Applied System Innovation

Respiratory motion serves as a major challenge during treatment of lung cancer patients using radiotherapy. In this work, an image-based method is presented to extract a respiratory signal directly from Cone Beam CT (CBCT) projections. A dense optical-flow method is used to acquire motion vectors between successive projections in each dataset, followed by the extraction of the dominant motion pattern by application of linear kernel Principal Component Analysis (PCA). The effectiveness of the method was tested on three patient datasets and the extracted breathing signal was compared to a ground-truth signal. The average phase shift was observed to be 1.936 ± 0.734 for patient 1, 1.185 ± 0.781 for patient 2 and 1.537 ± 0.93 for patient 3. Moreover, a 4D CBCT image was reconstructed, considering the respiratory signal extracted, using the proposed method, and compared to that reconstructed considering the ground-truth respiratory signal. Results showed that a minimal difference was found between the image reconstructed using the proposed method and the ground-truth in terms of clarity, motion artifacts and edge sharpness. Full article

Road traffic accidents (RTAs) are a significant public health and safety concern, resulting in numerous injuries and fatalities. The growing number of cases referred to traffic accident rooms in courts has underscored the necessity for an automated solution to determine victim indemnifications, particularly given the limited number of specialized judges and the complexity of cases involving multiple victims. This paper introduces RTACompensator, an artificial intelligence (AI)-driven decision support system designed to automate indemnification calculations for road accident victims. The system comprises two main components: a calculation module that determines initial compensation based on factors such as age, salary, and medical assessments, and a machine learning (ML) model that assigns liability based on police accident reports. The model uses Arabic bidirectional encoder representations from transformer (AraBERT) embeddings to generate contextual vectors from the report, which are then processed by extreme gradient boosting (XGBoost) to determine responsibility. The model was trained on a purpose-built Arabic corpus derived from real-world legal judgments. To expand the dataset, two data augmentation techniques were employed: multilingual bidirectional encoder representations from transformers (BERT) and Gemini, developed by Google DeepMind. Experimental results demonstrate the model’s effectiveness, achieving accuracy scores of 97% for the BERT-augmented corpus and 97.3% for the Gemini-augmented corpus. These results underscore the system’s potential to improve decision-making in road accident indemnifications. Additionally, the constructed corpus provides a valuable resource for further research in this domain, laying the groundwork for future advancements in automating and refining the indemnification process. Full article

This study introduces a novel technique called Synchronized Multi-Augmentation (SMA) combined with multi-backbone (MB) ensembling to enhance model performance and generalization in deep learning (DL) tasks in real-world scenarios. SMA utilizes synchronously augmented input data for training across multiple backbones, improving the overall feature extraction process. The outputs from these backbones are fused using two distinct strategies: the averaging fusion method, which averages predictions, and the dense fusion method, which averages features through a fully connected network. These methods aim to boost accuracy and reduce computational costs, particularly in Edge Intelligence (EI) systems with limited resources. The proposed SMA technique was evaluated on the CIFAR-10 dataset, highlighting its potential to enhance classification tasks in DL workflows. This study provides a comprehensive analysis of various backbones, their ensemble methods, and the impact of different SMAs on model performance. The results demonstrate that SMAs involving color adjustments, such as contrast and equalization, significantly improve generalization under varied lighting conditions that simulated real-world low-illumination conditions, outperforming traditional spatial augmentations. This approach is particularly beneficial for EI hardware, such as microcontrollers and IoT devices, which operate under strict constraints like limited processing power and memory and real-time processing requirements. This study’s findings suggest that employing SMA and MB ensembling can offer significant improvements in accuracy, generalization, and efficiency, making it a viable solution for deploying DL models on edge devices with constrained resources under real-world practical conditions. Full article

Text classifiers are Artificial Intelligence (AI) models used to classify new documents or text vectors into predefined classes. They are typically built using supervised learning algorithms and labelled datasets. Text classifiers produce a predefined class as an output, which also makes them susceptible to adversarial attacks. Text classifiers with high accuracy that are trained using complex deep learning algorithms are equally susceptible to adversarial examples, due to subtle differences that are indiscernible to human experts. Recent work in this space is mostly focused on improving adversarial robustness and adversarial example detection, instead of detecting adversarial attacks. In this paper, we propose a novel approach, explainable AI with integrated gradients (IGs) for the detection of adversarial attacks on text classifiers. This approach uses IGs to unpack model behavior and identify terms that positively and negatively influence the target prediction. Instead of random substitution of words in the input, we select the top p% words with the greatest positive and negative influence as substitute candidates using attribution scores obtained from IGs to generate k samples of transformed inputs by replacing them with synonyms. This approach does not require changes to the model architecture or the training algorithm. The approach was empirically evaluated on three benchmark datasets, IMDB, SST-2, and AG News. Our approach outperforms baseline models on word substitution rate, detection accuracy, and F1 scores while maintaining equivalent detection performance against adversarial attacks. Full article

This article presents the process of creating a virtual reality (VR) game designed to assess the impact of stress on heart rate variability (HRV). The game features dynamic and challenging scenarios to induce stress responses, incorporating advanced 3D modelling and 3D animation techniques. A study involving 20 volunteers was conducted, with electrocardiographic (ECG) data collected before and during game play. HRV analysis focused on fractal and multifractal characteristics, utilizing detrended fluctuation analysis (DFA) and multifractal detrended fluctuation analysis (MFDFA) methods. DFA results revealed decreased values of α₁, α₂, and α_all, indicating alterations in short-term and long-term correlations under stress. MFDFA further analyzed changes in fluctuation function Fq(s), generalized Hurst exponent Hq, multifractal scaling exponent τ(q), and multifractal spectrum f(α), showing significant differences in these parameters under stress. These findings validate the game’s effectiveness in simulating stress and its impact on HRV. The present study not only demonstrates the relationship between stress and the fractal characteristics of HRV but also offers a new foundation for future applications in psychology, physiology, and the development of VR technologies for stress management. Full article

In this paper, we develop an exact schedulability test and sufficient infeasibility test for fixed-priority scheduling on multiprocessor platforms. We base our tests on presenting real-time systems as a Kripke model for dynamic real-time systems with sporadic non-preemptible tasks running on a multiprocessor platform and an online scheduler using global fixed priorities. This model includes states and transitions between these states, allows us to formally justify a polynomial-time algorithm for an exact schedulability test using the idea of backward reachability. Using this algorithm, we perform the exact schedulability test for the above real-time systems, in which there is one more task than the processors. The main advantage of this algorithm is its polynomial complexity, while, in general, the problem of the exact schedulability testing of real-time systems on multiprocessor platforms is NP-hard. The infeasibility test uses the same algorithm for an arbitrary task-to-processor ratio, providing a sufficient infeasibility condition: if the real-time system under test is not schedulable in some cases, the algorithm detects this. We conduct an experimental study of our algorithms on the datasets generated with different utilization values and compare them to several state-of-the-art schedulability tests. The experiments show that the performance of our algorithm exceeds the performance of its analogues while its accuracy is similar. Full article

This manuscript presents the development and testing of a novel model designed to help organizations, particularly small and medium-sized enterprises (SMEs), address the challenges of integrating new technologies within the frameworks of Industry 4.0 and 5.0. The proposed model is a metamodel that evaluates organizational and contextual vulnerabilities concerning both existing technologies and potential external technologies under consideration for adoption. It synthesizes three foundational frameworks: the Viable System Model (VSM), the principles of viable and sustainable systems, and the Technology, Organization, and Environment (TOE) Model. The findings demonstrate the practical applicability of this model in an SME context, showcasing its ability to facilitate the gradual and sustainable adoption of new technologies. By aligning business needs with technological solutions and leveraging insights from computer science and organizational cybernetics, the model adapts to varying levels of technological adoption, integrating organizational dynamics and business evolution to support the implementation of emerging technologies. Full article

This work is devoted to the development of a biometric authentication system and the generation of a cryptographic key or a long password of 1024 bits based on a voice password, which ensures the protection of a biometric template from compromise. A new hybrid neural network model based on two types of trigonometric correlation neurons was proposed. The model is capable of recording correlation links between features and is resistant to data extraction attacks. The experiments were conducted on our own AIC-spkr-130 dataset and the publicly available RedDots, including recordings of user voices in different psycho-emotional states (sleepy state, alcohol intoxication). The results show that the proposed neural fuzzy extractor model provides an equal error probability level of EER = 2.1%. Full article

Wind turbine blade structural dynamics are crucial in the turbine structural design phase. Blade deflections and loads can affect the weight of the rotor as well as the power performance of a wind turbine if the deflections are extremely high. Predictions of the turbine’s blade deflections and loads can lead to informative decisions on optimizing the design of the blade. In this work, a multivariate machine learning (ML) approach is used to predict the blade’s dynamics based on the wind flow conditions and control actions of the turbine. Three different datasets were generated using the OpenFAST software tool for three different wind turbulence classes. Various ML algorithms were trained to predict the blade deflections at the tip and blade loads at the root in the edgewise and flapwise directions. The ML models were tested for generalization of the model to different flow conditions. A model is trained for one dataset with one of the turbulence classes and then used to predict the outputs of the other two datasets. The random forest ML algorithm gave the best accuracy for predicting the outputs for the dataset it was trained for, as well as the other two datasets. The accuracy of predictions was found to be higher in the edgewise direction for both load and deflection outputs. In the flapwise direction, the model could predict the outputs of the data it was trained for with an accuracy of around 99% and for the other two datasets with an accuracy of over 75%. While in the edgewise direction, the model trained on only one dataset gave a prediction accuracy above 95% for all three datasets. Full article

The increasing incorporation of Industrial Internet of Things (IIoT) devices into critical industrial operations and critical infrastructures necessitates robust security measures to safeguard confidential information and ensure dependable connectivity. Particularly in Cyber Physical Systems (CPSs), IIoT system security becomes critical as systems become more interconnected and digital. This paper introduces a novel Lightweight Industrial IoT Authentication (LI2A) method as a solution to address security concerns in the industrial sector and smart city infrastructure. Mutual authentication, authenticated message integrity, key agreement, soundness, forward secrecy, resistance to a variety of assaults, and minimal resource consumption are all features offered by LI2A. Critical to CPS operations, the approach prevents impersonation, man-in-the-middle, replay, eavesdropping, and modification assaults, according to a security study. The method proposed herein ensures the integrity of CPS networks by verifying communication reliability, identifying unauthorized message modifications, establishing a shared session key between users and IIoT devices, and periodically updating keys to ensure sustained security. A comprehensive assessment of performance takes into account each aspect of storage, communication, and computation. The communication and computing capabilities of LI2A, which are critical for the operation of CPS infrastructure, are demonstrated through comparisons with state-of-the-art systems from the literature. LI2A can be implemented in resource-constrained IIoT devices found in CPS and industrial environments, according to the results. By integrating IIoT devices into critical processes in CPS, it is possible to enhance security while also promoting urban digitalization and sustainability. Full article

Key performance indicators (KPIs) are crucial for managing business performance and optimization strategies. However, traditional KPIs are inflexible and cannot adapt to changes in staff, business units, functions, and processes. To address this issue, this paper proposes a method that combines statistics, machine learning (ML), and artificial intelligence (AI) to augment traditional KPIs with the flexibility of data-driven automation (DDA) techniques. This study builds a model that takes traditional KPIs generated by an integrated ecosystem as input data and assesses the suitability and correlation of the data using statistical techniques, such as Bartlett’s test of sphericity and the Kaiser–Meyer–Olkin (KMO) test of sampling adequacy. The model then employs exploratory Factor Analysis (FA) techniques to identify correlations and patterns, prioritize KPIs, and automatically generate smart KPIs for business optimization. The model is designed to adapt automatically by creating new KPIs as the business evolves and data change. A case study evaluation validates this approach, showing that DDA techniques can effectively create smart KPIs for business optimization. This approach provides a flexible and adaptable way to manage business performance and optimization strategies, enabling organizations to stay ahead of the competition and achieve their goals. Full article

This paper presents a new approach for enhancing autonomous vehicle navigation and obstacle avoidance based on the integration of reinforcement learning with multiple sensors for navigation. The proposed system is designed to enable a reinforcement learning decision algorithm capable of making real-time decisions in aiding the adaptive capability of a vehicle. This method was tested on a prototype vehicle with navigation based on a Ublox Neo 6M GPS and a three-axis magnetometer, while for obstacle detection, this system uses three ultrasonic sensors. The use of a model-free reinforcement learning algorithm and use of an effective sensor for obstacle avoidance (instead of LiDAR and a camera) provides the proposed system advantage in terms of computational requirements, adaptability, and overall cost. Our experiments show that the proposed method improves navigation accuracy substantially and significantly advances the ability to avoid obstacles. The prototype vehicle adapts very well to the conditions of the testing track. Further, the data logs from the vehicle were analyzed to check the performance. It is this cost-effective and adaptable nature of the system that holds some promise toward a solution in situations where human intervention is not feasible, or even possible, due to either danger or remoteness. In general, this research showed how the application of reinforcement learning combined with sensor fusion enhances autonomous navigation and makes vehicles perform more reliably and intelligently in dynamic environments. Full article

Additive manufacturing and digital warehouses are transforming the way industries manage and maintain their spare parts inventory. Considering digital warehouses and on-demand manufacturing for spare parts during the project phase is a strategic decision that involves trade-offs depending on the operational needs and pricing structure. This paper aims to explore the spare part evaluation process considering both physical and digital warehouse inventories. A case asset is purposefully selected and four spare part management concepts are studied using a simulation modeling approach. The results highlight that the relevant digital warehouse scenario, used in this case, managed to completely reduce all emissions related to global spare parts supply; however, this was at the expense of reducing availability by 15.1%. However, the hybrid warehouse scenario managed to increase availability by 11.5% while completely reducing all emissions related to global spare parts supply. Depending on the demand rate, the digital warehousing may not be sufficient alone to keep the production availability at the highest levels; however, it is effective in reducing the stock amount, simplifying the inventory management, and making the supply process more green and resilient. A generic estimation model for spare parts engineers is provided to determine the optimal specifications of their spare parts supply and inventory while considering digital warehouses and on-demand manufacturing. Full article

Nowadays, efficient dental healthcare systems are considered significant for upholding oral health. Also, the ability to utilize artificial intelligence for evaluating complex data implies that dental X-ray image recognition is a critical mechanism to enhance dental disease detection. Consequently, integrating deep learning algorithms into dental healthcare systems is considered a promising approach for enhancing the reliability and efficiency of diagnostic processes. In this context, an integrated artificial intelligence model is proposed to enhance model performance and interpretability. The basic idea of the proposed model is to augment the deep learning approach with Ensemble methods to improve the accuracy and robustness of dental healthcare. In the proposed model, a Non-Maximum Suppression (NMS) ensembled technique is employed to improve the accuracy of predictions along with combining outputs from multiple single models (YOLO8 and RT-DETR) to make a final decision. Experimental results on real-world datasets show that the proposed model gives high accuracy in miscellaneous dental diseases. The results show that the proposed model achieves 18% time reductions as well as 30% improvements in accuracy compared with other competitive deep learning algorithms. In addition, the effectiveness of the proposed integrated model, achieved 74% mAP50 and 58% mAP50-90, outperforming existing models. Furthermore, the proposed model grants a high degree of system reliability. Full article

Companies have tried to innovate in their training processes to increase their productivity indicators, reduce equipment maintenance costs, and improve the work environment. The use of Augmented Reality (AR) has been one of the implemented strategies to upgrade training processes, since it optimizes, through User Interface (UI) Design, experiences designed for users (UX) that are focused on education and training contexts. This research describes the definition and implementation of an IT architecture based on the ISO/IEC/IEEE 42010 standard using the Zachman and Kruchten frameworks. The methodological proposal presents an architecture seen from a business perspective, taking into account the strategic and technological components of the organization under a strategic alignment approach. The result is a six-layer architecture: The Government Strategy Layer (1) that accounts for the strategic component; the Business Layer (2) that presents the business management perspective; the Information Layer (4) that defines the metrics system: efficiency through task time, effectiveness through tasks completed, and satisfaction with overall satisfaction. In the Data Layer (4), the data collected with the metrics are structured in an industrial scenario with a cylinder turning process on a Winston Lathe. The experiment was carried out with two groups of 272 participants. In the Systems and Applications Layer (5), two applications were designed: a web client and a mobile application with augmented reality, and finally, the Networks and Infrastructure Layer (6), which delivers the two functional applications. The architecture validation was carried out using the mobile application. The analysis of the results showed a significance value of less than 0.001 in the three indicators: efficiency, effectiveness, and satisfaction in the Levene test and Student’s t-test. To corroborate the results, a test of equality of means with the Mann–Whitney U was carried out, showing that the three indicators presented significantly different values in the two experimental groups of this study. Thus, the group trained with the application obtained better results in the three indicators. The proposed architecture is adaptable to other training contexts. Information, data, and systems and application layers allowed for the exchange of training processes so that the augmented reality application is updated according to the new requirements. Full article

This review explores the novel integration of data-driven approaches, including artificial intelligence (AI) and machine learning (ML), in advancing building energy retrofits. This study uniquely emphasizes the emerging role of explainable AI (XAI) in addressing transparency and interpretability challenges, fostering the broader adoption of data-driven solutions among stakeholders. A critical contribution of this review is its in-depth analysis of innovative applications of AI techniques to handle incomplete data, optimize energy performance, and predict retrofit outcomes with enhanced accuracy. Furthermore, the review identifies previously underexplored areas, such as scaling data-driven methods to diverse building typologies and incorporating future climate scenarios in retrofit planning. Future research directions include improving data availability and quality, developing scalable urban simulation tools, advancing modeling techniques to include life-cycle impacts, and creating practical decision-support systems that integrate economic and environmental metrics, paving the way for efficient and sustainable retrofitting solutions. Full article

Microstrip filters are widely used in electronics and communications. Designing these filters requires knowledge in communications, microwave engineering, and radiofrequency systems. Specialized software facilitates the design process, often allowing optimization of results; however, such tools typically require expensive licenses, making them inaccessible to many students. While the literature includes some proposals for microstrip filter design, they generally have the limitation of not addressing parameter optimization. This paper presents a GUI (Graphical User Interface) for microstrip low-pass filter design, offering precise and reliable results at the desired cutoff frequency and attenuation, as demonstrated by experimental tests. The key strategy involves systematically following the steps of the classic design process, while simultaneously varying a specific parameter to analyze its impact on filter development. By exploring the variations in different parameters, various insightful analyses can be conducted. One of the notable achievements is the ability to design an optimal filter with a desired total length, while concurrently maximizing the performance of specific parameters. Additionally, this software is compatible with both MATLAB and Octave platforms, ensuring its usability across multiple environments. Full article

Global Quality Management System (G-QMS) in System of Systems (SoS) is a pioneering field of research essential for SoS G-organizations, which are characterized by their vast and complex technological systems and multi-organizational structures. Consequently, presenting significant challenges in implementing effective QMS for their operations. This manuscript completes the development of a novel conceptual model for G-QMSs in Sectors of SoS, drawing from extensive field research conducted within real SoS G-organizations employing the Grounded Theory methodology. This proposed model encompasses two foundational supra-entities, with this manuscript primarily dedicated to the second supra-entity, named “G-QMS in SoS”, which essentially represents Quality Management for SoS projects. The G-QMS in SoS model image is conceived through a description of its structural principles, entities architecture and interrelationships, alongside its complementary elements. Furthermore, the interrelationships between the two segment models that constitute G-QMS in Sectors of SoS are elucidated, offering a comprehensive view of the overarching model. Establishing a model for G-QMS in Sectors of SoS that describes the various structures of SoS projects and the G-organizations realizing them, as well as understanding the recommended G-QMS model, is vital as it directly impacts the success level of SoS projects and the effectiveness of the tailored G-QMS in these organizations. Full article

Leveraging data redundancy has long been recognized as an effective approach for concealing large amounts of secret data. In digital images, the 2D-pixel matrix inherently provides opportunities for redundancy, as each pixel is connected to its eight neighbors. Video segments, with their 3D structures, introduce an additional layer of redundancy known as temporal redundancy. Recent video steganography techniques have proposed utilizing this temporal redundancy for data concealment. This paper seeks to fully exploit the redundancy present in video segments by integrating both spatial and temporal redundancy through an Octree segmentation method. The video is divided into homogeneous, variable-sized 3D cubes to enhance redundancy in each region, thereby improving energy compaction in the 3D discrete cosine transform (3D-DCT) domain. Consequently, the hiding capacity is optimized because most of the signal’s energy is concentrated in a few significant 3D-DCT coefficients, leaving a substantial portion of insignificant coefficients. These insignificant coefficients can be replaced with secret data without significantly affecting the quality of the carrier signal. Full article