Search

Environmental mapping serves as a crucial element in Simultaneous Localization and Mapping (SLAM) algorithms, playing a pivotal role in ensuring the accurate representation necessary for autonomous robot navigation guided by SLAM. Current SLAM systems predominantly rely on grid-based map representations, encountering challenges such as measurement discretization for cell fitting and grid map interpolation for online posture prediction. Splines present a promising alternative, capable of mitigating these issues while maintaining computational efficiency. This paper delves into the efficiency disparities between B-Spline surface mapping and discretized cell-based approaches, such as grid mapping, within indoor environments. B-Spline Online SLAM and FastSLAM, utilizing Rao-Blackwellized Particle Filter (RBPF), are employed to achieve range-based mapping of the unknown 2D environment. The system incorporates deep learning networks in the B-Spline curve estimation process to compute parameterizations and knot vectors. The research implementation utilizes the Intel Research Lab benchmark dataset to conduct a comprehensive qualitative and quantitative analysis of both approaches. The B-Spline surface approach demonstrates significantly superior performance, evidenced by low error metrics, including an average squared translational error of 0.0016 and an average squared rotational error of 1.137. Additionally, comparative analysis with Vision Benchmark Suite demonstrates robustness across different environments, highlighting the effectiveness of B-Spline SLAM for real-world applications. [ABSTRACT FROM AUTHOR]

Highlights Three dimensional (3D) tubular braided composites are widely used in various industries due to their excellent mechanical properties and lightweight characteristics. However, traditional numerical and experimental methods face challenges in predicting mechanical properties quickly and accurately due to factors such as ambient temperature, component materials, and geometric parameters. To address this issue, this paper combines deep neural networks (DNN) and two‐scale finite element analysis to accelerate the solution speed. The dataset is first obtained through a two‐scale finite element model with temperature based on micro‐CT. Then, the mapping model of macroscopic compression elastic properties and the influencing factors of material properties is established by DNN and Bayesian Optimization with Hyperband (BOHB) hyperparameter optimization algorithm. The rapid prediction of axial compression elastic properties of 3D tubular braided composites under different ambient temperatures, component materials, porosities, braiding angles and fiber volume contents is achieved. Finally, the accuracy of the predicted results of the constructed model is verified by experiments. A BOHB optimized deep learning model coupled with a finite element framework is proposed Fast prediction of elastic properties of 3D tubular braided composites at different temperatures The accuracy of the prediction results of the constructed model is verified by experiments [ABSTRACT FROM AUTHOR]

Introduction: Amidst escalating global temperatures, increasing climate change, and rapid urbanization, addressing urban heat islands and improving outdoor thermal comfort is paramount for sustainable urban development. Green walls offer a promising strategy by effectively lowering ambient air temperatures in urban environments. While previous studies have explored their impact in various climates, their effectiveness in humid climates remains underexplored. Methods: This research investigates the cooling effect of a green wall during summer in a humid climate, employing two approaches: Field Measurement-Based Analysis (SC 1: FMA) and Deep Learning Model (SC 2: DLM). In SC 1: FMA, experiments utilized data loggers at varying distances from the green wall to capture real-time conditions. SC 2: DLM utilized a deep learning model to predict the green wall's performance over time. Results: Results indicate a significant reduction in air temperature, with a 1.5°C (6%) decrease compared to real-time conditions. Long-term analysis identified specific distances (A, B, C, and D) contributing to temperature reductions ranging from 1.5°C to 2.5°C, highlighting optimal distances for green wall efficacy. Discussion: This study contributes novel insights by determining effective distances for green wall systems to mitigate ambient temperatures, addressing a critical gap in current literature. The integration of a deep learning model enhances analytical precision and forecasts future outcomes. Despite limitations related to a single case study and limited timeframe, this research offers practical benefits in urban heat island mitigation, enhancing outdoor comfort, and fostering sustainable and climate-resilient urban environments. [ABSTRACT FROM AUTHOR]

Emotions significantly impact human thinking, judgment, health, and communication. EEG-based emotion detection has advanced with the use of Brain-Computer Interface (BCI) technology, proving more effective than other physiological data. Despite progress in affective computing, emotion recognition remains a challenge. However, it's increasingly common in brain–machine interfaces, and research shows EEG brain waves are valuable in identifying emotional states. This research introduces a novel automated system for emotion recognition using deep learning techniques on EEG data collected from the GAMEEMO dataset, where participants played emotional assessment games. The system is designed to identify four emotions experienced during gameplay. The proposed model, called EEGER, was trained exclusively on EEG signals and demonstrated a 99.99% accuracy with minimal computational time. Key to its efficiency is the use of LSTM (Long Short-Term Memory) classifiers, which simplify the process by automatically extracting relevant features. The system was tested across different learning rates and epoch values, showing that 10 epochs with a learning rate of 0.0001 were sufficient to achieve the best accuracy. EEGER was also compared with other methods like K-Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA), and Adaptive Boosting (AdaBoost), outperforming them in both accuracy and efficiency. These findings suggest that EEGER offers a promising new approach to EEG-based emotion recognition, optimizing performance with lower complexity and computation time. [ABSTRACT FROM AUTHOR]

Coal mining production processes are complex and prone to frequent accidents. With the continuous improvement of safety management systems in China's coal mining industry, a vast amount of coal mine safety experience knowledge (CMSEK) has been accumulated, originating from on site operations. This knowledge has been recorded and stored in paper or electronic documents but it remains unconnected, and the increasing volume of documents further complicates the reuse and sharing of this knowledge. In the era of large models and digitalization, this knowledge has yet to be fully developed and utilized. To address these issues, a risk management checklist was derived from coal mining site data. By integrating intelligent algorithm models and the coal industry knowledge engineering design, a coal mine safety experience knowledge graph (CMSEKG) was developed to enhance the efficiency of utilizing coal mine safety experience knowledge. Specifically, we creatively developed a coal mine safety experience knowledge representation framework, capable of representing coal mine risk inspection records from different sources and of various types. Furthermore, we proposed a deep learning-based coal mine safety entity recognition model (CMSNER), which can effectively extract coal mine safety experience knowledge from text. Finally, the CMSEKG was stored using the Neo4j graph database, and a knowledge graph was constructed using selected case information as examples. The CMSEKG effectively integrates fragmented safety management experience and professional knowledge, promoting knowledge services and intelligent applications in coal mining operations, thereby providing knowledge support for the prevention and management of coal mine risks. [ABSTRACT FROM AUTHOR]

Pore structures provide extra freedoms for the design of porous media, leading to desirable properties, such as high catalytic rate, energy storage efficiency, and specific strength. This unfortunately makes the porous media susceptible to failure. Deep understanding of the failure mechanism in microstructures is a key to customizing high-performance crack-resistant porous media. However, solving the fracture problem of the porous materials is computationally intractable due to the highly complicated configurations of microstructures. To bridge the structural configurations and fracture responses of random porous media, a unique generative deep learning model is developed. A two-step strategy is proposed to deconstruct the fracture process, which sequentially corresponds to elastic deformation and crack propagation. The geometry of microstructure is translated into a scalar of elastic field as an intermediate variable, and then, the crack path is predicted. The neural network precisely characterizes the strong interactions among pore structures, the multiscale behaviors of fracture, and the discontinuous essence of crack propagation. Crack paths in random porous media are accurately predicted by simply inputting the images of targets, without inputting any additional input physical information. The prediction model enjoys an outstanding performance with a prediction accuracy of 90.25% and possesses a robust generalization capability. The accuracy of the present model is a record so far, and the prediction is accomplished within a second. This study opens an avenue to high-throughput evaluation of the fracture behaviors of heterogeneous materials with complex geometries. [ABSTRACT FROM AUTHOR]

AbstractDeep learning-based super-resolution methods have been successfully applied to digital elevation model (DEM) downscaling studies by designing structures and loss functions of the model. However, little attention has been paid to the design of super-resolution models that can maintain the hydrological characteristics of the DEM, which is important for hydrological studies. This study introduces a super-resolution model that integrates hydrologic knowledge (HKSRCGAN), with the aim to effectively maintain topographic features as well as the hydrologic connectivity of the DEM. The hydrological knowledge derived from surface flow direction and hydrological features are integrated into a deep learning algorithm to guide model training. The 30 m spatial resolution FABDEM is used to demonstrate the utility of the proposed method. Results show that the HKSRCGAN outperforms the bicubic interpolation, SRCNN, SRGAN, SRResNet and TfaSR methods in reducing topographic errors and maintaining hydrologic characteristics. In the test area, the entropy difference analysis shows that the DEM generated by HKSRCGAN is similar to the information contained in the reference DEM. Furthermore, super-resolution models integrating hydrological knowledge are valuable for modeling terrain primarily shaped by gravity and surface water flows. In the future, deep learning-based models integrating hydrologic knowledge are expected to be applied in DEM upscaling to maintain consistent hydrological characteristics. [ABSTRACT FROM AUTHOR]

Millet is one of the major coarse grain crops in China. Its geographical origin and Fusarium fungal contamination with ergosterol and deoxynivalenol have a direct impact on food quality, so the rapid prediction of the geographical origins and fungal toxin contamination is essential for protecting market fairness and consumer rights. In this study, 600 millet samples were collected from twelve production areas in China, and traditional algorithms such as random forest (RF) and support vector machine (SVM) were selected to compare with the deep learning models for the prediction of millet geographical origin and toxin content. This paper firstly develops a deep learning model (wavelet transformation-attention mechanism long short-term memory, WT-ALSTM) by combining hyperspectral imaging to achieve the best prediction effect, the wavelet transformation algorithm effectively eliminates noise in the spectral data, while the attention mechanism module improves the interpretability of the prediction model by selecting spectral feature bands. The integrated model (WT-ALSTM) based on selected feature bands achieves optimal prediction of millet origin, with its accuracy exceeding 99% on both the training and prediction datasets. Meanwhile, it achieves optimal prediction of ergosterol and deoxynivalenol content, with the coefficient of determination values exceeding 0.95 and residual predictive deviation values reaching 3.58 and 3.38 respectively, demonstrating excellent model performance. The above results suggest that the combination of hyperspectral imaging with a deep learning model has great potential for rapid quality assessment of millet. This study provides new technical references for developing portable and rapid hyperspectral imaging inspection technology for on-site assessment of agricultural product quality in the future. [ABSTRACT FROM AUTHOR]

In the modern era, AI-driven algorithms have significantly influenced medical diagnosis and therapy. In this pilot study, we propose using Streamlit 1.38.0 to create an interactive dashboard, PoAna.v1—Pose Analysis, as a new approach to address these concerns. In real-time, our system accurately tracks and evaluates individualized rehabilitation exercises for patients suffering from low back pain using features such as exercise visualization and guidance, real-time feedback and monitoring, and personalized exercise plans. This dashboard was very effective for tracking rehabilitation progress. We recruited 32 individuals to participate in this pilot study. We monitored an individual's overall performance for one week. Of the participants, 18.75% engaged in rehabilitative exercises less frequently than twice daily; 81.25% did so at least three times daily. The proposed Long Short-Term Memory (LSTM) architecture had a training accuracy score of 98.8% and a testing accuracy of 99.7%, with an average accuracy of 10-fold cross-validation of 98.54%. On the pre- and post-test assessments, there is a significant difference between pain levels, with a p < 0.05 and a t-stat value of 12.175. The proposed system's usability score is 79.375, indicating that it provides a user-friendly environment for the user to use the PoAna.v1 web application. So far, our research suggests that the Streamlit 1.38.0-based dashboard improves patients' engagement, adherence, and success with exercise. Future research aims to add more characteristics that can improve the complete care of low back pain (LBP) and validate the effectiveness of this intervention in larger patient cohorts. [ABSTRACT FROM AUTHOR]

NASICON (Na 1 + x Zr 2 Si x P 3 - x O 12 ) is a well-established solid-state electrolyte, renowned for its high ionic conductivity and excellent chemical stability, rendering it a promising candidate for solid-state batteries. However, the intricate influence of ion doping on their performance has been a central focus of research, with existing studies often lacking comprehensive evaluation methods. This study introduces a deep-learning-based approach to efficiently evaluate ion-doped NASICON materials. We developed a convolutional neural network (CNN) model capable of predicting the performance of various ion-doped NASICON compounds by leveraging extensive datasets from prior experimental investigation. The model demonstrated high accuracy and efficiency in predicting ionic conductivity and electrochemical properties. Key findings include the successful synthesis and validation of three NASICON materials predicted by the model, with experimental results closely matching the model's predictions. This research not only enhances the understanding of ion-doping effects in NASICON materials but also establishes a robust framework for material design and practical applications. It bridges the gap between theoretical predictions and experimental validations. [ABSTRACT FROM AUTHOR]

Sentiment analysis is an automated approach which is utilized in process of analysing textual data to describe public opinion. The sentiment analysis has major role in creating impact in the day‐to‐day life of individuals. However, a precise interpretation of text still relies as a major concern in classifying sentiment. So, this research introduced Bidirectional Long Short Term Memory with Ranger AdaBelief Optimizer (Bi‐LSTM RAO) to classify sentiment of tweets. Initially, data is obtained from Twitter API, Sentiment 140 and Stanford Sentiment Treebank‐2 (SST‐2). The raw data is pre‐processed and it is subjected to feature extraction which is performed using Bag of Words (BoW) and Term Frequency‐Inverse Document Frequency (TF‐IDF). The feature selection is performed using Gazelle Optimization Algorithm (GOA) which removes the irrelevant or redundant features that maximized model performance and classification is performed using Bi LSTM–RAO. The RAO optimizes the loss function of Bi‐LSTM model that maximized accuracy. The classification accuracy of proposed method for Twitter API, Sentiment 140 and SST 2 dataset is obtained as 909.44%, 99.71% and 99.86%, respectively. These obtained results are comparably higher than ensemble framework, Robustly Optimized BERT and Gated Recurrent Unit (RoBERTa‐GRU), Logistic Regression‐Long Short Term Memory (LR‐LSTM), Convolutional Bi‐LSTM, Sentiment and Context Aware Attention‐based Hybrid Deep Neural Network (SCA‐HDNN) and Stochastic Gradient Descent optimization based Stochastic Gate Neural Network (SGD‐SGNN). [ABSTRACT FROM AUTHOR]

Fibre bundle (FB)‐based endoscopes are indispensable in biology and medical science due to their minimally invasive nature. However, resolution and contrast for fluorescence imaging are limited due to characteristic features of the FBs, such as low numerical aperture (NA) and individual fibre core sizes. In this study, we improved the resolution and contrast of sample fluorescence images acquired using in‐house fabricated high‐NA FBs by utilising generative adversarial networks (GANs). In order to train our deep learning model, we built an FB‐based multifocal structured illumination microscope (MSIM) based on a digital micromirror device (DMD) which improves the resolution and the contrast substantially compared to basic FB‐based fluorescence microscopes. After network training, the GAN model, employing image‐to‐image translation techniques, effectively transformed wide‐field images into high‐resolution MSIM images without the need for any additional optical hardware. The results demonstrated that GAN‐generated outputs significantly enhanced both contrast and resolution compared to the original wide‐field images. These findings highlight the potential of GAN‐based models trained using MSIM data to enhance resolution and contrast in wide‐field imaging for fibre bundle‐based fluorescence microscopy. Lay Description: Fibre bundle (FB) endoscopes are essential in biology and medicine but suffer from limited resolution and contrast for fluorescence imaging. Here we improved these limitations using high‐NA FBs and generative adversarial networks (GANs). We trained a GAN model with data from an FB‐based multifocal structured illumination microscope (MSIM) to enhance resolution and contrast without additional optical hardware. Results showed significant enhancement in contrast and resolution, showcasing the potential of GAN‐based models for fibre bundle‐based fluorescence microscopy. [ABSTRACT FROM AUTHOR]

Prediction using computer vision is getting prevalent nowadays because of satisfying results. The vision of Internet of Vehicles (IoV) expedites Vehicle to everything (V2X) communications by implementing heterogeneous global networks. Road crack is one of the major factors that causes road mishaps and damage to vehicles. To ensure smooth and safe driving, avoiding road crack in transportation planning and navigation is significant. To address this issue, we proposed a novel convolutional neural network (CNN)-based smart transportation system. We showed how to quantify the severity of the cracks. We proposed a post-processing algorithm to provide option to the driver to select the safest road toward the destination. The communication system for the proposed smart transportation system has also been introduced. The performance comparison of a few popular CNN architectures has been investigated. Simulation results showed that Resnet50 algorithm provides significantly high accuracy compared with SqueezeNet and InceptionV3 algorithm in order to detect road cracks for the proposed transportation system. We demonstrated high accuracy of measuring the crack severity via numerical analysis. The integration of the proposed system in next generation smart vehicles can ensure accurate detection of road cracks earlier enough providing the option to select alternate safe route toward a destination as advanced driver assistance service. Moreover, the proposed system can also play a key role in order to reduce road mishaps notably by warning the driver about the updated road surface conditions. [ABSTRACT FROM AUTHOR]

Intravenous fluid bags are essential in hospitals, but foreign particles can contaminate them during mass production, posing significant risks. Although produced in sanitary environments, contamination can cause severe problems if products reach consumers. Traditional inspection methods struggle with the flexible nature of these bags, which deform easily, complicating particle detection. Recent deep learning advancements offer promising solutions in regard to quality inspection, but high-resolution image processing remains challenging. This paper introduces a real-time deep learning-based inspection system addressing bag deformation and memory constraints for high-resolution images. The system uses object-level background rejection, filtering out objects similar to the background to isolate moving foreign particles. To further enhance performance, the method aggregates object patches, reducing unnecessary data and preserving spatial resolution for accurate detection. During aggregation, candidate objects are tracked across frames, forming tracks re-identified as bubbles or particles by the deep learning model. Ensemble detection results provide robust final decisions. Experiments demonstrate that this system effectively detects particles in real-time with over 98% accuracy, leveraging deep learning advancements to tackle the complexities of inspecting flexible fluid bags. [ABSTRACT FROM AUTHOR]

The accumulation of defects on wind turbine blade surfaces can lead to irreversible damage, impacting the aerodynamic performance of the blades. To address the challenge of detecting and quantifying surface defects on wind turbine blades, a blade surface defect detection and quantification method based on an improved Deeplabv3+ deep learning model is proposed. Firstly, an improved method for wind turbine blade surface defect detection, utilizing Mobilenetv2 as the backbone feature extraction network, is proposed based on an original Deeplabv3+ deep learning model to address the issue of limited robustness. Secondly, through integrating the concept of pre-trained weights from transfer learning and implementing a freeze training strategy, significant improvements have been made to enhance both the training speed and model training accuracy of this deep learning model. Finally, based on segmented blade surface defect images, a method for quantifying blade defects is proposed. This method combines image stitching algorithms to achieve overall quantification and risk assessment of the entire blade. Test results show that the improved Deeplabv3+ deep learning model reduces training time by approximately 43.03% compared to the original model, while achieving mAP and MIoU values of 96.87% and 96.93%, respectively. Moreover, it demonstrates robustness in detecting different surface defects on blades across different backgrounds. The application of a blade surface defect quantification method enables the precise quantification of different defects and facilitates the assessment of risk levels associated with defect measurements across the entire blade. This method enables non-contact, long-distance, high-precision detection and quantification of surface defects on the blades, providing a reference for assessing surface defects on wind turbine blades. Graphic Abstract [ABSTRACT FROM AUTHOR]

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Yuxiao Yang,1,2 Xingyuan Gao,3 Hongmei Liang,4 Qiuying Yang1,2 1School of Biomedical Engineering, Capital Medical University, Beijing, People’s Republic of China; 2Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, Beijing, People’s Republic of China; 3Design Department, Beijing HANHAIZHONGJIA Hydraulic Machinery Co., Ltd, Beijing, People’s Republic of China; 4Nursing Department, China Railway 17th Bureau Group Central Hospital, Taiyuan, People’s Republic of ChinaCorrespondence: Qiuying Yang, School of Biomedical Engineering, Capital Medical University, Beijing, People’s Republic of China, Tel +86 13691283439, Email yangqiuying@ccmu.edu.cnPurpose: AIDS presents serious harms to public health worldwide. In this paper, we used five single models: ARIMA, SARIMA, Prophet, BP neural network, and LSTM method to model and predict the number of monthly AIDS incidence cases and mortality cases in China. We have also proposed the LSTM-SARIMA combination model to enhance the accuracy of the prediction. This study provides strong data support for the prevention and treatment of AIDS.Methods: We collected data on monthly AIDS incidence cases and mortality cases in China from January 2010 to February 2024. Among them, for modeling, we used data from January 2010 to February 2021 and the rest for validation. Treatments were applied to the dataset based on its characteristics during modeling. All models in our study were performed using Python 3.11.6. Meanwhile, we used the constructed model to predict monthly incidence and mortality cases from March 2024 to July 2024. We then evaluated our prediction results using RMSE, MAE, MAPE, and SMAPE.Results: The deep learning methods of LSTM and BPNN outperform ARIMA, SARIMA, and Prophet in predicting the number of mortality cases. When predicting the number of AIDS incidence cases, there is little difference between the two types of methods, and the LSTM method performs slightly better than the rest of the methods. Meanwhile, the average error in predicting AIDS mortality cases is significantly lower than in predicting AIDS incidence cases. The LSTM-SARIMA method outperforms other methods in predicting AIDS incidence and mortality.Conclusion: Due to the different characteristics of the AIDS incidence and mortality cases series, the performance of distinct methods is slightly different. The AIDS mortality series is smoother than the incidence series. The combined LSTM-SARIMA model outperforms the traditional method in prediction and the LSTM method alone, which is of practical significance for optimizing the prediction results of AIDS.Keywords: AIDS, ARIMA model, Prophet model, deep learning model, LSTM-SARIMA combination model

AIM:To establish pupil diameter measurement algorithms based on infrared images that can be used in real-world clinical settings.METHODS:A total of 188 patients from outpatient clinic at He Eye Specialist Shenyang Hospital from Spetember to December 2022 were included, and 13 470 infrared pupil images were collected for the study. All infrared images for pupil segmentation were labeled using the Labelme software. The computation of pupil diameter is divided into four steps: image pre-processing, pupil identification and localization, pupil segmentation, and diameter calculation. Two major models are used in the computation process: the modified YoloV3 and Deeplabv3+ models, which must be trained beforehand.RESULTS:The test dataset included 1 348 infrared pupil images. On the test dataset, the modified YoloV3 model had a detection rate of 99.98% and an average precision(AP)of 0.80 for pupils. The DeeplabV3+ model achieved a background intersection over union(IOU)of 99.23%, a pupil IOU of 93.81%, and a mean IOU of 96.52%. The pupil diameters in the test dataset ranged from 20 to 56 pixels, with a mean of 36.06±6.85 pixels. The absolute error in pupil diameters between predicted and actual values ranged from 0 to 7 pixels, with a mean absolute error(MAE)of 1.06±0.96 pixels.CONCLUSION:This study successfully demonstrates a robust infrared image-based pupil diameter measurement algorithm, proven to be highly accurate and reliable for clinical application.

Abstract NASICON (Na $$_{1+x}$$ 1 + x Zr $$_2$$ 2 Si $$_x$$ x P $$_{3-x}$$ 3 - x O $$_{12}$$ 12 ) is a well-established solid-state electrolyte, renowned for its high ionic conductivity and excellent chemical stability, rendering it a promising candidate for solid-state batteries. However, the intricate influence of ion doping on their performance has been a central focus of research, with existing studies often lacking comprehensive evaluation methods. This study introduces a deep-learning-based approach to efficiently evaluate ion-doped NASICON materials. We developed a convolutional neural network (CNN) model capable of predicting the performance of various ion-doped NASICON compounds by leveraging extensive datasets from prior experimental investigation. The model demonstrated high accuracy and efficiency in predicting ionic conductivity and electrochemical properties. Key findings include the successful synthesis and validation of three NASICON materials predicted by the model, with experimental results closely matching the model’s predictions. This research not only enhances the understanding of ion-doping effects in NASICON materials but also establishes a robust framework for material design and practical applications. It bridges the gap between theoretical predictions and experimental validations. Graphical Abstract

Abstract Ovarian cysts pose significant health risks including torsion, infertility, and cancer, necessitating rapid and accurate diagnosis. Ultrasonography is commonly employed for screening, yet its effectiveness is hindered by challenges like weak contrast, speckle noise, and hazy boundaries in images. This study proposes an adaptive deep learning-based segmentation technique using a database of ovarian ultrasound cyst images. A Guided Trilateral Filter (GTF) is applied for noise reduction in pre-processing. Segmentation utilizes an Adaptive Convolutional Neural Network (AdaResU-net) for precise cyst size identification and benign/malignant classification, optimized via the Wild Horse Optimization (WHO) algorithm. Objective functions Dice Loss Coefficient and Weighted Cross-Entropy are optimized to enhance segmentation accuracy. Classification of cyst types is performed using a Pyramidal Dilated Convolutional (PDC) network. The method achieves a segmentation accuracy of 98.87%, surpassing existing techniques, thereby promising improved diagnostic accuracy and patient care outcomes.

Abstract Treatment-induced ototoxicity and accompanying hearing loss are a great concern associated with chemotherapeutic or antibiotic drug regimens. Thus, prophylactic cure or early treatment is desirable by local delivery to the inner ear. In this study, we examined a novel way of intratympanically delivered sustained nanoformulation by using crosslinked hybrid nanoparticle (cHy-NPs) in a thermoresponsive hydrogel i.e. thermogel that can potentially provide a safe and effective treatment towards the treatment-induced or drug-induced ototoxicity. The prophylactic treatment of the ototoxicity can be achieved by using two therapeutic molecules, Flunarizine (FL: T-type calcium channel blocker) and Honokiol (HK: antioxidant) co-encapsulated in the same delivery system. Here we investigated, FL and HK as cytoprotective molecules against cisplatin-induced toxic effects in the House Ear Institute - Organ of Corti 1 (HEI-OC1) cells and in vivo assessments on the neuromast hair cell protection in the zebrafish lateral line. We observed that cytotoxic protective effect can be enhanced by using FL and HK in combination and developing a robust drug delivery formulation. Therefore, FL-and HK-loaded crosslinked hybrid nanoparticles (FL-cHy-NPs and HK-cHy-NPs) were synthesized using a quality-by-design approach (QbD) in which design of experiment-central composite design (DoE-CCD) following the standard least-square model was used for nanoformulation optimization. The physicochemical characterization of FL and HK loaded-NPs suggested the successful synthesis of spherical NPs with polydispersity index 75%), drugs loading (~ 10%), stability (> 2 months) in the neutral solution, and appropriate cryoprotectant selection. We assessed caspase 3/7 apopototic pathway in vitro that showed significantly reduced signals of caspase 3/7 activation after the FL-cHy-NPs and HK-cHy-NPs (alone or in combination) compared to the CisPt. The final formulation i.e. crosslinked-hybrid-nanoparticle-embedded-in-thermogel was developed by incorporating drug-loaded cHy-NPs in poloxamer-407, poloxamer-188, and carbomer-940-based hydrogel. A combination of artificial intelligence (AI)-based qualitative and quantitative image analysis determined the particle size and distribution throughout the visible segment. The developed formulation was able to release the FL and HK for at least a month. Overall, a highly stable nanoformulation was successfully developed for combating treatment-induced or drug-induced ototoxicity via local administration to the inner ear. Graphical Abstract

Driver drowsiness can cause serious harm to drivers and other road participants. Exploring objective and efficient methods for detecting driver drowsiness has important application value for ensuring road safety. Considering the information complementary between local and global facial features for drowsiness detection, as well as the advantages of deep learning models in information mining, this paper proposes a deep learning model based on multi-granularity facial features and Long Short Term Memory (LSTM) network for driver drowsiness detection. To obtain local facial feature information, face detection and facial landmarks location are implemented based on Practical Facial Landmark Detector (PFLD). The local representation features of the eyes and mouth, as well as the head pose feature, are calculated from the coordinate information of facial landmarks. Furthermore, a global representation learning Vision Transformer (ViT) model that trained on the NTHU-DDD dataset to obtain higher-level semantic information. Due to drowsiness has an accumulative property, an LSTM network that takes the local and global multi-granularity representation features as input to further mine the drowsy clues in the temporal dimension. A large number of comparative experiments are conducted on the public NTHU-DDD dataset, and the results show that the proposed method outperformed other methods, achieving a detection accuracy of 93.15%. Experimental results show that the method can achieve much higher accuracy and can provide an alternative solution for the driver assistance system.

Using a combination of the long short-term memory model and hydrological change indicators, this study proposes an assessment framework at inter-annual and intra-annual scales to quantify the hydrological regime changes and ecological event responses caused by the regulation of the Three Gorges Dam (TGD) in the upper reaches of the Yangtze River. The results indicate that during the post-TGD period (2004–2019), 2 indicators of the natural flow regime undergo a high degree of alteration at the inter-annual scale, which increase to 12 when regulated flows are considered. Furthermore, we find that while climate and incoming water change significantly reduces the annual flow and monthly flow during the flood season, it increases the complexity (79%) and ecodeficit at the seasonal scale (94%). Among the 32 indicators of hydrologic alteration, TGD is the dominant factor influencing changes in 20 indicators, increasing the magnitude of low-flow events, decreasing the frequency of high-flow pulses, and advancing the timing of 1-day minimum flow (43 Julian date). From the hydrological perspective, the altered rising water conditions due to TGD regulation may cause an average decrease of 19.5% in the fry abundance for the Four Famous Major Carps. HIGHLIGHTS The multiscale changes in the flow regime were evaluated and the impact of dam construction by introducing entropy theory was quantified.; After 2003, the flow regime tended to be more complex, while the singularity of hydrological events increased, with the Three Gorges Dam being the dominant factor.; The dam advanced the timing of minimum flow, reduced the concentration of flow regimes, and increased the ecosurplus.;

Ovarian cysts pose significant health risks including torsion, infertility, and cancer, necessitating rapid and accurate diagnosis. Ultrasonography is commonly employed for screening, yet its effectiveness is hindered by challenges like weak contrast, speckle noise, and hazy boundaries in images. This study proposes an adaptive deep learning-based segmentation technique using a database of ovarian ultrasound cyst images. A Guided Trilateral Filter (GTF) is applied for noise reduction in pre-processing. Segmentation utilizes an Adaptive Convolutional Neural Network (AdaResU-net) for precise cyst size identification and benign/malignant classification, optimized via the Wild Horse Optimization (WHO) algorithm. Objective functions Dice Loss Coefficient and Weighted Cross-Entropy are optimized to enhance segmentation accuracy. Classification of cyst types is performed using a Pyramidal Dilated Convolutional (PDC) network. The method achieves a segmentation accuracy of 98.87%, surpassing existing techniques, thereby promising improved diagnostic accuracy and patient care outcomes. [ABSTRACT FROM AUTHOR]

Treatment-induced ototoxicity and accompanying hearing loss are a great concern associated with chemotherapeutic or antibiotic drug regimens. Thus, prophylactic cure or early treatment is desirable by local delivery to the inner ear. In this study, we examined a novel way of intratympanically delivered sustained nanoformulation by using crosslinked hybrid nanoparticle (cHy-NPs) in a thermoresponsive hydrogel i.e. thermogel that can potentially provide a safe and effective treatment towards the treatment-induced or drug-induced ototoxicity. The prophylactic treatment of the ototoxicity can be achieved by using two therapeutic molecules, Flunarizine (FL: T-type calcium channel blocker) and Honokiol (HK: antioxidant) co-encapsulated in the same delivery system. Here we investigated, FL and HK as cytoprotective molecules against cisplatin-induced toxic effects in the House Ear Institute - Organ of Corti 1 (HEI-OC1) cells and in vivo assessments on the neuromast hair cell protection in the zebrafish lateral line. We observed that cytotoxic protective effect can be enhanced by using FL and HK in combination and developing a robust drug delivery formulation. Therefore, FL-and HK-loaded crosslinked hybrid nanoparticles (FL-cHy-NPs and HK-cHy-NPs) were synthesized using a quality-by-design approach (QbD) in which design of experiment-central composite design (DoE-CCD) following the standard least-square model was used for nanoformulation optimization. The physicochemical characterization of FL and HK loaded-NPs suggested the successful synthesis of spherical NPs with polydispersity index < 0.3, drugs encapsulation (> 75%), drugs loading (~ 10%), stability (> 2 months) in the neutral solution, and appropriate cryoprotectant selection. We assessed caspase 3/7 apopototic pathway in vitro that showed significantly reduced signals of caspase 3/7 activation after the FL-cHy-NPs and HK-cHy-NPs (alone or in combination) compared to the CisPt. The final formulation i.e. crosslinked-hybrid-nanoparticle-embedded-in-thermogel was developed by incorporating drug-loaded cHy-NPs in poloxamer-407, poloxamer-188, and carbomer-940-based hydrogel. A combination of artificial intelligence (AI)-based qualitative and quantitative image analysis determined the particle size and distribution throughout the visible segment. The developed formulation was able to release the FL and HK for at least a month. Overall, a highly stable nanoformulation was successfully developed for combating treatment-induced or drug-induced ototoxicity via local administration to the inner ear. [ABSTRACT FROM AUTHOR]

Mobile texting has increased social engineering assaults like phishing. Because spam, or unsolicited text messages, spread phishing attempts that steal personal information. Traditional methods of spam detection, often based on statistical models or human rule-based systems, have difficulties in keeping up with the growing complexity of spamming strategies. Gathering pertinent data from social networks is a challenging task, mostly due to the limits imposed by privacy concerns and time constraints. The inefficiency and time-consuming nature of conventional frequency-based techniques to word encoding are generally recognized. Text classification has shown promising outcomes with the use of word embeddings and deep learning techniques. The proposed approach involves integrating deep learning with the Remora optimization algorithm framework (DL–ROA) to autonomously extract intricate patterns and nuanced information from text messages. The system's capacity to adapt to new spamming strategies enhances the DL–ROA. The proposed technique improves the accuracy of detection while reducing the inefficiency and time required to create contextual word vectors based on word frequency. Spam detection is achieved by using a hybrid deep model that combines long short-term memory (LSTM) and deep convolutional neural networks (DCNN) architectures. Empirical data demonstrate that the DL–ROA technique surpasses existing deep learning models in terms of accuracy, f1-score, and recall. In addition, the DL–ROA achieved an unprecedented accuracy rate of 98.25%. [ABSTRACT FROM AUTHOR]

Beat-by-beat monitoring of hemodynamic parameters in the left ventricle contributes to the early diagnosis and treatment of heart failure, valvular heart disease, and other cardiovascular diseases. Current accurate measurement methods for ventricular hemodynamic parameters are inconvenient for monitoring hemodynamic indexes in daily life. The objective of this study is to propose a method for estimating intraventricular hemodynamic parameters in a beat-to-beat style based on non-invasive PCG (phonocardiogram) and PPG (photoplethysmography) signals. Three beagle dogs were used as subjects. PCG, PPG, electrocardiogram (ECG), and invasive blood pressure signals in the left ventricle were synchronously collected while epinephrine medicine was injected into the veins to produce hemodynamic variations. Various doses of epinephrine were used to produce hemodynamic variations. A total of 40 records (over 12,000 cardiac cycles) were obtained. A deep neural network was built to simultaneously estimate four hemodynamic parameters of one cardiac cycle by inputting the PCGs and PPGs of the cardiac cycle. The outputs of the network were four hemodynamic parameters: left ventricular systolic blood pressure (SBP), left ventricular diastolic blood pressure (DBP), maximum rate of left ventricular pressure rise (MRR), and maximum rate of left ventricular pressure decline (MRD). The model built in this study consisted of a residual convolutional module and a bidirectional recurrent neural network module which learnt the local features and context relations, respectively. The training mode of the network followed a regression model, and the loss function was set as mean square error. When the network was trained and tested on one subject using a five-fold validation scheme, the performances were very good. The average correlation coefficients (CCs) between the estimated values and measured values were generally greater than 0.90 for SBP, DBP, MRR, and MRD. However, when the network was trained with one subject's data and tested with another subject's data, the performance degraded somewhat. The average CCs reduced from over 0.9 to 0.7 for SBP, DBP, and MRD; however, MRR had higher consistency, with the average CC reducing from over 0.9 to about 0.85 only. The generalizability across subjects could be improved if individual differences were considered. The performance indicates the possibility that hemodynamic parameters could be estimated by PCG and PPG signals collected on the body surface. With the rapid development of wearable devices, it has up-and-coming applications for self-monitoring in home healthcare environments. [ABSTRACT FROM AUTHOR]

In recent years, there has been a significant increase in the design of neural network models for solving math word problems (MWPs). These neural solvers have been designed with various architectures and evaluated on diverse datasets, posing challenges in fair and effective performance evaluation. This paper presents a comparative study of representative neural solvers, aiming to elucidate their technical features and performance variations in solving different types of MWPs. Firstly, an in-depth technical analysis is conducted from the initial deep neural solver DNS to the state-of-the-art GPT-4. To enhance the technical analysis, a unified framework is introduced, which comprises highly reusable modules decoupled from existing MWP solvers. Subsequently, a testbed is established to conveniently reproduce existing solvers and develop new solvers by combing these reusable modules, and finely regrouped datasets are provided to facilitate the comparative evaluation of the designed solvers. Then, comprehensive testing is conducted and detailed results for eight representative MWP solvers on five finely regrouped datasets are reported. The comparative analysis yields several key findings: (1) Pre-trained language model-based solvers demonstrate significant accuracy advantages across nearly all datasets, although they suffer from limitations in math equation calculation. (2) Models integrated with tree decoders exhibit strong performance in generating complex math equations. (3) Identifying and appropriately representing implicit knowledge hidden in problem texts is crucial for improving the accuracy of math equation generation. Finally, the paper also discusses the major technical challenges and potential research directions in this field. The insights gained from this analysis offer valuable guidance for future research, model development, and performance optimization in the field of math word problem solving. [ABSTRACT FROM AUTHOR]

Rapid population growth, economic growth, and technological developments in recent years have led to a significant increase in electricity consumption. Therefore, the estimation of electrical energy demand is crucial for the planning of electricity generation and consumption in cities. This study proposes a hybrid deep learning model that combines convolutional neural network (CNN) and long short-term memory (LSTM) techniques, both of which are deep learning techniques, to estimate electrical load demand. A hybrid deep learning model and LSTM model were applied to a dataset containing hourly electricity consumption and meteorological information of a city in Türkiye from 2017 to 2021. The results were evaluated using mean absolute percent error (MAPE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) metrics. The proposed CNN-LSTM hybrid model was compared to the LSTM model, with lower MAPE, MAE, and RMSE values. Furthermore, the CNN-LSTM model exhibited superior prediction performance with an R2 value of 0.8599 compared to the LSTM model with an R2 value of 0.8086. These results demonstrate the effectiveness of the proposed deep learning model in accurately estimating future electrical load demand to plan electricity generation for sustainable cities. [ABSTRACT FROM AUTHOR]

Background: Timely detection and treatment of serious diseases, including cancer, are crucial for saving lives and improving longevity. The Internet of Medical Things (IoMT) holds promise for enhancing healthcare by enabling real-time disease identification through automated image analysis. However, integrating large deep learning models with IoMT devices poses challenges. Objective: This study aims to develop an efficient deep learning model, "EffiPathNet," specifically designed for analyzing histopathological images with a focus on achieving both accuracy and speed. Method: EffiPathNet was developed to address the challenges associated with large models and to ensure compatibility with IoMT imaging devices. The model was tested on a reputable histopathological image dataset, evaluating its accuracy, speed, and computational requirements. Result: EffiPathNet achieved an average accuracy of 97.79% and a 0.987 F1 score, demonstrating its exceptional ability to accurately classify histopathological images. The model's lightweight design, requiring only a few kilobytes in size, enhances its compatibility with IoMT imaging devices. Main Findings: The study highlights EffiPathNet's efficacy in accurately classifying histopathological images and its potential for integration with IoMT devices. The lightweight design further enhances its suitability for practical IoMT applications. Conclusion: EffiPathNet emerges as a promising solution for real-time disease identification in histopathological images, combining high accuracy with computational efficiency. Its compatibility with IoMT devices suggests its potential for practical implementation in healthcare settings, contributing to timely and effective medical interventions. [ABSTRACT FROM AUTHOR]

Medical advances prolonging life have led to more permanent pacemaker implants. When pacemaker implantation (PMI) is commonly caused by sick sinus syndrome or conduction disorders, predicting PMI is challenging, as patients often experience related symptoms. This study was designed to create a deep learning model (DLM) for predicting future PMI from ECG data and assess its ability to predict future cardiovascular events. In this study, a DLM was trained on a dataset of 158,471 ECGs from 42,903 academic medical center patients, with additional validation involving 25,640 medical center patients and 26,538 community hospital patients. Primary analysis focused on predicting PMI within 90 days, while all-cause mortality, cardiovascular disease (CVD) mortality, and the development of various cardiovascular conditions were addressed with secondary analysis. The study's raw ECG DLM achieved area under the curve (AUC) values of 0.870, 0.878, and 0.883 for PMI prediction within 30, 60, and 90 days, respectively, along with sensitivities exceeding 82.0% and specificities over 81.9% in the internal validation. Significant ECG features included the PR interval, corrected QT interval, heart rate, QRS duration, P-wave axis, T-wave axis, and QRS complex axis. The AI-predicted PMI group had higher risks of PMI after 90 days (hazard ratio [HR]: 7.49, 95% CI: 5.40-10.39), all-cause mortality (HR: 1.91, 95% CI: 1.74–2.10), CVD mortality (HR: 3.53, 95% CI: 2.73–4.57), and new-onset adverse cardiovascular events. External validation confirmed the model's accuracy. Through ECG analyses, our AI DLM can alert clinicians and patients to the possibility of future PMI and related mortality and cardiovascular risks, aiding in timely patient intervention. [ABSTRACT FROM AUTHOR]

Proton-exchange membrane fuel cells (PEMFCs) play a crucial role in the transition to sustainable energy systems. Accurately estimating the state of health (SOH) of PEMFCs under dynamic operating conditions is essential for ensuring their reliability and longevity. This study designed dynamic operating conditions for fuel cells and conducted durability tests using both crack-free fuel cells and fuel cells with uniform cracks. Utilizing deep learning methods, we estimated the SOH of PEMFCs under dynamic operating conditions and investigated the performance of long short-term memory networks (LSTM), gated recurrent units (GRU), temporal convolutional networks (TCN), and transformer models for SOH estimation tasks. We also explored the impact of different sampling intervals and training set proportions on the predictive performance of these models. The results indicated that shorter sampling intervals and higher training set proportions significantly improve prediction accuracy. The study also highlighted the challenges posed by the presence of cracks. Cracks cause more frequent and intense voltage fluctuations, making it more difficult for the models to accurately capture the dynamic behavior of PEMFCs, thereby increasing prediction errors. However, under crack-free conditions, due to more stable voltage output, all models showed improved predictive performance. Finally, this study underscores the effectiveness of deep learning models in estimating the SOH of PEMFCs and provides insights into optimizing sampling and training strategies to enhance prediction accuracy. The findings make a significant contribution to the development of more reliable and efficient PEMFC systems for sustainable energy applications. [ABSTRACT FROM AUTHOR]

Simple Summary: This study addresses the significance of animal sounds as valuable indicators of both behavior and health in animals, emphasizing the challenges involved in collecting datasets for deep learning models. Particularly, in the context of classifying pig vocalization and non-vocalization, it is identified as laborious and time-consuming when relying on human efforts. In response to these challenges, the research proposes a new approach utilizing a deep learning model to automatically classify pig vocalization and non-vocalization with high accuracy. The success of this method not only provides an efficient means of collecting pig sound datasets but also presents a promising avenue for improving the classification of pig vocalization and non-vocalization in deep learning models, thereby contributing to advancements in animal behavior research and health monitoring. Since pig vocalization is an important indicator of monitoring pig conditions, pig vocalization detection and recognition using deep learning play a crucial role in the management and welfare of modern pig livestock farming. However, collecting pig sound data for deep learning model training takes time and effort. Acknowledging the challenges of collecting pig sound data for model training, this study introduces a deep convolutional neural network (DCNN) architecture for pig vocalization and non-vocalization classification with a real pig farm dataset. Various audio feature extraction methods were evaluated individually to compare the performance differences, including Mel-frequency cepstral coefficients (MFCC), Mel-spectrogram, Chroma, and Tonnetz. This study proposes a novel feature extraction method called Mixed-MMCT to improve the classification accuracy by integrating MFCC, Mel-spectrogram, Chroma, and Tonnetz features. These feature extraction methods were applied to extract relevant features from the pig sound dataset for input into a deep learning network. For the experiment, three datasets were collected from three actual pig farms: Nias, Gimje, and Jeongeup. Each dataset consists of 4000 WAV files (2000 pig vocalization and 2000 pig non-vocalization) with a duration of three seconds. Various audio data augmentation techniques are utilized in the training set to improve the model performance and generalization, including pitch-shifting, time-shifting, time-stretching, and background-noising. In this study, the performance of the predictive deep learning model was assessed using the k-fold cross-validation (k = 5) technique on each dataset. By conducting rigorous experiments, Mixed-MMCT showed superior accuracy on Nias, Gimje, and Jeongeup, with rates of 99.50%, 99.56%, and 99.67%, respectively. Robustness experiments were performed to prove the effectiveness of the model by using two farm datasets as a training set and a farm as a testing set. The average performance of the Mixed-MMCT in terms of accuracy, precision, recall, and F1-score reached rates of 95.67%, 96.25%, 95.68%, and 95.96%, respectively. All results demonstrate that the proposed Mixed-MMCT feature extraction method outperforms other methods regarding pig vocalization and non-vocalization classification in real pig livestock farming. [ABSTRACT FROM AUTHOR]

AbstractVisual content featured in Airbnb cover page photographs plays a crucial role in shaping consumers’ perceptions of properties. Despite its acknowledged importance, few empirical studies have investigated the influence of greenery content on consumer booking behavior. This study aims to determine whether green landscape elements in Airbnb cover page photographs stimulate consumption, employing a deep learning model for visual semantic segmentation. The findings confirm that green landscape elements positively impact consumer booking behavior, a trend that has become particularly pronounced following the COVID-19 pandemic. Furthermore, the emergence of the pandemic and the geographical location of Airbnb properties exert a positively disruptive moderating effect on the relationship between green landscape elements in cover page photographs and consumer booking behavior. This research enriches the existing literature by highlighting consumer visual preferences related to cover page photographs in the realm of shared accommodations. [ABSTRACT FROM AUTHOR]

Objectives: This study aims to demonstrate the preprocessing steps for knee MRI images to detect meniscal lesions using deep learning models and highlight their practical implications in diagnosing knee conditions, especially meniscal injuries, often caused by degeneration or trauma. Magnetic resonance imaging (MRI) is key in this field, especially when combined with ligament evaluations, and our research underscores the relevance and applicability of these techniques in real-world scenarios. Importantly, our findings suggest a promising future for the diagnosis of knee conditions. Materials and methods: We initially worked with DICOM-format images, the standard for medical imaging, utilizing the Python packages PyDicom and SimpleITK for preprocessing. We also addressed the NIfTI format commonly used in research. Our preprocessing methods, designed with efficiency in mind, encompassed modality-specific adjustments, orientation, spatial resampling, intensity normalization, standardization and conversion to algorithm input format. These steps ensure efficient data handling, accelerate training speeds, and reassure the audience about the effectiveness of our research. Results: Our study processed PD-sagittal images from 188 patients to create a test set for training a deep learning segmentation model. We successfully completed all preprocessing steps, including accessing DICOM header information using hexadecimal encoded identifiers and utilizing SimpleITK for efficient handling of both 2D and 3D DICOM data. Resampling was performed for all 188 sets. Additionally, manual segmentation was conducted on 188 MRI scans, focusing on regions of interest (ROIs), such as normal tissue and meniscus tears in both the medial and lateral menisci. This involved contrast adjustment and precise hand-tracing of the structures within the ROIs, demonstrating the effectiveness and potential of our research in diagnosing knee conditions, and offering hope for the future of knee MRI diagnosis. Conclusions: Our study introduces innovative preprocessing methods that have the potential to advance the field. By enhancing researchers' understanding of the importance of preprocessing steps, we anticipate that our techniques will streamline the preparation of standardized formats for deep learning model training and significantly benefit radiologists and orthopedic surgeons. These techniques could reduce time and effort in tasks like meniscal tear segmentation or localization, inspiring hope for more efficient and effective achievements in the field. [ABSTRACT FROM AUTHOR]

Objective: To automatically segment four body components at the T4 thoracic veertebra plane on chest CT in the newly diagnosed multiple myeloma (MM) patients by deep learning model, and to discuss the correlation between the four body components and the prognosis of the MM patients. Methods: The retrospective analysis was conducted on the clinical data of the MM patients diagnosed in our hospital from January 2017 to December 2021. The clinical informations such as age, gender, weight, height, and body mass index (BMI) of the patients were collected. The laboratory data of the patients were collected, including serum levels of lactate dehydrogenase (LDH), calcium (Ca), creatinine (Scr), albumin (Alb), hemoglobin (Hb), β2-microglobulin (β2-MG), and serum free light chains. The chest CT images of 79 regularly evaluated MM patients detected by deep learning model were divide into four body components: pectoralis major, pectoralis minor, subcutaneous fat, and mediastinal fat. Image J software was used to detect the areas of the four body components at the T4 thoracic vertebra plane, and their correlation with the prognosis of the MM patients was analyzed by Kaplan-Meier survival analysis. Results: The univariate analysis results showed that the area of subcutaneous fat, serum Ca levels, Scr levels, and International Staging System (ISS) stage were related to the overall survival (OS) of the MM patients (HR=2. 260, 95% CI: 1. 116-4. 578, P=0. 024; HR=2. 088, 95% CI: 1. 007-4. 327, P= 0. 048; HR=2. 209, 95% CI: 1. 105-4. 414, P=0. 025; HR=1. 730, 95% CI: 1. 040-2. 879, P= 0. 035). The multivariate analysis results showed that the area of subcutaneous fat among the four body components was an independent risk factor affecting the prognosis of the MM patients (95% CI: 1. 228- 5. 782, P=0. 013). The Log-Rank test results showed that compared with high subcutaneous fat area group, the OS of the patients in low subcutaneous fat area group was decreased(P=0. 018). There was no significant difference in OS of the patients with different genders between high subcutaneous fat area group and low subcutaneous fat area group (P>0. 05). In the patients without hematopoietic stem cell transplantation, compared with high subcutaneous fat area group, the OS of the patients in low subcutaneous fat area group was decreased (P=0. 037). Conclusion: Among the four body components at the T4 thoracic vertebra plane, the area of subcutaneous fat is related to the OS of the MM patients and it is an independent risk factor for the prognosis of the MM patients, while the areas of mediastinal fat, pectoralis major, and pectoralis minor have no predictive value for the prognosis of the MM patients. [ABSTRACT FROM AUTHOR]

Inferring gene regulatory networks (GRNs) allows us to obtain a deeper understanding of cellular function and disease pathogenesis. Recent advances in single-cell RNA sequencing (scRNA-seq) technology have improved the accuracy of GRN inference. However, many methods for inferring individual GRNs from scRNA-seq data are limited because they overlook intercellular heterogeneity and similarities between different cell subpopulations, which are often present in the data. Here, we propose a deep learning-based framework, DeepGRNCS, for jointly inferring GRNs across cell subpopulations. We follow the commonly accepted hypothesis that the expression of a target gene can be predicted based on the expression of transcription factors (TFs) due to underlying regulatory relationships. We initially processed scRNA-seq data by discretizing data scattering using the equal-width method. Then, we trained deep learning models to predict target gene expression from TFs. By individually removing each TF from the expression matrix, we used pre-trained deep model predictions to infer regulatory relationships between TFs and genes, thereby constructing the GRN. Our method outperforms existing GRN inference methods for various simulated and real scRNA-seq datasets. Finally, we applied DeepGRNCS to non-small cell lung cancer scRNA-seq data to identify key genes in each cell subpopulation and analyzed their biological relevance. In conclusion, DeepGRNCS effectively predicts cell subpopulation-specific GRNs. The source code is available at https://github.com/Nastume777/DeepGRNCS. [ABSTRACT FROM AUTHOR]

Compared to traditional swell height measurement methods, spaceborne global navigation satellite system reflectometry (GNSS-R) has many advantages, including remote sensing capabilities, global coverage, real-time monitoring, etc. It can provide wave observation data with high spatiotemporal resolution and is not limited by time, weather, and other conditions. Spaceborne GNSS-R provides a very effective method for estimating swell height, which can monitor and measure wave changes over a large area of the ocean surface in real time. This is of great significance for understanding the marine environment, climate change, and weather forecasting. However, there is relatively little research on the estimation of swell height using this technology, especially in the retrieval model of swell height. For this purpose, the article proposes a global ocean swell height retrieval method based on the convolutional neural network (CNN), convolutional long short-term memory (ConvLSTM) and fully connected network (FCN) hybrid deep learning model (i.e., CNN-ConvLSTM-FCN) for spaceborne GNSS-R. CNN-ConvLSTM-FCN model not only uses CNN to extract spatial features around specular points (SPs) from a two-dimensional (2-D) matrix of a single image (bistatic radar scattering cross-section (BRCS), effective scattering area, or power delay-Doppler map (DDM), but also uses ConvLSTM network to infer feature relationships and FCN to output estimated swell heights. The hybrid model improves its retrieval ability by simultaneously considering feature information related to time and space. The performance of the CNN-ConvLSTM-FCN model in retrieving swell height was tested using ERA5 and WaveWatch III swell height as reference data. The results show that when ERA5 data is used as a reference, compared to the empirical model method based on DDM average (DDMA) observable, the proposed CNN-ConvLSTM-FCN swell height retrieval model improves root mean square error (RMSE), correlation coefficient (CC), and mean absolute percentage error (MAPE) by 50.76%, 26.28%, and 29.63%, respectively. When WaveWatch III data is used as a reference, improvements in RMSE, CC, and MAPE are 51.09%, 25.35%, and 44.21%, respectively. The CNN-ConvLSTM-FCN model can demonstrate the ability of high-precision and high-resolution ocean swell height retrieval on a global scale, providing a new reference method for spaceborne GNSS-R ocean swell height estimation. [ABSTRACT FROM AUTHOR]

In architectural interior design, color is one of the important design elements. Through the reasonable combination of various color elements, it can effectively improve the interior environment and create an atmosphere that meets the preferences and needs of users. And with the continuous development of social economy, the application of color in interior design is becoming more and more widespread. Using different colors in interior design to harmonize not only can relieve people's visual fatigue, but also can bring people a pleasant mood. Different colors have different meanings, therefore, the use of color in interior design should be more flexible and color matching should be more innovative. The warm and cold, near and far, expansion and contraction of color make the color space the most dynamic key element in design. The grasp of color and scale of architectural space and the flexible use of color will directly affect the quality of architectural space design. Color can strengthen the form of interior space or destroy its form. In order to accurately grasp the connection between architectural space and color in interior design, this paper proposes a deep learning model-based feature extraction method for the connection between architectural space and color in interior design. First, we construct a product color sentiment imagery dataset; then, we build a model for generating architectural interior space layout and color design schemes based on the product color sentiment imagery dataset and conditional deep convolutional generation adversarial network, and innovatively generate product color design schemes. This algorithm can better balance the chromaticity, saturation, and clarity of images. When determining the similarity of indoor space colors, depth features are superior to point-to-point pixel distance and aesthetic features of indoor space colors. Finally, the effectiveness and applicability of the proposed method are verified in relevant experiments. [ABSTRACT FROM AUTHOR]

In this study, a tropical cyclone or typhoon rainfall forecast model based on Random Forest is developed to forecast the daily rainfall at 133 weather stations in China. The input factors to the model training process include rainfall observations during 1960–2018, typhoon information (position and intensity), station information (position and altitude), and properties of the western Pacific subtropical high. Model evaluation shows that besides the distance between a station and cyclone, the subtropical high properties are ranked very high in the model's feature importance, especially the subtropical ridgeline, and intensity. These aspects of the subtropical high influence the location and timing of typhoon landfall. The forecast model has a correlation coefficient of about 0.73, an Index of Agreement of nearly 0.8, and a mean bias of 1.28 mm based on the training dataset. Biases are consistently low, with both positive and negative signs, for target stations in the outer rainband (up to 1000 km, beyond which the model does not forecast) of typhoons. The range of biases is much larger for target stations in the inner-core (0–200 km) region. In this region, the model mostly overestimates (underestimates) the small (large) rain rates. Cases study of Typhoon Doksuri and Talim in 2023, as independent cases, shows the high performance of the model in forecasting the peak rain rates and timing of their occurrence of the two impactful typhoons. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to assess the impact of artificial intelligence (AI)-driven noise reduction algorithms on metal artifacts and image quality parameters in cone-beam computed tomography (CBCT) images of the oral cavity. Materials and Methods: This retrospective study included 70 patients, 61 of whom were analyzed after excluding those with severe motion artifacts. CBCT scans, performed using a Hyperion X9 PRO 13 × 10 CBCT machine, included images with dental implants, amalgam fillings, orthodontic appliances, root canal fillings, and crowns. Images were processed with the ClariCT.AI deep learning model (DLM) for noise reduction. Objective image quality was assessed using metrics such as the differentiation between voxel values (ΔVVs), the artifact index (AIx), and the contrast-to-noise ratio (CNR). Subjective assessments were performed by two experienced readers, who rated overall image quality and artifact intensity on predefined scales. Results: Compared with native images, DLM reconstructions significantly reduced the AIx and increased the CNR (p < 0.001), indicating improved image clarity and artifact reduction. Subjective assessments also favored DLM images, with higher ratings for overall image quality and lower artifact intensity (p < 0.001). However, the ΔVV values were similar between the native and DLM images, indicating that while the DLM reduced noise, it maintained the overall density distribution. Orthodontic appliances produced the most pronounced artifacts, while implants generated the least. Conclusions: AI-based noise reduction using ClariCT.AI significantly enhances CBCT image quality by reducing noise and metal artifacts, thereby improving diagnostic accuracy and treatment planning. Further research with larger, multicenter cohorts is recommended to validate these findings. [ABSTRACT FROM AUTHOR]

In the context of addressing new image classification tasks with insufficient training samples via pre-trained deep learning models, the methods based on the Bag-of-Deep-Visual-Words (BoDVW) model have achieved higher classification accuracy across various image classification tasks compared to directly using the new classification layer of the pre-trained model for classification. These methods perform a sequence of operations on the input image - deep feature extraction, feature encoding, and feature pooling - to obtain an image representation vector, which is then fed into classifiers for classification. However, they ignore two crucial aspects: the high-level semantic characteristics of deep features and their local context within the feature space, which limits the image classification performance. To address this issue, we propose a new image classification method with a unique workflow. Specifically, our method identifies low-entropy local regions in the feature space by constructing multiple decision trees, using the set of labelled deep features built from training images. For a given image, the voting vector of each deep feature from the image is calculated based on the category label distributions of the low-entropy local regions where it is located. This vector reflects the degree of support that the feature provides for the hypothesis that it belongs to each category. The voting vectors of all features are aggregated according to image regions of different sizes and positions to obtain the representation vector of the image. The representation vectors of testing images are input into Support Vector Machines (SVMs) trained using those of training images to predict their categories. Experimental results on six public datasets show that our method achieves higher classification accuracy by 0.07% to 3.6% (averaging at 0.8%) compared to two BoDVW methods, and by 0.1% to 10.69% (averaging at 2.69%) compared to directly using the new classification layer of the pre-trained model for classification. These results demonstrate the effectiveness of considering the high-level semantic characteristics of deep features and their local context within the feature space for image classification. Importantly, the unique workflow of our method opens up new potential avenues for improving classification performance. These include increasing the number of local regions where deep features primarily originate from one or a few image categories, improving the accuracy of low-entropy local region identification, and developing an end-to-end deep learning model based on this workflow. While maintaining classification accuracy comparable to recent works, our method offers notable potential for the advancement of the image classification field. [ABSTRACT FROM AUTHOR]

Objectives: This study delves into the cutting-edge field of deep learning techniques, particularly deep convolutional neural networks (DCNNs), which have demonstrated unprecedented potential in assisting radiologists and orthopedic surgeons in precisely identifying meniscal tears. This research aims to evaluate the effectiveness of deep learning models in recognizing, localizing, describing, and categorizing meniscal tears in magnetic resonance images (MRIs). Materials and methods: This systematic review was rigorously conducted, strictly following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Extensive searches were conducted on MEDLINE (PubMed), Web of Science, Cochrane Library, and Google Scholar. All identified articles underwent a comprehensive risk of bias analysis. Predictive performance values were either extracted or calculated for quantitative analysis, including sensitivity and specificity. The meta-analysis was performed for all prediction models that identified the presence and location of meniscus tears. Results: This study's findings underscore that a range of deep learning models exhibit robust performance in detecting and classifying meniscal tears, in one case surpassing the expertise of musculoskeletal radiologists. Most studies in this review concentrated on identifying tears in the medial or lateral meniscus and even precisely locating tears—whether in the anterior or posterior horn—with exceptional accuracy, as demonstrated by AUC values ranging from 0.83 to 0.94. Conclusions: Based on these findings, deep learning models have showcased significant potential in analyzing knee MR images by learning intricate details within images. They offer precise outcomes across diverse tasks, including segmenting specific anatomical structures and identifying pathological regions. Contributions: This study focused exclusively on DL models for identifying and localizing meniscus tears. It presents a meta-analysis that includes eight studies for detecting the presence of a torn meniscus and a meta-analysis of three studies with low heterogeneity that localize and classify the menisci. Another novelty is the analysis of arthroscopic surgery as ground truth. The quality of the studies was assessed against the CLAIM checklist, and the risk of bias was determined using the QUADAS-2 tool. [ABSTRACT FROM AUTHOR]

Lyme disease, caused by a bacterium transmitted through the bite of an infected tick, is often misdiagnosed due to its similarity to other conditions like drug rash. This research introduces an innovative approach by integrating prominent deep learning models, including UNet, Inception Model, and XGBoost, into the Deep Neuro-Fuzzy System. Utilizing a comprehensive Kaggle dataset, authors study aims to achieve heightened accuracy in recognizing and segmenting Lyme disease from medical images. Implemented in Python, authors advanced image processing methods demonstrate exceptional performance, reaching an outstanding accuracy of 97.36% after the recognition stage. To further enhance accuracy, authors introduce an additional layer of sophistication through the incorporation of the mayfly optimization (MO) approach. This strategic integration of MO contributes to the outstanding accuracy achieved by their models. This research not only addresses the challenges of Lyme disease misdiagnosis but also presents a robust framework for medical image recognition. Leveraging the collaborative and open nature of Kaggle and the versatility of the Python programming ecosystem, authors work contributes to advancing the field of Lyme disease detection and medical image processing. [ABSTRACT FROM AUTHOR]

The diseases that affect the plants cannot be easily avoided due to rapid and substantial changes in the environment and climate. Generally, paddy crops are affected by several conditions including pests and nutritional deficiencies. Hence, it is important to detect these disease-affected paddy crops at an early stage for better productivity. To detect and classify the problems in this specific domain, deep learning approaches are utilized. In this paper, a novel attention convolutional stacked recurrent based binary Kepler search (ACSR-BKS) algorithm is used to detect diseases, nutritional deficiencies, and pest patterns at an early stage via diverse significant pipelines namely the data augmentation, data pre-processing, and classification phase thereby providing pest patterns and identifying nutritional deficiencies. Subsequent to data collection processes, the images are augmented via zooming, rotating, flipping horizontally, shifting of height, width, and rescaling. To acquire the accurate and best results in terms of classification, the parameters need to be tuned and adjusted using the binary Kepler search algorithm. The results revealed that the accuracy of the proposed ACSR-BKS algorithm is 98.2% in terms of detecting the diseases. Then, the obtained results are compared with the other existing approaches. Additionally, it is revealed that the yield of paddy can also be improved by utilizing the proposed disease-detecting methods. [ABSTRACT FROM AUTHOR]

Over the past three decades, a lot of research has been conducted on remote sensing-based techniques for estimating aboveground biomass (AGB) in forest ecosystems. Due to the complexity of satellite images, the conventional image classification methods have been unable to meet the actual application needs. In our proposed work, the estimation of aboveground biomass has been performed on the basis of a Region of Interest (RoI). Initially, this method is employed to measure the green portions of the areas at the local level. The biomass of the subtropical woods in the areas of India, Indonesia, and Thailand is estimated in this work, using data from Deep Globe LIDAR images. Initially, the satellite images are pre-processed. The ROI method is used to select the green portion of the area. The green portion in the satellite images is segmented using the K-means algorithm and binary classification. An empirical formula is used to calculate the carbon weight. The results obtained show 92% accuracy. [ABSTRACT FROM AUTHOR]

The diagnosis of Diabetic Retinopathy (DR) demands a paradigm shift towards more accurate and efficient solutions to overcome vision impairment. Therefore, the current study introduces a new Modified Regularisation Long Short-term Memory (MR-LSTM) framework approach for DR diagnosis. The proposed framework leverages the power of deep learning and provides a dynamic and robust solution for the early detection of DR, which in turn preserves a patient’s vision. The proposed framework uses a DR Debrecen Dataset from the UCI database with 21 distinct features relevant to retinal health, and employs a series of data preprocessing steps, including data cleaning, normalisation, and transformation, to ensure data quality and compatibility. The MR-LSTM framework excels at capturing temporal dependencies in sequential retinal images, offering a unique advantage in understanding the progression of DR. The MR-LSTM framework is implemented using Python libraries, and the results are compared with those of other popular models. It is observed that the MR-LSTM framework outperforms other models and achieves an accuracy of 97.12 percent and an F1 Score of 98.49. Furthermore, the Receiver Operating Characteristic (ROC) curve reveals an area under the curve of 0.97, highlighting the exceptional ability to discriminate between positive and negative cases of the proposed framework. By revolutionising DR diagnosis with the proposed MR-LSTM framework, it can achieve accurate, timely, and accessible solutions in the fight against vision-threatening conditions.

BackgroundAging is marked by the gradual deterioration of cells, tissues, and organs and is a major risk factor for many chronic diseases. Considering the complex mechanisms of aging, traditional Chinese medicine (TCM) could offer distinct advantages. However, due to the complexity and variability of metabolites in TCM, the comprehensive screening of metabolites associated with pharmacology remains a significant issue.MethodsA reliable and integrated identification method based on UPLC-Q Exactive-Orbitrap HRMS was established to identify the chemical profiles of Huan Shao Dan (HSD). Then, based on the theory of sequential metabolism, the metabolic sites of HSD in vivo were further investigated. Finally, a deep learning model and a bioactivity assessment assay were applied to screen potential anti-aging metabolites.ResultsThis study identified 366 metabolites in HSD. Based on the results of sequential metabolism, 135 metabolites were then absorbed into plasma. A total of 178 peaks were identified from the sample after incubation with artificial gastric juice. In addition, 102 and 91 peaks were identified from the fecal and urine samples, respectively. Finally, based on the results of the deep learning model and bioactivity assay, ginsenoside Rg1, Rg2, and Rc, pseudoginsenoside F11, and jionoside B1 were selected as potential anti-aging metabolites.ConclusionThis study provides a valuable reference for future research on the material basis of HSD by describing the chemical profiles both in vivo and in vitro. Moreover, the proposed screening approach may serve as a rapid tool for identifying potential anti-aging metabolites in TCM.