Search Results (13)

Affected by the complex underwater environment and the limitations of low-resolution sonar image data and small sample sizes, traditional image recognition algorithms have difficulties achieving accurate sonar image recognition. The research builds on YOLOv7 and devises an innovative fast recognition model designed explicitly for sonar images, namely the Dual Attention Mechanism YOLOv7 model (DA-YOLOv7), to tackle such challenges. New modules such as the Omni-Directional Convolution Channel Prior Convolutional Attention Efficient Layer Aggregation Network (OA-ELAN), Spatial Pyramid Pooling Channel Shuffling and Pixel-level Convolution Bilat-eral-branch Transformer (SPPCSPCBiFormer), and Ghost-Shuffle Convolution Enhanced Layer Aggregation Network-High performance (G-ELAN-H) are central to its design, which reduce the computational burden and enhance the accuracy in detecting small targets and capturing local features and crucial information. The study adopts transfer learning to deal with the lack of sonar image samples. By pre-training the large-scale Underwater Acoustic Target Detection Dataset (UATD dataset), DA-YOLOV7 obtains initial weights, fine-tuned on the smaller Smaller Common Sonar Target Detection Dataset (SCTD dataset), thereby reducing the risk of overfitting which is commonly encountered in small datasets. The experimental results on the UATD, the Underwater Optical Target Detection Intelligent Algorithm Competition 2021 Dataset (URPC), and SCTD datasets show that DA-YOLOV7 exhibits outstanding performance, with [email protected] scores reaching 89.4%, 89.9%, and 99.15%, respectively. In addition, the model maintains real-time speed while having superior accuracy and recall rates compared to existing mainstream target recognition models. These findings establish the superiority of DA-YOLOV7 in sonar image analysis tasks. Full article

Wearing safety helmets at construction sites is a major measure to prevent safety accidents, so it is essential to supervise and ensure that workers wear safety helmets. This requires a high degree of real-time performance. We improved the network structure based on YOLOv7. To enhance real-time performance, we introduced GhostModule after comparing various modules to create a new efficient structure that generates more feature mappings with fewer linear operations. SE blocks were introduced after comparing several attention mechanisms to highlight important information in the image. The EIOU loss function was introduced to speed up the convergence of the model. Eventually, we constructed the efficient model EGS-YOLO. EGS-YOLO achieves a mAP of 91.1%, 0.2% higher than YOLOv7, and the inference time is 13.3% faster than YOLOv7 at 3.9 ms (RTX 3090). The parameters and computational complexity are reduced by 37.3% and 33.8%, respectively. The enhanced real-time performance while maintaining the original high precision can meet actual detection requirements. Full article

Precise and rapid detection of seatbelts is an essential research field for intelligent traffic management. In order to improve the detection precision of seatbelts and speed up algorithm inference velocity, a lightweight seatbelt detection algorithm is proposed. Firstly, by adding the G-ELAN module designed in this paper to the YOLOv7-tiny network, the optimization of construction and reduction of parameters are accomplished, and the ResNet is compressed with the channel pruning approach to decrease computational overheads. Then, the Mish activation function is utilized to replace the Leaky Relu in the neck to enhance the non-linear competence of the network. Finally, the triplet attention module is integrated into the model after pruning to make up for the underlying performance reduction caused by the previous stage and upgrade overall detection precision. The experimental results based on the self-built seatbelt dataset showed that, compared to the initial network, the Mean Average Precision (mAP) achieved by the proposed GM-YOLOv7 was improved by 3.8%, while the volume and the computation amount were lowered by 20% and 24.6%, respectively. Compared with YOLOv3, YOLOX, and YOLOv5, the mAP of GM-YOLOv7 increased by 22.4%, 4.6%, and 4.2%, respectively, and the number of computational operations decreased by 25%, 63%, and 38%, respectively. In addition, the accuracy of the improved RST-Net increased to 98.25%, while the parameter value was reduced by 48% compared to the basic model, effectively improving the detection performance and realizing a lightweight structure. Full article

Underwater target detection plays a crucial role in marine environmental monitoring and early warning systems. It involves utilizing optical images acquired from underwater imaging devices to locate and identify aquatic organisms in challenging environments. However, the color deviation and low illumination in these images, caused by harsh working conditions, pose significant challenges to an effective target detection. Moreover, the detection of numerous small or tiny aquatic targets becomes even more demanding, considering the limited storage and computing power of detection devices. To address these problems, we propose the YOLOv7-CHS model for underwater target detection, which introduces several innovative approaches. Firstly, we replace efficient layer aggregation networks (ELAN) with the high-order spatial interaction (HOSI) module as the backbone of the model. This change reduces the model size while preserving accuracy. Secondly, we integrate the contextual transformer (CT) module into the head of the model, which combines static and dynamic contextual representations to effectively improve the model’s ability to detect small targets. Lastly, we incorporate the simple parameter-free attention (SPFA) module at the head of the detection network, implementing a combined channel-domain and spatial-domain attention mechanism. This integration significantly improves the representation capabilities of the network. To validate the implications of our model, we conduct a series of experiments. The results demonstrate that our proposed model achieves higher mean average precision (mAP) values on the Starfish and DUO datasets compared to the original YOLOv7, with improvements of 4.5% and 4.2%, respectively. Additionally, our model achieves a real-time detection speed of 32 frames per second (FPS). Furthermore, the floating point operations (FLOPs) of our model are 62.9 G smaller than those of YOLOv7, facilitating the deployment of the model. Its innovative design and experimental results highlight its effectiveness in addressing the challenges associated with underwater object detection. Full article

One of the most commonly encountered issues in large cities is air pollution. As a major city, Bandung also experiences the same problem. This issue arises due to the increasing levels of human activity. This contributes to elevated levels of pollutants in the atmosphere, which can impact human life and ecosystems. This research is intended to map the regions in Bandung based on their air quality. This study used ambient air quality measurement results from Bandung, which included PM₁₀, PM_2.5, dust, SO₂, CO, and NO₂. This ambient air quality measurement was conducted by the Department of Environment and Hygiene in Bandung. The research methodology utilized in this study was multidimensional scaling analysis. The outcomes of the examination carried out utilizing the multidimensional scaling technique reveal a clustering of regions in Bandung, West Java, based on their air quality. According to the research findings, the locations were grouped into four quadrants, each with different air quality characteristics. Some locations showed high similarity, while others did not exhibit similarity with other groups. These findings can be used for policy-making and improving air quality in Bandung. Conclusions were drawn from the formed groups, where each group had high similarity among its members, but differed from the members of other groups. Among all observed locations in Bandung City, there were areas that were most similar when viewed based on the distance between objects, namely Punclut St. and KPAD Sarijadi; Soekarno Hatta St. (in front of Astra Bizz) and Elang St.; and Buah Batu St. (in front of STSI/ISBI) and Bunderan Cibiru. Full article

Background: This Phase 1/2 study is based on the hypothesis that immune checkpoint inhibitors are more effective when given earlier in the course of the disease for advanced soft tissue sarcoma. Methods: Phase I endpoints—maximum tolerated dose in previously treated patients; Phase II endpoints—best response, progression free survival and overall survival and incidence of adverse events in previously untreated patients; Phase I treatments—escalating doses of trabectedin (1.0, 1.2, 1.5 mg/m²) as continuous intravenous infusion over 24 h every 3 weeks, 1 mg/kg of ipilimumab given intravenously every 12 weeks, and 3 mg/kg of nivolumab given intravenously every 2 weeks; Phase II treatments—maximum tolerated dose of trabectedin and defined doses of ipilimumab and nivolumab. Results: Phase I (n = 9)—the maximum tolerated dose of trabectedin was 1.2 mg/m²; Phase II (n = 79)—6 complete responses, 14 partial responses, 49 stable disease, 25.3% best response rate, 87.3% disease control rate; median progression-free survival, 6.7 months (CI 95%: 4.4–7.9), median overall survival, 24.6 months (CI 95%: 17.0–.); Grade 3/4 therapy-related adverse events (n = 92)—increased ALT (25%), fatigue (8.7%), increased AST (8.7%), decreased neutrophil count (5.4%) and anemia (4.6%). Conclusion: SAINT is a safe and effective first-line treatment for advanced soft tissue sarcoma. Full article

Mineral bone composition (dry matter, bones ash, P, Ca, Zn, Mn, Mg, and Cu) and Pb levels of tibiotarsi of seven White-Tailed Sea Eagles were assessed. Lead intoxication in different bird species including waterfowl and raptors is being studied worldwide. The bones were analyzed for Pb by mass spectrometry with excitation in inductively coupled plasma (ICP-MS Elan DRC II) and for bone composition by Atomic Emission Spectrometer (Agilent 4100 Microwave Plasma). Pb levels ranging from 3.54 µg/g to 74.6 µg/g DM suggest that some of the investigated birds might have been intoxicated by Pb. Results of this analysis were divided into two groups of bones, with bone Pb levels higher and lower than Pb toxicity levels, and mineral bone compositions of both groups were compared. The present study shows the differentiation of bone mineral composition among seven examined White-Tailed Sea Eagles, considered a specific species in raptors. Pb intoxication may not have a major influence on mineral bone composition in raptors. It also suggests that assessing bone composition of raptor bones may help finding the possible cause of their deaths. Full article

Previous studies on the neural cognitive mechanisms of aspectual processing in second language (L2) learners have focused on Indo-European languages with rich inflectional morphology. These languages have aspects which are equipped with inflected verb forms combined with auxiliary or modal verbs. Meanwhile, little attention has been paid to Mandarin Chinese, which has limited morphological inflection, and its aspect is equipped with aspectual particles (e.g., le, zhe, guo). The present study explores the neurocognitive mechanism of Mandarin Chinese aspect processing among two groups of late Mandarin Chinese proficient learners with Thai (with Mandarin Chinese-like aspect markers) and Indonesian (lack of Mandarin Chinese-like aspect markers) as their first language (L1). We measured event-related potentials (ERPs) time locked to the aspect marker le in two different conditions (the aspect violation sentences and the correct sentences). A triphasic ELAN-LAN-P600 effect was produced by the Mandarin Chinese native speakers. However, there was no ELAN and LAN in Indonesian native speakers and Thai native speakers, except a 300–500 ms negativity widely distributed in the right hemisphere and P600-like effect. This suggests that both groups of Mandarin Chinese learners cannot reach the same level as Mandarin Chinese native speakers to process Mandarin Chinese aspect information, probably due to the complex feature of Mandarin Chinese aspect maker, the participants’ L2 proficiency and age of L2 acquisition. Full article

Local area energy networks (E-LANs) are cyber-physical systems whose physical layer is a meshed low-voltage microgrid fed by a multiplicity of sources, i.e., utilities, energy storage systems, and distributed power sources. The cyber layer includes distributed measurement, control, and communication units, located at end-user premises, as well as centralized supervision and dispatchment control. As compared with standard microgrid, the E-LAN encompasses the ability for end-users to actively contribute to the operation of the microgrid while acting as independent energy traders in the electrical market. Operational goals include active contribution of end-users to power sharing, loss reduction, voltage stability, demand response, fault identification and clearing, isolation of sub-grids for maintenance, islanding, and black start. Economic goals include the possibility, for each end-user, to decide in every moment, based on convenience, how his energy and power capacity is shared with other users, e.g., for demand response or to trade energy in the electric market. This paper introduces a comprehensive theoretical approach of E-LAN control to achieve all the above operational goals while providing a high level of dynamic protection against faults or other events affecting the system functionality, e.g., overloads or fast transients. It shows that meshed microgrids are the necessary infrastructure to implement the desired functionalities. Full article

Alcohol consumption is a modifiable risk factor for non-communicable diseases. This study aimed to characterize alcohol consumers at the nutritional, anthropometric, and sociodemographic levels. Data from 9218 participants from Argentina, Brazil, Chile, Colombia, Costa Rica, Ecuador, Peru, and Venezuela participating in “Latin American Health and Nutrition Study (ELANS)”, a multi-country, population-based study, were used. Dietary intake was collected through two, 24 h recalls. Participants were classified into consumers (n = 1073) and non-alcohol consumers (n = 8145) using a cut-off criterium of ≥15 g/day of alcohol consumption calculated from the estimation of their usual daily intake. Among alcohol consumers, the mean alcohol consumption was 69.22 ± 2.18 grams (4.6. beverages/day), contributing to 484.62 kcal, which corresponded to 16.86% of the total energy intake. We found that the risk of alcohol consumption was higher in young and middle-aged men from low and middle socioeconomic status. Argentine, Brazil, and Chile had the highest percentage of consumers, while Ecuador showed the highest alcohol consumption. Alcohol drinkers were characterized by having higher body weight and wider neck, waist, hips circumferences. Alcohol drinkers had a higher energy intake, with macronutrients providing relatively less energy at the expense of the energy derived from alcohol. Alcohol drinkers showed lower and higher consumptions of healthy and unhealthy food groups, respectively. In addition, adequacy ratios for all micronutrients assessed were lower in alcohol consumers. All these deleterious effects of alcohol on nutritional and anthropometric parameters increased with the number of alcoholic beverages consumed daily. Altogether, these findings suggest that limiting alcohol consumption can contribute to reducing the risk of obesity, metabolic syndrome, and diet-related diseases. Full article

Patients with pancreatic ductal adenocarcinoma (PDAC) suffer debilitating and deadly weight loss, known as cachexia. Development of therapies requires biomarkers to diagnose, and monitor cachexia; however, no such markers are in use. Via Somascan, we measured ~1300 plasma proteins in 30 patients with PDAC vs. 11 controls. We found 60 proteins specific to local PDAC, 46 to metastatic, and 67 to presence of >5% cancer weight loss (FC ≥ |1.5|, p ≤ 0.05). Six were common for cancer stage (Up: GDF15, TIMP1, IL1RL1; Down: CCL22, APP, CLEC1B). Four were common for local/cachexia (C1R, PRKCG, ELANE, SOST: all oppositely regulated) and four for metastatic/cachexia (SERPINA6, PDGFRA, PRSS2, PRSS1: all consistently changed), suggesting that stage and cachexia status might be molecularly separable. We found 71 proteins that correlated with cachexia severity via weight loss grade, weight loss, skeletal muscle index and radiodensity (r ≥ |0.50|, p ≤ 0.05), including some known cachexia mediators/markers (LEP, MSTN, ALB) as well as novel proteins (e.g., LYVE1, C7, F2). Pathway, correlation, and upstream regulator analyses identified known (e.g., IL6, proteosome, mitochondrial dysfunction) and novel (e.g., Wnt signaling, NK cells) mechanisms. Overall, this study affords a basis for validation and provides insights into the processes underpinning cancer cachexia. Full article

End-stage renal disease (ESRD) patients have a high mortality rate that exceeds that of non-ESRD population. The hemodialysis procedure induces neutrophil activation and elastase release, which might have a role in the inflammatory process and in the development of oxidative stress. The ELANE gene encodes the neutrophil elastase. We analyzed the effect of ELANE promoter region polymorphisms and its relation with the circulating levels of elastase, as well as several clinical, biochemical and inflammatory markers in 123 ESRD patients. We found two duplications in heterozygosity in the promoter region and a new polymorphism, the c.-801G>A. ESRD patients heterozygous for the c.-903T>G polymorphism had no changes in the circulating levels of elastase or other evaluated variables, and those homozygous for the c.-741G>A polymorphism showed significant effects on neutrophils count, as well as in neutrophils/lymphocytes ratio, which might be associated with an increased inflammatory process. Full article

Over the past decade, enormous progress has been made in the understanding of severe congenital neutropenia (SCN), by identification of several causal gene mutations: in ELANE, GFI1, HAX1, WAS and G3PC3. SCN is a preleukemic condition, independent of the genetic subtype. Acquired CSF3R mutations are specific for SCN and are strongly associated with malignant progression. In this review, we describe the known genetic subtypes of SCN, their molecular basis and clinical presentation and summarize the available evidence on CSF3R mutations and monosomy 7 in malignant conversion. Full article