Search Results (2,169)

Sleep staging based on PSG is largely confined to clinical settings, while home-based sleep monitoring often faces the challenges of insufficient unimodal information and missing modalities. Aiming to overcome these challenges, this paper proposes a unified multimodal model for sleep staging based on cardiopulmonary signals. First, a heterogeneous multi-scale feature encoder with long and short branches is adopted to adapt to the cross-modal heterogeneity of ECG and THX. It combines a Transformer encoder and a Dilated CNN to complete feature fusion and temporal modeling. Subsequently, the unified model adaptively handles flexible modality combinations by introducing global context via a modal feature alignment strategy, which is built upon a framework consisting of a bimodal global branch and unimodal dedicated branches. On the SHHS dataset, the proposed model achieved Cohen’s kappa coefficients of 0.7547, 0.7121, and 0.7305 for four-stage sleep classification under ECG+THX, ECG-only, and THX-only inputs, respectively, demonstrating consistent improvements over three separately trained individual models. Furthermore, the model exhibits robust generalization performance on the P2018 external dataset and across samples with different severity levels of SDB. This work establishes a reliable algorithmic baseline for unobtrusive, long-term home sleep monitoring with missing modalities. Full article

Remote center-of-motion mechanisms are essential in minimally invasive surgery because they allow surgical instruments or an endoscopic camera to pivot around a trocar entry point while eliminating lateral motion at the incision. This paper presents the design, kinematic modeling, prototype implementation and preliminary evaluation under laboratory conditions of a compact, spherical, remote center-of-motion robot for minimally invasive surgical orientation tasks. The proposed mechanism uses a spherical kinematic architecture actuated by a contra-rotating differential gearbox. This gearbox generates two coaxial output rotations of equal magnitude and opposite direction from a single input, mechanically synchronizing the opposed motion of the two base links and eliminating the need for cable-pulley transmission or dual electronically synchronized motors. A second actuator chain rotates the gearbox assembly around the base axis, thereby decoupling the extension–retraction motion from base-axis rotation. Forward and inverse kinematic formulations were derived for teleoperation of the robot using a 7 degrees of freedom haptic device and for remote center-of-motion orientation control using a 3-axis joystick. A proof-of-concept prototype was developed and integrated with a custom embedded controller, closed-loop motor control, a master-console interface and video feedback loop. The system was evaluated in a phantom-torso setup using a custom endoscopic camera, internal visual markers and an OptiTrack-based measurement of the remote center-of-motion accuracy. The qualitative experiment confirmed functional integration of the mechanical, electronic and software subsystems, while the optical-tracking measurement showed that the pivot constraint was maintained with a mean deviation of 1.69 mm and a root-mean-square deviation of 2.13 mm over the analyzed orientation sweep. The main limitations remain the 1:1 gearbox ratio, limited actuator torque, additively manufactured gearing and the absence of repeated-trial repeatability and full workspace characterization. Full article

The optimal expansion of unbalanced three-phase distribution networks in non-interconnected zones requires the simultaneous resolution of two highly complex planning decisions: the selection of feeder routes and the sizing of conductors. This problem, formulated as a non-convex mixed-integer nonlinear program (MINLP), poses significant computational challenges due to the combinatorial explosion of radial topologies, discrete conductor choices, and the nonlinearity of three-phase power-flow equations. While metaheuristics offer flexible exploration, they lack optimality guarantees and repeatability, whereas exact MINLP solvers provide rigorous solutions but become computationally intractable for systems of realistic size. To overcome these limitations, this paper introduces a novel hybrid exact–metaheuristic framework that synergistically combines the global exploration capabilities of the Equilibrium Optimizer (EO) with the rigorous evaluation power of an exact MINLP model. In this cascade architecture, EO efficiently navigates the discrete space of radial topologies, while the exact MINLP stage, solved using BONMIN with an interior-point branch-and-bound scheme, optimizes conductor selection and evaluates the full annualized cost, rigorously enforcing voltage, ampacity, and physical constraints. The proposed methodology was validated on 10-, 30-, 50-, and 110-node test systems derived from real Colombian non-interconnected zones (Nuquí, Leticia, San Andrés, and a large-scale urban case). Comparative analysis against pure metaheuristics (SSA, GWO, VSA) and standalone MINLP demonstrates that EO-MINLP consistently yields the lowest total annualized costs, achieving savings of up to 0.42%, 0.71%, and 1.36% over the best pure metaheuristic for the 10-, 30-, and 50-node systems, respectively. Crucially, the hybrid strategy dramatically enhances scalability, reducing the standalone MINLP computational time by 15.79%, 78.68%, and 88.95% for these cases, while preserving solution quality and improving repeatability (standard deviation reduced from over 1.2% to as low as 0.11%). For the challenging 110-node system, where the standalone MINLP proved computationally infeasible, the proposed method successfully delivered a feasible, high-quality solution with a standard deviation of just 0.43%, confirming its practical applicability to large-scale planning. These results demonstrate that the EO-MINLP framework provides a robust, scalable, and economically superior tool for the cost-effective design of unbalanced distribution networks, effectively bridging the gap between the flexibility of stochastic search and the rigor of mathematical programming. Full article

Choosing among closely related higher-education programmes requires interpretation of heterogeneous applicant data while preserving data confidentiality. This study compares ten locally executable large language model (LLM) configurations as semantic rankers, contextualises their performance against a hybrid term frequency–inverse document frequency (TF–IDF) cosine baseline, and evaluates robustness when relevant competencies are expressed indirectly. The main benchmark comprised 50 anonymised applicant profiles and 10 degree programmes; an additional processed-profile robustness set comprising 10 profiles was used to reduce direct lexical overlap with the programme catalogue. Rankings were evaluated using Accuracy@1, Accuracy@3, normalised discounted cumulative gain at 5 (NDCG@5) and mean reciprocal rank at 5 (MRR@5), while structured-output validity and inference time were assessed for the LLMs. Among the local LLMs, gpt-oss-20b-MXFP4 achieved the highest Accuracy@1 (0.76), whereas gemma-4-E4B-it-Q8_0 achieved the highest Accuracy@3 (0.92), and Ministral-3-14B-Reasoning-2512-Q4_K_M provided a favourable quality–latency balance. On the main benchmark, TF–IDF achieved Accuracy@1 = 0.88 and NDCG@5 = 0.9557, exceeding all LLM configurations and demonstrating a strong lexical signal. On the processed-profile robustness set, the Accuracy@1 of the TF–IDF baseline decreased to 0.60, whereas gemma achieved 0.90. The results provide initial evidence that several local LLM configurations can reproduce observed programme-selection patterns in a limited pilot benchmark. However, the findings should be interpreted as task-specific model-comparison results rather than as full validation of an autonomous career guidance system. Full article

Off-grid residential microgrids in tropical regions require storage architectures capable of maintaining renewable electricity supply under variable solar resources, evening demand peaks, and diverse household consumption levels. In PV–battery–hydrogen systems, however, economic indicators can be difficult to interpret when software-reported costs are compared directly with externally calculated LCOE values based on different accounting conventions. This study presents a metric-reconciled techno-economic reconstruction approach for retained PV–battery–hydrogen microgrid configurations serving off-grid residential demand in Chetumal, Mexico. The objective is not to introduce a new global optimization or to claim the universal superiority of a specific architecture, but to separate archived HOMER Pro benchmark outputs from an external techno-economic model (TEM). The TEM reconstructs net present cost, scheduled replacements, salvage treatment, discounted delivered electricity, HOMER-derived LCOE, TEM-derived LCOE, sensitivity indicators, and storage role metrics using declared accounting assumptions. The approach is applied to two representative residential demand scenarios of 16.67 and 53.42 kWh/day. Both retained configurations achieved a 100% renewable fraction with negligible unmet load. Battery discharge increased from 827.12 kWh/year in the low-demand case to 6125.52 kWh/year in the high-demand case, highlighting the increasing role of the battery in short-duration balancing. In contrast, the hydrogen pathway acted as a delayed-backup layer by converting surplus PV electricity into hydrogen and later recovering it through PEM fuel cell generation. The TEM closely matched the HOMER-derived LCOE benchmark, with deviations below 4%, yielding TEM-derived LCOE values of 0.3320 and 0.3571 USD/kWh for the low- and high-demand cases, respectively. Sensitivity analysis showed that delivered electricity, discount rate, PV cost, and battery cost were the main LCOE drivers, while deterministic multi-parameter scenarios confirmed the combined influence of financing, component costs, O&M, PV degradation, and electricity delivered. Overall, the proposed approach provides an auditable basis for metric reconciliation, early-stage technology assessment, and storage role interpretation in tropical off-grid microgrids. Future extensions should include architecture-level re-optimization, flexible loads, degradation-aware modeling, and part-load component behavior. Full article

Commercial refrigeration systems represent some of the largest energy consumers in supermarkets, and therefore particular attention needs to be paid to increasing energy efficiency to reduce overall energy consumption and meet climate goals by 2030. This study investigates the performance of a CO₂ (R744) commercial refrigeration system with evaporators operating alternately in dry and flooded modes. This operation is possible due to a particular adjustment using liquid sensors installed in the middle of both low-temperature (LT) and medium-temperature (MT) liquid separators, which transmit information to the controllers that regulate the compressor rack and evaporators, to switch from dry to flooded operation when the liquid level rises and vice versa when the level drops. The results show that the correct regulation of the system of 50% with 6K superheat operation and 50% with 3K superheat operation on MT evaporators, respectively, and 50% with 6K superheat operation and 50% with 4K superheat operation on LT evaporators leads to a reduction of energy consumption compared to 100% operation of all evaporators with 6K superheat by 6.9% per year for the compressor rack. Full article

Glaucoma is a leading cause of blindness, and early detection is critical. Convolutional neural networks (CNNs) have shown impressive performance in glaucoma diagnosis, but their black-box nature remains a barrier to clinical use. Existing explainable AI (XAI) methods such as Grad-CAM have limitations in identifying and quantifying subtle regional features. In this study, we propose a method to clarify what CNNs focus on by analyzing how model performance changes under localized adversarial noise. Using VGG16 for glaucoma classification, we applied noise generated by the Fast Gradient Sign Method (FGSM) to the whole fundus image and to specific subregions, then compared the impact on classification performance. Results showed that perturbations to the optic disc, especially its outer margin, had the greatest effect on model performance. This suggests that the CNN captures fine anatomical features such as optic disc cupping and neuroretinal rim thinning, which aligns with what ophthalmologists typically look for. At the same time, perturbations in the macula and perivascular regions also affected performance, indicating gaps between current clinical diagnostic criteria and the CNN’s decision-making process. This approach can help establish the clinical reliability of CNNs and may also reveal features that have not been recognized in conventional clinical practice. Full article

The first edition of the Special Issue entitled “Emerging Paradigms in AI, Autonomous Systems, and Intelligent Technologies”, published in Technologies within the Information and Communication Technologies section, was conceived around a practical observation that is now widely shared in engineering research: automation remains useful, but contemporary technological systems increasingly require autonomy, real-time decision making, transparent reasoning, robust communication, and reliable interaction with the physical world [...] Full article

In the Argoverse 2 experiments reported here, the simplest Constant Turn Rate and Acceleration (CTRA) decoder was stable but missed many interaction-driven turns and merges, while residual decoders without enough control improved early displacement but increased final-horizon error. This paper therefore studies a compact decoder in which each of the six futures is represented as a CTRA anchor plus an autoregressive position residual. The residual gated recurrent unit (GRU) is initialized from fused target-history, top-k neighbor, and lane-polyline context, and its contribution is scaled by a mode-specific gate and learned exponential decay. On the 10k/2k sanity ablations, CTRA-only decoding reached ${\mathrm{minFDE}}_6=7.189$ m, while autoregressive residuals with a larger correction GRU reduced it to $4.157$ m; removing the gate increased it again to $4.946$ m. On the full Argoverse 2 validation split, the final configuration achieves a minimum average displacement error of ${\mathrm{minADE}}_6=1.21$ m and a minimum final displacement error of ${\mathrm{minFDE}}_6=2.78$ m. The reported diagnostics show that the compact model generates a useful six-mode set, but still needs better probability ranking for top-1 selection. Full article

Modern multi-agent deep reinforcement learning algorithms have demonstrated empirical success in communication games, yet their black box nature precludes the analytical identification of the transition from random babbling to coordinated signalling. This study introduces an explicitly parameterised, interpretable surrogate model of belief evolution in Lewis signalling games. The proposed ordinary differential equation retains the strategic structure of cheap talk while permitting the closed-form computation of the Jacobian spectrum at the uniform babbling equilibrium. It was proven that the onset of communication corresponded to a supercritical pitchfork bifurcation with a critical threshold determined by the dissipation and sensitivity parameters. Consequently, the leading eigenvalue of the dynamics serves as a detector of the emergence point. The analytical predictions were validated through iterative simulations of Lewis signalling games, illustrating how the critical threshold dictates the consistent and stable transition from stochastic babbling to separating equilibrium. Moreover, a phenomenological experiment demonstrates a possible path toward extending spectral diagnostics to policies parameterised by neural networks in a low-dimensional setting, serving as a bridge towards potential method adaptation for general deep reinforcement learning policies, without fully validating the theoretical framework. Full article

This paper presents a code-based static verification of the FA125 hydraulic drilling rig mast under its governing design load combination. Unlike the previously published dynamic investigation of the same platform, the present work establishes the baseline static load path, identifies the governing structural members, evaluates the local stress state in the mast-to-support connection plates, and computes the effective safety coefficients. The mixed finite element model integrates the lattice mast, the support frame, and the base assembly, utilizing beam elements for the slender load-bearing members and shell elements for the localized plate-type connection regions. The governing load combination encompasses structural self-weight, maximum hook load (14.90 kN), and the reactive torque transmitted by the drilling head (0.50 kNm). The maximum mast-top displacement was limited to 4.75 mm. The critical beam elements were located within the lateral base-support region, developing peak compressive and tensile stresses of 70.08 MPa and 69.21 MPa, respectively. The highest localized shell-level von Mises stress (23.62 MPa) was concentrated within the mast-to-support interface connection plates. The results mathematically confirm that the existing FA125 steel structure satisfies the active design criteria, providing a distinct static reference map required for subsequent structural optimization, lightweighting, and selective material substitution. Full article

Gesture recognition systems powered by artificial intelligence provide a promising solution for mobility and independence for individuals with physical disabilities. However, the deployment of such systems remains limited due to some challenges related to robustness, different user requirements, affordability for lower income people, and adaptation to low-resource environments. This study presents a systematic review of gesture-controlled intelligent wheelchair systems published recently. After searching academic databases, 600 studies were found. After removing duplicate and irrelevant studies and applying the inclusion and exclusion criteria, 72 of the most relevant studies were selected for detailed analysis. The review identifies three major approaches: vision-based methods, sensor-based techniques, and signal-based techniques utilizing electromyography (EMG) and inertial measurement units (IMU), and hybrid multimodal frameworks. A comparative study is conducted to analyze performance metrics, computational requirements, datasets, and validation strategies among these approaches. The findings identify several critical research gaps, including limited real-world testing, insufficient handling of pathological tremors, weak environmental robustness, and the lack of culturally aligned gesture vocabularies. The findings identify important design considerations and research directions for developing robust, affordable, and accessible intelligent wheelchair systems suitable for underserved people in low-resource environments. Full article

To address the insufficient representation of terrain constraints and surface resistance in traditional path planning for off-road environments, this study proposes an improved A* path planning method for unmanned ground vehicles. First, an off-road environment model is constructed using Digital Elevation Model (DEM) and land cover data, and environment–vehicle traversability is evaluated by integrating geometric and support-based traversability analyses. Geometric constraints are determined using slope thresholds, minimum ground clearance, and approach/departure angles, while support-based traversability is quantified through a surface velocity influence coefficient to reflect traversal-efficiency differences under various surface conditions. These terrain and surface constraints are incorporated into the actual cost function of the A* algorithm, and a direction-corrected heuristic function is designed to enhance goal-directed search. Experiments conducted in Jiancaoping District, Taiyuan, show that, compared with the traditional A* algorithm, the proposed method reduces cumulative travel time, maximum path slope, and expanded nodes by 15.3%, 22.9%, and 47.8%, respectively, with only a 2.4% increase in path length. The results demonstrate that the proposed method effectively avoids steep and high-resistance areas while achieving coordinated optimization of path length, traversal efficiency, and terrain safety. Full article

This research evaluates the feasibility of implementing photovoltaic solar systems in the Ecuadorian Amazon to harness solar energy and increase energy security in the region. It is based on the need to reduce direct dependence on fossil fuels and existing hydroelectric systems. The overall framework is to transform the energy matrix to utilize incident solar energy, integrating it with current hydroelectric and thermal generation. The fundamental goal is to evaluate the energy resource using specialized software such as Homer Pro and develop designs for the proper operation of photovoltaic solar technology, which will contribute its surplus energy to the National Interconnected System (SNI) and, therefore, reduce the country’s high dependence on the hydrological cycle. The results obtained demonstrate that solar power plants can be of great benefit to the country, especially when combined with wind and existing hydroelectric power. This will contribute to the diversification of energy sources and, consequently, to energy security through the increase in renewable energy. In the worst-case scenario, the cost of energy can be 7 cents per kWh, and in the best-case scenario, in a combined dispatch, 3 cents per kWh. Full article

Atmospheric turbulence distorts the wavefront of propagating optical radiation, degrading image resolution in astronomical telescopes and reducing power density at the target in focusing applications. These effects can be studied under controlled laboratory conditions using turbulence-generating devices—such as fan heaters (rough control), phase plates, or active mirrors (fine control)—in combination with a wavefront sensor for measurements. To support this research, we developed a software simulator for reconstructing atmospheric phase fluctuations. The integrated software–hardware system can generate phase screens following Kolmogorov turbulence statistics, incorporating parameters for wind velocity and the D/r₀ ratio. Phase screens were produced with an average approximation error of 0.01 µm (less than 5%). The average reconstruction error was 0.017 µm, corresponding to approximately 8%. The newly developed phase screen simulator outperforms the fastest existing version in several key aspects. Its aperture size is doubled, increasing from 400 mm to 800 mm, while the phase screen generation resolution expands by half, from 700 × 700 pixels to 1024 × 1024 pixels. The operating wavelength range also broadens significantly—from a maximum of 2.2 µm in the existing tool to 10 µm in the new one. Additionally, the wind velocity range becomes 1.5 times wider, extending from 30 m/s to 50 m/s. The developed tool might be useful for the performance analysis of wireless links, particularly in the estimation of bit error rate and quantum efficiency using the wavefront root mean square error. Full article