDF). Our approach involves extracting multiscale features from multiple convolutional layers and fusing them to generate more robust representations for efficient image retrieval. Experimental results on CIFAR10 and NUS-WIDE datasets demonstrate that our method surpasses the performance of state-of-the-art hashing techniques.

In recent years, applying deep learning to solve physics problems has attracted much attention. Data-driven deep learning methods produce operators that can learn solutions to the whole system of partial differential equations. However, the existing methods are only evaluated on simple flow equations (e.g., Burger's equation), and only consider the generalization ability on different initial conditions. In this paper, we construct CFDBench, a benchmark with four classic problems in computational fluid dynamics (CFD): lid-driven cavity flow, laminar boundary layer flow in circular tubes, dam flows through the steps, and periodic Karman vortex street. Each flow problem includes data with various boundary conditions, fluid physical properties, and domain geometries. Compared to existing datasets, the advantages of CFDBench are (1) comprehensive. It contains common physical parameters such as velocity, pressure, and cavity fraction. (2) realistic. It is very suitable for deep learning solutions of fluid mechanics equations. (3) challenging. It has a certain learning difficulty, prompting to find models with strong learning ability. (4) standardized. CFDBench facilitates a comprehensive and fair comparison of different deep learning methods for CFD. We make appropriate modifications to popular deep neural networks to apply them to CFDBench and enable the accommodation of more changing inputs. The evaluation on CFDBench reveals some new shortcomings of existing works and we propose possible directions for solving such problems.

Facial emotion detection is a challenging task that deals with emotion recognition. It has applications in various domains, such as behavior analysis, surveillance systems and human-computer interaction (HCI). Numerous studies have been implemented to detect emotions, including classical machine learning algorithms and advanced deep learning algorithms. For the machine learning algorithm, the hand-crafted feature needs to be extracted, which is a tiring task and requires human effort. Whereas in deep learning models, automated feature extraction is employed from samples. Therefore, in this study, we have proposed a novel and efficient deep learning model based on Neural Architecture Search Network utilizing superior artificial networks such as RNN and child networks. We performed the training utilizing the FER 2013 dataset comprising seven classes: happy, angry, neutral, sad, surprise, fear, and disgust. Furthermore, we analyzed the robustness of the proposed model on CK+ datasets and comparing with existing techniques. Due to the implication of reinforcement learning in the network, most representative features are extracted from the sample network. It extracts all key features without losing the key information. Our proposed model is based on one stage classifier and performs efficient classification. Our technique outperformed the existing models attaining an accuracy of 98.14%, recall of 97.57%, and precision of 97.84%.

One of the most prevalent brain diseases, epilepsy is characterized by recurring seizures that happen quite frequently. During seizures, a patient suffers uncontrollable muscle contractions that cause loss of motion and balance, which could lead to harm or even death. Establishing an automatic method for warning patients about impending seizures requires extensive research. It is possible to anticipate seizures by analyzing the Electroencephalogram (EEG) signal from the scalp region of the human brain. Time domain-based features such as Hurst exponent (Hur), Tsallis Entropy (TsEn), improved permutation entropy (impe), and amplitude-aware permutation entropy (AAPE) were extracted from EEG signals. In order to diagnose epileptic seizure children from normal children automatically, this study conducted two sessions, in the first session, the extracted features from the EEG dataset were classified using three machine learning (ML)-based models including support vector machine (SVM), K nearest neighbor (KNN), or decision tree (DT), while in the second session, the dataset was classified using three deep learning (DL)-based recurrent neural network (RNN) classifiers including a gated recurrent unit (GRU), long short-term memory (LSTM), and bidirectional (BiLSTM). The EEG dataset obtained from the Neurology Clinic at the Ibn-Rushd Training Hospital. In this regard, detailed explanations and research from the time domain and entropy characteristics show that using GRU, LSTM, and BiLSTM RNN deep learning classifiers on the All−time−entropy fusion feature improves the final classification results.

In an ever-evolving landscape of higher education, this study delves into the transformative potential of merging deep learning principles and meaningful pedagogy in language acquisition, aided by artificial intelligence (AI) technologies. Drawing from a qualitative research design, it navigates the post-pandemic educational landscape, examining shifts in language education, student perspectives, and adaptations. Through comprehensive data collection methods, including literature review, interviews, and classroom observations, the study presents insights from 30 participants from SMC. The qualitative findings reveal emerging themes related to deep learning, meaningful learning, AI integration, and language acquisition, underscoring their profound impact on teaching methods and student engagement. This research contributes to the field by shedding light on innovative approaches that elevate language acquisition in an AI-evolving educational environment. The study concludes with implications for school administrators, teachers, and students, offering recommendations for future research directions, ultimately striving to enhance language education in the modern era.

This paper explores the use of different deep learning models for predicting precipitation in 56 meteorological stations in Jilin Province, China. The models used include Stacked-LSTM, Transformer, and SVR, and Gaussian noise is added to the data to improve their robustness. Results show that the Stacked-LSTM model performs the best, achieving high prediction accuracy and stability. The study also conducts variable attribution analysis using LightGBM and finds that temperature, dew point, precipitation in previous days, and air pressure are the most important factors affecting precipitation prediction, which is consistent with traditional meteorological theory. The paper provides detailed information on the data processing, model training, and parameter settings, which can serve as a reference for future precipitation prediction tasks. The findings suggest that adding Gaussian noise to the dataset can improve the model's generalization ability, especially for predicting days with zero precipitation. Overall, this study provides useful insights into the application of deep learning models in precipitation prediction and can contribute to the development of meteorological forecasting and applications.

With the rise of the Internet of Things (IOT), mobile devices and Location-Based Social Network (LBSN), an abundant amount of trajectory data has made research on location prediction more popular. The check-in data shared through LBSN hides information related to life patterns, obtaining this information is helpful for location prediction. However, the trajectory data recorded by mobile devices is different from check-in data that has semantic information. In order to obtain the user’s semantic, relevant studies match the stay point to the nearest Point of Interest (POI), but location error may lead to wrong semantic matching. Therefore, we propose A Self-Attention for Next Location Prediction based on Semantic Mining to predict the next location. When calculating the semantic feature of a stay point, the first step is to search for the k nearest POI, then use the reciprocal of the distance from the stay point to the k nearest POI and the number of categories as weights. Finally, we use the probability to express semantic without losing other important semantic information. Furthermore, this research combined with sequential pattern mining can bring richer semantic features. In order to better perceive the trajectory, temporal features learn periodicity of time series by sine function. In terms of location features, we build a directed weighted graph and regard the frequency of users visiting locations as the weight, so the location features are rich in contextual information. We then adopt the Self-Attention model to capture long-term dependencies in long trajectory sequences. Experiments in Geolife show that the semantic matching of this study improved by 45.78% in TOP@1 compared with the closest distance search for POI. Compared with the baseline, the model proposed in this study improved by 2.5% in TOP@1.

With the continuous development of network technology, complex network systems generate massive unbalanced attack traffic. Due to the severe imbalance in the quantities of normal samples and attack samples, as well as among different types of attack samples, intrusion detection systems suffer from low detection rates for rare class attack data. In this paper, we propose a geometric synthetic minority oversampling technique based on optimized kernel density estimation algorithm. This method can generate diverse rare class attack data by learning the distribution of rare class attack data while maintaining similarity with the original sample features. Meanwhile, the balanced data is input to a feature extraction module built upon multiple denoising autoencoders, reducing information redundancy in high-dimensional data and improving the detection performance for unknown attacks. Subsequently, a soft voting ensemble learning technique is utilized for multi-class anomaly detection on the balanced and dimensionally reduced data. Finally, an intrusion detection system is constructed based on data preprocessing, imbalance handling, feature extraction, and anomaly detection modules, and validated on the NSL-KDD and N-BaIoT datasets. Comparative experiments with baseline models and other state-of-the-art methods demonstrate that the proposed system improves the detection rate of rare class attack data. Furthermore, it achieves a good overall detection rate on the Internet of Things dataset (N-BaIoT), indicating its strong applicability.

Keywords: Convolutional Neural Network, Deep Learning, Skin cancer, Generative Adversarial Network

Target recognition mainly includes three approaches: optical image-based, echo detection-based, and passive signal analysis-based methods. Among them, the passive signal-based method is closely integrated with practical applications due to its strong environmental adaptability. Based on passive radar signal analysis, we design an "end-to-end" model that cascades a noise estimation network with a recognition network to identify working modes in noise environment. The noise estimation network is implemented based on U-Net, which adopts a method of feature extraction and reconstruction to adaptively estimate the noise mapping level of the sample, which can help the recognition network to reduce noise interference. Focusing on the characteristics of radar signal, the recognition network is realized based on Multi-Scale Convolutional Attention Network (MSCANet). Firstly, the deep group convolution is used to isolate the channel interaction in the shallow network. Then, through the multi-scale convolution module, finer-grained features of the signal are extracted without increasing the complexity of the model. Finally, the self-attention mechanism is used to suppress the influence of low-correlation and negative-correlation channels and spaces. This method overcomes the problem that the conventional method is seriously disturbed by noise. We validated the proposed method in 81 kinds of noise environments, achieving an average accuracy of 94.65%. Additionally, we discussed the performance of six machine learning algorithms and four deep learning algorithms. Compared to these methods, proposed MSCANet achieved an accuracy improvement of approximately 17%. Our method demonstrates better generalization and robustness.

With the continuous progress of remote sensing image object detection tasks in recent years, researchers in this field have gradually shifted the focus of their research from horizontal object detection to the study of object detection in arbitrary directions. It is worth noting that some properties are different from the horizontal object detection during oriented object detection that researchers have yet to notice much. This article presents the design of a straightforward and efficient arbitrary-oriented detection system, leveraging the inherent properties of the orientation task, including the rotation angle and box aspect ratio. In the detection of low aspect ratio objects, the angle is of little importance to the orientation bounding box, and it is even difficult to define the angle information in extreme categories. Conversely, in the detection of objects with high aspect ratios, the angle information plays a crucial role and can have a decisive impact on the quality of the detection results. By exploiting the aspect ratio of different targets, this letter proposes a ratio-balanced angle loss that allows the model to make a better trade-off between low-aspect ratio objects and high-aspect ratio objects. The rotation angle of each oriented object, which we naturally embed into a two-dimensional Euclidean space for regression, thus avoiding an overly redundant design and preserving the topological properties of the circular space. The performance of the UCAS-AOD, HRSC2016, and DLR-3K datasets show that the proposed model in this paper achieves a leading level in terms of both accuracy and speed. The code is released at https://github.com/minghuicode/Periodic-Pseudo-Domain.

Artificial Intelligence (AI) has many advantages over humans in that it can detect incredibly subtle patterns within large quantities of data. This study suggests using AI algorithms in user research tasks for mining variables ranging from the tone of voice, image banks, historical records, and product use to determine where brands sit and where there could be competitive advantages. This study reviews the current design processes of User Experience (UX) designers and the advancements in Deep Learning (DL). It identifies potential areas of automation in the Preparation, Incubation and Illumination stages of the design process. It recognises the possibility of using Long Short-Term Memory (LSTM) models to automate design feedback and the creation of alternate designs with Generative Adversarial Networks (GANs).