Current Approaches in Engineering Research and Technology Vol. 2

Remote sensing (RS) data and crop classification techniques provide useful information for crop yield estimation and prediction. Deep learning (DL) has seen a massive rise in popularity for remote sensing (RS)-based applications over the past few years. However, the performance of DL algorithms is dependent on the optimization of various hyperparameters since the hyperparameters have a huge impact on the performance of deep neural networks. The impact of hyperparameters on the accuracy and reliability of DL models is a significant area for investigation. The study region Charsadda is located in the Khyber Pakhtunkhwa, province of Pakistan. Five dates were chosen for satellite imagery in this investigation to capture the reflectance of crops at various growth stages. In this study, the grid Search algorithm is used for hyperparameters optimization of long short-term memory (LSTM) network for the RS-based classification. The hyperparameters considered for this study are optimizer, activation function, batch size, and the number of LSTM layers. In this study, over 1,000 hyperparameter sets are evaluated and the results of all the sets are analyzed to see the effects of various combinations of hyperparameters as well as the individual parameter effect on the performance of the LSTM model. The performance of the LSTM model is evaluated using the performance metric of minimum loss and average loss and it was found that classification can be highly affected by the choice of optimizer; however, other parameters such as the number of LSTM layers have less influence. This study shows that tuning the hyperparameters improves the model performance. The LSTM model for RS data yields the best performance with Adam, Nadam, RMSProp, and Adamax optimizers whereas it does not perform well with SGD, Adagrad, and Adadelta.

The welding process induces changes in the Heat-Affected Zone (HAZ) owing to thermal effects. This implies alterations in mechanical properties and microstructure based on the magnitude of absorbed heat and cooling time. The analysis presented in this article reveals that the base metal, initially composed of ferrite and pearlite, undergoes a change in grain size after welding. During welding, the heat produced during the process can affect the microhardness and the microstructure of the material. The change in the microstructure and the microhardness can be discovered by carrying out a microhardness test on the welded sample and comparing changes in the three different zones i.e the base, the weld and the Heat affected zone (HAZ), or by carrying out a microstructural examination on the welded sample and see the grain dispersion in relation to their sizes. In this work, the weld quality of manual arc welded samples of low-carbon steel St3sp destined for bridge construction to be used in Cameroon has been investigated. After a chemical analysis of the material, a microhardness test and a microstructural examination were also done. Results show that a composition of pearlite and ferrite was seen with a composition of 20/80 respectively. For weld zone and HAZ it changes due to thermal processes. So the micro-structure analysis shows that the base metal is a ferrite and pearlite having a grain size of 11-12 on a scale corresponding to an average grain diameter \(\approx\)of 7 microns. The structure of the weld metal is also made up of ferrite and pearlite with columnar crystals of cast metal. The HAZ is made up of Widmanstätten. The width of the HAZ zone is about 1,5mm in different areas of heat affected zone and is observed fine-grained ferrite-pearlite structure with a high degree of dispersion. A micro-crack was revealed with a length of 1,7 mm in the HAZ of sample number 7 and a 1,2 mm length of micro-crack in the weld zone of this same probe was also revealed. The modeling of the micro-crack shows that the velocity of its propagation in the welded zone is higher as much than that in the heat-affected zone i.e. in the welded zone is estimated at 64.59m/s, while in heat affected zone is 0,354.1 m/s. This means that in the absence of welded and environmental defects, failure of structure will be common in the welded zone.

Centered on its inherent data sharing and low latency features, cloud infrastructure is considered as an effective alternative to conventional information technology. Cloud service providers (CSPs) like Amazon, are capable of providing cloud users with various services by integrating powerful data centers. Users may utilize high-quality software to move their local data processing systems to cloud storage and save considerable investments in their local infrastructures. Annotation techniques by utilizing the pairs of meaning attributes are usually more descriptive, as they provide more details than the untyped methods. A new solution to use more concise queries with such annotations is the "pay-as-you-go" querying technique in data spaces.

With the explosion in increased population migrating to cities, housing infrastructure poses one of the biggest challenges in India as well as other countries. The need for a safe space to live which transforms the quality and well-being reducing environmental challenges is a necessity. This article advocates for a paradigm shift in construction methodologies, emphasizing the adoption of emerging technologies to build faster while delivering superior quality homes at an economically viable scale. Central to this transformation is the utilization of Mass Timber Construction within a sustainable construction framework. By harnessing the potential of mass timber technology, we aim to mitigate the environmental impact of traditional construction practices and usher in a new era of carbon-neutral buildings and faster construction.

The purpose of this research highlights about cellulose and cellulignin fibres obtained from sugarcane bagasse (SCB) waste can be used as reinforcing filler in a thermoplastic polymer matrix. Natural fiber composites are one of the most appealing replacements for non-biodegradable glass and carbon fibers in the fabrication of thermosetting and thermoplastic composites. In the recent decade, there has been an increase in global warming, environmental changes, and other issues. Environmentally friendly products, such as natural composite materials, are being developed by researchers and academics to protect life on the planet. The injection method was used to create the low-density polyethylene (LDPE) and sugarcane bagasse (SCB) composites. Fiber loading was set to be varied from 10 to 30 wt%. To improve interfacial bonding, the fibres were chemically modified using an alkali treatment, and the effects on the fiber/matrix interaction were evaluated using scanning electron micrographs (SEM). Tensile, impact, and hardness were used to determine the mechanical properties and corrosion tests. The study found that sugarcane bagasse fibers, like other natural fibers, reinforce polyethylene. The treated SCB fibers' tensile strength and modulus were found to be greatly increased by around 13% and 196%, respectively, when compared to plain LDPE. This was owing to the observed improvement in interfacial adhesion between the fiber and matrix. The impact resistance and hardness of the composite enhanced by 55.28% and 26%, respectively, over neat LDPE. According to SEM analysis, the alkali treatment affected the morphology of fibers.

Infill wall frames are widely used structures, including in earthquake-prone locations. The role of infill walls is often neglected in frame planning. However, infill walls play a role in improving frame performance under cyclic lateral loads. The material forming the infill wall, the type of connector between the column and the infill wall, and the connector distance determine the behavior of the frames. These things need to be analyzed to understand the performance of the frames. This research aimed to obtain the performance level of framed masonry wall (FMW) and framed lightweight concrete wall (FCW) structures to withstand cyclic lateral loads. The research was carried out using finite element-based software. The research results showed that FMW and FCW were highly ductile. FCW had a higher strength than FMW. However, it was not more ductile than FCW. The cumulative energy dissipation of FCW was 56.85% greater than FMW because it could bear lateral cyclic loads better. This indicates that masonry and lightweight concrete have the potential to infill walls for frames in earthquake-prone areas.

The permeable volume and trans-membrane pressure difference of all 3520 days, from October 2011 to November 2021, in an A²/O-MBR RWTP (recycled water treatment plant) in Xi'an Siyuan University have been indiscriminately used to study an evaluation method of MBR hollow fiber membrane. The 1 m³permeable volume of 1000 m²membrane area at 1 day and 1 kPa trans-membrane pressure (TMP) difference is defined as one industrial permeability, 1 VMD.  The VMD of every day is directly calculated by using the daily computer's records of the RWTP.  After excluding some anomalies from the original data, an arithmetic average of each 25 days (as a group unit) effective VMD was calculated.  Then, group units are reduced into annual units.  After four years, a power equation is fitted into the annual VMD attenuation equation of the previous four years of RWTP operation.  The calculation of the annual VMD attenuation equation is straightforward, simple, and convenient.  The VMD declined annually by about 0.78.  The TMP increased annually by about 0.66 kPa.

In recent years, rural communities in China have been actively exploring a novel approach to elderly care that integrates treatment with health preservation. For instance, in 2018, the number of licensed physicians and registered nurses per 1000 people in rural areas was significantly lower than in urban areas, indicating a shortage of medical professionals. This study aims to contribute to the sustainable development of rural elderly care by introducing smart technology, specifically fall posture monitoring, into public services and facilities within rural communities. There are two main types of intelligent technologies used for monitoring the health of elderly individuals in their living environments: vision-based human activity recognition (HAR) and sensor-based HAR. Additionally, the focus of this study is on addressing a critical issue in elderly medical care: the timely feedback and treatment of falls. To begin, we conducted a comprehensive review of the current status and challenges associated with the application of fall posture monitoring technology. Additionally, we examined the environmental factors that contribute to the risk of falls in public spaces for the elderly. These assessments serve as the technical and environmental foundation for developing the proposed service framework. Our research was conducted from two primary perspectives: the supply of service resources that combine treatment with health preservation and the identification of risk factors associated with outdoor public spaces in the community where falls are likely to occur. Data for this study were collected through behavior mapping and field interviews. In conclusion, we presented a constructive logic for the development of a public service field that effectively combines treatment with health preservation. This logic encompasses the integration of technology applications, resource coordination, and improvements to the physical environment. The findings from this study provide a scientific basis for the construction of public service fields in “smart villages” and serve as practical references for similar villages striving to adopt this innovative model. This approach has the potential to improve the quality of care for elderly individuals in rural communities and promote the integration of medical treatment and care. By leveraging the insights gained from this research, it is expected that rural communities would be better equipped to address the challenges of elderly care and facilitate the widespread adoption of this integrated care model.

This article discusses the errors caused by several flux limiters in advection-diffusion flow solutions. Numerous affordances have been developed to reduce the spurious oscillation during the last decade to solve various problems arising in mathematical physics. Flux limiters are widely used in numerical simulations to prevent spurious oscillation in the flow with strong property gradients. However, applying a flux limiter on flow without a strong property gradient such as advection-diffusion flow can cause errors due to the action of the limiter on the higher-order part of the flux. A method for applying one-dimensional limiters to two-dimensional unstructured mesh was also suggested. By contrasting a test case's finite volume solution with a reference solution, the error was calculated. According to the study, second-order finite volumes with flow limiters had greater calculation errors than those without limiters.

However, the error of third-order finite volume with flux limiter is less than that of second-order without flux limiter. Among the flux limiters tested in this study, Venkatakrishnan’s flux limiter produces the highest error, followed by Van Leer’s limiter, EULER and SMART limiter.

A novel approach is proposed to improve lane marking identification in autonomous driving systems by combining deep learning-based segmentation with traditional lane detection methods. This approach aims to address challenges faced by each technique individually, such as CNNs struggling with precise localization and traditional methods facing scalability issues. By integrating segmentation with handcrafted features and specialized fitting, the proposed method enhances network convergence speed and location accuracy. A unique lane fitting method based on convergent line prediction is introduced, particularly beneficial for challenging highway conditions. Experimental evaluations on four datasets demonstrate the effectiveness of this approach, showcasing notable improvements in robustness and accuracy in lane marking detection.