Search

The soil quality plays a crucial role in providing essential nutrients for crop growth and ensuring a bountiful yield. Identifying the soil composition, which includes sand, silt particles, and the mixture of clay in specific proportions, is vital for making informed decisions about crop selection and managing weed growth. Furthermore, soil pollution from emerging contaminants presents a substantial risk to water resource management and food production. Developing numerical models to comprehensively describe the transport and reactions of chemicals within both the plants and soil is of utmost importance in crafting effective mitigation strategies. To address the limitations of traditional models, this paper devises an innovative approach that leverages deep learning to predict hydroponic and soil compound dynamics during plant growth. This method not only enhances the understanding of how plants interact with their environment but also aids in making more informed decisions about agriculture, ultimately contributing to more sustainable and efficient crop production. The data needed to perform the developed hydroponic and soil compound prediction model is acquired from online resources. After that, this data is forwarded to the feature extraction phase. The weighted features, deep belief network (DBN) features, and the original features are achieved in the feature extraction stage. To get the weighted features, the weights are optimally obtained using the Iteration-assisted Enhanced Mother Optimization Algorithm (IEMOA). Subsequently, these extracted features are fed into the Multi-Scale feature fusion-based Convolution Autoencoder with a Gated Recurrent Unit (MS-CAGRU) network for hydroponic and soil compound prediction. Thus, the hydroponic and soil compound prediction data is attained in the end. Finally, the performance evaluation of the suggested work is conducted and contrasted with numerous conventional models to showcase the system’s efficacy. [ABSTRACT FROM AUTHOR]

Ambient assisted living (AAL) is a groundbreaking approach that harnesses the power of smart technology to offer all-encompassing care and support for elderly and differently abled individuals in their day-to-day lives. Progressive innovation in AAL solutions can facilitate and support day-to-day routines, expanding the time they can live autonomously and supporting proficiency. This research mainly analyzes AAL's significant role in tending to the exceptional difficulties these populations face. AAL frameworks incorporate an array of sensors, gadgets, and intelligent calculations that help monitor current circumstances and exercises, empowering early recognition of peculiarities, fall counteraction, and customized help. This research introduces a novel attention transfer learning-based crossover chimp (ATL-CC) algorithm for AAL, which combines crossover-based chimp optimization with a transformer-based model for transfer learning, integrating an attention mechanism. The ATL-CC algorithm aims to enhance activity recognition and classification within AAL environments. Precision, accuracy, recall, root mean square error, and F1-score are evaluated, where accuracy attains the value of 98.9%, precision attains the value of 97.4%, recall attains the value of 98%, and F1-score attains the value of 96%. Overall, AAL arises as a promising arrangement that upholds the deprived and advances respect, independence, and inclusivity in maturing and various societies. [ABSTRACT FROM AUTHOR]

Aluminium foams possess multi-functional properties and a low specific weight, making them one of the most suitable choices in the application domain of the automobile and aviation sectors, vibrating machining, and structural parts. Compared to traditional fabrication routes, friction stir processing (FSP) is gaining acceptance as it is a cost-effective, highly efficient, and innocuous process to fabricate the foam precursors from the bulk substrate. In the current study, FSP was utilized to develop a precursor with MgCO3 powder acting as the blowing agent. The FSP experiments were performed as per Taguchi's L8 orthogonal array. The precursor was heat treated in an electric furnace at a holding temperature of 650 °C for 10 min. After the post-heat treatments, this precursor resulted in a porous structure due to the evolution of CO2 gas from the composite. The simultaneous effect of tool rotation speed, traverse speed, and shoulder diameter was investigated on the pore size and porosity of the foam produced. The composite parameter "unit stirring" is found to be closely related to the processed zone (PZ) and volume processing rate of the processed zone, pore size, and the degree of porosity. The highest porosity of 16.67% was obtained with an average pore size of 10.5 µm. The largest pore size, 17.8 µm, was observed to be associated with a porosity of 14.40%. The analysis of the Kiviat plot revealed that the values of the PZ area and volume processing rate possess a polar symmetry with unit stirring. The pore size and pore density were both found to be symmetrically distributed about the unit stirring. [ABSTRACT FROM AUTHOR]

In modern scenarios, Industry 4.0 entails invention with various advanced technology, and blockchain is one among them. Blockchains are incorporated to enhance privacy, data transparency aswell as security for both large and small scale enterprises. Industry 4.0 is considered as a new synthesis fabrication technique that permits the manufacturers to attain their target effectively. However, because numerous devices and machines are involved, data security and privacy are always concerns. To achieve intelligence in Industry 4.0, blockchain technologies can overcome potential cybersecurity constraints. Nowadays, the blockchain and internet of things (IoT) are gaining more attention because of their favorable outcome in several applications. Though they generate massive data that need to be effectively optimized and in this research work, deep learning-based techniques are employed for this. This paper proposes a novel mutated leader sine cosine algorithm-based deep convolutional neural network (MLSC-DCNN) in order to attain a secure and optimized IoT blockchain for Industry 4.0. Here, an MLSC is hybridized using a mutated leader and sine cosine algorithm to enhance the weight function and minimize the loss factor of DCNN. Finally, the experimentation is carried out for various simulation measures. The comparative analysis is made for Best Tip Selection Method (BTSM), Smart Block-Software Defined Networking (SDN), and the proposed approach. The evaluation results show that the proposed approach attains better performances than BTSM and SDN. [ABSTRACT FROM AUTHOR]

Currently, the furious competitiveness in global markets and speedy improvements in information technology lead to shorter product life cycles, lesser transportation capabilities, and increased demands as well. In most business scenarios, the supply chain network is becoming one of the most vital focusing areas. In the supply chain network, blockchain technology is a promising solution for secure information sharing. However, it is a bit critical in maintaining security at each level of the blockchain and hence the public–private–key cryptography is more commonly preferred. This study intends to construct a new privacy preservation model in the field of supply chain networks based on blockchain technology by undergoing three major phases, namely, (a) data sanitization, (b) key generation, and (c) restoration. Further, the sensitive fields in the original data are selected during the data sanitization phase, and in the key generation phase; the optimal key is generated to hide the selected sensitive fields. The hidden data with the secured key is transferred from the source (manufacturer) to destination (vendor) in the supply chain network via the blockchain. The restoration process takes place in the receiver side with the help of the same key. Among all these data flow methods, the optimal key selection is the critical issue that needs to be overridden to make the data transmission secured. As a novelty, a new optimization algorithm referred to as Whale with New Crosspoint‐based Update (WNU), which is the advanced version of Whale Optimization Algorithm (WOA), is developed here to select the optimal key. Finally, the proposed WNU model is analyzed in terms of Hiding Failure (HF) rate, Information Preservation (IP) Rate, and False Rule generation (FR), and Degree of Modification (DM). The proposed secured information sharing in supply chain management (SCM) with blockchain technology will be validated by comparing it over the traditional models in terms of security as well. [ABSTRACT FROM AUTHOR]

Titanium aluminides qualify adequately for advanced aero-engine applications in place of conventional nickel based superalloys. The combination of high temperature properties and lower density gives an edge to the titanium aluminide alloys. Nevertheless, challenges remain on how to process these essentially intermetallic alloys in to an actual product. Electron Beam Melting (EBM), an Additive Manufacturing Method, can build complex shaped solid parts from a given feedstock powder, thus overcoming the shortcomings of the conventional processing techniques such as machining and forging. The amount of energy supplied by the electron beam has considerable influence on the final build quality in the EBM process. Energy input is decided by the beam voltage, beam scan speed, beam current, and track offset distance. In the current work, beam current and track offset were varied to reflect three levels of energy input. Microstructural and mechanical properties were evaluated for these samples. The microstructure gradually coarsened from top to bottom along the build direction. Whereas higher energy favored lath microstructure, lower energy tended toward equiaxed grains. Computed tomography analysis revealed a greater amount of porosity in low energy samples. In addition, the lack of bonding defects led to premature failure in the tension test of low energy samples. Increase in energy to a medium level largely cancelled out the porosity, thereby increasing the strength. However, this trend did not continue with the high energy samples. Electron microscopy and X-ray diffraction investigations were carried out to understand this non-linear behavior of the strength in the three samples. Overall, the results of this work suggest that the input energy should be considered primarily whenever any new alloy system has to be processed through the EBM route. [ABSTRACT FROM AUTHOR]

Micro-electrical discharge machining (EDM) is a slow process as compared to laser machining, on the contrary laser machining lacks good surface quality. To overcome the drawbacks of both these processes, this paper suggests a hybrid machining process which combines laser and micro-EDM processes for drilling microholes in advanced engineering materials such as Nickel–Titanium (Ni–Ti)-based shape memory alloy. To achieve the objective of the suggested hybrid process, pilot holes are drilled with laser machine and rimmed out by micro-EDM drilling. The suggested process requires investigation of various combinations of micro-EDM drilling process conditions to obtain optimum machining parameters for the hybrid process. It has been found that the proposed hybrid machining process resulted in 50–65% reduction in machining time without affecting the quality of microholes as compared to the standard micro-EDM process. [ABSTRACT FROM PUBLISHER]