Search Results (7,547)

Artificial intelligence (AI) and machine learning (ML), especially deep learning, have profoundly transformed biology by enabling precise interpretation of complex genomic and proteomic data. This review presents a comprehensive overview of cutting-edge AI methodologies spanning from foundational neural networks to advanced transformer architectures and large language models (LLMs). These tools have revolutionized our ability to predict gene function, identify genetic variants, and accurately determine protein structures and interactions, exemplified by landmark milestones such as AlphaFold and DeepBind. We elaborate on the synergistic integration of genomics and protein structure prediction through AI, highlighting recent breakthroughs in generative models capable of designing novel proteins and genomic sequences at unprecedented scale and accuracy. Furthermore, the fusion of multi-omics data using graph neural networks and hybrid AI frameworks has provided nuanced insights into cellular heterogeneity and disease mechanisms, propelling personalized medicine and drug discovery. This review also discusses ongoing challenges including data quality, model interpretability, ethical concerns, and computational demands. By synthesizing current progress and emerging frontiers, we provide insights to guide researchers in harnessing AI’s transformative power across the biological spectrum from genes to functional proteins. Full article

Molecular simulation is central to modern drug discovery but is often limited by high computational cost and the complexity of molecular interactions. Deep-learning drug–target interaction (DTI) prediction can accelerate screening; however, many models underuse the local functional structure features—binding motifs, reactive groups, and residue-level fragments—that drive recognition. We present LoF-DTI, a framework that explicitly represents and couples such local features. Drugs are converted from SMILES into molecular graphs and targets from sequences into feature representations. On the drug side, a Jumping Knowledge (JK) enhanced Graph Isomorphism Network (GIN) extracts atom- and neighborhood-level patterns; on the target side, residual CNN blocks with progressively enlarged receptive fields, augmented by N-mer substructural statistics, capture multi-scale local motifs. A Gated Cross-Attention (GCA) module then performs atom-to-residue interaction learning, highlighting decisive local pairs and providing token-level interpretability through attention scores. By prioritizing locality during both encoding and interaction, LoF-DTI delivers competitive results across multiple benchmarks and improves early retrieval relevant to virtual screening. Case analyses show that the model recovers known functional binding sites, suggesting strong potential to provide mechanism-aware guidance for molecular simulation and to streamline the drug design pipeline. Full article

The calculation of energy consumption in building plans is usually carried out after design completion, resulting in high time costs and hindering their application in the early design stage. This study focused on the heating and cooling demands of nearly zero energy residential buildings in Jinan and developed an envelope optimization model for the design stage. Firstly, field research on residential buildings in Jinan was conducted, and the shape coefficient based on research data was determined. Subsequently, ten design parameters were selected, and a prediction function was established through multiple linear regression. Finally, the mechanisms between the parameters and energy consumption were revealed, and the reliability of the model was verified. Results showed that the most energy-efficient shape coefficient is an 18-story rectangular building with a length of 52.6 m, a width of 15.1 m, and a floor-to-floor height of 3 m. The goodness of fit of the prediction function is 0.994. The adjusted R² and RMSE of the neural network model in interpretable analysis are 0.933 and 0.089, respectively. The window-to-wall ratio significantly impacts energy consumption. This study addresses the lack of energy optimization by establishing a process that first determines energy-efficient parameter combinations and then refines the architectural scheme, and provides software to assist architects in design during schematic phases. Full article

The frequency content of strong ground motion significantly affects the response of engineered systems under seismic excitation. Among some scalar parameters which exist in the literature, the mean period T_m has proved to be the most efficient. Ground Motion Predictive Equations (GMPEs) are usually developed for ground motion parameters through the calibration of coefficients of predefined functional forms, via linear or nonlinear regression, and based on recorded ground motion data. Such expressions of T_m are rare in the literature. Recently, the use of machine learning (ML) algorithms in earthquake engineering and engineering seismology has increased. The Artificial Neural Network (ANN) is an effective ML algorithm which has already been explored for the development of GMPEs for amplitude-based ground motion parameters. Within the work presented herein, multiple nonlinear regression (NLR)- and ANN-based GMPEs are developed for T_m using the latest strong motion database for shallow earthquakes in Greece. To the author’s knowledge, the implementation of ANN for producing GMPEs for T_m for shallow earthquake events has not been explored. Direct comparison between the NLR- and ANN-based GMPEs is performed, in terms of performance indexes, aleatory uncertainty, and working examples, as well as testing against earthquake events not included in the original dataset. The results reveal that the ANN-based GMPEs are useful in reducing aleatory uncertainty, although care should be taken in their implementation to avoid overfitting issues. Full article

Reservoir computing is an approach to machine learning that leverages the dynamics of a complex system alongside a simple, often linear, machine learning model for a designated task. While many efforts have previously focused their attention on integrating neurons, which produce an output in response to large, sustained inputs, we focus on using differentiating neurons, which produce an output in response to large changes in input. Here, we introduce a small-world graph built from rings of differentiating neurons as a Reservoir Computing substrate. We find the coupling strength and network topology that enable these small-world networks to function as an effective reservoir. The dynamics of differentiating neurons naturally give rise to oscillatory dynamics when arranged in rings, where we study their computational use in the Reservoir Computing setting. We demonstrate the efficacy of these networks in the MNIST digit recognition task, achieving comparable performance of 90.65% to existing Reservoir Computing approaches. Beyond accuracy, we conduct systematic analysis of our reservoir’s internal dynamics using three complementary complexity measures that quantify neuronal activity balance, input dependence, and effective dimensionality. Our analysis reveals that optimal performance emerges when the reservoir operates with intermediate levels of neural entropy and input sensitivity, consistent with the edge-of-chaos hypothesis, where the system balances stability and responsiveness. The findings suggest that differentiating neurons can be a potential alternative to integrating neurons and can provide a sustainable future alternative for power-hungry AI applications. Full article

As urbanization accelerates, solid waste volume increases, making municipal solid waste incineration (MSWI) a primary disposal method. However, low combustion efficiency and harmful gas emissions, such as nitrogen oxides (NO_X), contribute to significant environmental pollution. Improving combustion efficiency and reducing pollutants are critical challenges in waste incineration. Due to the process’s complexity and operational fluctuations, traditional PID and model-based methods often fail to deliver optimal results, making this a key research focus. To address this, this paper proposes an optimal control method for the solid waste incineration process, aimed at improving combustion efficiency and reducing emissions. By establishing Radial Basis Function (RBF) neural network prediction models for CO, CO₂, and NO_X, and integrating an improved Pelican Optimization Algorithm (IPOA), an optimized control strategy for air volume and pressure settings is developed. Experimental results demonstrate that the proposed method significantly enhances combustion efficiency while effectively reducing NO_X emissions. Furthermore, under varying operational conditions, the method can adaptively adjust the air volume and pressure settings, ensuring system adaptability to new conditions and maintaining both combustion efficiency and NO_X emission concentrations within target ranges. Full article

Medical endoscopic video processing requires real-time execution of color component acquisition, color filter array (CFA) demosaicing, and high dynamic range (HDR) compression under low-light conditions, while adhering to strict thermal constraints within the surgical handpiece. Traditional hardware-aware neural architecture search (NAS) relies on fixed hardware design spaces, making it difficult to balance accuracy, power consumption, and real-time performance. A collaborative “power-accuracy” optimization method is proposed for hardware-aware NAS. Firstly, we proposed a novel hardware modeling framework by abstracting FPGA heterogeneous resources into unified cell units and establishing a power–temperature closed-loop model to ensure that the handpiece surface temperature does not exceed clinical thresholds. In this framework, we constrained the interstage latency balance in pipelines to avoid routing congestion and frequency degradation caused by deep pipelines. Then, we optimized the NAS strategy by using pipeline blocks and combined with a hardware efficiency reward function. Finally, color component acquisition, CFA demosaicing, dynamic range compression, dynamic precision quantization, and streaming architecture are integrated into our framework. Experiments demonstrate that the proposed method achieves 2.8 W power consumption at 47 °C on a Xilinx ZCU102 platform, with a 54% improvement in throughput (vs. hardware-aware NAS), providing an engineer-ready lightweight network for medical edge devices such as endoscopes. Full article

Inter-saccadic times or eye fixation durations (EFDs) are relatively stable at around 250 ms, equivalent to four saccades per second. However, the mean and standard deviation are not sufficient to describe the frequency histogram distribution of EFD. The exGaussian has been proposed for fitting the EFD histograms. The present report tries to adjust a competition model (C model) between the saccadic and the fixation network to the EFD histograms. This model is at a rather conceptual level (computational level in Marr’s classification). Both models were adjusted to EFD from an open database with data of 179,473 eye fixations. The C model showed to be able, along with exGaussian model, to be compatible with explaining the EFD distributions. The two parameters of the C model can be ascribed to (i) a refractory period for new saccades modeled by a sigmoid equation (A parameter), while (ii) the ps parameter would be related to the continuous competition between the saccadic network related to the saliency map and the eye fixation network, and would be modeled through a geometric probability density function. The model suggests that competition between neural networks would be an organizational property of brain neural networks to facilitate the decision process for action and perception. In the visual scene scanning, the C model dynamic justifies the early post-saccadic stability of the foveated image, and the subsequent exploration of a broad space in the observed image. The code to extract the data and to run the model is added in the ^{Supplementary Materials}. Additionally, entropy of EFD is reported. Full article

In this study, a guar gum-based adsorbent was developed and evaluated for the removal of Ni(II) ions from aqueous solutions through a combined experimental and machine learning (ML) approach. The adsorbent was characterized using FTIR, SEM, XRD, TGA, and BET analyses to confirm surface functionality and porous morphology suitable for metal binding. Batch adsorption experiments were conducted to optimize the effects of pH, adsorbent dosage, contact time, temperature, and initial metal concentration. The adsorption efficiency increased with higher pH and adsorbent dosage, achieving a maximum Ni(II) removal of 97% (qₘ = 86.0 mg g⁻¹) under optimal conditions (pH 6.0, dosage 1.0 g L⁻¹, contact time 60 min, and initial concentration 50 mg L⁻¹). The process followed the pseudo-second-order kinetic and Langmuir isotherm models. Thermodynamic results revealed the spontaneous, endothermic, and physical nature of the adsorption process. To complement the experimental findings, artificial neural network (ANN) and k-nearest neighbor (KNN) models were developed to predict Ni(II) removal efficiency based on process parameters. The ANN model yielded a higher prediction accuracy (R² = 0.97) compared to KNN (R² = 0.95), validating the strong correlation between experimental and predicted outcomes. The convergence of experimental optimization and ML prediction demonstrates a robust framework for designing eco-friendly, biopolymer-based adsorbents for heavy metal remediation. Full article

Urban Form (UF), as a synthesis of urban functions and socioeconomic elements, is closely associated with Anthropogenic Carbon Emissions (ACE) and has important implications for low-carbon urban planning. As a key national economic strategy region, the Yangtze River Economic Belt (YREB) exhibits pronounced heterogeneity in urban development, highlighting the urgent need to elucidate the interaction mechanisms between UF and ACE to support carbon reduction strategies. This study employs nighttime light data and carbon emission records from 2002 to 2022 in the YREB. By integrating Support Vector Regression (SVR), Random Forest (RF), and Gradient Boosting Decision Tree (GBDT), we developed a neural network ensemble model (RSG-Net) to analyze the impacts and driving mechanisms of UF on ACE. The results indicate the following: (1) Over the past two decades, total ACE in the YREB increased by 196%, displaying a three-phase trajectory of rapid growth, deceleration, and rebound. (2) The RSG-Net model achieved superior predictive performance, with an R² of 0.93, an RMSE of 1.96 × 10⁶ t, an RPD of 3.69, and a PBIAS of 4.53%. (3) Based on Pearson correlation analysis and SHAP (Shapley Additive Explanations) feature importance, beyond economic and demographic indicators, the most influential UF indicators are ranked as Number of Urban Patches (NP), Normalized Difference Vegetation Index (NDVI), and Construction Land Concentration (CLC). These findings demonstrate that the RSG-Net model can not only predict ACE but also identify key UF factors and explain their interrelationships, thereby providing technical support for the formulation of urban carbon reduction strategies. Full article

In the domain of mining and mineral processing, LIDAR sensors are employed to obtain precise three-dimensional measurements of the surrounding environment. However, the functionality of these sensors is hindered by the dust produced by mining operations. In order to address this problem, a neural network-based method is proposed. This method is capable of filtering dust measurements in real time from point clouds obtained using LIDARs. The proposed method is trained and validated using real data, yielding results that are at the forefront of the field. Furthermore, a public database is constructed using LIDAR sensor data from diverse dusty environments. The database is made public for use in the training and benchmarking of dust filtering methods. Full article

Accurate depth image inpainting in complex urban environments remains a critical challenge due to occlusions, reflections, and sensor limitations, which often result in significant data loss. We propose a hybrid deep learning framework that explicitly combines local and global modelling through Convolutional Neural Networks (CNNs) and Transformer modules. The model employs a multi-branch parallel architecture, where the CNN branch captures fine-grained local textures and edges, while the Transformer branch models global semantic structures and long-range dependencies. We introduce an optimized attention mechanism, Agent Attention, which differs from existing efficient/linear attention methods by using learnable proxy tokens tailored for urban scene categories (e.g., façades, sky, ground). A content-guided dynamic fusion module adaptively combines multi-scale features to enhance structural alignment and texture recovery. The frame-work is trained with a composite loss function incorporating pixel accuracy, perceptual similarity, adversarial realism, and structural consistency. Extensive experiments on the Paris StreetView dataset demonstrate that the proposed method achieves state-of-the-art performance, outperforming existing approaches in PSNR, SSIM, and LPIPS metrics. The study highlights the potential of multi-scale modeling for urban depth inpainting and discusses challenges in real-world deployment, ethical considerations, and future directions for multimodal integration. Full article

Physics-Informed Neural Networks (PINNs) have emerged as a promising paradigm for solving partial differential equations (PDEs) by embedding physical laws into the learning process. However, standard PINNs often suffer from training instabilities and unbalanced optimization when handling multi-term loss functions, especially in problems involving singular perturbations, fractional operators, or multi-scale behaviors. To address these limitations, we propose a novel gradient variance weighting physics-informed neural network (GVW-PINN), which adaptively adjusts the loss weights based on the variance of gradient magnitudes during training. This mechanism balances the optimization dynamics across different loss terms, thereby enhancing both convergence stability and solution accuracy. We evaluate GVW-PINN on three representative PDE models and numerical experiments demonstrate that GVW-PINN consistently outperforms the conventional PINN in terms of training efficiency, loss convergence, and predictive accuracy. In particular, GVW-PINN achieves smoother and faster loss reduction, reduces relative errors by one to two orders of magnitude, and exhibits superior generalization to unseen domains. The proposed framework provides a robust and flexible strategy for applying PINNs to a wide range of integer- and fractional-order PDEs, highlighting its potential for advancing data-driven scientific computing in complex physical systems. Full article

The efficient and non-destructive inspection of the chlorophyll content of grey jujube leaf is of great significance for its growth surveillance and nutritional diagnosis. Near-infrared spectroscopy combined with chemometric methods provides an effective approach to achieve this goal. This study took grey jujube leaves as the research object, systematically collected near-infrared spectral data in the range of 4000–10,000 cm⁻¹, and simultaneously measured their soil and plant analyzer development (SPAD) value as a reference index for chlorophyll content. Through various pretreatment and their combination methods on the original spectrum—smooth, standard normal variable transformation (SNV), first derivative (FD), second derivative (SD), smooth + first derivative (Smooth + FD), smooth + second derivative (Smooth + SD), standard normal variable transformation + first derivative (SNV + FD), standard normal variable transformation + second derivative (SNV + SD)—the effects of different methods on the quality of the spectrum and its correlation with SPAD value were compared. The competitive adaptive reweighted sampling algorithm (CARS) was adopted to extract the characteristic wavelength, aiming to reduce data dimensionality and optimize model input. Both BP neural network and RBF neural network prediction models were established, and the model performance under different training functions was compared. The results indicate that after Smooth + FD pretreatment, followed by CARS screening of the characteristic wavelength, the BP neural network model trained using the LBFGS algorithm demonstrated the best performance, with its coefficient of determination (R²) of 0.87 (training set) and 0.85 (validation set), root mean square error (RMSE) of 1.36 (training set) and 1.35 (validation set), and residual prediction deviation (RPD) of 2.81 (training set) and 2.56 (validation set) showing good prediction accuracy and robustness. Research indicates that by combining near-infrared spectroscopy with feature extraction and machine learning methods, the rapid and non-destructive inspection of the grey jujube leaf SPAD value can be achieved, providing reliable technical support for the real-time monitoring of the nutritional status of jujube trees. Full article

Pipeline leak detection through acoustic signal measurement faces critical challenges, including insufficient utilization of time-frequency domain features, poor adaptability to noisy environments, and inadequate exploitation of frequency-domain prior knowledge in existing deep learning approaches. This paper proposes a Multi-Scale Frequency-Aware Transformer (MSFAT) architecture that integrates measurement-based acoustic signal analysis with artificial intelligence techniques. The MSFAT framework consists of four core components: a frequency-aware embedding layer that achieves joint representation learning of time-frequency dual-domain features through parallel temporal convolution and frequency transformation, a multi-head frequency attention mechanism that dynamically adjusts attention weights based on spectral distribution using frequency features as modulation signals, an adaptive noise filtering module that integrates noise detection, signal enhancement, and adaptive fusion functions through end-to-end joint optimization, and a multi-scale feature aggregation mechanism that extracts discriminative global representations through complementary pooling strategies. The proposed method addresses the fundamental limitations of traditional measurement-based detection systems by incorporating domain-specific prior knowledge into neural network architecture design. Experimental validation demonstrates that MSFAT achieves 97.2% accuracy and an F1-score, representing improvements of 10.5% and 10.9%, respectively, compared to standard Transformer approaches. The model maintains robust detection performance across signal-to-noise ratio conditions ranging from 5 to 30 dB, demonstrating superior adaptability to complex industrial measurement environments. Ablation studies confirm the effectiveness of each innovative module, with frequency-aware mechanisms contributing most significantly to the enhanced measurement precision and reliability in pipeline leak detection applications. Full article