Search Results (8,365)

It is proposed that the process of learning may be represented as a trajectory within the phase space of long-term memory. The research uses an artificial neural network design to explore, in theory, if starting from different points within the phase space affects how quickly learning occurs. Using a Monte Carlo method, 1000 virtual agents were trained using the Levenberg–Marquardt algorithm to recognise a large set of Arabic digits at ten different skill levels. The simulations replicated the typical learning curves observed in human learning and were successful in distinguishing ten levels of skill. First, and in line with previous research, the results provide convincing evidence that learning consolidates a selected set of pathways within the network. Second, and critical to the hypothesis, the distance in the phase space, calculated as the difference in average connectivity between skill levels, is highly predictive of both learning time and performance. The findings strongly support the hypothesis that learning represents progression along a trajectory connecting two points within the phase state landscape. As these properties may be more pronounced in biological systems because of their greater complexity, these results shed new light on individual variance in learning. Full article

Background: Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by social deficits, repetitive behaviors, and heightened anxiety. Despite extensive research, effective interventions targeting core symptoms remain limited. Gami-Guibitang (GBT), a traditional herbal formula, has been clinically prescribed for anxiety-related symptoms and cognitive complaints, yet its effects on ASD-associated behavioral and molecular abnormalities have not been fully elucidated. Objective: This study aimed to evaluate the anxiolytic and neuroregulatory effects of GBT in a valproic acid (VPA)-induced ASD mouse model, focusing on behavioral outcomes and hippocampal synaptic protein expression. Methods: Pregnant C57BL/6N mice received a single intraperitoneal injection of VPA (500 mg/kg) at embryonic day 12.5. Male offspring were administered GBT (150 mg/kg, p.o.) twice daily for 4 weeks from postnatal day 21 (PND 21). These mice were behaviorally evaluated by the open-field test, elevated plus maze, marble-burying test, Y-maze, three-chamber social interaction test, and Morris water maze. Western blot analysis was conducted to examine hippocampal expression of phosphorylated and total CREB and GluR1, PI3K/Akt signaling components, as well as GABRA1 and GABRB1. Results: VPA-exposed offspring exhibited increased anxiety-like behaviors, altered repetitive behaviors, dysregulated exploratory activity, and impaired spatial learning, and reduced spontaneous alternation performance in the Y-maze. GBT reduced anxiety-like behaviors in the elevated plus maze and marble burying tests, partially improved spatial learning acquisition in the Morris water maze, and normalized excessive locomotor activity, without significantly affecting short-term working memory performance. At the molecular level, GBT significantly attenuated VPA-induced hyperphosphorylation of CREB, GluR1, PI3K, and Akt, indicating suppression of aberrant synaptic signaling rather than global enhancement. In addition, GBT increased GABRA1 expression toward control levels and enhanced GABRB1 expression beyond baseline, suggesting selective modulation of GABAergic receptor subunit composition rather than simple normalization. Conclusions: These findings provide preclinical evidence that GBT alleviates anxiety-like behavior and modulates hippocampal synaptic signaling disrupted by prenatal VPA exposure. By attenuating aberrant excitatory signaling and selectively regulating GABAergic receptor balance, GBT may represent a multi-target herbal candidate for modulating ASD-associated emotional dysregulation and domain-specific cognitive dysfunction, rather than acting as a broad cognitive enhancer. Full article

In the post-Moore’s Law era, conventional Von Neumann architectures face critical limitations, such as the “memory wall” and excessive power consumption, particularly when processing unstructured data. Neuromorphic computing, inspired by the human brain, offers a promising solution through parallel processing and adaptive learning. Among the candidates for artificial synapses, memristors based on two-dimensional MXenes (specifically Ti₃C₂T_x) have attracted significant attention due to their unique layered structure, high metallic conductivity, and tunable physicochemical properties. This review provides a comprehensive analysis of MXene-based memristors, from material synthesis to system-level applications. We examine how different synthesis strategies, including etching methods, directly influence device performance and elucidate the underlying resistive switching mechanisms driven by ion migration, valence change, and interfacial processes. Furthermore, the review demonstrates the efficacy of MXenes in emulating biological synaptic functions—such as spike-timing-dependent plasticity (STDP) and long-term potentiation/depression (LTP/LTD)—and their application in tasks like handwritten digit recognition. Finally, we highlight emerging frontiers in flexible electronics and in-sensor computing, offering insights into the future trajectory of integrated sensing, memory, and computation. Full article

Price volatility in steel reinforcement bars (rebar) plays a pivotal role in managing construction project costs, with precise forecasting being essential for maintaining corporate profitability and ensuring market stability. This research conducts a comprehensive evaluation of five prominent forecasting models—Autoregressive Integrated Moving Average (ARIMA), eXtreme Gradient Boosting (XGBoost), Prophet, Long Short-Term Memory (LSTM), and Transformer—specifically applied to steel rebar price prediction. The study emphasizes the influence of feature selection, defined as the number of historical price data points utilized for prediction, on the accuracy of these models. Furthermore, it develops a hybrid forecasting framework grounded in a residual complementarity mechanism aimed at improving long-term predictive performance. The results reveal that the ARIMA model delivers consistent and reliable short-term forecasts, particularly within a two-month horizon, whereas the Prophet model effectively captures long-term price trends but suffers from notable short-term bias. A two-stage hybrid model (referred to as Combination Model II), which integrates ARIMA and Prophet through residual inversion, demonstrates superior forecasting accuracy over a six-month period. This hybrid approach surpasses the standalone ARIMA model by more than 70% across key evaluation metrics—including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Symmetric Mean Absolute Percentage Error (SMAPE), and Mean Absolute Scaled Error (MASE)—and exceeds the performance of the standalone Prophet model by over 90%. This integration effectively combines the high short-term precision of ARIMA with the long-term trend stability of Prophet. Within the domain of machine learning and deep learning models, XGBoost achieves optimal predictive accuracy when utilizing between one and four features. The predictive performance of LSTM does not exhibit a straightforward linear relationship with the number of features; however, certain feature combinations enable it to outperform other models. Transformer models maintain stable accuracy when employing feature sets ranging from one to five and twelve to seventeen, but display considerable variability in performance when the feature count lies between five and twelve. This investigation delineates the optimal parameter ranges and contextual applicability for each model. The proposed hybrid forecasting methodology, alongside a model transfer strategy encompassing data preprocessing adjustments, parameter optimization, and weight adaptation, offers practical applicability to other commodity markets such as cement and concrete. Consequently, this research provides a scientifically grounded framework to support procurement decision-making processes within construction enterprises. Full article

Resource-constrained intelligent systems increasingly require reliable long-form reasoning capabilities under limited computational and memory budgets, particularly in edge and embedded sensing environments. However, reinforcement learning for long-horizon decision generation remains highly unstable in such low-resource settings due to severe reward sparsity and imbalanced credit assignment, which often lead to non-convergent or excessively verbose generation behavior. In this work, we propose AF-CuRL (Answer-Focused Curriculum Reinforcement Learning), a lightweight reinforcement learning framework designed to stabilize long-form generation without increasing model size or computational cost. AF-CuRL improves optimization learnability through two complementary objective-level designs: (1) answer-focused token reweighting, which concentrates policy updates on reward-critical regions of generated sequences to alleviate credit assignment imbalance, and (2) a two-phase curriculum reward schedule that prioritizes stable termination and output regularity before shifting toward correctness-oriented optimization. We evaluate AF-CuRL on a 1.5B-parameter language model under strictly constrained training settings, using mathematical reasoning tasks as a controlled and reproducible proxy for long-horizon, rule-based decision-making commonly encountered in intelligent sensing and embedded systems. Experimental results demonstrate consistent improvements in both decision accuracy and generation regularity, including higher termination reliability and reduced generation length, compared with standard sequence-level reinforcement learning baselines. These results suggest that, for resource-limited and edge-intelligent systems, structured objective design can be more effective than model scaling for achieving stable and efficient long-form reasoning, providing a practical reinforcement learning solution for intelligent systems operating under real-world constraints. Full article

Background/Objectives: Stewartia pseudocamellia Maxim. (S. pseudocamellia) has been reported to possess antioxidant and anti-inflammatory properties and contains various bioactive flavonoids and phenolic compounds. These components may contribute to neuroprotective effects relevant to depression and cognitive dysfunction. This study was conducted to evaluate the effects of 20% ethanolic extract from S. pseudocamellia leaves (ESP) on chronic unpredictable mild stress (CUMS)-induced depressive-like behaviors and cognitive dysfunction in C57BL/6 mice. Methods: C57BL/6 mice were divided into six groups: normal control (NC), normal sample (NS; ESP 100 mg/kg), CUMS, L-theanine (Thea; 4 mg/kg), ESP 50 mg/kg, and ESP 100 mg/kg groups. Phytochemical profiling of ESP was performed using ultra-performance liquid chromatography–quadrupole time-of-flight tandem mass spectrometry (UPLC-Q-TOF-MS/MS). Depressive-like behaviors and cognitive function were assessed, along with stress-related hormonal regulation and associated cellular signaling pathways. Results: Phytochemical profiling of ESP identified procyanidin B2, epicatechin, rutin, catechin gallate, kaempferol 3-O-glucoside, and quercitrin as major constituents. ESP significantly alleviated CUMS-induced depressive-like behaviors and improved spatial learning and memory. These effects were associated with modulation of stress-related hormones in serum and hypothalamic–pituitary–adrenal (HPA) axis–related proteins in the brain. ESP also enhanced antioxidant defense by activating the Nrf2 signaling pathway and improving mitochondrial function. Furthermore, ESP attenuated neuroinflammation and apoptosis by regulating the TLR4/NF-κB and JNK pathways, and promoted neuroplasticity by modulating cholinergic activity, with enhanced BDNF/TrkB signaling in the cerebral cortex and hippocampus. Conclusions: Collectively, these findings suggest that ESP exerts protective effects against CUMS-induced depressive-like behaviors and cognitive deficits in a preclinical model. Full article

Objectives: This longitudinal single-case series evaluated an AI-based routine-learning system as assistive technology (AT) for elite Boccia athletes with severe Cerebral Palsy (CP). The study aimed to provide an innovative outcome measurement approach for individualized monitoring by integrating performance scores and longitudinal kinematic variability indicators. Methods: Three national-level players performed 694 throws over eight weeks. To ensure technical credibility, trials were rated through a consensus-based assessment by a panel of two experts, serving as ground truth for AI modeling. The system utilized a Bidirectional Long Short-Term Memory (Bi-LSTM) architecture to extract 29 kinematic features and perform regression-based scoring, providing real-time augmented feedback. Results: High-baseline tasks maintained stable scores (7–9), while intermediate tasks showed significant score increases, reflecting motor learning transitions. The model achieved a Mean Squared Error of 1.14 and a Mean Absolute Error of 1.13, demonstrating high alignment with expert standards. Training demonstrated stable convergence, with loss reducing from 7.45 to 1.19. Notably, for the most severely impaired athlete, the AI system detected a 4.69% reduction in kinematic variability despite stagnant performance scores. This provides empirical evidence of movement stabilization within the cognitive stage that traditional observation might overlook. Conclusions: The Bi-LSTM system enabled accurate tracking of performance and motor variability, revealing distinct learning curves based on task difficulty. These findings demonstrate the feasibility of AI-enabled motion analysis as an AT for outcome measurement, supporting data-driven coaching where conventional evaluation is constrained by the rarity and severity of disabilities. Full article

This study examines Italian adolescents’ willingness to use electronic devices rather than printed paper for reading and writing activities, a behavioural choice that differs from more conventional pro-environmental actions due to its implications for learning and well-being. We design an online vignette experiment with two informational conditions: an individual-impact and a social-impact treatment. Socially framed information is associated with a higher propensity to prefer digital tools relative to individual framing, although overall treatment effects are modest. Stronger treatment responsiveness emerges only when students reflect on avoidable printing practices. Preferences are primarily shaped by socio-demographic factors, particularly gender, educational background, and health and environmental attitudes. Paper is valued for its perceived benefits to reasoning, memory, and reading enjoyment, while digital tools are favoured for their ease of writing and editing. Even if not fully generalizable, our findings highlight the atypical nature of a paper–digital trade-off: when consumption choices involve cognitive or identity-related considerations, sustainability-based messages alone may be insufficient. Full article

Background: Insulin resistance (IR) has emerged as a key player in the pathogenesis of cognitive impairment in Parkinson’s disease (PD). This study aims to systematically compare glucolipotoxicity-based (TyG, AIP) versus adiposity-driven (TyG-BMI, METS-IR) IR indices for their associations with PD dementia and to develop a clinically applicable nomogram using an interpretable machine learning framework. Methods: This cross-sectional study analyzed 251 PD patients: 42 with normal cognition, 160 with mild cognitive impairment (PD-MCI) and 49 with dementia (PDD). Logistic and linear regression examined associations between IR indices and cognitive impairment across different domains. Six machine learning models were compared for dementia classification, with the optimal model interpreted using SHapley Additive exPlanations (SHAP) to construct a nomogram. Results: Each standard deviation increase in TyG and AIP was linked to 79% (OR 1.79, 95%CI 1.04–3.07) and 75% (OR 1.75, 95%CI 1.05–2.91) higher risk of PDD, respectively, but not PD-MCI. In contrast, TyG-BMI and METS-IR showed no significant associations with either condition. TyG showed linear negative correlations with memory and orientation, and inverted U-shaped associations with visuospatial function and attention. AIP exhibited linear negative correlation with memory. The logistic regression model achieved the highest performance (AUC of 0.759) among six machine learning models. Crucially, SHAP analysis visually quantified TyG as a top modifiable predictor, facilitating the construction of an interpretable clinical nomogram. Conclusions: Glucolipotoxicity-based indices (TyG, AIP), unlike BMI-dependent markers (TyG-BMI, METS-IR), are robustly linked to PD dementia through domain-specific linear or nonlinear patterns. This suggests metabolic dysregulation predicts risk independent of weight loss. Furthermore, integrating SHAP-based interpretability transforms complex algorithms into a transparent, actionable tool for early risk stratification. Full article

The growing number of Internet of Things (IoT) devices has driven the need for energy-efficient communication in long-range, low-power networks like LoRa. LoRa offers wide coverage with minimal transmission power. However, radio communication remains the main energy consumer in end devices. Data compression can mitigate this issue by reducing packet size and transmission frequency. This work presents a comprehensive evaluation of classical and cutting-edge lossless compression algorithms applied to LoRa networks. Evaluated algorithms include Huffman, LZW, BSC, CMIX, PAQ8PX, GMIX, and LSTM-compress. Experiments were conducted using a Raspberry Pi 5 integrated with an RFM95W LoRa module and INA219 sensors to measure real-time power consumption, CPU load, and memory usage. Results show that classical methods, particularly LZW, achieve the best energy efficiency and reduce LoRa transmission energy by up to 7.41%. In contrast, cutting-edge machine learning (ML)-based algorithms, such as CMIX and PAQ8PX, achieve higher compression ratios but exhibit excessive computational and memory overhead, resulting in negative energy gains. Metadata overheads, including dynamic Huffman tables (28–128 bytes), also affect payload efficiency for small packets. These findings indicate that LZW is the most practical choice for energy-constrained LoRa nodes. At the same time, modern compressors, including ML-based ones, are better suited for gateways or edge servers with higher computational capacity. An open-source implementation of the experimental framework and scripts used in this study is available in the project’s public GitHub repository. Full article

This paper presents a compact floating memtranstor (MT) emulator, a memory element characterized by a direct φ–q relationship, realized without analog multipliers or complex circuitry. The proposed design employs only two active blocks—a voltage differential transconductance amplifier (VDTA) and a voltage differential current conveyor (VDCC)—along with three grounded capacitors and a single grounded electronically tunable resistor. The emulator accurately reproduces the fundamental φ–q dynamics, exhibiting origin-crossing pinched hysteresis loops under sinusoidal excitation, and operates at a low supply voltage of ±0.9 V. Electronic tunability is achieved via bias-controlled transconductance modulation, enabling flexible adaptation across excitation frequencies and operating conditions. Validation is performed through analytical modeling, Monte Carlo simulations, temperature sensitivity analysis, and full LTspice post-layout simulations using a 180 nm CMOS process. The full-custom layout occupies 2529.49 μm², with robust performance confirmed under parasitic and process variations. Adaptive learning simulations demonstrate the emulator’s artificial synaptic plasticity, highlighting its suitability for neuromorphic computing, chaos-based circuits, and nonlinear dynamical systems. The compact, low-power, and multiplier-free architecture establishes the proposed MT emulator as a practical platform for emerging analog memory-centric applications. To validate the feasibility of the proposed solution, experimental tests are performed using commercially available components. Full article

Agent-based modeling (ABM) is a powerful tool for simulating building users’ dynamic behavior in demand response (DR) programs. However, ABM faces several challenges, particularly in encoding building users’ natural language features and common sense into rules or mathematical equations. To overcome these limitations, this paper proposes an agent framework based on large language models (LLMs) to simulate building users’ air-conditioning setpoint adjustment behavior under DR. This framework leverages LLMs’ natural language processing capabilities to replicate building users’ reasoning and decision-making processes. It consists of five modules: persona, perception, decision, reflection, and memory. Agents are assigned diverse personas through natural language descriptions based on empirical survey data. LLMs drive agents to reason and make decisions based on incentive prices and historical experiences. The results show that the LLM-based agent has common sense derived from natural language-defined personas and exhibits human-like irrational characteristics. This demonstrates the feasibility of replacing rules with natural language in ABM. The LLM-based agent can more effectively model hard-to-parameterize human features and provide decision explanations through LLM outputs. The results show that the inclusion of reflection and memory modules enables the agent to learn from previous decisions and reduce unreasonable choices. Full article

To support multimedia and deep learning applications running on containers within a server, both processor cores and main memory space are critical resources for performance tuning. With the growing memory demands of applications to maintain intermediate data, installing additional dynamic random-access memory (DRAM) modules increases not only hardware costs but also the static and dynamic energy consumption of a server. In this study, both DRAM and non-volatile memory (NVM) are leveraged to provide short access latency and large main memory capacity for a server running multiple containers with diverse applications. Contention for memory space and processor cores among containers is jointly modeled as part of the performance optimization problem for the hybrid memory system of the server. Our memory and computing resource scheduling algorithms are thus developed to judiciously balance the usage of cores and DRAM space among tasks, while NVM is utilized to increase the degree of parallelism to reduce the Makespan of task batches. Benchmark programs were used to generate the input task set, and experimental results show that our solution outperforms others by achieving at least an 18.34% reduction in Makespan when 100 distinct containerized tasks are executed on a system with 512 gigabytes (GB) of NVM, 32 GB of DRAM, and eight cores. Full article

The primary focus of enhancing the efficiency of operations in the Industry 4.0 setting is Predictive and Preventive Maintenance (PPM). The paper introduces a predictive-maintenance system based on the Unified Namespace (UNS), which involves real-time sensor measurements, photogrammetry, and modelling of a digital twin to improve fault prediction and responsiveness to maintenance. This experiment was conducted over six months in a medium-sized discrete electromechanical production plant equipped with motors, Variable Speed Drives (VSDs), robot/cobots, precision grip systems, pipework systems, Magnemotion/linear motor drives, and a CNC machine. The continuous data, such as high-frequency vibration, temperature, current, and pressure, were monitored and analysed with machine-learning models, including support-vector machines, Gradient Boosting, long-short-term memory, and Random Forest, through which temporal degradation can be predicted. UNS architecture integrated all sensor and imaging data into a vendor-neutral data model through OPC UA to help ensure that all experiments could be integrated consistently and be updated in real time to real digital twins. The suggested system correctly identified mechanical and electrical failures and predicted failures before they really took place. Consequently, machine downtime was reduced by 42.25%, and Mean Time to Repair (MTTR) by 36%, compared to the prior six-month baseline period. These improvements were associated with earlier anomaly detection and digital-twin-supported pre-inspection. Overall, the findings indicate that the integration of UNS with multi-modal sensing and digital-twin technologies may enhance predictive maintenance performance in comparable industrial settings. The framework provides a data-driven, scalable solution to organisations that aim to modernise their maintenance processes, attain greater reliability and better equipment utilisation, as well as enhanced Industry 4.0 preparedness. Full article

Multi-sensor fusion provides richer information for bearing fault diagnosis. However, under variable working conditions, the coupling relationships among signals from different sensors exhibit significant non-stationarity and directionality, posing challenges for modeling and practical deployment. Existing methods often rely on fixed or symmetric graph structures or construct correlation relationships entirely based on data-driven approaches; this makes balancing physical consistency, robustness, and computational efficiency difficult. To address these issues, we propose a Physics-guided Adaptive Graph Transformer Network (AGTN) for multi-modal bearing fault diagnosis under variable working conditions. More specifically, we offer innovative improvements across three aspects. Firstly, we introduce domain knowledge priors into the graph structure learning process to adaptively construct sparse and asymmetric dynamic graph structures that capture physically meaningful directional dependencies among different sensor signals. Secondly, we combine a graph-aware transformer to jointly model the temporal features and structural correlations of multi-source signals. Finally, we further introduce a hierarchical subgraph training strategy that significantly reduces memory usage and training time while ensuring diagnostic performance. Experimental results on a self-built multi-condition bearing dataset show that AGTN achieves an average diagnostic accuracy of 99.42% under the same distribution conditions and demonstrates good generalization and robustness, e.g., variable speed and load and sensor failure. In particular, when using only 25% of the nodes for training, the model can still maintain a diagnostic accuracy of 97.9%, while reducing the peak memory usage to about 19% of that of full-graph training. The above results validate the effectiveness of the proposed method under complex industrial conditions, as well as its practical application potential in resource-constrained scenarios. Full article