RESUMEN
Rime optimization algorithm (RIME) encounters issues such as an imbalance between exploitation and exploration, susceptibility to local optima, and low convergence accuracy when handling problems. This paper introduces a variant of RIME called IRIME to address these drawbacks. IRIME integrates the soft besiege (SB) and composite mutation strategy (CMS) and restart strategy (RS). To comprehensively validate IRIME's performance, IEEE CEC 2017 benchmark tests were conducted, comparing it against many advanced algorithms. The results indicate that the performance of IRIME is the best. In addition, applying IRIME in four engineering problems reflects the performance of IRIME in solving practical problems. Finally, the paper proposes a binary version, bIRIME, that can be applied to feature selection problems. bIRIMR performs well on 12 low-dimensional datasets and 24 high-dimensional datasets. It outperforms other advanced algorithms in terms of the number of feature subsets and classification accuracy. In conclusion, bIRIME has great potential in feature selection.
RESUMEN
Axolotls are uniquely able to completely regenerate the spinal cord after amputation. The underlying governing mechanisms of this regenerative response have not yet been fully elucidated. We previously found that spinal cord regeneration is mainly driven by cell-cycle acceleration of ependymal cells, recruited by a hypothetical signal propagating from the injury. However, the nature of the signal and its propagation remain unknown. In this theoretical study, we investigated whether the regeneration-inducing signal can follow a reaction-diffusion process. We developed a computational model, validated it with experimental data, and showed that the signal dynamics can be understood in terms of reaction-diffusion mechanism. By developing a theory of the regenerating outgrowth in the limit of fast reaction-diffusion, we demonstrate that control of regenerative response solely relies on cell-to-signal sensitivity and the signal reaction-diffusion characteristic length. This study lays foundations for further identification of the signal controlling regeneration of the spinal cord.
RESUMEN
Inductive generalization is adaptive in novel contexts for both biological and artificial intelligence. Spontaneous generalization in inexperienced animals raises questions on whether predispositions (evolutionarily acquired biases, or priors) enable generalization from sparse data, without reinforcement. We exposed neonate chicks to an artificial social partner of a specific color, and then looked at generalization on the red-yellow or blue-green ranges. Generalization was inconsistent with an unbiased model. Biases included asymmetrical generalization gradients, some preferences for unfamiliar stimuli, different speed of learning, faster learning for colors infrequent in the natural spectrum. Generalization was consistent with a Bayesian model that incorporates predispositions as initial preferences and treats the learning process as an update of predispositions. Newborn chicks are evolutionarily prepared for generalization, via biases independent from experience, reinforcement, or supervision. To solve the problem of induction, biological and artificial intelligence can use biases tuned to infrequent stimuli, such as the red and blue colors.
RESUMEN
Current studies in early cancer detection based on liquid biopsy data often rely on off-the-shelf models and face challenges with heterogeneous data, as well as manually designed data preprocessing pipelines with different parameter settings. To address those challenges, we present AutoCancer, an automated, multimodal, and interpretable transformer-based framework. This framework integrates feature selection, neural architecture search, and hyperparameter optimization into a unified optimization problem with Bayesian optimization. Comprehensive experiments demonstrate that AutoCancer achieves accurate performance in specific cancer types and pan-cancer analysis, outperforming existing methods across three cohorts. We further demonstrated the interpretability of AutoCancer by identifying key gene mutations associated with non-small cell lung cancer to pinpoint crucial factors at different stages and subtypes. The robustness of AutoCancer, coupled with its strong interpretability, underscores its potential for clinical applications in early cancer detection.
RESUMEN
Bronchoscopic-assisted discrimination of lung tumors presents challenges, especially in cases with contraindications or inaccessible lesions. Through meta-analysis and validation using the HumanMethylation450 database, this study identified methylation markers for molecular discrimination in lung tumors and designed a sequencing panel. DNA samples from 118 bronchial washing fluid (BWF) specimens underwent enrichment via multiplex PCR before targeted methylation sequencing. The Recursive Feature Elimination Cross-Validation and deep neural network algorithm established the CanDo classification model, which incorporated 11 methylation features (including 8 specific to the TBR1 gene), demonstrating a sensitivity of 98.6% and specificity of 97.8%. In contrast, bronchoscopic rapid on-site evaluation (bronchoscopic-ROSE) had lower sensitivity (87.7%) and specificity (80%). Further validation in 33 individuals confirmed CanDo's discriminatory potential, particularly in challenging cases for bronchoscopic-ROSE due to pathological complexity. CanDo serves as a valuable complement to bronchoscopy for the discriminatory diagnosis and stratified management of lung tumors utilizing BWF specimens.
RESUMEN
Animal behavior analysis plays a crucial role in contemporary neuroscience research. However, the performance of the frame-by-frame approach may degrade in scenarios with occlusions or motion blur. In this study, we propose a spatiotemporal network model based on YOLOv8 to enhance the accuracy of key-point detection in mouse behavioral experimental videos. This model integrates a time-domain tracking strategy comprising two components: the first part utilizes key-point detection results from the previous frame to detect potential target locations in the subsequent frame; the second part employs Kalman filtering to analyze key-point changes prior to detection, allowing for the estimation of missing key-points. In the comparison of pose estimation results between our approach, YOLOv8, DeepLabCut and SLEAP on videos of three mouse behavioral experiments, our approach demonstrated significantly superior performance. This suggests that our method offers a new and effective means of accurately tracking and estimating pose in mice through spatiotemporal processing.
RESUMEN
Discovering causal effects is at the core of scientific investigation but remains challenging when only observational data are available. In practice, causal networks are difficult to learn and interpret, and limited to relatively small datasets. We report a more reliable and scalable causal discovery method (iMIIC), based on a general mutual information supremum principle, which greatly improves the precision of inferred causal relations while distinguishing genuine causes from putative and latent causal effects. We showcase iMIIC on synthetic and real-world healthcare data from 396,179 breast cancer patients from the US Surveillance, Epidemiology, and End Results program. More than 90% of predicted causal effects appear correct, while the remaining unexpected direct and indirect causal effects can be interpreted in terms of diagnostic procedures, therapeutic timing, patient preference or socio-economic disparity. iMIIC's unique capabilities open up new avenues to discover reliable and interpretable causal networks across a range of research fields.
RESUMEN
For dexterous control of the hand, humans integrate sensory information and prior knowledge regarding their bodies and the world. We studied the role of touch in hand motor control by challenging a fundamental prior assumption-that self-motion of inanimate objects is unlikely upon contact. In a reaching task, participants slid their fingertips across a robotic interface, with their hand hidden from sight. Unbeknownst to the participants, the robotic interface remained static, followed hand movement, or moved in opposition to it. We considered two hypotheses. Either participants were able to account for surface motion or, if the stationarity assumption held, they would integrate the biased tactile cues and proprioception. Motor errors consistent with the latter hypothesis were observed. The role of visual feedback, tactile sensitivity, and friction was also investigated. Our study carries profound implications for human-machine collaboration in a world where objects may no longer conform to the stationarity assumption.
RESUMEN
Accurate optic disc (OD) segmentation has a great significance for computer-aided diagnosis of different types of eye diseases. Due to differences in image acquisition equipment and acquisition methods, the resolution, size, contrast, and clarity of images from different datasets show significant differences, resulting in poor generalization performance of deep learning networks. To solve this problem, this study proposes a multi-level segmentation network. The network includes data quality enhancement module (DQEM), coarse segmentation module (CSM), localization module (OLM), and fine segmentation stage module (FSM). In FSM, W-Net is proposed for the first time, and boundary loss is introduced in the loss function, which effectively improves the performance of OD segmentation. We generalized the model in the REFUGE test dataset, GAMMA dataset, Drishti-GS1 dataset, and IDRiD dataset, respectively. The results show that our method has the best OD segmentation performance in different datasets compared with state-of-the-art networks.
RESUMEN
In daily life, our brain needs to eliminate irrelevant signals and integrate relevant signals to facilitate natural interactions with the surrounding. Previous study focused on paradigms without effect of dominant laterality and found that human observers process multisensory signals consistent with Bayesian causal inference (BCI). However, most human activities are of bilateral interaction involved in processing of interhemispheric sensory signals. It remains unclear whether the BCI framework also fits to such activities. Here, we presented a bilateral hand-matching task to understand the causal structure of interhemispheric sensory signals. In this task, participants were asked to match ipsilateral visual or proprioceptive cues with the contralateral hand. Our results suggest that interhemispheric causal inference is most derived from the BCI framework. The interhemispheric perceptual bias may vary strategy models to estimate the contralateral multisensory signals. The findings help to understand how the brain processes the uncertainty information coming from interhemispheric sensory signals.
RESUMEN
The immune system discriminates between harmful and harmless antigens based on past experiences; however, the underlying mechanism is largely unknown. From the viewpoint of machine learning, the learning system predicts the observation and updates the prediction based on prediction error, a process known as "predictive coding." Here, we modeled the population dynamics of T cells by adopting the concept of predictive coding; conventional and regulatory T cells predict the antigen concentration and excessive immune response, respectively. Their prediction error signals, possibly via cytokines, induce their differentiation to memory T cells. Through numerical simulations, we found that the immune system identifies antigen risks depending on the concentration and input rapidness of the antigen. Further, our model reproduced history-dependent discrimination, as in allergy onset and subsequent therapy. Taken together, this study provided a novel framework to improve our understanding of how the immune system adaptively learns the risks of diverse antigens.
RESUMEN
The chromatin loop plays a critical role in the study of gene expression and disease. Supervised learning-based algorithms to predict the chromatin loops require large priori information to satisfy the model construction, while the prediction sensitivity of unsupervised learning-based algorithms is still unsatisfactory. Therefore, we propose an unsupervised algorithm, Ecomap-loop. It takes advantage of extrusion complex-associated patterns, including CTCF, RAD21, and SMC enrichments, as well as the orientation distribution of CTCF motif of loops to build feature matrices; then the eigen decomposition model is employed to obtain the cell type-specific loops. We compare the performance of Ecomap-loop with the state-of-the-art unsupervised algorithm using Hi-C, ChIA-PET, expression quantitative trait locus (eQTL), and CRISPR interference (CRISPRi) screen data; the results show that Ecomap-loop achieves the best in four cell types. In addition, the functional analysis reveals the ability of Ecomap-loop to predict active functionality-related and cell type-specific loops.
RESUMEN
Many groups of stingless insects have independently evolved mimicry of bees to fool would-be predators. To investigate this mimicry, we trained artificial intelligence (AI) algorithms-specifically, computer vision-to classify citizen scientist images of bees, bumble bees, and diverse bee mimics. For detecting bees and bumble bees, our models achieved accuracies of 91.71 % and 88.86 % , respectively. As a proxy for a natural predator, our models were poorest in detecting bee mimics that exhibit both aggressive and defensive mimicry. Using the explainable AI method of class activation maps, we validated that our models learn from appropriate components within the image, which in turn provided anatomical insights. Our t-SNE plot yielded perfect within-group clustering, as well as between-group clustering that grossly replicated the phylogeny. Ultimately, the transdisciplinary approaches herein can enhance global citizen science efforts as well as investigations of mimicry and morphology of bees and other insects.
RESUMEN
Smartphones touchscreen interactions may help resolve if and how real-world behavioral dynamics are shaped by aging. Here, in a sample spanning the adult life span (16 to 86 years, N = 598, accumulating 355 million interactions), we clustered the smartphone interactions according to their next inter-touch interval dynamics. There were age-related behavioral losses at the clusters occupying short intervals (â¼100 ms, R2 â¼ 0.8) but gains at the long intervals (â¼4 s, R2 â¼ 0.4). Our approach revealed a sophisticated form of behavioral aging where individuals simultaneously demonstrated accelerated aging in one behavioral cluster versus a deceleration in another. Contrary to the common notion of a simple behavioral decline with age based on conventional cognitive tests, we show that the nature of aging systematically varies according to the underlying dynamics. Of all the imaginable factors determining smartphone interactions, age-sensitive cognitive and behavioral processes may dominatingly shape smartphone dynamics.
RESUMEN
Smartphones offer unique opportunities to trace the convoluted behavioral patterns accompanying healthy aging. Here we captured smartphone touchscreen interactions from a healthy population (N = 684, â¼309 million interactions) spanning 16 to 86 years of age and trained a decision tree regression model to estimate chronological age based on the interactions. The interactions were clustered according to their next interval dynamics to quantify diverse smartphone behaviors. The regression model well-estimated the chronological age in health (mean absolute error = 6 years, R2 = 0.8). We next deployed this model on a population of stroke survivors (N = 41) to find larger prediction errors such that the estimated age was advanced by 6 years. A similar pattern was observed in people with epilepsy (N = 51), with prediction errors advanced by 10 years. The smartphone behavioral model trained in health can be used to study altered aging in neurological diseases.
RESUMEN
The spiking variability of neural networks has important implications for how information is encoded to higher brain regions. It has been well documented by numerous labs in many cortical and motor regions that spiking variability decreases with stimulus onset, yet whether this principle holds in the OB has not been tested. In stark contrast to this common view, we demonstrate that the onset of sensory input can cause an increase in the variability of neural activity in the mammalian OB. We show this in both anesthetized and awake rodents. Furthermore, we use computational models to describe the mechanisms of this phenomenon. Our findings establish sensory evoked increases in spiking variability as a viable alternative coding strategy.
RESUMEN
Research publications are the major repository of scientific knowledge. However, their unstructured and highly heterogenous format creates a significant obstacle to large-scale analysis of the information contained within. Recent progress in natural language processing (NLP) has provided a variety of tools for high-quality information extraction from unstructured text. These tools are primarily trained on non-technical text and struggle to produce accurate results when applied to scientific text, involving specific technical terminology. During the last years, significant efforts in information retrieval have been made for biomedical and biochemical publications. For materials science, text mining (TM) methodology is still at the dawn of its development. In this review, we survey the recent progress in creating and applying TM and NLP approaches to materials science field. This review is directed at the broad class of researchers aiming to learn the fundamentals of TM as applied to the materials science publications.
RESUMEN
The expeditious development of information technology has led to the rise of artificial intelligence (AI). However, conventional computing systems are prone to volatility, high power consumption, and even delay between the processor and memory, which is referred to as the von Neumann bottleneck, in implementing AI. To address these issues, memristor-based neuromorphic computing systems inspired by the human brain have been proposed. A memristor can store numerous values by changing its resistance and emulate artificial synapses in brain-inspired computing. Here, we introduce six types of memristors classified according to their operation mechanisms: ionic migration, phase change, spin, ferroelectricity, intercalation, and ionic gating. We review how memristor-based neuromorphic computing can learn, infer, and even create, using various artificial neural networks. Finally, the challenges and perspectives in the competing memristor technology for neuromorphic computing systems are discussed.
RESUMEN
Buildings in Iraqi cities such as Baghdad and Mosul suffer from several problems such as the application of new materials in modern buildings that changed not just the identity of architectural heritage but also the quality of thermal comfort in façade design. This, unfortunately, adds to the damage regarding environmental sustainability and cultural values away from adaptable solutions to improve energy efficiency in building performance. One of the measures that must be taken to correctly plan in harmony with the Iraqi cities is to ensure the environmental control as part of the overall performance of building façade to maintain an active, healthy indoor environment while preserving the propriety of facade design elements, screen pattern, order and details. Therefore, there are many sustainable trends that vary in their usefulness such as biomimetics examples inspired from natural models in which form and function dictate one another. This is in order to maintain the integrated design relation between transparency, function, and elegance in the overall performance of façade elements. The research question is, how important is the choice of material in developing a sustainable element that revives environmental control while preserving the identity and values of façade design? The main goal of the research study is to identify the role of advanced technologies and the choice of smart glazing materials to revive the quality of thermal comfort in a way that not just sustains the identity of facade elements socially and culturally, but also to be responsive to the changes of climate conditions. Therefore, this research utilizes more than one technological tool such as Revit as a BIM tool with the application of smart dynamic materials such as Photovoltaics and Electrochromic in order to restore part of the design expression and enhance the building performance through its elements in contemporary façade design and its details. In this work, it can be seen that applying a set of technological tools allows to clearly illustrate the impact of smart dynamic materials to improve the quality of design and comfort while protecting the identity of contemporary façade elements when compared to static or traditional materials, aesthetically, and functionally.
RESUMEN
BACKGROUND: Alzheimer's Disease (AD) is a neurodegenerative disease characterized by progressive loss of memory and general decline in cognitive functions. Multi-modal imaging such as structural MRI and DTI provide useful information for the classification of patients on the basis of brain biomarkers. Recently, CNN methods have emerged as powerful tools to improve classification using images. NEW METHOD: In this paper, we propose a transfer learning scheme using Convolutional Neural Networks (CNNs) to automatically classify brain scans focusing only on a small ROI: e.g. a few slices of the hippocampal region. The network's architecture is similar to a LeNet-like CNN upon which models are built and fused for AD stage classification diagnosis. We evaluated various types of transfer learning through the following mechanisms: (i) cross-modal (sMRI and DTI) and (ii) cross-domain transfer learning (using MNIST) (iii) a hybrid transfer learning of both types. RESULTS: Our method shows good performances even on small datasets and with a limited number of slices of small brain region. It increases accuracy with more than 5 points for the most difficult classification tasks, i.e., AD/MCI and MCI/NC. COMPARISON WITH EXISTING METHODS: Our methodology provides good accuracy scores for classification over a shallow convolutional network. Besides, we focused only on a small region; i.e., the hippocampal region, where few slices are selected to feed the network. Also, we used cross-modal transfer learning. CONCLUSIONS: Our proposed method is suitable for working with a shallow CNN network for low-resolution MRI and DTI scans. It yields to significant results even if the model is trained on small datasets, which is often the case in medical image analysis.