Purpose Fused deposition modeling (FDM) has gained much attention in recent years for producing porous scaffolds due to its customization, cost-effectiveness and compatibility with biodegradable materials. The purpose of this research is to investigate the influence of infill density, raster angle orientation and infill pattern on the mechanical and dynamic behavior of composite scaffolds. This study aims to optimize scaffold designs for applications requiring enhanced mechanical strength and vibration characteristics. Design/methodology/approach In this research work, carbon fiber-reinforced polylactic acid composite scaffolds are fabricated with different infill densities of 40%, 50% and 60% and raster angle orientations of 0°, 45° and 90°. Findings The free vibration test is performed on the scaffold printed with different infill patterns of circle, square and hexagonal shapes and infill densities of 40%, 50% and 60%. The natural frequency of the scaffolds produced by PLA/CF composites is determined experimentally. The scaffold (V9) with a hexagon infill pattern and 60% infill density has the highest value of natural frequency of 19.53 Hz. The mechanical properties, such as tensile, flexural, impact and hardness are determined experimentally. Originality/value The results showed that the composite scaffold (S9) with 60% infill density and 90° raster angle orientation has obtained high mechanical properties when compared with other scaffolds. Using scanning electron microscopy, the fractured composite scaffolds are analyzed to visualize the adhesion behavior of carbon fiber and polymer matrix.

Advanced techniques in medical image segmentation often leverage deep learning methodologies. UNet and its variants plays a major role in image segmentation of medical images. UNet based networks have so many limitations that there needs an improvement in the segmentation performance. The proposed UNet++ architecture integrates dense skip connections and nested convolutions to enhance feature representation and improve accuracy of segmentation. Its superior performance and versatility make it a precious tool for assisting clinicians in detection of diseases and planning for treatment, ultimately improving patient outcomes in neuro-oncology. In this paper, the new method called GAAUNET++ (Gated Axial Attention UNet++) have been proposed with enhancements like 1. The inclusion of the Axial Attention gate aims to enhance performance while also capturing global features of the image. 2. Different metrics like precision, dice coefficient, recall and IoU have been used. The results shows that the proposed approach achieves finer performance in segmentation and accuracy also has been improved.

An open network known as the "energy internet" links every component of the whole energy supply chains, from the generations. Due to their ability to mimic regional flow dynamics that have an impact on wind farm production, regional meteorological models are increasingly being used as a general tool for wind resource forecasting. In this study, higher vertical and horizontal resolutions WRF (weather research and forecasting) paradigm simulation are used to anticipate and validate production for a genuine onshore wind farm. This paper proposed a DeepFore which is a power forecasting system for hybrid renewable energy systems. Initially, the dataset is generated by the hybrid system. This data is preprocessed to improve the quality of the data by incorporating, filtering and outlier detection techniques. Then, this enriched data is fed into K++ means clustering algorithm to separate the normal data from faulty data. With the normal and original data, Teaching-Learning based optimization algorithm attempts to realize the optimal features which are important for forecasting. Finally, Deep SARSA which is deep reinforcement learning algorithm is incorporated to determine the power generated by the hybrid system. Better winds energy prediction estimations enable more efficient utilization of the produced electricity, according to computational models.

The number of possibilities to analyze educational data using data mining techniques is expanding, with the goal of improving learning outcomes. There is an explosion in data produced by online and virtual education, e-learning platforms, and institutional IT. Using these statistics, teachers could gain valuable insights into their students' learning habits. Academic performance of students and other useful information can be analyzed with the help of educational data mining. Model training consists of three primary steps: data preprocessing, feature selection, and training the model. To eliminate unwanted problems like noise and redundant attributes, data preparation is necessary. By prioritizing which features to calculate, the mRMR algorithm lowers calculation costs. Feature selection plays a crucial role in training A-CNN-BiLSTM models. The suggested approach routinely outperforms BiLSTM and CNN, two state-of-the-art algorithms. With a data accuracy percentage of 96.57%, it's clear that there was a significant improvement.

This work addresses the experimental investigation of the mechanical, free vibration, electrical resistivity, and moisture uptake characteristics of Phoenix sp. fiber-reinforced polyester composites (PFRPC) fabricated using the compression molding method. The polyester matrix (PM) was added with Phoenix sp. fibers (PSFs) of different content (5, 10, 15, 20, and 25 wt%) and length (10, 20, and 30 mm) and studied their effect on the aforesaid properties. The results reveal that the composites having 20 wt% of 20 mm length PSFs exhibited optimum mechanical properties. At this loading, the ultimate tensile strength and modulus were 48.36 MPa and 2.86 GPa, respectively, while the flexural strength and modulus were 83.89 MPa and 2.91 GPa, respectively. Furthermore, this composite exhibits an impact strength of 22.04 kJ/m(2) and an interlaminar shear strength of 41.88 MPa. The increase in PSF content and length resulted in greater stiffness and decreased mass of the composites, leading to an enhanced natural frequency. The inclusion of PSFs showed a decline in electrical resistivities due to their moisture-absorbing capability. In contrast, the hydrophilic behavior of PSFs led to a rise in the water absorption rate of the composites due to the increase in fiber variables. Scanning electron microscopy examination shows that short fiber-reinforced composites have more fiber pull-outs due to the limited area of contact, whereas long fiber-added composites possess better bonding with the PM.

The acoustic properties of the Fused Deposition Modelling (FDM) printed PLA wood composite was investigated. Initially tensile and flexural of wood PLA composite was studied with respect to varying layer thickness (0.15 mm, 0.20 mm, and 0.30 mm), infill density (30 %, 60 %, and 90 %), and pattern (Layer, Triangle, and Hexagon). The outcomes demonstrated that the specimen produced with a hexagonal pattern, 90% infill density, and 0.2 mm layer thickness had the highest tensile (16 MPa) and flexural strength (16 MPa). Utilizing this optimized parameter, micro-perforated panels were printed and acoustic properties were studied. Five specimens with a 3 mm thickness, various perforation diameters (5 mm, 4 mm, and 3 mm), and architecturally tapered perforations were fabricated. Using the impedance tube approach, the sound transmission loss and sound absorption coefficients were measured. The findings indicate that, in comparison to all the printed specimens, tapered type perforation with an exterior diameter of 5 mm and an internal diameter of 4.7 mm showed highest sound absorption coefficient of 0.60 Hz. A viscous loss is obtained by its convergent hole diameter reduction, which results in sound attenuations and is easily absorbed in the micro-perforated panel. Similar to this, the specimen printed with smaller perforation diameters (3 mm) had a high sound transmission loss of 79 dB. The small diameter of the perforations prevented the passage of sound waves. The current study is anticipated to lay the groundwork for extensive future research on these classes of materials, potentially serving as a catalyst for advancements in FDM based polymeric materials research and development.

Acrylonitrile butadiene styrene (ABS) polymer and carbon fiber reinforced acrylonitrile butadiene styrene (CF/ABS) spur gears were 3D-printed using fusion deposition modeling (FDM) with different fillet radii of 0.25, 0.50, and 0.75 mm. The performance of the fabricated gears was studied with the effect of fillet radius on varying load and speed conditions. The thermal properties of the gears were also investigated. The results indicated that 3D-printed CF/ABS spur gear exhibited better performance than the pure ABS. The 3D-printed CF/ABS gear with fillet radius of 0.25 mm recorded the highest wear and thermal stresses. However, the optimum performance was exhibited by the gear sample with highest fillet radius of 0.75 mm. Repeated gear tooth loading during service caused an increase in gear temperature due to the hysteresis and friction. Using optical microscopy, the tooth structures of both 3D-printed ABS and CF/ABS spur gears were analyzed before and after loading conditions to establish their failure mechanism. Evidently, various applications of the FDM 3D-printed spur gears depend on their different performances under loads and operating speeds. The methods and findings of this work can be regarded as helpful for future related work related to cellulosic reinforcing particles in a polymer matrix.

Purpose Additive manufacturing of polymer composites is a transformative technology that leverages the benefits of both composite material and 3D printing to produce highly customizable, lightweight and efficient composites for a wide range of applications. Design/methodology/approach In this research work, glass fiber-reinforced polylactic acid (PLA) filament is used to print the specimen via fusion deposition modeling process. The process parameters such as infill densities (40%, 50% and 60%) and raster angle/orientations (0°, 45° and 90°) are varied, and the specimens for tensile, flexural, impact, hardness and wear testing are prepared as per their respective ASTM standards. Findings The results revealed that with an increase in infill density, the mechanical properties of glass fiber-PLA specimens increase progressively. Optimal tensile properties and flexural properties are obtained at 0° and 90° raster angle orientations and 60% infill density. Minimum wear rate is achieved at 0° raster angle orientation and it increases at 45° and 90° raster angle orientations. Originality/value Using SEM, the microscopic analysis of the fractured specimen was analyzed to study the interface between the fibers and matrix and it indicates the presence of good adhesion between the layers at 60% infill density and 0° print orientation.

A blockchain-based trust management model has been developed for preserving location privacy in Vehicular Impromptu Networks (VANETs), a crucial component of Intelligent Traffic Systems (ITS). VANETs offer high mobility, but security concerns have remained unresolved, especially when leveraging Location-Based Services (LBS). Thanks to this technology, cars can request LBS with authentication while keeping their personal data secret. Anonymous shrouding zones are created to protect vehicle privacy, blockchain technology is employed to improve data security, and a trust management algorithm is implemented to control vehicle behavior. Through extensive testing, the system’s resilience to various trust model attacks has been demonstrated, effectively safeguarding vehicle privacy. Simulation results further confirm the viability and effectiveness of the proposed system in real-world scenarios.

Fused filament fabrication is a promising additive manufacturing technology and an alternative to traditional processes for the fabrication of polymer and fiber-reinforced polymer composites. In this work, the effects of process parameters such as layer thickness, infill density, and infill pattern on the ageing and free vibration characteristics of three-dimensional printed composites were investigated. It was observed that the water absorption rate is higher in acrylonitrile butadiene styrene (ABS) printed specimens compared to carbon fiber reinforced acrylonitrile butadiene styrene (CF/ABS) specimens due to the effect of carbon fiber which acts as a strong hydrophobic material. The free vibration characteristic of the printed composite specimen is found as per American Society for Testing Materials standards. From the results, it is found that the 5 % addition of carbon fiber, hexagonal pattern, and 0.30 mm layer thickness show an increase in the vibration behaviour of the composites compared to the specimen printed without reinforcement. Experimental modal analysis was carried out on a cantilever beam-like sample and revealed that the addition of fiber has enhanced natural frequencies and damping ratio.

A slotted cavity-backed Substrate Integrated Waveguide (SIW) antenna is suggested for use in wireless applications. The SIW cavity-backed antenna that is being proposed is designed for multiband operations. The operational frequencies for UMTS, WLAN, C-band and wave applications are 2.15 GHz, 2.7 GHz, 4.2 GHz, and 6.8 GHz respectively. Two typical modes are provided by a rectangular cavity (i.e., TE110 and TE120). The SIW cavity's current distribution is altered by loading slots on top of the cavity. The traditional modes couple together without enlarging the antenna and provide a new resonance frequency (i.e. Hybrid mode). As a result, the proposed antenna can operate in several bands, and the mode theory method has been used to explore radiating modes.

Additive manufacturing has the capacity to manufacture functional parts with complicated geometries, fused filament fabrication is a viable additive manufacturing method and an alternative to standard processes for the creation of polymer and fiber-reinforced polymer composites. The influence of process parameters such as layer thickness, infill density, and infill pattern on the interlaminar bonding performance of three-dimensional printed composites was examined in this study. Due to the existence of high porosity and inadequate layer to layer bond, interlaminar shear strength values increase as layer height increases from 0.15 mm to 0.2 mm and decrease by 0.3 mm. The specimens were also subjected to a wettability test to determine the printed material’s adhesive behavior. Scanning electron microscope was used to perform fractography analysis, and fractured specimens were seen. The test findings revealed that carbon fiber reinforced ABS specimens have good interlaminar shear strength and layer adhesive. When comparing carbon fiber reinforced ABS specimens to ABS specimens, the test results demonstrated that interlaminar shear strength and good adhesion between the layers are attained in carbon fiber reinforced ABS specimens.

Education is essential for the development and prosperity of every nation. The minds and hearts of those who receive an education are molded in the process. It empowers people and makes them want to achieve their goals. Traditional higher education functions similarly to the brick-and-mortar business model in that students acquire a uniform education by physically attending classrooms on a regular (full- or part-time) basis. However, the standard educational system has many problems, and major improvements are on the horizon. One possible aspect of the future educational system is the proliferation of online education. The proposed strategy makes use of feature selection, preprocessing, and model training. Field extraction, data cleaning and filtering, user identification, and data synthesis are among preprocessing techniques employed by our team. By locating the correlation matrix's eigenvalues and eigenvectors, PCA can be used for feature selection. After deciding on a set of features, the models are trained via BiRNN-CNN. CNN and BiRNN are two common alternatives, although the proposed method surpasses them both. The proposed method was successful to the tune of 98.23%.

Agriculture is considered one of the primary sectors in India. Especially rice is the primary stable food widely cultivated and consumed by 50% of the Indian population. Paddy crop is susceptible to several diseases like other crops that indirectly affect agricultural development and economic loss. To address this limitation, in this study, we have applied deep learning algorithms for the recognition and classification of diseases at an earlier stage. The paddy plant disease diagnosis is made by applying image processing techniques to identify the changes in leaves and its texture. We have used pre-processing techniques for segmentation, feature extraction and classification of disease. First, we have to perform data augmentation to improve the number of images in the dataset. Second, the segmentation of plant leaves are performed to identify the test infected region. Then, we applied CNN algorithm to extract features from the data. After feature extraction, we trained different classification algorithms to recognize and classify the images into disease and non-disease images. The application of machine learning and deep learning algorithms helps in the precise location and identification of infectious leaves that help farmers to use automated methods for disease diagnosis.

One of the essential parts of electrical hardware utilized in the operation of an energy system is a transformer. Transformers are monitored regularly to prevent issues that are prohibitively expensive to repair and that may result in the loss of electricity. With the distribution transformer, serving as an example of a load current, temperature, and oil level indicator, the primary objective of this article is to use the Internet of Things (IoT) to monitor and uncover errors in the distribution networks in real time. This is a unified system that keeps track of different characteristics that have an immediate bearing on the transformer. The three main challenges that contribute to the distribution transformer failure are overloading, oil temperature load current, and inadequate transformer cooling. It is challenging to manually assess the status of every transformer in the current electric networks due to the widespread distribution of the transformers. Different types of sensors are utilized in order to keep track of the temperature, oil level, current, and voltage. The microprocessor acts in response to the interpretations provided by the sensor in order to maintain a consistent working environment for the transformer. The system that has been suggested has a cheap price point, is simple to operate, and can inspect and show data using IoT.

Metal Matrix Composite has evoked a keen interest in potential applications in aerospace and automotive industries, owing to their superior strength-to-weight ratio and temperature resistance. Nowadays, welding strength on composite materials is more essential. So, in this project, we consider the effect of TIG welding on aluminium matrix composite (Al & Sn). The TIG welding on aluminium alloys like (Al 6061& Al 6063) has lost its welding strength by around 30% in Al 6063 & 50% in Al 6061. To regain the welding strength, we need a heat treatment process like hardening and tempering, which is a more costly and time-consuming one. To eradicate this problem, we will mix the malleable Tin (Sn) in different ratios of 90:10 and 85:15 for the aluminium alloys (Al 6061 & Al 6063). Then analyzing the effect of TIG welding on the aluminium metal matrix, the welding strength of the aluminium metal matrix composite is increased by 5% compared to the previous material.

In the recent days, super alloys especially nickel based materials are used more than 50% of aerospace gas turbine components such as turbine disc, blades etc., It becomes very hard to shape these materials with the use of traditional machining processes due to its improved strength at higher temperature. To overcome the issues faced during conventional machining, the various advanced machining techniques are tried for machining these super alloys. In the present study, Inconel 738 was cut by wire electrical discharge machining using 0.25 mm diameter copper wire. Demineralized water was used as dielectric fluid between tool and workpiece electrode. During the process, voltage, wire feed rate, time of pulse on and pulse off were adjusted at four different values and totally sixteen slots were cut to analyze the machining characteristics. The machined surfaces were tested for its surface finish, rate of material removal and kerf width. The ANOVA was performed using Minitab software to find out the optimized variables and percentage contribution of each parameter in providing the influencing results. Wire feed rate was the most influencing parameter to have the lowest kerf width. As far as Material removal rate, the four parameters were had the significant impact in increasing the MRR. Voltage is the important process parameter to reduce the surface roughness.

The main objective of this work is to understand how the tool wear and surface roughness are influenced by various cutting fluids and machining parameters in turning EN8 SAE/AISI 1040 steel. Cutting fluids should be chosen by acidic nature test and viscosity test. It should have proper lubricity and act as a coolant. Vegetable oils like groundnut, coconut, and sunflower are considered to check their properties. Among these oils, groundnut and coconut oils were selected based on their properties. Experimental studies on the performances of both newly developed environmentally friendly vegetable-based cutting fluids (coconut oil and ground nut oil) and commercial cutting fluids in turning processes were reported. Performances of cutting fluids were compared with respect to surface roughness, cutting and feed forces and tool wear during longitudinal turning ofEN8 SAE/AISI 1040 steel. Experimental results were also compared with dry cutting conditions. Based on the results, the best-cutting fluid was selected.

One of the most significant issues in the telecom industry is jumping of customer to another network called customer churn. It has a direct impact on the revenue of the business, particularly in the telecom sector. As a result, businesses are attempting to develop strategies for anticipating customer turnover. Therefore, it is crucial to identify the factors that influence customer churn. Our paper demonstrates how to identify customer attrition effectively in the telecom sector. Our article includes a churn ANN model, which helps telecom businesses manage the individuals who are willing to churn, as well as some practical data analysis, which can be used to draw conclusions from the data. This prediction model with a high accuracy score can be created using neural networks, machine learning algorithms, artificial intelligence and other technologies.