Search

Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure, and inability to learn continually. We present the initial design for an AI system, Agential AI (AAI), in principle operating independently or on top of statistical methods, designed to overcome these issues. AAI's core is a learning method that models temporal dynamics with guarantees of completeness, minimality, and continual learning, using component-level variation and selection to learn the structure of the environment. It integrates this with a behavior algorithm that plans on a learned model and encapsulates high-level behavior patterns. Preliminary experiments on a simple environment show AAI's effectiveness and potential.

Robotic devices hold great potential for efficient and reliable assessment of neuromotor abnormalities in post-stroke patients. However, spasticity caused by stroke is still assessed manually in clinical settings. The limited and variable nature of data collected from patients has long posed a major barrier to quantitatively modelling spasticity with robotic measurements and fully validating robotic assessment techniques. This paper presents a simulation framework developed to support the design and validation of elbow spasticity models and mitigate data problems. The framework consists of a simulation environment of robot-assisted spasticity assessment, two motion controllers for the robot and human models, and a stretch reflex controller. Our framework allows simulation based on synthetic data without experimental data from human subjects. Using this framework, we replicated the constant-velocity stretch experiment typically used in robot-assisted spasticity assessment and evaluated four types of spasticity models. Our results show that a spasticity reflex model incorporating feedback on both muscle fibre velocity and length more accurately captures joint resistance characteristics during passive elbow stretching in spastic patients than a force-dependent model. When integrated with an appropriate spasticity model, this simulation framework has the potential to generate extensive datasets of virtual patients for future research on spasticity assessment., Comment: 7 pages, 5 figures; Submitted to ICORR-2025

Adaptive networks today rely on overparameterized fixed topologies that cannot break through the statistical conflicts they encounter in the data they are exposed to, and are prone to "catastrophic forgetting" as the network attempts to reuse the existing structures to learn new task. We propose a structural adaptation method, DIRAD, that can complexify as needed and in a directed manner without being limited by statistical conflicts within a dataset. We then extend this method and present the PREVAL framework, designed to prevent "catastrophic forgetting" in continual learning by detection of new data and assigning encountered data to suitable models adapted to process them, without needing task labels anywhere in the workflow. We show the reliability of the DIRAD in growing a network with high performance and orders-of-magnitude simpler than fixed topology networks; and demonstrate the proof-of-concept operation of PREVAL, in which continual adaptation to new tasks is observed while being able to detect and discern previously-encountered tasks., Comment: Presented in Deployable AI (DAI) workshop at AAAI-2024

The layer-upon-layer approach in additive manufacturing, open or closed cells in polymeric or metallic foams involve an intrinsic microstructure tailored to the underlying applications. Homogenization of such architectured materials creates metamaterials modeled by higher-gradient models, specifically when the microstructure's characteristic length is comparable to the length scale of the structure. In this study, we conduct a comparative analysis of various finite elements methods for solving problems in strain-gradient elasticity. We employ open-source packages from Firedrake and FEniCS. Different finite element formulations are tested: we implement Lagrange, Argyris, Hermite elements, a Hu--Washizu type (mixed) formulation, as well as isogeometric analysis with Non-Uniform Rational B-Splines (NURBS). For the numerical study, we investigate one- and two-dimensional problems discussed in the literature of strain-gradient modeling. All developed codes are open-access to encourage research in Finite Element Method (FEM) based computation of generalized continua.

The alignment of optical systems is a critical step in their manufacture. Alignment normally requires considerable knowledge and expertise of skilled operators. The automation of such processes has several potential advantages, but requires additional resource and upfront costs. Through a case study of a simple two mirror system we identify and examine three different automation approaches. They are: artificial neural networks; practice-led, which mimics manual alignment practices; and design-led, modelling from first principles. We find that these approaches make use of three different types of knowledge 1) basic system knowledge (of controls, measurements and goals); 2) behavioural skills and expertise, and 3) fundamental system design knowledge. We demonstrate that the different automation approaches vary significantly in human resources, and measurement sampling budgets. This will have implications for practitioners and management considering the automation of such tasks., Comment: Author Accepted Manuscript- 8 pages, The 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE 2024), Aug28-Sep1st 2024, Bari, Italy. Keywords: Automation, optimisation, regression, behaviour analysis, artificial neural networks, optical systems, mathematical model, human factors, sampling cost, cost benefit analysis

The rise in online professional development (PD) opportunities for teachers, accelerated by the COVID-19 pandemic, necessitates an examination of the effectiveness of these online PD programs and the design elements that best enhance teachers' knowledge. This review synthesizes findings from nine studies that systematically investigate experimental and observational research evaluating formal online PD programs for teachers. The studies employed various research designs, including randomized controlled trials (RCTs), pretest-posttest designs, and mixed-method approaches. Key characteristics of the studies were analyzed, including publication dates, originating nations, targeted demographics, research objectives, program information, study designs, participants, data collection methods, and reported results. The findings indicate that effective online PD programs enhance teachers' content knowledge (CK), pedagogical content knowledge (PCK), instructional practices, self-efficacy, and professional competence. Despite the benefits, the review also identifies several barriers to the effective implementation of online PD. These include organizational challenges, time constraints, technical difficulties, and issues related to sustaining new practices. The need for continuous support, practical application of new knowledge, and interactive elements to foster engagement and collaboration among educators is also highlighted. The review concludes with recommendations for future online PD programs, emphasizing the importance of well-designed, flexible, and supportive structures that address the unique needs of educators. The profound influence of COVID-19 on the adoption of online PD underscores the necessity for further research into effective design components and support mechanisms. This review serves as a valuable resource for program designers and decision-makers aiming to enhance the effectiveness of online PD for educators. [This paper was published in: "EJER Congress 2024 International Eurasian Educational Research Congress Conference Proceedings," edited by Senel Poyrazli, Ani Publishing, 2024, pp. 61-77.]

Segmenting multiple objects (e.g., organs) in medical images often requires an understanding of their topology, which simultaneously quantifies the shape of the objects and their positions relative to each other. This understanding is important for segmentation networks to generalize better with limited training data, which is common in medical image analysis. However, many popular networks were trained to optimize only pixel-wise performance, ignoring the topological correctness of the segmentation. In this paper, we introduce a new topology-aware loss function, which we call PI-Att, that explicitly forces the network to minimize the topological dissimilarity between the ground truth and prediction maps. We quantify the topology of each map by the persistence image representation, for the first time in the context of a segmentation network loss. Besides, we propose a new mechanism to adaptively calculate the persistence image at the end of each epoch based on the network's performance. This adaptive calculation enables the network to learn topology outline in the first epochs, and then topology details towards the end of training. The effectiveness of the proposed PI-Att loss is demonstrated on two different datasets for aorta and great vessel segmentation in computed tomography images.

The use of unmanned aerial vehicles (UAVs) for a variety of commercial, civilian, and defense applications has increased many folds in recent years. While UAVs are expected to transform future air operations, there are instances where they can be used for malicious purposes. In this context, the detection, classification, and tracking (DCT) of UAVs (DCT-U) for safety and surveillance of national air space is a challenging task when compared to DCT of manned aerial vehicles. In this survey, we discuss the threats and challenges from malicious UAVs and we subsequently study three radio frequency (RF)-based systems for DCT-U. These RF-based systems include radars, communication systems, and RF analyzers. Radar systems are further divided into conventional and modern radar systems, while communication systems can be used for joint communications and sensing (JC&S) in active mode and act as a source of illumination to passive radars for DCT-U. The limitations of the three RF-based systems are also provided. The survey briefly discusses non-RF systems for DCT-U and their limitations. Future directions based on the lessons learned are provided at the end of the survey., Comment: This paper is under review for IEEE COMST. arXiv admin note: text overlap with arXiv:2211.10038

This study presents a pioneering effort to replicate human neuromechanical experiments within a virtual environment utilising a digital human model. By employing MyoSuite, a state-of-the-art human motion simulation platform enhanced by Reinforcement Learning (RL), multiple types of impedance identification experiments of human elbow were replicated on a musculoskeletal model. We compared the elbow movement controlled by an RL agent with the motion of an actual human elbow in terms of the impedance identified in torque-perturbation experiments. The findings reveal that the RL agent exhibits higher elbow impedance to stabilise the target elbow motion under perturbation than a human does, likely due to its shorter reaction time and superior sensory capabilities. This study serves as a preliminary exploration into the potential of virtual environment simulations for neuromechanical research, offering an initial yet promising alternative to conventional experimental approaches. An RL-controlled digital twin with complete musculoskeletal models of the human body is expected to be useful in designing experiments and validating rehabilitation theory before experiments on real human subjects., Comment: 8 pages, 5 figures; Submitted to WCCI-2024

This paper presents the ArBanking77, a large Arabic dataset for intent detection in the banking domain. Our dataset was arabized and localized from the original English Banking77 dataset, which consists of 13,083 queries to ArBanking77 dataset with 31,404 queries in both Modern Standard Arabic (MSA) and Palestinian dialect, with each query classified into one of the 77 classes (intents). Furthermore, we present a neural model, based on AraBERT, fine-tuned on ArBanking77, which achieved an F1-score of 0.9209 and 0.8995 on MSA and Palestinian dialect, respectively. We performed extensive experimentation in which we simulated low-resource settings, where the model is trained on a subset of the data and augmented with noisy queries to simulate colloquial terms, mistakes and misspellings found in real NLP systems, especially live chat queries. The data and the models are publicly available at https://sina.birzeit.edu/arbanking77.

Encoder-decoder networks become a popular choice for various medical image segmentation tasks. When they are trained with a standard loss function, these networks are not explicitly enforced to preserve the shape integrity of an object in an image. However, this ability of the network is important to obtain more accurate results, especially when there is a low-contrast difference between the object and its surroundings. In response to this issue, this work introduces a new shape-aware loss function, which we name FourierLoss. This loss function relies on quantifying the shape dissimilarity between the ground truth and the predicted segmentation maps through the Fourier descriptors calculated on their objects, and penalizing this dissimilarity in network training. Different than the previous studies, FourierLoss offers an adaptive loss function with trainable hyperparameters that control the importance of the level of the shape details that the network is enforced to learn in the training process. This control is achieved by the proposed adaptive loss update mechanism, which end-to-end learns the hyperparameters simultaneously with the network weights by backpropagation. As a result of using this mechanism, the network can dynamically change its attention from learning the general outline of an object to learning the details of its contour points, or vice versa, in different training epochs. Working on 2879 computed tomography images of 93 subjects, our experiments revealed that the proposed adaptive shape-aware loss function led to statistically significantly better results for liver segmentation, compared to its counterparts.