Explore the vast range of titles available.

Pedestrian detection based on deep learning methods have reached great success in the past few years with several possible real-world applications including autonomous driving, robotic navigation, and video surveillance. In this work, a new neural network two-stage pedestrian detector with a new custom classification head, adding the triplet loss function to the standard bounding box regression and classification losses, is presented. This aims to improve the domain generalization capabilities of existing pedestrian detectors, by explicitly maximizing inter-class distance and minimizing intra-class distance. Triplet loss is applied to the features generated by the region proposal network, aimed at clustering together pedestrian samples in the features space. We used Faster R-CNN and Cascade R-CNN with the HRNet backbone pre-trained on ImageNet, changing the standard classification head for Faster R-CNN, and changing one of the three heads for Cascade R-CNN. The best results were obtained using a progressive training pipeline, starting from a dataset that is further away from the target domain, and progressively fine-tuning on datasets closer to the target domain. We obtained state-of-the-art results, MR−2 of 9.9, 11.0, and 36.2 for the reasonable, small, and heavy subsets on the CityPersons benchmark with outstanding performance on the heavy subset, the most difficult one.

Steatotic liver disease (SLD), formerly named fatty liver disease, has a prevalence estimated at 30–38% in adults. Detection of SLD is important, since prompt initiation of treatment can stop disease progression, lead to a reduction in adverse outcomes, and reduce the economic burden associated with the disease. We report the development of a novel Deep Learning (DL) method for the prediction of SLD, which consists of transforming the input variables from tabular data into images, with the goal of using the pattern recognition power of DL models to reach the best prediction performance. The dataset used in this study includes registries from 2,999 patients. The data of each patient, originally represented as a vector, is converted into an image replicating each variable in rows and columns. Our DL models reach better results compared to those of traditional ML models at various levels of sensitivity and specificity. A sensitivity of 0.9497, a specificity of 0.6417, and an AUCROC of 0.8662 were reached with one DL model. We also achieved significantly better results relative to those obtained with the Hepatic Steatosis Index (HSI). Our DL models reach higher AUCROC values compared to those of the traditional ML models, and also with respect to those obtained with HSI.

The diagnosis of major depressive disorder (MDD) and bipolar disorder (BD) relies on symptom-based evaluations. Both MDD as well as BD present episodes of depressed mood, often leading to misdiagnosis and treatment delays. Our study presents a novel deep learning–based diagnostic approach that employs microglial cells as biosensors to identify disease-specific image features induced by patient-derived plasma small extracellular vesicles (sEVs), enabling differentiation among MDD, BD, and control (CTRL) groups. Microglial morphological changes in response to plasma sEVs were captured using fluorescence microscopy. Individual cell images were grouped into structured M×M arrays and processed through a DenseNet121 convolutional neural network (CNN). To enhance classification robustness, P image arrays per subject were generated using random cell image permutations and affine transformations. Final diagnoses were assigned through weighted voting across all arrays. Model performance was assessed using repeated subject-disjoint random splits. The CNN-based image analysis framework accurately distinguished between MDD, BD, and CTRL subjects. The best model configuration correctly classified 44 out of 45 individuals across the five cross-validations. By combining deep learning and microglial cell-based biosensing, our results support the proof-of-concept for building a novel diagnostic platform for the differential diagnosis between MDD and BD.

Background Early prediction of Gestational Diabetes Mellitus (GDM) risk is of particular importance as it may enable more efficacious interventions and reduce cumulative injury to mother and fetus. The aim of this study is to develop machine learning (ML) models, for the early prediction of GDM using widely available variables, facilitating early intervention, and making possible to apply the prediction models in places where there is no access to more complex examinations. Methods The dataset used in this study includes registries from 1,611 pregnancies. Twelve different ML models and their hyperparameters were optimized to achieve early and high prediction performance of GDM. A data augmentation method was used in training to improve prediction results. Three methods were used to select the most relevant variables for GDM prediction. After training, the models ranked with the highest Area under the Receiver Operating Characteristic Curve (AUCROC), were assessed on the validation set. Models with the best results were assessed in the test set as a measure of generalization performance. Results Our method allows identifying many possible models for various levels of sensitivity and specificity. Four models achieved a high sensitivity of 0.82, a specificity in the range 0.72–0.74, accuracy between 0.73–0.75, and AUCROC of 0.81. These models required between 7 and 12 input variables. Another possible choice could be a model with sensitivity of 0.89 that requires just 5 variables reaching an accuracy of 0.65, a specificity of 0.62, and AUCROC of 0.82. Conclusions The principal findings of our study are: Early prediction of GDM within early stages of pregnancy using regular examinations/exams; the development and optimization of twelve different ML models and their hyperparameters to achieve the highest prediction performance; a novel data augmentation method is proposed to allow reaching excellent GDM prediction results with various models.

Stochastic Resonance (SR) is a phenomenon, mainly present in nonlinear detection systems, in which the addition of certain amount of noise, called optimal noise, has proven to enhance detection performance of subthreshold stimuli. When added noise is present only during the stimulus, an additional enhancement can be reached. This phenomenon was called time Coincidence Enhanced Stochastic Resonance (CESR). The aim of this study was to study the effect of spatially distributed vibrotactile noise in subthreshold stimuli detection. The correct response rates from two different stimuli conditions were compared, using four tactile stimulator systems to excite four different spatial locations on the fingertip. Under two different conditions, the stimuli were present in only one randomly chosen stimulator. For the first condition, all stimulators contain optimal noise level. In the second condition, the optimal noise was present only at the stimulator with the stimulus. SR threshold principle should not produce different correct response rates between the two conditions, since in both cases the noise enables the subthreshold stimulus to go above threshold. The stimulus signal used was a rectangular displacement controlled pulse that lasted 300ms within a 1.5s attention interval, applied to the exploratory zone of the index finger of 13 human subjects. For all subjects it was found that detection rates were better (p<0.0003) when noise was spatially coincident with the stimulus, compared to the condition in which noise was present simultaneously in all the stimulators. According to our literature review this is the first report of SR being influenced by the spatial location of the noise. These results were not found previously reported, so represent the discovery of a new phenomenon. We call this phenomenon Spatial-Coincidence-Enhanced Stochastic Resonance (SCESR). As results show, the optimal noise level is dependent on the relative position between stimulus and noise.

Many applications in image analysis require the accurate classification of complex patterns including both color and texture, e.g., in content image retrieval, biometrics, and the inspection of fabrics, wood, steel, ceramics, and fruits, among others. A new method for pattern classification using both color and texture information is proposed in this paper. The proposed method includes the following steps: division of each image into global and local samples, texture and color feature extraction from samples using a Haralick statistics and binary quaternion-moment-preserving method, a classification stage using support vector machine, and a final stage of post-processing employing a bagging ensemble. One of the main contributions of this method is the image partition, allowing image representation into global and local features. This partition captures most of the information present in the image for colored texture classification allowing improved results. The proposed method was tested on four databases extensively used in color–texture classification: the Brodatz, VisTex, Outex, and KTH-TIPS2b databases, yielding correct classification rates of 97.63%, 97.13%, 90.78%, and 92.90%, respectively. The use of the post-processing stage improved those results to 99.88%, 100%, 98.97%, and 95.75%, respectively. We compared our results to the best previously published results on the same databases finding significant improvements in all cases.

Background The tactile sense is being used in a variety of applications involving tactile human-machine interfaces. In a significant number of publications the classical threshold concept plays a central role in modelling and explaining psychophysical experimental results such as in stochastic resonance (SR) phenomena. In SR, noise enhances detection of sub-threshold stimuli and the phenomenon is explained stating that the required amplitude to exceed the sensory threshold barrier can be reached by adding noise to a sub-threshold stimulus. We designed an experiment to test the validity of the classical vibrotactile threshold. Using a second choice experiment, we show that individuals can order sensorial events below the level known as the classical threshold. If the observer's sensorial system is not activated by stimuli below the threshold, then a second choice could not be above the chance level. Nevertheless, our experimental results are above that chance level contradicting the definition of the classical tactile threshold. Results We performed a three alternative forced choice detection experiment on 6 subjects asking them first and second choices. In each trial, only one of the intervals contained a stimulus and the others contained only noise. According to the classical threshold assumptions, a correct second choice response corresponds to a guess attempt with a statistical frequency of 50%. Results show an average of 67.35% (STD = 1.41%) for the second choice response that is not explained by the classical threshold definition. Additionally, for low stimulus amplitudes, second choice correct detection is above chance level for any detectability level. Conclusions Using a second choice experiment, we show that individuals can order sensorial events below the level known as a classical threshold. If the observer's sensorial system is not activated by stimuli below the threshold, then a second choice could not be above the chance level. Nevertheless, our experimental results are above that chance level. Therefore, if detection exists below the classical threshold level, then the model to explain the SR phenomenon or any other tactile perception phenomena based on the psychophysical classical threshold is not valid. We conclude that a more suitable model of the tactile sensory system is needed.

This study aimed to evaluate the effect of two platelet preparations used in the clinic, pure platelet-rich plasma (P-PRP) and the supernatant of calcium-activated P-PRP (S-PRP), on the phenotype of human macrophages. Surface markers and cytokine production of human monocyte-derived macrophages were analyzed after 24 h stimulation with P-PRP or S-PRP. P-PRP and S-PRP present no difference in the expression of CD206, a M2 tissue-repair macrophage-related marker. However, these same macrophages presented different levels of CD163, CD86 as well as different IL-10 secretion capacities after 24 h incubation. These platelet preparations do not have an equivalent biological effect over macrophages, which suggest that they may present different clinical regenerative potentials.

Prediction of Large for Gestational Age (LGA) risk is important as it can enable earlier, more effective interventions, and avoid or mitigate cumulative injury to both mother and baby at the time of delivery. The goal of this research is to improve the prediction of LGA using machine learning (ML) models and variables that are widely available as that allow for broad intervention in late pregnancy and during delivery. An improved prediction of LGA was achieved using twelve ML models with hyperparameter optimization. Also, to improve the LGA prediction a data augmentation method was employed in the training set. Additionally, improvement in LGA prediction was obtained with four variable selection methods employed to identify the most significant variables. To rank the best models on the validation set after training, the Area under the Receiver Operating Characteristic Curve (AUROC) was used. Finally, to assess the generalization performance, the best models were evaluated on the test set. Our method enabled us to identify several models with high sensitivity and specificity. The best models included those that achieved a sensitivity of 0.84, a specificity of 0.84, an accuracy of 0.84, and AUCROC 0.83, requiring 14 variables. Another model reached an accuracy of 0.87, a sensitivity of 0.71, and a specificity of 0.90 with an AUCROC of 0.83 (14 variables). Additionally, a model with a sensitivity of 0.58, the same as that described by Hadlock et al. [1] for ultrasound, required 10 variables, and reached an accuracy of 0.91, a specificity of 0.97, and an AUCROC of 0.86. Both models included maternal BMI (body mass index), First Control, Maternal Weight, BMI Last Control, and EFW (estimated fetal weight) as the most important variables. The main contributions of our study include the prediction of LGA using data obtained from standard clinical evaluations during prenatal care, as well as the development ML models, tuning the hyperparameters to improve prediction results, thus achieving high levels of sensitivity and specificity. To achieve optimal LGA prediction outcomes across different models, a data augmentation approach is introduced, an important improvement in LGA prediction over using only Hadlock's ultrasound formula.

A crucial step in developing automated visual inspection systems for wood boards is image segmentation, which aims to achieve a high defect detection rate with a low false positive rate (clear wood areas identified as defect areas). In this study, a neurofuzzy color image segmentation method for wood surface defect detection is proposed. The method is called fuzzy min-max neural network for image segmentation (FMMIS). The FMMIS method grows boxes from a set of pixels called seeds, to find the minimum bounded rectangle (MBR) for each defect present in the wood board image. An automatic method to select seeds from defective regions as starting points to FMMIS is also presented. The FMMIS method was applied to a set of 900 images of radiata pine boards, which included samples from the following 10 categories of defects: birdseye and freckle, bark and pitch pockets, wane, splits, blue stain, stain, pith, dead knots, live knots, and holes. The FMMIS achieved a defect detection rate of 95 percent on the test set, with only 6 percent of false positives. To measure the quality of segmentation, the area recognition rate (ARR) criterion was computed using as a reference the manually placed MBR for each defect. The ARR achieved 94.4 percent on the test set. Also a relative index was used to compare the quality of segmentation between FMMIS and the segmentation module of a previously developed system, based on histogram thresholding. The results show that FMMIS allows us to obtain significant improvements compared with previous work.