Search

Obstacle avoidance is essential for the effective operation of autonomous mobile robots, enabling them to detect and navigate around obstacles in their environment. While deep learning provides significant benefits for autonomous navigation, it typically requires large, accurately labeled datasets, making the data's preparation and processing time-consuming and labor-intensive. To address this challenge, this study introduces a transfer learning (TL)-based automatic labeling segmentation (ALS) framework. This framework utilizes a pretrained attention-based network, DifferNet, to efficiently perform semantic segmentation tasks on new, unlabeled datasets. DifferNet leverages prior knowledge from the Cityscapes dataset to identify high-entropy areas as road obstacles by analyzing differences between the input and resynthesized images. The resulting road anomaly map was refined using depth information to produce a robust drivable area and map of road anomalies. Several off-the-shelf RGB-D semantic segmentation neural networks were trained using pseudo-labels generated by the ALS framework, with validation conducted on the GMRPD dataset. Experimental results demonstrated that the proposed ALS framework achieved mean precision, mean recall, and mean intersection over union (IoU) rates of 80.31%, 84.42%, and 71.99%, respectively. The ALS framework, through the use of transfer learning and the DifferNet network, offers an efficient solution for semantic segmentation of new, unlabeled datasets, underscoring its potential for improving obstacle avoidance in autonomous mobile robots. [ABSTRACT FROM AUTHOR]

The behavior of multilevel atomic ensembles (e.g., alkali-metal atoms) can be influenced significantly by the intensity of a driving field (or controlling/coupling field). The phase coherence between two transition pathways driven by a probe light and a driving field can lead to the effect known as electromagnetically induced transparency (EIT). In EIT, the probe light can pass through a three-level alkali-metal atomic vapor without absorption or reflection when two coherent resonances (transition pathways driven by the driving and probe fields) are present and the linewidths of the transparency windows are sufficiently narrow. The optical characteristics of atomic systems can also be affected by the Doppler broadening of the absorption profile in a spectroscope. Our analysis indicates that both broadenings (related to the transitions excited by the driving and probe fields) can be expanded, leading to an increase in the transmittance and reflectance broadenings when a coupling field with adaptive strength is applied; the corresponding temperature would, thus, be implemented and readable. We show that the most suitable preparation for temperature sensing via an EIT vapor is to provide 80 times the spontaneous decay rate (SDR) of the excited atomic levels. This configuration results in reflectance and transmittance values that range between zero and one and cover a temperature range of 0 K to 600 K. As an example, we demonstrate the integration of specialized coating technologies with EIT ensembles for temperature sensing in the range of dozens of kelvins at and above room temperature. A key advantage of this temperature-sensing system is its ability to use adaptive resonant visible light as the probe field. This novel approach may find applications in providing unprecedented levels of precision and control in temperature sensing for coating processes and in the design of other photonic or optical devices. It can also be used to determine the temperature-dependent behavior of the specific heat of alkali-metal solids and gases (including the latent heats of vaporization or sublimation of alkali-metal solids) through the reflection and transmission spectra of the vaporized EIT atomic vapors. [ABSTRACT FROM AUTHOR]

Inconsistent lighting phenomena in digital images, such as underexposure and overexposure, pose challenges in computer vision. Many studies have developed to address these issues. However, most of these techniques cannot remedy both exposure problems simultaneously. Meanwhile, existing methods that claim to be capable of handling these cases have not yielded optimal results, especially for images with blur and noise distortions. Therefore, this study proposes a system to improve underexposed and overexposed photos, consisting of two different residual attention convolution networks with the CIELab color space as the input. The first model working on the L-channel (luminance) is responsible for recovering degraded image illumination by using residual memory block networks with self-attention layers. The next model based on dense residual attention networks aims to restore degraded image colors using ab-channels (chromatic). A properly exposed image is produced by fusing the output of these models and converting them to RGB color space. Experiments on degraded synthetic images from two public datasets and one real-life exposure dataset demonstrate that the proposed system outperforms the state-of-the-art algorithms in optimal illumination and color correction outcomes for underexposed and overexposed images. [ABSTRACT FROM AUTHOR]

The uncertainty due to road fluctuations and vision system dynamics represents a big challenge to adjusting the steering angle of autonomous vehicles (AVs). Furthermore, AVs require fast action to follow the target lane to overcome lateral deviation with minor errors. In this regard, this paper introduces a fast model predictive controller formulated based on the discrete-time Laguerre function (DTLF) to overcome the high computational burden of the traditional MPC. To improve the hybrid DTLF-MPC performance, a modern and effective dandelion optimizer (DO) strategy is used in this work, which resulted in obtaining the optimal DTLF-MPC parameters and achieving satisfactory results. Furthermore, the proposed hybrid DTLF-MPC is designed based on different algorithms in the literature to evaluate the performance of the DO. Several scenarios are discussed in this paper to confirm the effectiveness and efficiency of the proposed control strategy system against the vision system uncertainty and road fluctuations. The results emphasize that the proposed DTLF-MPC based on the DO can achieve the best damping performance for the lateral deviations with less overshoot; around 0.4533, and a settling time of around 0.01979 s compared with other algorithms. [ABSTRACT FROM AUTHOR]

Thyroid nodules are widespread in the United States and the rest of the world, with a prevalence ranging from 19 to 68%. The problem with nodules is whether they are malignant or benign. Ultrasonography is currently recommended as the initial modality for evaluating thyroid nodules. However, obtaining a good diagnosis from ultrasound imaging depends entirely on the radiologists levels of experience and other circumstances. There is a tremendous demand for automated and more reliable methods to screen ultrasound images more efficiently. This research proposes an efficient and quick detection deep learning approach for thyroid nodules. An open and publicly available dataset, Thyroid Digital Image Database (TDID), is used to determine the robustness of the suggested method. Each image is formatted into a pyramid tile-based data structure, which the proposed VGG-16 model evaluates to provide segmentation results for nodular detection. The proposed method adopts a top-down approach to hierarchically integrate high- and low-level features to distinguish nodules of varied sizes by employing fuse features effectively. The results demonstrated that the proposed method outperformed the U-Net model, achieving an accuracy of 99%, and was two times faster than the competitive model. [ABSTRACT FROM AUTHOR]

Urinary incontinence (UI) is a common problem affecting older adult women globally, but studies regarding combined treatments for all types of UI are still lacking. Here we evaluate the efficacy of a comprehensive rehabilitation program for women with UI. A comprehensive rehabilitation program was introduced that combines pelvic floor muscle (PFM) exercises, functional electrical stimulation, and timely biofeedback during the training process. Data of patients with stress (SUI), urgency (UUI), or mixed (MUI) urinary incontinence who participated in this program between 2016 and 2019 were reviewed retrospectively. Seventy-three subjects (mean age 59.2 ± 12.7 years) were enrolled. After 12 weeks of rehabilitation, vaginal pressure and control accuracy increased in all groups. PFM maximum recruitment increased significantly at week 12 in SUI and UUI, but not in MUI. At week 6, only the SUI group had achieved significant improvements in vaginal pressure, PFM maximum recruitment and control accuracy. The Short-form Urogenital Distress Inventory (UDI-6) and Incontinence Impact Questionnaire-7 (IIQ-7) scores declined dramatically after the program started, and significant improvements were maintained to week 48. The comprehensive rehabilitation program is effective and decreases urinary leakage episodes and improves quality of life in women with UI, especially SUI. [ABSTRACT FROM AUTHOR]

Over the past few years, the study of environmental sound classification (ESC) has become very popular due to the intricate nature of environmental sounds. This paper reports our study on employing various acoustic features aggregation and data enhancement approaches for the effective classification of environmental sounds. The proposed data augmentation techniques are mixtures of the reinforcement, aggregation, and combination of distinct acoustics features. These features are known as spectrogram image features (SIFs) and retrieved by different audio feature extraction techniques. All audio features used in this manuscript are categorized into two groups: one with general features and the other with Mel filter bank-based acoustic features. Two novel and innovative features based on the logarithmic scale of the Mel spectrogram (Mel), Log (Log-Mel) and Log (Log (Log-Mel)) denoted as L2M and L3M are introduced in this paper. In our study, three prevailing ESC benchmark datasets, ESC-10, ESC-50, and Urbansound8k (Us8k) are used. Most of the audio clips in these datasets are not fully acquired with sound and include silence parts. Therefore, silence trimming is implemented as one of the pre-processing techniques. The training is conducted by using the transfer learning model DenseNet-161, which is further fine-tuned with individual optimal learning rates based on the discriminative learning technique. The proposed methodologies attain state-of-the-art outcomes for all used ESC datasets, i.e., 99.22% for ESC-10, 98.52% for ESC-50, and 97.98% for Us8k. This work also considers real-time audio data to evaluate the performance and efficiency of the proposed techniques. The implemented approaches also have competitive results on real-time audio data. [ABSTRACT FROM AUTHOR]

Signet-ring cell carcinoma (SRC) in advanced gastric cancer (GC) is often associated with more invasiveness and a worse prognosis than other cell types. The genetic alterations associated with gastric carcinogenesis in SRC are still unclear. In this study, 441 GC patients receiving curative surgery for GC between 2005 and 2013 were enrolled. The clinicopathological characteristics and genetic alterations of GC patients with and without SRC were compared. Among the 441 GC patients, 181 had SRC. For early GC, patients with SRC had more tumors located in the middle and lower stomach, more infiltrating tumors and better overall survival (OS) rates than those without SRC. For advanced GC, patients with SRC had more scirrhous type tumors, more PIK3CA amplifications, fewer microsatellite instability-high (MSI-H) tumors, more peritoneal recurrences and worse 5-year OS rates than those without SRC. For advanced GC with SRC, patients with peritoneal recurrence tended to have PD-L1 expression. For advanced GC without SRC, patients with liver metastasis tended to have PD-L1 expression, PI3K/AKT pathway mutations, TP53 mutations and MSI-H tumors. For advanced GC, PD-L1 expression was associated with peritoneal recurrence in SRC tumors, while non-SRC tumors with liver metastasis were likely to have PI3K/AKT pathway mutations, TP53 mutations and PD-L1 expression; immunotherapy and targeted therapy may be beneficial for these patients. [ABSTRACT FROM AUTHOR]

Background: Epstein–Barr virus (EBV)-associated gastric cancer (GC) is one of four major gastric cancer types and is traditionally considered to be related to lymphoepithelioma-like GC. Few studies have investigated the clinical significance of EBV infection in intestinal/solid type, diffuse (poorly cohesive) type, and lymphoepithelioma-like GC. Methods: A total of 460 GC patients receiving curative surgery were enrolled. The clinicopathological features, genetic alterations and prognoses were compared between patients with and without EBV infection. Results: EBV-positive GC patients (n = 43) had more tumors located in the upper and middle stomach, more common in lymphoepithelioma-like carcinoma, more lymphoid stroma, fewer Helicobacter pylori infections, and higher programmed death-ligand 1 (PD-L1) expression than EBV-negative GC patients. For intestinal/solid type GC, EBV-positive tumors were more likely to be located in the upper and middle stomach, have more lymphoid stroma, fewer Helicobacter pylori infections, higher PD-L1 expression, and more liver metastases than EBV-negative tumors. For diffuse (poorly cohesive) type GC, EBV-positive tumors were more likely to be located in the upper stomach, and have more lymphoid stroma than EBV-negative tumors. For lymphoepithelioma-like GC, EBV-positive tumors had more PI3K/AKT pathway mutations than EBV-negative tumors. Conclusions: Intestinal/solid type GC patients with EBV-positive tumors were associated with higher PD-L1 expression and more liver metastases, while lymphoepithelioma-like GC patients with EBV-positive tumors had more PI3K/AKT pathway mutations. Immunotherapy and targeted therapy may be beneficial for these groups of patients. Routine EBV survey is recommended in GC. [ABSTRACT FROM AUTHOR]

This paper presents a novel architecture of the vision/position hybrid control for a Hexa parallel robot. The 3D vision system is combined with the Proportional-Integral-Derivative (PID) position controller to form a two-level closed-loop controller of the robot. The 3D vision system measures the pose of the end-effector after the PID control. The measurement of the 3D vision system is used as a feedback of the second closed-loop control. The 3D vision system has a simple structure using two fixed symmetric cameras at the top of the robot and four planar colored markers on the surface of the end-effector. The 3D vision system detects and reconstructs the 3D coordinates of colored markers. Based on the distance and coplanarity constraints of the colored markers, the optimization problem is modeled for the real-time adjustment, which is implemented during the operation of the robot to minimize the measurement error of the 3D vision system due to both the initial calibration of the stereo camera and the external noise affecting image processing. The bacterial foraging optimization is appropriately configured to solve the optimization problem. The experiment is performed on a specific Hexa parallel robot to assess the effectiveness and feasibility of the proposed real-time adjustment using the bacterial foraging optimization. The experimental result shows that it has high accuracy and fast computation time although the experiment is conducted on a laptop with an average hardware configuration. An experimental comparison of the performance between the proposed method and another control method is also implemented. The results show the superiority and application potential of the proposed method. [ABSTRACT FROM AUTHOR]

Background: There has been no report regarding the clinicopathological features and genetic mutations regarding elevated microsatellite alterations at selected tetranucleotide repeats (EMAST) in gastric cancer (GC). Methods: The correlation among EMAST status, microsatellite instability (MSI) status, mutations of common GC-related genes and 16 DNA repair-associated genes, and the clinicopathological features were analyzed. Results: Among the 360 GC patients enrolled, there were 76 (21.1%) with EMAST+ tumors and 284 with EMAST− tumors, and 59 (16.4%) were MSI-high (MSI-H) tumors, and 301 were microsatellite stable (MSS) tumors. Patients with EMAST+ tumors exhibited an earlier pathological T category and had more genetic mutations in the PI3K/AKT pathway, ARID1A and DNA repair-associated genes than those with EMAST− tumors. Patients with MSI-H tumors have more genetic mutations in the PI3K/AKT pathway and DNA repair-associated genes than those with MSS tumors. In the subgroup analysis for MSI-H GC, EMAST+ tumors were associated with earlier pathological T and N categories, earlier TNM stages, higher frequency of DNA-repair-associated genetic mutations, and a better survival rate than EMAST− tumors. Conclusions:PI3K/AKT pathway mutations may play an important role in EMAST+ and/or MSI-H GC. EMAST+/MSI-H tumors seem to represent a different subtype of gastric cancer from EMAST−/MSI-H tumors. [ABSTRACT FROM AUTHOR]

Pollen is the male gametophyte of higher plants. Its major function is to deliver sperm cells to the ovule to ensure successful fertilization. During this process, many interactions occur among pollen tubes and pistil cells and tissues, and calcium ion (Ca2+) dynamics mediate these interactions among cells to ensure that pollen reaches the embryo sac. Although the precise functions of Ca2+ dynamics in the cells are unknown, we can speculate about its roles on the basis of its spatial and temporal characteristics during these interactions. The results of many studies indicate that calcium is a critical element that is strongly related to pollen germination and pollen tube growth. [ABSTRACT FROM AUTHOR]

Long-term morbidities can develop after traumatic brain injury (TBI). Some studies have suggested that the risk of stroke is higher after TBI, but the association between concussion and stroke remains unclear. Using a national cohort, the authors analyzed the incidence of both hemorrhagic and ischemic strokes in patients with previous concussion. A representative cohort of approximately one million people was followed up for four years. Patients with new-onset concussion were identified ( n = 13,652) as the concussion group. Subsequently, the incidence rates of later stroke events in the concussion group were compared to a sex-, age- and propensity score-matched comparison group ( n = 13,652). The overall incidence rate of stroke in the concussion group was higher than that of the comparison group (9.63 versus 6.52 per 1000 person-years, p < 0.001). Significantly higher stroke risk was observed in the concussion group than in the comparison group (crude hazard ratio 1.48, p < 0.001; adjusted HR 1.65, p < 0.001). In the concussion group, the cumulative incidence rates of both ischemic stroke and hemorrhagic stroke were higher than those of the comparison group (8.9% vs. 5.8% and 2.7% vs. 1.6%, respectively, both p < 0.001). Concussion is an independent risk factor for both ischemic and hemorrhagic strokes. Prevention and monitoring strategies of stroke are therefore suggested for patients who have experienced concussion.

Objectives: This study aimed to investigate the long-term risk of stroke in adult patients with spinal deformity. Specifically, the study addressed the possible protective effect of surgery for spinal deformity against stroke., Methods: Using the National Health Insurance Research Database (NHIRD), a monopolistic national database in Taiwan, this retrospective cohort study analyzed the incidence of stroke in patients with adult spinal deformity (ASD) in a 11-year period. A total of 13,503 patients, between 55 and 75 years old, were identified for the diagnosis of ASD. The patients were grouped into two: the surgical group (n = 10,439) who received spinal fusion surgery, and the control group (n = 2124) who received other medical treatment. The incidence rates of all subsequent cerebrovascular accidents, including ischemic and hemorrhagic strokes, were calculated. Hazard ratios for stroke were calculated use a full cohort and a propensity score matched cohort. Adjustments for co-morbidities that may predispose to stroke, including hypertension, diabetes mellitus, arrhythmia and coronary heart disease were conducted. Kaplan-Meier and Cox regression analyses were performed to compare the risk of stroke between the two groups., Results: During the total observation period of 50,450 person-years, the incidence rate of stroke in the surgical group (15.55 per 1000 person-years) was significantly lower than that of the control group (20.89 per 1000 person-years, p < 0.001). Stroke was more likely to occur in the control group than in the surgical group (crude hazard ratio 1.34, p < 0.001; adjusted HR 1.28, p < 0.001, by a propensity score matched model)., Conclusions: In this national cohort of more than 13,000 ASD patients covering 10 years, stroke was approximately 25% less likely to happen in patients who underwent spinal fusion surgery than those who received medical management. Therefore, spinal fusion surgery may provide a protective effect against stroke in adult patients with spinal deformity.

The disabling pathophysiologic effects of lipid and neuroprotective effects of statins have recently been demonstrated for acute spinal cord injuries in animal models. This large scale population-based study aimed to investigate the effect hyperlipidemia and the use of statins in patients with lumbar spine injury. The National Health Insurance Research Database of Taiwan was used to identify patients with lumbar spine injury. A total of 2844 patients were grouped into three: no hyperlipidemia, hyperlipidemia using low-dose of statins (≤90 of the defined daily dosage (DDD)), and severe hyperlipidemia using high-dose of statins (>90 DDD). A Cox multiple regression model was used to compare the incidence rates of disability among the three groups. The results showed that patients with hyperlipidemia appeared a higher risk of permanent disability (adjusted HR = 1.38, p = 0.28). In subgroup analysis, patients with severe hyperlipidemia had a higher risk of disability (adjusted HR = 3.1, p < 0.004), whereas hyperlipidemia using low-dose statins had a similar risk of permanently disability (adjusted HR = 0.83, p = 0.661). Hyperlipidemia adversely affected the neurological outcomes of lumbar spinal injury. Statins may have the potential to reverse this higher risk of disability. However, this beneficiary effect of statins only existed in patients using a lower dose (≤90 DDD).

A single-webcam distance measurement technique for indoor robot localization is proposed in this paper. The proposed localization technique uses webcams that are available in an existing surveillance environment. The developed image-based distance measurement system (IBDMS) and parallel lines distance measurement system (PLDMS) have two merits. Firstly, only one webcam is required for estimating the distance. Secondly, the set-up of IBDMS and PLDMS is easy, which only one known-dimension rectangle pattern is needed, i.e., a ground tile. Some common and simple image processing techniques, i.e., background subtraction are used to capture the robot in real time. Thus, for the purposes of indoor robot localization, the proposed method does not need to use expensive high-resolution webcams and complicated pattern recognition methods but just few simple estimating formulas. From the experimental results, the proposed robot localization method is reliable and effective in an indoor environment.