Loss Values Research Articles

Replace part of regenerative rice silage feed with whole cottonseed enhances growth performance and nutrient digestibility via regulating gH/IGF axis in beef cattle

This work was designed to assess the impacts of whole cottonseed (WCs) on growth performance, nutrient digestion, GH /IGF-1 axis, and meat quality in beef cattle. Twenty-four healthy male simmental cattle (18 months old and 370.5 ± 12.5 kg) were arbitrarily classified into two groups (n=12 per group): Control group (without WCs) and WCs replaced group (part of regenerative rice silage was replaced with WCs). The dry matter intake (DMI) was declined(P < 0.01), while the average daily gain (ADG) was increased(P < 0.05), therefore the feed conversion ratio (FCR) was lower (P < 0.05) in WCs replaced group. Beef cattle consuming WCs had a higher digestibility of total gastrointestinal nutrients (P < 0.01 or P < 0.05). The growth hormone receptor (GHR), insulin-like growth factor 1 (IGF-1), and insulin-like growth factor 1 receptor (IGF-1R) mRNA amounts were all enhanced (P < 0.05) in liver, longissimus dorsi muscle, and semitendinosus muscle of beef cattle after feeding WCs relative to control group. The mRNA amounts of phosphoinositide 3-kinase (PI3K), protein kinase B (Akt), mammalian target of rapamycin (mTOR), and ribosomal protein S6 kinase beta-1 (S6K1) and the protein phosphorylation levels of Akt、mTOR, and S6K1 were all markedly enhanced (P < 0.05 or P < 0.01) in liver, longissimus dorsi muscle, and semitendinosus muscle for WCs replacement. The shear force and cooking loss values having somewhat raised(P < 0.05) for WCs replacement. Altogether, WCs improves the growth performance and nutrient digestibility via regulating GH/IGF axis in beef cattle, and has negative effects on meat quality.

Variational quantum algorithm for designing quantum information maskers* *Supported by the National Natural Science Foundation of China (under Grant Nos. 12105090 and 12074107), the Program of Outstanding Young and Middle-aged Scientific and Technological Innovation Team of Colleges and Universities in Hubei Province of China (under Grant No. T2020001), and the Innovation Group Project of the Natural Science Foundation of Hubei

Since the concept of quantum information masking was proposed by Modi et al (2018 Phys. Rev. Lett. 120, 230 501), many interesting and significant results have been reported, both theoretically and experimentally. However, designing a quantum information masker is not an easy task, especially for larger systems. In this paper, we propose a variational quantum algorithm to resolve this problem. Specifically, our algorithm is a hybrid quantum–classical model, where the quantum device with adjustable parameters tries to mask quantum information and the classical device evaluates the performance of the quantum device and optimizes its parameters. After optimization, the quantum device behaves as an optimal masker. The loss value during optimization can be used to characterize the performance of the masker. In particular, if the loss value converges to zero, we obtain a perfect masker that completely masks the quantum information generated by the quantum information source, otherwise, the perfect masker does not exist and the subsystems always contain the original information. Nevertheless, these resulting maskers are still optimal. Quantum parallelism is utilized to reduce quantum state preparations and measurements. Our study paves the way for wide application of quantum information masking, and some of the techniques used in this study may have potential applications in quantum information processing.

Insertion Loss Value Dependency of the Low Height Noise Barriers Distance From Railway Track

Insertion Loss Value Dependency of the Low Height Noise Barriers Distance From Railway Track

A Research on Advanced Noise Suppression and Recognition Technology of SAR Images

Synthetic Aperture Radar (SAR) has been commonly utilized in both military and civilian fields in the past decade because of its all-weather, high-resolution, and strong penetration capabilities. However, due to its unique coherent imaging characteristics, speckle noise will be generated in SAR images, which greatly degrades the image quality and hinders subsequent target recognition work. In this paper, several denoising methods will be compared and estimated by indexes such as signal-to-noise ratio (SNR) and other indicators to estimate the model quality. Then the better method will be selected to preprocess SAR images and perform target recognition on the processed images. Based on the classic CNN model, a Squeeze-and-Excitation block will be added into the convolutional layer and train the model using part of the MSTAR dataset SAR images. During training, the SAR image samples are preliminarily divided into 8 classes, and the neural network is trained using the training set and validation set. When the training accuracy, validation accuracy, and validation loss value reach a relatively ideal value, training is stopped. Finally, the model is used to recognize the SAR image categories and compare the average recognition accuracy with the actual image categories. In addition, by comparing the average recognition accuracy before and after noise suppression, the experiments can also verify the performance of the method in SAR image noise suppression.

Multi-source domain generalization tool wear prediction based on wide convolution weighted antagonism

Abstract While traditional deep learning models achieve high accuracy in predicting tool wear under consistent working conditions, actual production processes frequently involve varying conditions due to different processing methods. The wear data of different working conditions have a large difference in distribution, so that the wear signal of milling cutter trained in one working condition can only predict the wear value of the working condition, which will cause a large waste of material and manpower for actual production. Therefore, a domain generalization method utilizing wide deep convolutional neural networks and weighted antagonistic multi-source domain generalization is introduced for tool wear prediction, and multi-source domain wide depth convolutional weighted adversarial domain generalization model (WDCNNWAL) model is constructed. After filtering and de-noising the original data, it is input into WDCNN for automatic feature learning, and the resulting multi-source feature signals are input into the prediction model and discriminator respectively to obtain corresponding loss values. Furthermore, Wasserstein distance is used to measure the probability distribution distance of multi-source feature signals as a weighted value combined with the discriminator loss function, and the final loss value is obtained by adding together. Finally, the tool wear prediction model is set up using a backpropagation neural network. Various milling wear experimental data along with the NASA tool wear public dataset were utilized to assess the predictive performance of the trained model. The model achieves a high level of generalization in tool wear prediction, with average root mean squared error (RMSE) of 0.0599 and 0.2075, as well as average R 2 of 0.9037 and 0.9196 on the NASA and self-collecting datasets respectively. To validate its exceptional precision in generalization performance, comparative experiments were conducted with other data-driven methods resulting in over a 50% reduction in average RMSE and more than a 40% increase in average R 2.

1D Magnetic Nickel‐Carbon Matrix Nanotube Composites Derived from Hydrogen‐Bonded Organic Frameworks and Metal–Organic Frameworks for Electromagnetic Wave Absorption

AbstractHydrogen‐bonded organic frameworks (HOFs) and metal–organic frameworks (MOFs) emerge as promising materials for electromagnetic wave (EMW) absorption, due to their high specific surface area and readily modifiable characteristics. In this study, 1D magnetic nickel‐carbon matrix nanotube composites (Ni‐HMCNTs) from a mixture of HOFs and MOFs (Ni‐HMNTs) for EMW absorption are synthesized. The Ni‐HMNTs are achieved via a one‐step method involving a single‐pot solvothermal reaction among melamine, trimeric acid, and nickel nitrate. This process involves a HOF‐to‐MOF transformation, characterized by the penetration of Ni ions into the HOF structure via a competitive coordination reaction, resulting in the hollow structure of Ni‐HMNTs. Subsequent calcination of Ni‐HMNTs yields Ni‐HMCNTs optimized for EMW absorption. Remarkably, with a filling degree of only 10 wt%, 1.2 Ni‐HMCNTs‐700 (heat‐treated at 700 °C) exhibits exceptional EMW absorption properties, with a minimum reflection loss (RLmin) value of −50.4 dB and a maximum effective absorption bandwidth (EAB) of 7.32 GHz (10.64–17.96 GHz). These findings pave the way for further exploration of magnetically modified HOFs/MOFs for EMW applications.

Development of an oral cancer detection system through deep learning

ObjectiveWe aimed to develop an AI-based model that uses a portable electronic oral endoscope to capture intraoral images of patients for the detection of oral cancer.Subjects and methodsFrom September 2019 to October 2023, 205 high-quality annotated images of oral cancer were collected using a portable oral electronic endoscope at the Chinese PLA General Hospital for this study. The U-Net and ResNet-34 deep learning models were employed for oral cancer detection. The performance of these models was evaluated using several metrics: Dice coefficient, Intersection over Union (IoU), Loss, Precision, Recall, and F1 Score.ResultsDuring the algorithm model training phase, the Dice values were approximately 0.8, the Loss values were close to 0, and the IoU values were around 0.7. In the validation phase, the highest Dice values ranged between 0.4 and 0.5, while the Loss values increased, and the training loss began to decrease gradually. In the test phase, the model achieved a maximum Precision of 0.96 with a confidence threshold of 0.990. Additionally, with a confidence threshold of 0.010, the highest F1 score reached was 0.58.ConclusionThis study provides an initial demonstration of the potential of deep learning models in identifying oral cancer.

Production of Functional White Bread Enriched with Various Dietary Fibers with High Consumer Acceptance.

Fiber-enriched breads are inferior to wheat flour (white) breads in terms of volume, taste, and textural characteristics. The aim of this study was to produce functional dietary fiber (DF)-enriched white bread (WB) with high consumer acceptance. Wheat fiber (WF) was added to wheat flour as an insoluble fiber source (5%); polydextrose and inulin were used as soluble fibers at three different concentrations (2, 4, and 6%) individually or in combination. Their effects on dough rheology (farinograph and extensograph properties) and bread properties (volume, baking loss, moisture, texture, color, sensory, and crumb-grain characteristics) were investigated. The addition of WF, polydextrose and inulin had significant effects on dough rheology and bread properties. Hardness, chewiness, cell density, and DF content of breads were generally increased, whereas volume yield, baking loss, moisture and porosity values decreased with increasing DF concentration. The bread with the highest DF content (PD6IN6) contained 7.1 times more DF than WB. According to the results of sensory analysis, except for the sample with 6% concentration of polydextrose and inulin, all the other breads had very high overall acceptance values. Although the breads produced in the study have a high fiber content, their important quality characteristics (moisture content, volume yield, cell density, color values and sensory properties) are similar to those of WB. As a result, the overall quality characteristics of bread made with different dietary fibers were maintained, and functional WB enriched with DF were produced with high consumer acceptance.

Optimization algorithm of power system line loss management using big data analytics

As global energy demand continues to rise and renewable energy sources develop rapidly, the operational efficiency and stability of power systems have emerged as primary challenges in energy management. Line loss within these systems is a critical factor for both energy efficiency and economic performance. This study leverages an electric energy data management platform that facilitates the sharing of archival information, the development of line loss calculation models, and the automated computation of electricity and line loss formulas. This ensures accurate and real-time calculations of line losses in the power grid, supporting multi-time scale analyses and providing timely, comprehensive data for effective line loss management. The platform utilizes theoretical line loss values to identify anomalies, which are categorized into five types: topological relationships, archival information, data collection, electricity metering, and consumption behavior. In response to the abnormal monthly power imbalance rate of 220 kV and 110 KV stations, and the − 3.684% exceeding the − 1% assessment limit, the designed line loss management system service layer does not need to go deep into the bottom layer of the power system. It hides the complexity of the power grid through middleware and provides data, application, and security services.

Trajectory prediction based on the dynamic characteristics and coupling relationships among vehicles in highway scenarios

In dynamic and highly interactive traffic scenarios, vehicle trajectory prediction has become a critical and complex problem in vehicle assistance systems due to the uncertainty of traffic participant behaviour. This study proposes a novel vehicle trajectory prediction method called the Dynamic Coupling-based Long and Short-Term Memory Network (DSKM-LSTM). The method innovatively combines a vehicle dynamics model with the dynamic coupling between vehicles by integrating the intrinsic motion laws of the vehicles with the correlation of the motion parameters (position, velocity, and acceleration) between the vehicles via Kalman filtering. Subsequently, this information is embedded into a Long Short-Term Memory (LSTM)-based encoder-decoder framework to encode and decode historical trajectories with the fused information in order to predict future driving trajectories. Additionally, this paper introduces a dynamic loss function that optimizes the generalization capability and iteration time of DSKM-LSTM by adjusting the threshold value in real time and dynamically updating the loss value. This approach effectively addresses the problem of insufficient objectivity and accuracy in existing vehicle trajectory prediction models and provides a theoretical foundation for generating objective and interpretable trajectories in the field of trajectory prediction. Validation results on three publicly available datasets show that DSKM-LSTM achieves efficient and accurate long-term (5-s) trajectory prediction in complex traffic scenarios (e.g., motorways).

Robust thoracic CT image registration with environmental adaptability using dynamic Welsch's function and hierarchical structure-awareness strategy.

Robust registration of thoracic computed tomography (CT) images is strongly impacted by motion during acquisition, high-density objects, and noise, particularly in lower-dose acquisitions. Despite the enhanced registration speed achieved by popular deep learning (DL) methods, their robustness is often neglected. This study aimed to develop a robust thoracic CT image registration algorithm to address the aforementioned issues. A novel, anatomical structure-aware hierarchical registration. By this method, employing a divide-and-conquer approach, dissimilarity metrics, and regularization terms are selected for different regions based on their distinct image features and motion patterns. These terms are then innovatively reconstructed using the Welsch's function, which allows control over the penalty distribution on the loss values. Subsequently, a novel Welsch parameter update strategy is designed for the task of thoracic CT image registration, enabling dynamic sparsity in registration from coarse to fine levels to accommodate various levels of noise and sliding motion. Moreover, the majorization-minimization (MM) algorithm is used to handle the Welsch terms by constructing surrogate functions based on the current variable values for variable update, thereby reducing the complexity of optimization. Experimental results on publicly available deformable image registration lab four-dimensional CT (DIR-Lab 4DCT) and chronic obstructive pulmonary disease (COPD) datasets with and without noise, showed that our proposed method achieves comparable performance to state-of-the-art methods in noise-free scenarios [1.14 and 1.19 mm compared to 1.14 and 1.35 mm target registration errors (TREs)], while demonstrating superior robustness in the presence of noise (1.78 and 2.38 mm compared to 2.00 and 3.31 mm TREs). Ablation studies also validated the effectiveness of each component in the method. A novel and robust algorithm for thoracic CT image registration has been proposed, which has significant potential for valuable clinical applications, including surgical quantitative imaging.

Genetic validation of a TSC2 immunohistochemistry assay in TSC/mTOR-pathway altered renal tumors.

Pathogenic mutations in the genes associated with tuberous sclerosis complex (TSC)/mTOR pathway are linked to histologically diverse renal cell neoplasms, including eosinophilic solid and cystic renal cell carcinoma (ESC RCC), low grade oncocytic tumor (LOT), eosinophilic vacuolated tumor (EVT), and xanthomatous giant cell renal cell carcinoma (XGC RCC). Here, we validate a TSC2 immunohistochemistry (IHC) assay by comparison to genomic data in these neoplasms. Automated TSC2 IHC was performed on formalin-fixed paraffin embedded (FFPE) tissues from 38 genetically-confirmed TSC/mTOR-associated renal tumors (6ESCs, 16 EVTs, 13 LOTs, 2 XGC and 1 clear cell RCC) and visually scored in a semi-dichotomous fashion compared to internal control tissue. The positive predictive value (PPV) of TSC2 protein loss for underlying pathogenic mutation in TSC2 was 92% (11/12), while the negative predictive value (NPV) of intact TSC2 by IHC for lack of underlying pathogenic mutation in TSC2 was 81% (21/26). Intact TSC2 by IHC was 95% (21/22) specific for absence of underlying pathogenic TSC2 mutation. All the cases lacking TSC2 mutation with intact TSC2 protein had an underlying mutation in TSC1, MTOR or PIK3CA. Loss of TSC2 was 77% (10/13) sensitive for underlying TSC2 truncation mutations and 33% (1/3) sensitive for underlying TSC2 missense mutations. Overall, 73% (8/11) tumors with TSC2 IHC loss and underlying pathogenic alterations in TSC2 showed heterogeneous protein loss, with rare interspersed positively staining tumor cells. These data support TSC2 IHC as a potentially useful assay for the diagnostic workup of renal tumors suspected to belong to the TSC/mTOR-associated subgroups.

Construction of 2D/2D heterostructure with porous few layer g-C3N4 and NiCo2O4 nanosheets towards electromagnetic wave absorption

Developing high-performance materials with ultra-high reflection loss (RL ≤ -65 dB) for electromagnetic wave (EMW) absorption is pivotal to address electromagnetic pollution, but it is still challenging. Herein, a two-dimensional (2D)/2D PFL g-C3N4/NiCo2O4 heterostructure with porous few-layer g-C3N4 (PFL g-C3N4) and ultrathin NiCo2O4 nanosheets has been prepared by self-assembly, hydrothermal reaction, and calcination strategies. The 2D/2D heterostructure exhibits extraordinary EMW absorption property, achieving a reflection loss (RL) value of -68.59 dB and an effective absorption bandwidth (EAB) of 1.92 GHz at a matching thickness of 2.5 mm. As expected, the porous few layer g-C3N4 nanosheets provide rich interface which increases multiple reflection paths and enhances the conduction loss. The cooperative effects of magnetic loss, dielectric loss, and impedance matching contribute to the exceptional EMW absorption property of PFL g-C3N4/NiCo2O4 (2D/2D) heterostructure. The potential of PFL g-C3N4/NiCo2O4 in actual radar stealth is verified through radar scattering cross-section (RCS) simulation. This work paves the way for utilizing 2D/2D heterostructure as an ultra-efficient EMW absorbers.

Polymetallic red mud direct materialization strategy towards zero waste emission: Electromagnetic wave absorption conversion and sodium solidification

Red mud is an industrial hazardous alkaline solid waste, whereas it is rich in polymetallic components showing a high comprehensive utilization value. Direct materialization of red mud towards zero waste emission is a more reasonable and environmentally friendly strategy. In this work, a novel materialization approach of red mud via converting the polymetallic constituents into functional ferrite material by phase reconstruction with MnO2 was proposed. The mineral phase reconstruction, microstructure evolution, reaction interface observation, electromagnetic property, and the materialization conversion mechanism were investigated. It was found that the complicated phases in red mud were transferred to simple forms including the magnetic ferrites (Ca/Na/Al/Ti-bearing Mn ferrite) and weakly magnetic silicates ((Na,Al,Ca)2SiO3) after phase reconstruction. The reconstructed red mud after sintering at 1200 ℃ for 120min in air atmosphere had satisfactory electromagnetic property. Magnetism study demonstrated the soft magnetic property with maximum saturation magnetization of 34.22emu/g and coercivity of only 7.0Oe. Compared with the original red mud, effective electromagnetic wave absorption with reflection loss (RL) values of the reconstructed red mud below -20 dB were satisfied across a wider frequency bandwidth of 5-18GHz, and the minimum RL value was lower as -32.4dB with a thinner veneer thickness of 15mm, highlighting its excellent electromagnetic wave absorption performance. Moreover, Na solidification behaviors indicated that Na was solidified in the sintered product, which can reduce the possible environmental hazards of red mud alkalinity. The novel materialization treatment with zero waste emission exhibits a favorable application prospect with a large red mud batching ratio about 50wt%.

Deep learning model for detection acute cardiogenic pulmonary edema in cases of preeclampsia

&lt;span lang="EN-US"&gt;The physiological changes during the pregnancy period increase the risk of developing pulmonary edema and acute respiratory failure. This condition falls under critical medical emergencies associated with maternal mortality. This study utilized a convolutional neural networks (CNN) architectural model employing chest Xray dataset images. CNN utilizes the convolution process by moving a convolutional kernel of a certain size across an image, allowing the computer to derive new representative information from the multiplication of portions of the image with the utilized filter.&lt;/span&gt;&lt;span lang="EN-US"&gt;To simplify, the vanishing gradient issue occurs when information dissipates before reaching its destination due to the lengthy path between input and output layers. This study was developed model for detection acute cardiogenic pulmonary Edema in pre-eclampsia cases using chest Xray images, implemented using PyTorch, Keras, and MxNet. The validated model achieved its optimum with accuracy 90.65% and binary cross-entropy loss (BCELoss) value of 0.4538. It exhibited an improved sensitivity value of 83.514% using a 5% dataset and a specificity value of 57.273%. This indicates an increase in sensitivity value by 83.514% using a 5% data set and a specificity value of 57.273%. The research results demonstrate an improvement in accuracy compared to several similar studies that also utilized CNN models.&lt;/span&gt;

Enhanced microwave absorption properties of Ti3AlC2 particles modified by a facile preoxidation strategy

MAX phases are considered to be promising microwave absorbing materials in fifth-generation (5G) communications, but their high electrical conductivity causes impedance mismatching, weakening their ability to absorb microwaves. Here, we present a universal preoxidation strategy to improve the impedance matching and the microwave absorption performance of a Ti3AlC2 MAX phase absorbing material. The microwave absorption properties of Ti3AlC2 particles were enhanced after preoxidation at temperatures of 500-700 °C for only 30 min in air, as compared with unoxidized Ti3AlC2 particles. More interestingly, the 600 °C-preoxidized Ti3AlC2 material reached a minimum reflection loss (RLmin) value of -50.56 dB at 8.87 GHz, superior to -12.36 dB at 12.82 GHz for the original Ti3AlC2 material. The preoxidized Ti3AlC2 particles were covered by a thin oxidation layer comprising both amorphous TiO2 (a-TiO2) and rutile TiO2 (R-TiO2). The oxidation layer endows the preoxidized Ti3AlC2 particles with good impedance matching, and a large number of nano-interfaces of a-TiO2/R-TiO2 and micro-interfaces of a-TiO2/Ti3AlC2 also contribute to the dielectric loss mechanism, thus improving its microwave absorption ability. This work provides a practical strategy for the fundamental study and the optimal design of MAX microwave absorbing materials.

Thermal-Hydraulic Characteristics of an Earth Air Heat Exchanger: An experimental analysis

The pipe layout design has a great effect on the thermal-hydraulic characteristics of earth air heat exchanger (EAHE) systems. So, in the current study proposed four new buried pipe design configurations; low to high to low, high to low to high, spiral, and circular, in addition to the straight or uniform for comparison. These five configurations are tested and analyzed experimentally depending on the thermo-hydraulic performance for summer cooling requirements with variation of Re in the range of 18041 – 40843. The results show that changing the uniform design of the EAHE with fixed pipe length enhances both the heat transfer process and pressure loss values. At the same operating conditions, the circular design has the best performance compared to the other ones. For all pipe shapes, the cooling effect increases with the increase of air Re. The thermal- hydraulic performance of the circular design pipe is higher than that of the other pipe designs. The highest coefficient of performance (COP) average values that can be obtained at Re = 18041 is 3.05 for circular shape and enhances by 48.08 % compared to uniform shape. The effectiveness of EAHE with circular shape is improved by about 3.52 % compared to uniform shape at Re = 18041. Spiral design is optimum design based on the Nu value which reaches about 48 with enhancement 12.56% and 0.34 % compared to uniform and circular shapes respectively, at Re = 40843. The hydrothermal performance factor is highest in the case of circular shape with value about 21.9 at Re = 21257. By increasing Re, the drawbacks of the increasing in the total entropy generation are reflected negatively on the exergy efficiency. The specific cost of the circular shape at Re = 40843 is the optimum value by about 0.7 $/W. Spiral and circular shapes have a decrease of CO2 emissions less than uniform shape by percentage varied from 2.93 % to 13.84% for decrease in the Re from 21257 to 40843. It is concluded that using EAHE with four new shapes is highly efficient in increasing cooling capacity and energy consumption in buildings.

Hollow conductive polypyrrole microtubes as microwave absorbents with good seawater corrosion resistance

Conductive polymers materials with hollow micro/nanostructure due to their special electrical properties and corrosion resistance have potential applications in microwave absorption, especially in marine environment. Herein, one-dimensional hollow conductive polypyrrole microtubes (H-PPyM) were prepared by in-situ polymerization of pyrrole monomer with methyl orange (MO) as soft template and FeCl3 as oxidant based on structural regulation strategy. The morphology and conductivity of H-PPyM can be easily controlled by adjusting the content proportion of MO. The results indicated that the surface morphology of polypyrrole changed from random granular to microtubular and the conductivity also gradually rose with the content increase of MO. When the content proportion of MO was 0.25 g, the obtained H-PPyM-0.25 composites possed notable microwave absorption capacity, simultaneously achieving ultrabroad effective absorption bandwidth (EAB, 6.7 GHz) and strong reflection loss value (RL, -33.6 dB) at a thickness of 2.6 mm with the filling content of only 10 wt.%, respectively. Furthermore, the corresponding H-PPyM-0.25 products soaked in corrosive medium (3.5 wt% NaCl solution) for one month still displayed stable tubular hollow structure and excellent microwave absorption performance with RLmin of -43.8 dB and EAB of 6.2 GHz. The research results can not only help to understand the relationship among the morphology and microwave absorption of PPy, but also open a new avenue for preparing excellent seawater corrosion resistant microwave absorption materials.

Effect of theoretical volume fraction (TVF) of reinforcements on Al5083/SiC and Al5083/ZrB2 surface composites produced by friction stir processing

This study focuses on the effects of theoretical volume fraction (TVF) on the microstructure and mechanical properties of silicon carbide (SiC) and zirconium diboride (ZrB2) ceramic reinforced Al5083 surface composites (SC). Al5083-H111 was used as the base material (BM), SiC and ZrB2 were used as reinforcement materials, and TVFs were determined as 5, 10, 15, and 20% for SCs produced by the friction stirring process (FSP). Macrostructure, microstructure, X-ray diffraction (XRD) analysis and mechanical properties such as microhardness, tensile strength (UTS), and wear behaviour were characterised. When the TVF and AVF values of SiC and ZrB2 particles were compared, it was found that the AVFs were lower than the TVFs. Significant decreases in the changes in the SZ areas of SiC and ZrB2 particle SCs were detected depending on the reinforcement size. In the time-dependent axial load graphs of SiC and ZrB2 reinforced samples, load values ranging from 7800 to 8200 N were obtained and it was determined that these values were sufficient for friction heat, hydrostatic pressure, and plasticization in FSP. As a result of mechanical characterisation processes, the microhardness values and wear rates of ZrB2 reinforced SCs in the stir zone (SZ) were higher than SiC reinforced SCs. When the reinforcement particles were compared, it was observed that ZrB2 reinforced SCs exhibited higher microhardness and wear resistance than SiC reinforced SCs. As a result of all tests and investigations, it was determined that the ideal TVFs were 15% for SiC reinforced SCs and 5% for ZrB2 reinforced SCs. The microhardness value of ZrB2 reinforced SC with 20% TVF was 119.6 HV, while the UTS and volume loss values of ZrB2 reinforced SC with 5% TVF were found to be the highest values with 305.86 MPa and 1.83 mm3, respectively. Compared to BM, these values showed significant improvements in mechanical test results, especially in wear behavior. The results obtained showed an improvement of 55% in microhardness, 3.3% in UTS values, and 309% in wear behavior.

Classification of Duration in Global Terorism using ResNet

Terrorism is a global threat that affects the political, economic, and social stability of many countries. The number of victims killed is based on the duration of the terrorism incident. This study uses the Residual Network (ResNet) model to classify terrorism incidents based on the duration of the incident (less than 24 hours and more than 24 hours) using the Global Terrorism Database (GTD) dataset. The GTD data used covers terrorism incidents from 1970 to 2017, with a total of 181,691. After preprocessing the data by converting categorical features to numeric and removing missing values, the data was divided into training, validation, and test sets with a composition of 70%, 15%, and 15%. The results show that the ResNet model is able to achieve a validation accuracy of 99.61% and a validation loss value of 0.0183. These findings show that the ResNet model is effective in classifying the duration of terrorism incidents and has the potential to be used in the development of better terrorism prevention systems.