Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 9.381
Filtrar
1.
Int J Mol Sci ; 25(7)2024 Mar 28.
Artigo em Inglês | MEDLINE | ID: mdl-38612602

RESUMO

Molecular property prediction is an important task in drug discovery, and with help of self-supervised learning methods, the performance of molecular property prediction could be improved by utilizing large-scale unlabeled dataset. In this paper, we propose a triple generative self-supervised learning method for molecular property prediction, called TGSS. Three encoders including a bi-directional long short-term memory recurrent neural network (BiLSTM), a Transformer, and a graph attention network (GAT) are used in pre-training the model using molecular sequence and graph structure data to extract molecular features. The variational auto encoder (VAE) is used for reconstructing features from the three models. In the downstream task, in order to balance the information between different molecular features, a feature fusion module is added to assign different weights to each feature. In addition, to improve the interpretability of the model, atomic similarity heat maps were introduced to demonstrate the effectiveness and rationality of molecular feature extraction. We demonstrate the accuracy of the proposed method on chemical and biological benchmark datasets by comparative experiments.


Assuntos
Benchmarking , Descoberta de Drogas , Animais , Fontes de Energia Elétrica , Estro , Aprendizado de Máquina Supervisionado
2.
Sci Adv ; 10(15): eadn0858, 2024 Apr 12.
Artigo em Inglês | MEDLINE | ID: mdl-38608028

RESUMO

Miniaturized neuromodulation systems could improve the safety and reduce the invasiveness of bioelectronic neuromodulation. However, as implantable bioelectronic devices are made smaller, it becomes difficult to store enough power for long-term operation in batteries. Here, we present a battery-free epidural cortical stimulator that is only 9 millimeters in width yet can safely receive enough wireless power using magnetoelectric antennas to deliver 14.5-volt stimulation bursts, which enables it to stimulate cortical activity on-demand through the dura. The device has digitally programmable stimulation output and centimeter-scale alignment tolerances when powered by an external transmitter. We demonstrate that this device has enough power and reliability for real-world operation by showing acute motor cortex activation in human patients and reliable chronic motor cortex activation for 30 days in a porcine model. This platform opens the possibility of simple surgical procedures for precise neuromodulation.


Assuntos
Fontes de Energia Elétrica , Córtex Motor , Humanos , Animais , Suínos , Reprodutibilidade dos Testes
3.
Sensors (Basel) ; 24(7)2024 Mar 28.
Artigo em Inglês | MEDLINE | ID: mdl-38610372

RESUMO

The build-up of lactate in solid tumors stands as a crucial and early occurrence in malignancy development, and the concentration of lactate in the tumor microenvironment may be a more sensitive indicator for analyzing primary tumors. In this study, we designed a self-powered lactate sensor for the rapid analysis of tumor samples, utilizing the coupling between the piezoelectric effect and enzymatic reaction. This lactate sensor is fabricated using a ZnO nanowire array modified with lactate oxidase (LOx). The sensing process does not require an external power source or batteries. The device can directly output electric signals containing lactate concentration information when subjected to external forces. The lactate concentration detection upper limit of the sensor is at least 27 mM, with a limit of detection (LOD) of approximately 1.3 mM and a response time of around 10 s. This study innovatively applied self-powered technology to the in situ detection of the tumor microenvironment and used the results to estimate the growth period of the primary tumor. The availability of this application has been confirmed through biological experiments. Furthermore, the sensor data generated by the device offer valuable insights for evaluating the likelihood of remote tumor metastasis. This study may expand the research scope of self-powered technology in the field of medical diagnosis and offer a novel perspective on cancer diagnosis.


Assuntos
Nanofios , Neoplasias , Humanos , Ácido Láctico , Neoplasias/diagnóstico , Fontes de Energia Elétrica , Eletricidade , Microambiente Tumoral
4.
Sci Rep ; 14(1): 7626, 2024 04 01.
Artigo em Inglês | MEDLINE | ID: mdl-38561445

RESUMO

This study explored the application of generative pre-trained transformer (GPT) agents based on medical guidelines using large language model (LLM) technology for traumatic brain injury (TBI) rehabilitation-related questions. To assess the effectiveness of multiple agents (GPT-agents) created using GPT-4, a comparison was conducted using direct GPT-4 as the control group (GPT-4). The GPT-agents comprised multiple agents with distinct functions, including "Medical Guideline Classification", "Question Retrieval", "Matching Evaluation", "Intelligent Question Answering (QA)", and "Results Evaluation and Source Citation". Brain rehabilitation questions were selected from the doctor-patient Q&A database for assessment. The primary endpoint was a better answer. The secondary endpoints were accuracy, completeness, explainability, and empathy. Thirty questions were answered; overall GPT-agents took substantially longer and more words to respond than GPT-4 (time: 54.05 vs. 9.66 s, words: 371 vs. 57). However, GPT-agents provided superior answers in more cases compared to GPT-4 (66.7 vs. 33.3%). GPT-Agents surpassed GPT-4 in accuracy evaluation (3.8 ± 1.02 vs. 3.2 ± 0.96, p = 0.0234). No difference in incomplete answers was found (2 ± 0.87 vs. 1.7 ± 0.79, p = 0.213). However, in terms of explainability (2.79 ± 0.45 vs. 07 ± 0.52, p < 0.001) and empathy (2.63 ± 0.57 vs. 1.08 ± 0.51, p < 0.001) evaluation, the GPT-agents performed notably better. Based on medical guidelines, GPT-agents enhanced the accuracy and empathy of responses to TBI rehabilitation questions. This study provides guideline references and demonstrates improved clinical explainability. However, further validation through multicenter trials in a clinical setting is necessary. This study offers practical insights and establishes groundwork for the potential theoretical integration of LLM-agents medicine.


Assuntos
Lesões Encefálicas Traumáticas , Humanos , Lesões Encefálicas Traumáticas/tratamento farmacológico , Encéfalo , Bases de Dados Factuais , Fontes de Energia Elétrica , Empatia
5.
J Acoust Soc Am ; 155(4): 2538-2548, 2024 Apr 01.
Artigo em Inglês | MEDLINE | ID: mdl-38591939

RESUMO

Long-term fixed passive acoustic monitoring of cetacean populations is a logistical and technological challenge, often limited by the battery capacity of the autonomous recorders. Depending on the research scope and target species, temporal subsampling of the data may become necessary to extend the deployment period. This study explores the effects of different duty cycles on metrics that describe patterns of seasonal presence, call type richness richness, and daily call rate of three blue whale acoustics populations in the Southern Indian Ocean. Detections of blue whale calls from continuous acoustic data were subsampled with three different duty cycles of 50%, 33%, and 25% within listening periods ranging from 1 min to 6 h. Results show that reducing the percentage of recording time reduces the accuracy of the observed seasonal patterns as well as the estimation of daily call rate and call call type richness. For a specific duty cycle, short listening periods (5-30 min) are preferred to longer listening periods (1-6 h). The effects of subsampling are greater the lower the species' vocal activity or the shorter their periods of presence. These results emphasize the importance of selecting a subsampling scheme adapted to the target species.


Assuntos
Acústica , Balaenoptera , Animais , Cetáceos , Fontes de Energia Elétrica , Oceano Índico
6.
PLoS One ; 19(4): e0297068, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38593127

RESUMO

Compared with visible light images, thermal infrared images have poor resolution, low contrast, signal-to-noise ratio, blurred visual effects, and less information. Thermal infrared sports target detection methods relying on traditional convolutional networks capture the rich semantics in high-level features but blur the spatial details. The differences in physical information content and spatial distribution of high and low features are ignored, resulting in a mismatch between the region of interest and the target. To address these issues, we propose a local attention-guided Swin-transformer thermal infrared sports object detection method (LAGSwin) to encode sports objects' spatial transformation and orientation information. On the one hand, Swin-transformer guided by local attention is adopted to enrich the semantic knowledge of low-level features by embedding local focus from high-level features and generating high-quality anchors while increasing the embedding of contextual information. On the other hand, an active rotation filter is employed to encode orientation information, resulting in orientation-sensitive and invariant features to reduce the inconsistency between classification and localization regression. A bidirectional criss-cross fusion strategy is adopted in the feature fusion stage to enable better interaction and embedding features of different resolutions. At last, the evaluation and verification of multiple open-source sports target datasets prove that the proposed LAGSwin detection framework has good robustness and generalization ability.


Assuntos
Fontes de Energia Elétrica , Exame Físico , Generalização Psicológica , Conhecimento , Luz
7.
PLoS One ; 19(4): e0301516, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38568998

RESUMO

The integration of renewable energy systems into electricity grids is a solution for strengthening electricity distribution networks (SEDNs). Renewable energies such as solar photovoltaics are suitable for reinforcing a low-voltage line by offering an electrical energy storage system. However, the integration of photovoltaic systems can lead to problems of harmonic distortion due to the presence of direct current or non-linear feedback in networks from other sources. Therefore, connection standards exist to ensure the quality of the energy before injection at a point of common coupling (PCC). In this work, particle swarm optimization (PSO) is used to control a boost converter and to evaluate the power losses and the harmonic distortion rate. The test on the IEEE 14 bus standard makes it possible to determine the allocation or integration nodes for other sources such as biomass, wind or hydrogen generators, in order to limit the impact of harmonic disturbances (LIHs). The evaluation of the harmonic distortion rate, the power losses as well as the determination of the system size is done using an objective function defined based on the integration and optimization constraints of the system. The proposed model performs better since the grid current and voltage are stabilized in phase after the photovoltaic source is injected.


Assuntos
Fontes de Energia Elétrica , Modelos Teóricos , Algoritmos , Energia Renovável , Eletricidade
8.
J Neural Eng ; 21(2)2024 Apr 11.
Artigo em Inglês | MEDLINE | ID: mdl-38565099

RESUMO

Objective.The study of emotion recognition through electroencephalography (EEG) has garnered significant attention recently. Integrating EEG with other peripheral physiological signals may greatly enhance performance in emotion recognition. Nonetheless, existing approaches still suffer from two predominant challenges: modality heterogeneity, stemming from the diverse mechanisms across modalities, and fusion credibility, which arises when one or multiple modalities fail to provide highly credible signals.Approach.In this paper, we introduce a novel multimodal physiological signal fusion model that incorporates both intra-inter modality reconstruction and sequential pattern consistency, thereby ensuring a computable and credible EEG-based multimodal emotion recognition. For the modality heterogeneity issue, we first implement a local self-attention transformer to obtain intra-modal features for each respective modality. Subsequently, we devise a pairwise cross-attention transformer to reveal the inter-modal correlations among different modalities, thereby rendering different modalities compatible and diminishing the heterogeneity concern. For the fusion credibility issue, we introduce the concept of sequential pattern consistency to measure whether different modalities evolve in a consistent way. Specifically, we propose to measure the varying trends of different modalities, and compute the inter-modality consistency scores to ascertain fusion credibility.Main results.We conduct extensive experiments on two benchmarked datasets (DEAP and MAHNOB-HCI) with the subject-dependent paradigm. For the DEAP dataset, our method improves the accuracy by 4.58%, and the F1 score by 0.63%, compared to the state-of-the-art baseline. Similarly, for the MAHNOB-HCI dataset, our method improves the accuracy by 3.97%, and the F1 score by 4.21%. In addition, we gain much insight into the proposed framework through significance test, ablation experiments, confusion matrices and hyperparameter analysis. Consequently, we demonstrate the effectiveness of the proposed credibility modelling through statistical analysis and carefully designed experiments.Significance.All experimental results demonstrate the effectiveness of our proposed architecture and indicate that credibility modelling is essential for multimodal emotion recognition.


Assuntos
Benchmarking , Emoções , Fontes de Energia Elétrica , Eletroencefalografia , Reconhecimento Psicológico
9.
Waste Manag ; 180: 96-105, 2024 May 15.
Artigo em Inglês | MEDLINE | ID: mdl-38564915

RESUMO

The growing electric vehicle industry has increased the demand for raw materials used in lithium-ion batteries (LIBs), raising concerns about material availability. Froth flotation has gained attention as a LIB recycling method, allowing the recovery of low value materials while preserving the chemical integrity of electrode materials. Furthermore, as new battery chemistries such as lithium titanate (LTO) are introduced into the market, strategies to treat mixed battery streams are needed. In this work, laboratory-scale flotation separation experiments were conducted on two model black mass samples: i) a mixture containing a single cathode (i.e., NMC811) and two anode species (i.e., LTO and graphite), simulating a mixed feedstock prior to hydrometallurgical treatment; and ii) a graphite-TiO2 mixture to reflect the expected products after leaching. The results indicate that graphite can be recovered with > 98 % grade from NMC811-LTO-graphite mixtures. Additionally, it was found that flotation kinetics are dependent on the electrode particle species present in the suspension. In contrast, the flotation of graphite from TiO2 resulted in a low grade product (<96 %) attributed to the significant entrainment of ultrafine TiO2 particles. These results suggest that flotation of graphite should be preferably carried out before hydrometallurgical treatment of black mass.


Assuntos
Grafite , Lítio , Reciclagem/métodos , Fontes de Energia Elétrica , Íons
10.
J Environ Manage ; 357: 120774, 2024 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-38569265

RESUMO

The booming electric vehicle market has led to an increasing number of end-of-life power batteries. In order to reduce environmental pollution and promote the realization of circular economy, how to fully and effectively recycle the end-of-life power batteries has become an urgent challenge to be solved today. The recycling & remanufacturing center is an extremely important and key facility in the recycling process of used batteries, which ensures that the recycled batteries can be handled in a standardized manner under the conditions of professional facilities. In reality, different adjustment options for existing recycling & remanufacturing centers have a huge impact on the planning of new sites. This paper proposes a mixed-integer linear programming model for the siting problem of battery recycling & remanufacturing centers considering site location-adjustment. The model allows for demolition, renewal, and new construction options in planning for recycling & remanufacturing centers. By adjusting existing sites, this paper provides an efficient allocation of resources under the condition of meeting the demand for recycling of used batteries. Next, under the new model proposed in this paper, the uncertainty of the quantity and capacity of recycled used batteries is considered. By establishing different capacity conditions of batteries under multiple scenarios, a robust model was developed to determine the number and location of recycling & remanufacturing centers, which promotes sustainable development, reduces environmental pollution and effectively copes with the risk of the future quantity of used batteries exceeding expectations. In the final results of the case analysis, our proposed model considering the existing sites adjustment reduces the cost by 3.14% compared to the traditional model, and the average site utilization rate is 15.38% higher than the traditional model. The results show that the model has an effective effect in reducing costs, allocating resources, and improving efficiency, which could provide important support for decision-making in the recycling of used power batteries.


Assuntos
Fontes de Energia Elétrica , Reciclagem , Incerteza , Reciclagem/métodos , Poluição Ambiental , Eletricidade
11.
PLoS One ; 19(4): e0302275, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38626177

RESUMO

Although deep-learning methods can achieve human-level performance in boundary detection, their improvements mostly rely on larger models and specific datasets, leading to significant computational power consumption. As a fundamental low-level vision task, a single model with fewer parameters to achieve cross-dataset boundary detection merits further investigation. In this study, a lightweight universal boundary detection method was developed based on convolution and a transformer. The network is called a "transformer with difference convolutional network" (TDCN), which implies the introduction of a difference convolutional network rather than a pure transformer. The TDCN structure consists of three parts: convolution, transformer, and head function. First, a convolution network fused with edge operators is used to extract multiscale difference features. These pixel difference features are then fed to the hierarchical transformer as tokens. Considering the intrinsic characteristics of the boundary detection task, a new boundary-aware self-attention structure was designed in the transformer to provide inductive bias. By incorporating the proposed attention loss function, it introduces the direction of the boundary as strongly supervised information to improve the detection ability of the model. Finally, several head functions with multiscale feature inputs were trained using a bidirectional additive strategy. In the experiments, the proposed method achieved competitive performance on multiple public datasets with fewer model parameters. A single model was obtained to realize universal prediction even for different datasets without retraining, demonstrating the effectiveness of the method. The code is available at https://github.com/neulmc/TDCN.


Assuntos
Conscientização , Baixa Visão , Humanos , Fontes de Energia Elétrica , Gestão da Informação , Menopausa
12.
Int J Med Robot ; 20(2): e2632, 2024 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-38630888

RESUMO

BACKGROUND: Real-time prediction of the remaining surgery duration (RSD) is important for optimal scheduling of resources in the operating room. METHODS: We focus on the intraoperative prediction of RSD from laparoscopic video. An extensive evaluation of seven common deep learning models, a proposed one based on the Transformer architecture (TransLocal) and four baseline approaches, is presented. The proposed pipeline includes a CNN-LSTM for feature extraction from salient regions within short video segments and a Transformer with local attention mechanisms. RESULTS: Using the Cholec80 dataset, TransLocal yielded the best performance (mean absolute error (MAE) = 7.1 min). For long and short surgeries, the MAE was 10.6 and 4.4 min, respectively. Thirty minutes before the end of surgery MAE = 6.2 min, 7.2 and 5.5 min for all long and short surgeries, respectively. CONCLUSIONS: The proposed technique achieves state-of-the-art results. In the future, we aim to incorporate intraoperative indicators and pre-operative data.


Assuntos
Laparoscopia , Humanos , Salas Cirúrgicas , Fontes de Energia Elétrica
13.
J Neural Eng ; 21(2)2024 Apr 09.
Artigo em Inglês | MEDLINE | ID: mdl-38565124

RESUMO

Objective.Recent studies have shown that integrating inertial measurement unit (IMU) signals with surface electromyographic (sEMG) can greatly improve hand gesture recognition (HGR) performance in applications such as prosthetic control and rehabilitation training. However, current deep learning models for multimodal HGR encounter difficulties in invasive modal fusion, complex feature extraction from heterogeneous signals, and limited inter-subject model generalization. To address these challenges, this study aims to develop an end-to-end and inter-subject transferable model that utilizes non-invasively fused sEMG and acceleration (ACC) data.Approach.The proposed non-invasive modal fusion-transformer (NIMFT) model utilizes 1D-convolutional neural networks-based patch embedding for local information extraction and employs a multi-head cross-attention (MCA) mechanism to non-invasively integrate sEMG and ACC signals, stabilizing the variability induced by sEMG. The proposed architecture undergoes detailed ablation studies after hyperparameter tuning. Transfer learning is employed by fine-tuning a pre-trained model on new subject and a comparative analysis is performed between the fine-tuning and subject-specific model. Additionally, the performance of NIMFT is compared to state-of-the-art fusion models.Main results.The NIMFT model achieved recognition accuracies of 93.91%, 91.02%, and 95.56% on the three action sets in the Ninapro DB2 dataset. The proposed embedding method and MCA outperformed the traditional invasive modal fusion transformer by 2.01% (embedding) and 1.23% (fusion), respectively. In comparison to subject-specific models, the fine-tuning model exhibited the highest average accuracy improvement of 2.26%, achieving a final accuracy of 96.13%. Moreover, the NIMFT model demonstrated superiority in terms of accuracy, recall, precision, and F1-score compared to the latest modal fusion models with similar model scale.Significance.The NIMFT is a novel end-to-end HGR model, utilizes a non-invasive MCA mechanism to integrate long-range intermodal information effectively. Compared to recent modal fusion models, it demonstrates superior performance in inter-subject experiments and offers higher training efficiency and accuracy levels through transfer learning than subject-specific approaches.


Assuntos
Gestos , Reconhecimento Psicológico , Rememoração Mental , Fontes de Energia Elétrica , Redes Neurais de Computação , Eletromiografia
14.
PLoS One ; 19(4): e0301910, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38635672

RESUMO

With the increasing demand for electricity, microgrid systems are facing issues such as insufficient backup capacity, frequent load switching, and frequent malfunctions, making research on microgrid resilience crucial, especially to improve system power supply reliability. This paper proposes a method for analyzing the resilience metric of new energy grid-connected microgrid system, and proposes optimization strategies to improve resilience. Firstly, a measurement method for the resilience of the microgrid system is established based on the operating characteristics of the system components. Secondly, the sensitivity relationship between system resilience and parameters is established, and an optimization model for resilience improvement strategies of microgrid systems based on parameter sensitivity is constructed. Finally, simulation verification is conducted based on the IEEE 37-node microgrid system. The results show that the proposed measurement method can scientifically and reasonably measure the resilience of the microgrid system, and the resilience improvement strategy significantly improves the operational resilience, verifying the effectiveness and robustness of the proposed analysis method.


Assuntos
Resiliência Psicológica , Reprodutibilidade dos Testes , Simulação por Computador , Sistemas Computacionais , Fontes de Energia Elétrica
15.
PLoS One ; 19(4): e0298809, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38635682

RESUMO

With the rapid development of the Internet, the continuous increase of malware and its variants have brought greatly challenges for cyber security. Due to the imbalance of the data distribution, the research on malware detection focuses on the accuracy of the whole data sample, while ignoring the detection rate of the minority categories' malware. In the dataset sample, the normal data samples account for the majority, while the attacks' malware accounts for the minority. However, the minority categories' attacks will bring great losses to countries, enterprises, or individuals. For solving the problem, this study proposed the GNGS algorithm to construct a new balance dataset for the model algorithm to pay more attention to the feature learning of the minority attacks' malware to improve the detection rate of attacks' malware. The traditional malware detection method is highly dependent on professional knowledge and static analysis, so we used the Self-Attention with Gate mechanism (SAG) based on the Transformer to carry out feature extraction between the local and global features and filter irrelevant noise information, then extracted the long-distance dependency temporal sequence features by the BiGRU network, and obtained the classification results through the SoftMax classifier. In the study, we used the Alibaba Cloud dataset for malware multi-classification. Compared the GSB deep learning network model with other current studies, the experimental results showed that the Gaussian noise generation strategy (GNGS) could solve the unbalanced distribution of minority categories' malware and the SAG-BiGRU algorithm obtained the accuracy rate of 88.7% on the eight-classification, which has better performance than other existing algorithms, and the GSB model also has a good effect on the NSL-KDD dataset, which showed the GSB model is effective for other network intrusion detection.


Assuntos
Algoritmos , Grupos Minoritários , Humanos , Segurança Computacional , Fontes de Energia Elétrica , Internet
16.
PLoS One ; 19(4): e0301019, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-38573957

RESUMO

Automatic and accurate segmentation of medical images plays an essential role in disease diagnosis and treatment planning. Convolution neural networks have achieved remarkable results in medical image segmentation in the past decade. Meanwhile, deep learning models based on Transformer architecture also succeeded tremendously in this domain. However, due to the ambiguity of the medical image boundary and the high complexity of physical organization structures, implementing effective structure extraction and accurate segmentation remains a problem requiring a solution. In this paper, we propose a novel Dual Encoder Network named DECTNet to alleviate this problem. Specifically, the DECTNet embraces four components, which are a convolution-based encoder, a Transformer-based encoder, a feature fusion decoder, and a deep supervision module. The convolutional structure encoder can extract fine spatial contextual details in images. Meanwhile, the Transformer structure encoder is designed using a hierarchical Swin Transformer architecture to model global contextual information. The novel feature fusion decoder integrates the multi-scale representation from two encoders and selects features that focus on segmentation tasks by channel attention mechanism. Further, a deep supervision module is used to accelerate the convergence of the proposed method. Extensive experiments demonstrate that, compared to the other seven models, the proposed method achieves state-of-the-art results on four segmentation tasks: skin lesion segmentation, polyp segmentation, Covid-19 lesion segmentation, and MRI cardiac segmentation.


Assuntos
COVID-19 , Exame Físico , Humanos , Fontes de Energia Elétrica , Coração , Redes Neurais de Computação , Processamento de Imagem Assistida por Computador
17.
Sensors (Basel) ; 24(6)2024 Mar 16.
Artigo em Inglês | MEDLINE | ID: mdl-38544174

RESUMO

We present a thin and elastic tactile sensor glove for teaching dexterous manipulation tasks to robots through human demonstration. The entire glove, including the sensor cells, base layer, and electrical connections, is made from soft and stretchable silicone rubber, adapting to deformations under bending and contact while preserving human dexterity. We develop a glove design with five fingers and a palm sensor, revise material formulations for reduced thickness, faster processing and lower cost, adapt manufacturing processes for reduced layer thickness, and design readout electronics for improved sensitivity and battery operation. We further address integration with a multi-camera system and motion reconstruction, wireless communication, and data processing to obtain multimodal reconstructions of human manipulation skills.


Assuntos
Eletrônica , Mãos , Humanos , Movimento (Física) , Tato , Fontes de Energia Elétrica
18.
Sci Rep ; 14(1): 7416, 2024 03 28.
Artigo em Inglês | MEDLINE | ID: mdl-38548825

RESUMO

Predicting the interaction affinity between drugs and target proteins is crucial for rapid and accurate drug discovery and repositioning. Therefore, more accurate prediction of DTA has become a key area of research in the field of drug discovery and drug repositioning. However, traditional experimental methods have disadvantages such as long operation cycles, high manpower requirements, and high economic costs, making it difficult to predict specific interactions between drugs and target proteins quickly and accurately. Some methods mainly use the SMILES sequence of drugs and the primary structure of proteins as inputs, ignoring the graph information such as bond encoding, degree centrality encoding, spatial encoding of drug molecule graphs, and the structural information of proteins such as secondary structure and accessible surface area. Moreover, previous methods were based on protein sequences to learn feature representations, neglecting the completeness of information. To address the completeness of drug and protein structure information, we propose a Transformer graph-based early fusion research approach for drug-target affinity prediction (GEFormerDTA). Our method reduces prediction errors caused by insufficient feature learning. Experimental results on Davis and KIBA datasets showed a better prediction of drugtarget affinity than existing affinity prediction methods.


Assuntos
Descoberta de Drogas , Reposicionamento de Medicamentos , Sequência de Aminoácidos , Fontes de Energia Elétrica , Aprendizagem
19.
Sci Rep ; 14(1): 7395, 2024 03 28.
Artigo em Inglês | MEDLINE | ID: mdl-38548898

RESUMO

Serous cavity effusion is a prevalent pathological condition encountered in clinical settings. Fluid samples obtained from these effusions are vital for diagnostic and therapeutic purposes. Traditionally, cytological examination of smears is a common method for diagnosing serous cavity effusion, renowned for its convenience. However, this technique presents limitations that can compromise its efficiency and diagnostic accuracy. This study aims to overcome these challenges and introduce an improved method for the precise detection of malignant cells in serous cavity effusions. We have developed a transformer-based classification framework, specifically employing the vision transformer (ViT) model, to fulfill this objective. Our research involved collecting smear images and corresponding cytological reports from 161 patients who underwent serous cavity drainage. We meticulously annotated 4836 patches from these images, identifying regions with and without malignant cells, thus creating a unique dataset for smear image classification. The findings of our study reveal that deep learning models, particularly the ViT model, exhibit remarkable accuracy in classifying patches as malignant or non-malignant. The ViT model achieved an impressive area under the receiver operating characteristic curve (AUROC) of 0.99, surpassing the performance of the convolutional neural network (CNN) model, which recorded an AUROC of 0.86. Additionally, we validated our models using an external cohort of 127 patients. The ViT model sustained its high-level screening performance, achieving an AUROC of 0.98 at the patient level, compared to the CNN model's AUROC of 0.84. The visualization of our ViT models confirmed their capability to precisely identify regions containing malignant cells in multiple serous cavity effusion smear images. In summary, our study demonstrates the potential of deep learning models, particularly the ViT model, in automating the screening process for serous cavity effusions. These models offer significant assistance to cytologists in enhancing diagnostic accuracy and efficiency. The ViT model stands out for its advanced self-attention mechanism, making it exceptionally suitable for tasks that necessitate detailed analysis of small, sparsely distributed targets like cellular clusters in serous cavity effusions.


Assuntos
Líquidos Corporais , Humanos , Área Sob a Curva , Comportamento Compulsivo , Drenagem , Fontes de Energia Elétrica
20.
Sci Rep ; 14(1): 7608, 2024 03 31.
Artigo em Inglês | MEDLINE | ID: mdl-38556570

RESUMO

Human pose estimation is a crucial area of study in computer vision. Transformer-based pose estimation algorithms have gained popularity for their excellent performance and relatively compact parameterization. However, these algorithms often face challenges including high computational demands and insensitivity to local details. To address these problems, the Twin attention module was introduced in TransPose to improve model efficiency and reduce resource consumption. Additionally, to address issues related to insufficient joint feature representation and poor network recognition performance, the enhanced TransPose model, named VTTransPose, replaced the basic block in the third subnet with the intra-level feature fusion module V block. The performance of the proposed VTTransPose model was validated on the public datasets COCO val2017 and COCO test-dev2017. The experimental results on COCO val2017 and COCO test-dev2017 indicate that the AP evaluation index scores of the VTTransPose network proposed are 76.5 and 73.6 respectively, marking improvements of 0.4 and 0.2 over the original TransPose network. Additionally, VTTransPose exhibited a reduction of 4.8G FLOPs, 2M parameters, and approximately 40% lower memory usage during training compared to the original TransPose model. All the experimental results demonstrate that the proposed VTTransPose is more accurate, efficient, and lightweight compared to the original TransPose model.


Assuntos
Algoritmos , Fontes de Energia Elétrica , Humanos , Reconhecimento Psicológico , Gêmeos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...