Head Section Research Articles

Longitudinal combustion instability in a hypergolic liquid bipropellant combustor with single dual-swirl coaxial injector

Self-excited longitudinal combustion instabilities were investigated in a hypergolic liquid bipropellant combustor, which applied single dual-swirl coaxial injector. Hot-fire tests were conducted for four different injector geometries, while extensive tests on injection conditions were carried out for each injector geometry. The synchronous measurement of the pressure and heat release rate was applied, successfully capturing the process of the pressure and heat release rate enhanced coupling and developing into in-phase oscillation. By calculating Rayleigh index at the head and middle section of the chamber, it is shown that Rayleigh index of the middle section is even higher than that of the head, indicating a long heat release zone. When the combustion instability occurs, the pressure in propellant manifolds also oscillates with the same frequency and lags behind the oscillation in the combustor. Compared to the oscillation in the outer injector manifold, the oscillation in the inner injector manifold shows a higher correlation with that in the chamber in amplitude and phase. Based on numerical simulations of the multiphase cold flow inside the injector and combustion process in the chamber, it is found that injector geometries affect longitudinal combustion instability by changing spray cone angle. The spray with small cone angle is more sensitive to the modulation of longitudinal pressure wave in combustion simulations, which is more likely to excite the longitudinal combustion instability. Meanwhile, the combustion instability may be related to the pulsating coherent structure generated by the spray fluctuation, which is determined by injection conditions. Besides, a positive feedback closed-loop system associated with the active fluctuation and passive oscillation of the spray is believed to excite and sustain the longitudinal combustion instability.

Assessing the Impact of Human Resource Competency and Employee Commitment on Performance at Urban Republic, a Member of the Erajaya Group, Palembang

Companies must innovate and improve employee performance in today’s competitive business climate to maintain their market share. Urban Republic, a company headquartered in Palembang and part of the Erajaya Group, is the subject of this study, which examines the relationship between employee participation and HR competency and performance. Improving employee performance requires HR competency, including technical and non-technical skills, and employee commitment, characterized by loyalty and dedication. For Urban Republic to remain competitive, they must understand how these elements affect performance. This study aimed to assess the impact of employee commitment and HR competency on performance. Three sections of labor area heads, store leaders, and staff were given surveys as part of the quantitative approach. Multiple regression analysis was used to analyze the data, supported by validity, reliability, and classical assumption tests. The results showed that employee dedication showed almost significant significance, indicating a possible influence, while employee competence had a statistically significant impact on employee performance. Dedication and HR competency significantly impact performance when the two work together. This analysis emphasizes the importance of continuous HR development investment and the potential benefits of employee commitment. To reduce the risk of employee turnover, it is recommended that HR training programs be improved, employee recognition programs be strengthened, commitment issues be addressed, and staff well-being be monitored to avoid burnout. It is recommended that more research be conducted to examine the intricacies of employee dedication and how it impacts work outcomes. The study concluded that a balanced focus on HR competency and employee commitment is essential to optimize employee performance at Urban Republic

Experimental investigation of equilibrium and temporal scour around the round head of the rubble mound breakwater in case of breaking and non-breaking waves

In this study, local sediment movements caused by regular wave effects around the head section of rubble mound breakwater were investigated experimentally. The experiments were performed in a wave channel with a length of 33 m, a width of 3.6 m and a depth of 1.2 m. A plunger-type wave generator was located at the offshore side, generating regular waves of varying heights and periods. Uniform sandbed material of three different grain sizes was used, alongside two distinct breakwater slopes and six different wave characteristics. Experiments were performed under both breaking and non-breaking wave conditions. Time-dependent scour depth and water level measurements were determined by using measuring equipment working with an ultrasonic method. In the paper, new empirical relations were derived for temporal relative scour depths and the non-dimensional time scale parameter and the non-dimensional time scale parameter. The determination coefficient and scatter index of these derived relations were calculated and evaluated statistically. It was observed that the relations are in good agreement with those obtained from experiments. Additionally, the findings indicate that wave breaking significantly reduces the equilibrium scour depth.

Indocyanine green uptake by human tumor and non‑tumor cell lines and tissue.

Indocyanine green (ICG) is a potential promising dye for a better intraoperative tumor border definition and an improved patient outcome by potentially improving tumor border visualization compared with traditional white light guided surgery. Here, the cellular uptake of ICG in human squamous cell carcinoma (SCC026) and immortalized non-cancer skin (HaCaT) cell lines was evaluated to study the tumor-specific cellular uptake of ICG. The spatial distribution of ICG inside tumor tissue was investigated in tissue sections of head and neck squamous cell carcinoma at a microscopic level. ICG uptake and internalization was observed in living cells after 2.5 h and in the nucleus after 24 h. In dead cells, higher and faster uptake was observed. In the tissue sections, higher ICG signal intensity could be detected in connective tissue and surrounding clusters and blood vessels. In conclusion, no distinct ICG uptake by tumor cells was detected in cancer cell lines and tumor tissue. ICG localization in certain regions of tumor tissue appears to be a result of enhanced tissue permeability and retention, but not specific to tumor cells.

A novel model for detecting prestress by external anchor head section of prestressed anchor cables

Prestressed anchor cables are widely used in ocean engineering, the accurate and efficient prestress measurement is crucial for ensuring their safety and stability. In this study, a new theoretical model based on the Hertz contact theory and fractal theory was proposed to establish the relationship between tangential contact stiffness (TCS) at the interface of the anchorage and the anchor bedding plate in the external anchor head section. This model was validated through indoor static load tests, and its feasibility for practical application was explored by indoor dynamic load tests. The results demonstrate that both tangential load and tensile load are the primary factors determining the value of TCS. TCS decreases with increasing tangential load, but increases with growth in tensile force. The calculated theoretical values based on the proposed model align closely with test data from indoor static load tests, indicating the efficiency of the proposed model in prestress evaluation. The correlation trends between TCS and tensile force observed in dynamic load tests exhibit good consistency with those found in static load tests, which also align with calculated values based on the proposed model, demonstrating its feasibility in dynamic load tests. The proposed model is modified by considering the interactions between the micro-convex bodies, and other parameter such as fractal dimension D need to be considered when applying the proposed model. These findings can provide valuable insights for the application of prestressed anchor cables in ocean engineering.

Template‐Refine Network for Siamese Object Tracking

Various mainstream target tracking algorithms based on Siamese networks are gradually becoming a trend in the field of deep learning tracking due to their concurrent advantages of accuracy and speed. Most Siamese network‐based trackers describe the tracking of a target object as a similar matching problem, and these trackers have achieved more advanced performance in several public tests. Most trackers often suffer from tracking drift or performance degradation owing to the non‐updating of the template in the first frame and the target appearance encounters disturbing environments such as occlusion and drastic deformation. Therefore, to address this problem, this paper introduces a template updating mechanism and proposes a refine structure network based on the template updating of Siamese networks as well as the greater similarity of target features in two adjacent frames, which improves the tracking accuracy while limiting the amount of computation using an anchor‐free method in order not to lose the tracking speed, and only needs to be trained by selecting the most suitable pre‐training network, thus greatly reducing the amount of network computation. Meanwhile, in the application of the refine structure, with the aim of making the weight design of the target localisation module more reasonable, we propose a new Refine Head section and analyze and design the update threshold to optimize the overall network. This method is practiced in SiamFC++ algorithm, which firstly designs the template refine module, inputs the image that needs to be improved, and then outputs it to the Refine Head to complete the template update and applies it to the tracking of the subsequent frames, thereby constituting the SiamTRN (Template‐Refine Network). According to the experiments, the improved structure of the method can effectively implement the refine module function and enhance the performance of the tracker on public datasets, such as OTB100, VOT2016, UAV123 and GOT‐10 k. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Biomechanical design optimization and experimental verification of Bezier curve based two-sectional cervical pillow with variable-density cellular structure

The fundamental function of an optimal cervical pillow is to provide sufficient support to maintain normal spinal alignment and minimize biological stress on the contact surface throughout sleep. The recent advancements in cervical pillows have mainly focused on the subjective and objective evaluations of support comfort, as well as the relationship between pillow height and cervical vertebrae posture. However, only a few studies have addressed shape design guidelines and mechanical performances of the pillows themselves. In this study, a two-sectional contour cervical pillow comprising an arc and a Bezier curve is designed to support the head and neck. The design of the arc-shaped neck section incorporates the Cobb’s angle and Borden value from healthy individuals to reflect the consistency of normal cervical anatomical features. The Bezier curve-based head section takes the head length and neck depth into account as significant individual differences. Static analysis and lattice optimization are performed in ANSYS Workbench to develop a variable-density cellular structure, aimed at improving air permeability and reducing the risk of pressure ulcers associated with the cervical pillow. The rapid prototyping technique fused deposition modeling (FDM) and thermoplastic material polylactic acid (PLA) are employed for fabricating different cellular structures. The results demonstrate that the neck section experiences less stress and greater deformation in comparison to the head section, indicating good comfort and support provided by the designed cervical pillow. Additionally, the compressive, bending, and cushion properties of the 3D-printed cervical pillow with variable-density cellular structure are experimentally validated, further confirming its effectiveness.

Study on the Identification, Failure Mode, and Spatial Distribution of Bank Collapses after the Initial Impoundment in the Head Section of Baihetan Reservoir in Jinsha River, China

After the initial impoundment of the Baihetan Reservoir in April 2021, the water level in front of the dam rose about 200 m. The mechanical properties and effects of the bank slopes in the reservoir area changed significantly, resulting in many bank collapses. This study systematically analyzed the bank slope of the head section of the reservoir, spanning 30 km from the dam to Baihetan Bridge, through a comprehensive investigation conducted after the initial impoundment. The analysis utilized UAV flights and ground surveys to interpret the bank slope’s distribution characteristics and failure patterns. A total of 276 bank collapses were recorded, with a geohazard development density of 4.6/km. The slope gradient of 26% of the collapsed banks experienced an increase ranging from 5 to 20° after impoundment, whereas the remaining sites’ inclines remained unchanged. According to the combination of lithology and movement mode, the bank failure mode is divided into six types, which are the surface erosion type, surface collapse type, surface slide type, bedding slip type of clastic rock, toppling type of clastic rock, and cavity corrosion type of carbonate rock. It was found that the collapsed banks in the reservoir area of 85% developed in the reactivation of old landslide deposits, while 15% in the clastic and carbonate rock. This study offers guidance for the next phase of bank collapse regulations and future geohazards prevention strategies in the Baihetan Reservoir area.

Transient Analysis on the Crosswind Effect to the Aerodynamics of High-speed Train Travelled on the Bridge Between Two Tunnels at Jakarta -Bandung Track

The rapid evolution of global transportation technology is exemplified by Indonesia's innovative high-speed train initiative, linking Jakarta and Bandung in an impressive 45 minutes. Operating at 350 km/h, the HST CR400AF underscores the importance of aerodynamics in high-speed rail systems. This study delves into the significant impact of crosswind on key aerodynamic factors (drag, lift, rolling moment) within the tunnel-bridge-tunnel configuration. Leveraging Computational Fluid Dynamics (CFD) through ANSYS FLUENT, the analysis explores crosswind variations at 0 m/s, 10 m/s, and 25 m/s. Results reveal a proportional increase in aerodynamic load with higher crosswind intensities: 1.67 times for drag, 58.8 times for lift, and 29.8 times for rolling moment. Notable observations include pronounced aerodynamic load fluctuations during the "OUT" process, with the head section bearing the greatest load, followed by the tail and middle sections. These findings contribute valuable insights to the global discourse on enhancing safety and efficiency in high-speed rail systems

A novel vortex control method for improving anti-overturning performance of a high-speed train with leeward airbag structures under crosswinds

The high-speed train's head and cross sections have been designed in an innovative way to meet the requirements of aerodynamic drag reduction and crosswind stability of the train. However, with the continuous increase in the running speed of high-speed trains and the continuous reduction of the total weight of the car body, it is critical to develop new strategies to ensure train safety in crosswind environment. In the current study, a novel vortex control method with airbag structure installation on the leeward side (LWS) of the train was proposed to disturb the leeward large vortices, with expectation to weaken the vortices adjacent the train body and increase the surface pressure on the leeward side. The leeward airbag structures (LASs) contribute to reducing the pressure difference between the windward and leeward sides of the train body. As a result, a reduction of the lateral force and overturning moment coefficients is obtained. An amazing observation is that an extra lift force is achieved by LASs, which leads to an anti-overturning moment, further improving the anti-overturning performance of the high-speed train. Compared with the original model, the LASs can decrease the lateral force coefficients by 7.1%, while the lift coefficient is increased by 12.8%, which together reduces the overturning moment coefficient by 13.1%. It indicates that the main influence factor for crosswind stability of the train tends to be changed after the installation of LASs. The aerodynamic performance of the tail car is more sensitive to the LASs as compared to that of the head and middle cars, i.e., the reduction of the overturning moment coefficient is about 44.6% for the tail car, whereas it is only 7.8% and 12.5% for the head and middle cars, respectively. Thus, the LASs proposed in the current work can significantly improve the anti-overturning performance of high-speed trains, which will provide a novel anti-overturning approach for higher-speed trains.

Description, life cycle, and development of the myxozoan Myxobolus rasmusseni n. sp. in fathead minnows, Pimephales promelas: A possible emerging pathogen in southern Alberta, Canada

Morphological, gene sequence, host tissue tropism, and life cycle characteristics were utilized to describe the myxozoan, Myxobolus rasmusseni n. sp. from fathead minnow, Pimephales promelas, collected from reservoirs in southern Alberta. Results from serial histological sections of whole heads showed that myxospores were contained within irregular-shaped and sized coelozoic capsules (=plasmodia). Clusters of membrane-bound, myxospore-filled plasmodia filled the head cavities of juvenile fathead minnows, leading to the development of large, white, disfiguring lesions in mid to late summer. Bilateral exopthalmia (pop-eye disease) was a common outcome of M. rasmusseni n. sp. development. BLASTn search of a 1974 bp sequence of the 18S rDNA gene isolated from myxospores indicated that M. rasmusseni n. sp. was distinct from other coelozoic and histozoic Myxobolus spp. cataloged in GenBank. 18S rDNA gene sequences from triactinomyxon spores released from the oligochaete Tubifex were 100% identical to sequences from myxospores collected from syntopic fathead minnows. Results from a longitudinal survey of the 2020 cohort of fathead minnows showed that young-of-the-year are exposed at 1–5 mo and that 60–90% of these had developed myxospore-filled lesions approximately one year later. Data regarding potential sources and timing of M. rasmusseni n. sp. emergence in fathead minnow populations are needed.

Research on Human Posture Estimation Algorithm Based on YOLO-Pose.

In response to the numerous challenges faced by traditional human pose recognition methods in practical applications, such as dense targets, severe edge occlusion, limited application scenarios, complex backgrounds, and poor recognition accuracy when targets are occluded, this paper proposes a YOLO-Pose algorithm for human pose estimation. The specific improvements are divided into four parts. Firstly, in the Backbone section of the YOLO-Pose model, lightweight GhostNet modules are introduced to reduce the model's parameter count and computational requirements, making it suitable for deployment on unmanned aerial vehicles (UAVs). Secondly, the ACmix attention mechanism is integrated into the Neck section to improve detection speed during object judgment and localization. Furthermore, in the Head section, key points are optimized using coordinate attention mechanisms, significantly enhancing key point localization accuracy. Lastly, the paper improves the loss function and confidence function to enhance the model's robustness. Experimental results demonstrate that the improved model achieves a 95.58% improvement in mAP50 and a 69.54% improvement in mAP50-95 compared to the original model, with a reduction of 14.6 M parameters. The model achieves a detection speed of 19.9 ms per image, optimized by 30% and 39.5% compared to the original model. Comparisons with other algorithms such as Faster R-CNN, SSD, YOLOv4, and YOLOv7 demonstrate varying degrees of performance improvement.

Non-geodesic winding design method for the composite shell of unequal-pole-hole solid rocket motor

Advanced composite materials have the advantages of high specific strength, high specific modulus, good fatigue resistance, good shock absorption performance, and strong designability. They are widely used in the fields of national defense science and technology and civil engineering. To make a more accurate winding design of the composite shell of the non-equidistant solid rocket motor, based on the ANSYS ACP composite structure design and analysis software, this paper uses the cubic spline function method to design the fiber winding thickness of the shell head section for a solid rocket motor. The Runge-Kutta method is used to calculate the changing winding angle of the non-geodesic line, and the changing winding angle and winding thickness on the head are simulated based on the look-up table interpolation table module in ACP. Finally, the mechanical properties of the designed shell under certain internal pressure are simulated and analyzed. Through the simulation analysis of the designed engine model, it is found that the connection between the front head and the barrel section is a weak profit, and the follow-up study should reinforce this area.

Early Drought Detection in Maize Using UAV Images and YOLOv8+

The escalating global climate change significantly impacts the yield and quality of maize, a vital staple crop worldwide, especially during seedling stage droughts. Traditional detection methods are limited by their single-scenario approach, requiring substantial human labor and time, and lack accuracy in the real-time monitoring and precise assessment of drought severity. In this study, a novel early drought detection method for maize based on unmanned aerial vehicle (UAV) images and Yolov8+ is proposed. In the Backbone section, the C2F-Conv module is adopted to reduce model parameters and deployment costs, while incorporating the CA attention mechanism module to effectively capture tiny feature information in the images. The Neck section utilizes the BiFPN fusion architecture and spatial attention mechanism to enhance the model’s ability to recognize small and occluded targets. The Head section introduces an additional 10 × 10 output, integrates loss functions, and enhances accuracy by 1.46%, reduces training time by 30.2%, and improves robustness. The experimental results demonstrate that the improved Yolov8+ model achieves precision and recall rates of approximately 90.6% and 88.7%, respectively. The mAP@50 and mAP@50:95 reach 89.16% and 71.14%, respectively, representing respective increases of 3.9% and 3.3% compared to the original Yolov8. The UAV image detection speed of the model is up to 24.63 ms, with a model size of 13.76 MB, optimized by 31.6% and 28.8% compared to the original model, respectively. In comparison with the Yolov8, Yolov7, and Yolo5s models, the proposed method exhibits varying degrees of superiority in mAP@50, mAP@50:95, and other metrics, utilizing drone imagery and deep learning techniques to truly propel agricultural modernization.

IoT-based framework for digital twins in steel production: A case study of key parameter prediction and optimization for CSR

Cold-rolled strips are a pivotal product of advanced strip rolling technology in iron and steel production with stringent process standards. Over an extended period, the existence of 'information silos' between cold strip rolling (CSR) and its upstream processes, particularly hot strip rolling (HSR), causes a persistent challenge in achieving collaborative optimization throughout the entire process, thereby constraining progress in product quality. To overcome this challenge, a digital twin framework was proposed to consolidate diverse data from HSR and CSR production lines into a centralized data centre, forming a 'data continent.' This approach establishes a comprehensive dataset for model-driven training and prediction in virtual space. An improved Light gradient boosting machine (IlightGBM) is introduced, enabling high-precision rolling force prediction in unsteady-state rolling and providing essential variables for establishing the tension optimization objective function. A control function is implemented to minimize rolling force fluctuations, and three population algorithms (TPA) are devised for its solution. This strategy successfully realizes collaborative tension optimization across multiple stands, with the rolling speed acting as a follower. The proposed approach was implemented in a large-scale steel plant equipped with a complete HSR and CSR production line, effectively mitigating flatness defects and thickness deviation in the strip's head section. Thus, the proposed framework is reliable and can be flexibly applied to strip manufacturing processes.

ANALISIS DESKRIPTIF GAYA KEPEMIMPINAN SITUASIONAL KEPALA RUANGAN PERAWATAN RUMAH SAKIT PKU MUHAMMADIYAH YOGYAKARTA

The PKU Muhammadiyah HospitalOf Yogyakarta is referred Islamic hospital type B in Special Governmental State Yogyakarta and Central Java. In spite of being referred hospital, in giving service and nursing care has not been optimal. Head of nursing section has significant role in organizing associate nurse in effort of better service. A successful head section must be a good identifier and could appreciating the spirit of curiosity. Four situational leadership style such as, instructing, consulting, participating and delegating, will be analyze to see the tendency of leadership style that be used by the head of nursing section of PKU Muhammadiyah Hospital of Yogyakarta.This research is the quantitative-descriptive research. Measurement tools of this research using questioners that being distribute to 94 respondent. The subject of this research is vocational nurse on inpatient room of the PKU Muhammdiyah Hospital of Yogyakarta.Result of this research in the way of leadership assessed by associate nurse on head nursing section in patient room shows that ibnu shina room used consulting style 72,7%, marwah 56,3% consulting, roudhoh 63,3% consulting, arafah 53,8% participating, shofa-musdalifah 71,4% consulting, zam-zam 81,8% participating, and multazam 72,2% consulting.The style of situational leadership dominantly applied by the head nurse section of PKU based on the assessment of associate nurse is consulting leadership. The style of situational leadership not applied by the head nurse section is instructing.

Modeling of the removal of combustion products in the pipe of a low-rise building as a control object

The features of the formation and methods of preventing condensation in the chimney of an apartment low-rise building with an individual decentralized heat supply system are considered. A mathematical model of the technological process of removing flue gases from gas boilers in an apartment building through a collective chimney pipe as a multidimensional control object with distributed parameters, which is understood as a set of thermophysical processes occurring during the removal of combustion products. Numerical simulation of a collective chimney pipe is performed on the example of a three-storey apartment building with gas boilers installed in each apartment as a control object. A method of step-by-step experiments is proposed. At the first stage, the dependences of the distribution of the temperature field inside the chimney during non-stationary operation of boilers and changing ambient temperature are obtained. The phenomenon of condensate occurrence has been confirmed experimentally, and the most characteristic areas subject to its occurrence have been identified. During the second stage of research, it was found that it is most effective and economically feasible to prevent the formation of condensate by using a heating cable in the attic and chimney head sections. It is shown that the change of control actions has an effect on the temperature of adjacent sections of the chimney. The revealed non-stationarity is taken into account by inter-channel connections through the object in the block diagram. It is proved that, in relation to solving the problem of removing combustion products from the chimney, an object with distributed parameters can be represented by a model with concentrated parameters, for which the structure is synthesized and proper operators and operators of inter-channel connections are found in the form of transfer functions with variable parameters. The resulting model is problem-oriented to create a two-dimensional automatic temperature control system on the inner surface of the chimney in order to prevent the formation of condensate in the pipe.

Unleashing the power of AI in detecting metal surface defects: an optimized YOLOv7-tiny model approach.

The detection of surface defects on metal products during the production process is crucial for ensuring high-quality products. These defects also lead to significant losses in the high-tech industry. To address the issues of slow detection speed and low accuracy in traditional metal surface defect detection, an improved algorithm based on the YOLOv7-tiny model is proposed. Firstly, to enhance the feature extraction and fusion capabilities of the model, the depth aware convolution module (DAC) is introduced to replace all ELAN-T modules in the network. Secondly, the AWFP-Add module is added after the Concat module in the network's Head section to strengthen the network's ability to adaptively distinguish the importance of different features. Finally, in order to expedite model convergence and alleviate the problem of imbalanced positive and negative samples in the study, a new loss function called Focal-SIoU is used to replace the original model's CIoU loss function. To validate the effectiveness of the proposed model, two industrial metal surface defect datasets, GC10-DET and NEU-DET, were employed in our experiments. Experimental results demonstrate that the improved algorithm achieved detection frame rates exceeding 100 fps on both datasets. Furthermore, the enhanced model achieved an mAP of 81% on the GC10-DET dataset and 80.1% on the NEU-DET dataset. Compared to the original YOLOv7-tiny algorithm, this represents an increase in mAP of nearly 11% and 9.2%, respectively. Moreover, when compared to other novel algorithms, our improved model demonstrated enhanced detection accuracy and significantly improved detection speed. These results collectively indicate that our proposed enhanced model effectively fulfills the industry's demand for rapid and efficient detection and recognition of metal surface defects.

Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy

Real-time video surveillance, especially CCTV systems, requires fast and accurate face detection. Object detection models with slow inference times are ineffective in real-time. This study addresses this challenge by improving the inference speed of the YOLOv8 model, a leading object detection framework known for its accuracy and speed. We focus on pruning the model's architecture, particularly the P5 head section, which detects larger objects. According to Bochkovskiy's 2020 research, this modification enhances the model's performance specifically for medium and small objects in CCTV footage. The standard YOLOv8 model and its modified version were compared for inference time, mean Average Precision (mAP), and model weight. The pruned YOLOv8 model cuts inference time by 15.56%, from 4.5 ms to 3.8 ms, and reduces model weight. The advantages mentioned above are offset by a 1.6% decrease in mean average precision. This research advances object detection technology by demonstrating architectural modifications' efficacy. These changes make the model faster and lighter, making it suitable for real-time surveillance. The accuracy trade-off is slight. The implications of these findings are crucial for implementing efficient object detection systems in CCTV surveillance. These findings also lay the groundwork for future research to improve such systems' speed-accuracy trade-off.

Intelligent Gangue Sorting System Based on Dual-Energy X-ray and Improved YOLOv5 Algorithm

Intelligent gangue sorting with high precision is of vital importance for improving coal quality. To tackle the challenges associated with coal gangue target detection, including algorithm performance imbalance and hardware deployment difficulties, in this paper, an intelligent gangue separation system that adopts the elevated YOLO-v5 algorithm and dual-energy X-rays is proposed. Firstly, images of dual-energy X-ray transmission coal gangue mixture under the actual operation of a coal mine were collected, and datasets for training and validation were self-constructed. Then, in the YOLOv5 backbone network, the EfficientNetv2 was used to replace the original cross stage partial darknet (CSPDarknet) to achieve the lightweight of the backbone network; in the neck, a light path aggregation network (LPAN) was designed based on PAN, and a convolutional block attention module (CBAM) was integrated into the BottleneckCSP of the feature fusion block to raise the feature acquisition capability of the network and maximize the learning effect. Subsequently, to accelerate the rate of convergence, an efficient intersection over union (EIOU) was used instead of the complete intersection over union (CIOU) loss function. Finally, to address the problem of low resolution of small targets leading to missed detection, an L2 detection head was introduced to the head section to improve the multi-scale target detection performance of the algorithm. The experimental results indicate that in comparison with YOLOv5-S, the same version of the algorithm proposed in this paper increases by 19.2% and 32.4% on mAP @.5 and mAP @.5:.95, respectively. The number of parameters decline by 51.5%, and the calculation complexity declines by 14.7%. The algorithm suggested in this article offers new ideas for the design of identification algorithms for coal gangue sorting systems, which is expected to save energy and reduce consumption, reduce labor, improve efficiency, and be more friendly to the embedded platform.