Umar Ibrahim, Abubakar Yakubu Zandam, Fatima Muhammad Adam
et al.
Aspect-based sentiment analysis (ABSA) plays a pivotal role in understanding the nuances of sentiment expressed in text, particularly in the context of diverse languages and cultures. This paper presents a novel deep convolutional neural network (CNN)-based model tailored for aspect and polarity classification in Hausa movie reviews, as Hausa is an underrepresented language with limited resources and presence in sentiment analysis research. One of the primary implications of this work is the creation of a comprehensive Hausa ABSA dataset, which addresses a significant gap in the availability of resources for sentiment analysis in underrepresented languages. This dataset fosters a more inclusive sentiment analysis landscape and advances research in languages with limited resources. The collected dataset was first preprocessed using Sci-Kit Learn to perform TF-IDF transformation for extracting feature word vector weights. Aspect-level feature ontology words within the analyzed text were derived, and the sentiment of the reviewed texts was manually annotated. The proposed model combines convolutional neural networks (CNNs) with an attention mechanism to aid aspect word prediction. The model utilizes sentences from the corpus and feature words as vector inputs to enhance prediction accuracy. The proposed model leverages the advantages of the convolutional and attention layers to extract contextual information and sentiment polarities from Hausa movie reviews. The performance demonstrates the applicability of such models to underrepresented languages. With 91% accuracy on aspect term extraction and 92% on sentiment polarity classification, the model excels in aspect identification and sentiment analysis, offering insights into specific aspects of interest and their associated sentiments. The proposed model outperformed traditional machine models in both aspect word and polarity prediction. Through the creation of the Hausa ABSA dataset and the development of an effective model, this study makes significant advances in ABSA research. It has wide-ranging implications for the sentiment analysis field in the context of underrepresented languages.
Salvatore Annunziata, Luca Lomazzi, Marco Giglio
et al.
The survivability approach necessitates a vulnerability assessment, which quantifies the likelihood that a platform will be rendered inoperative when exposed to a threat—whether man-made or natural. This concept is closely tied to survivability, defined as the probability that a platform will complete its assigned mission. Detection and potential exposure to a threat can significantly reduce a system’s survivability. As a result, vulnerability evaluation has become a critical aspect of designing platforms that operate in high-risk environments. Numerous techniques have been developed for vulnerability assessment, with many studies aimed at achieving increasingly accurate evaluations to improve the reliability and safety of mechanical systems. Notably, in 1985, Ball introduced the concept of survivability, outlining various design solutions and techniques for fixed-wing and rotary-wing aircraft. Since then, several vulnerability assessment programs have been launched, leading to the creation of some of the most resilient platforms in use today. The assessment of vulnerability plays a key role in determining solutions to enhance the likelihood of a system successfully completing its mission. In this context, this paper presents the application of in-house software to analyze a fixed-wing Remotely Piloted Aircraft System (RPAS). The model used to validate the software’s capabilities was developed using publicly available data, enabling a practical demonstration of the software’s functionality. Applied to this case study, the software assesses the RPAS vulnerability against various impact threats. The software not only evaluates vulnerability but also suggests protective solutions to mitigate it. This application demonstrates how the software can enhance the reliability and safety of an existing operational system while also showcasing its potential for use during the preliminary design phase of a broader range of platforms.
Arsić Dušan, Nikolić Ružica R., Arsić Aleksandra
et al.
The rotary excavator is a complex machine system, the main part of the ECS (excavator-conveyer-spreader) system, used in open-pit mining. Such a machine’s service life can last for decades, it generally operates in the harsh exploitation conditions, which requires that its vital structures must be continuously controlled and well maintained. Damage or fracture of parts or assemblies of a rotary excavator can be caused by influence of various manufacturing, construction, exploitation conditions or environmental factors. Analysis of those eventual failures can be performed by various methods, out of which the most suitable are the failure analysis methods, for example the fault-tree analysis (FTA), the Ishikawa fishbone (cause-and-effect) diagrams or the failure modes and effects analysis (FMEA). In this article are presented results of the fault tree analysis of possible causes of rotary excavator’s parts, as well as measures to prevent their damages and/or fractures and to extend the service life of an excavator as a whole. The model of the organizational system for the rotary excavator’s maintenance is given, as well.
Machine design and drawing, Engineering machinery, tools, and implements
José P. P. G. Lopes de Almeida, Vinícius G. Machado
This article addresses the multifaceted challenges inherent in the development of the novel REEFS (Renewable Electric Energy From Sea) wave energy converter (WEC). Building on the submerged pressure differential principle, it frames similar WECs before focusing on REEFS that combines renewable energy generation with coastal protection, functioning as an artificial reef. The review follows chronological criteria, encompassing experimental proof-of-concept, small-scale laboratory modeling, simplified and advanced computational fluid dynamics (CFD) simulations, and the design of a forthcoming real-sea model deployment. Key milestones include the validation of a passive variable porosity system, demonstration of wave-to-wire energy conversion, and quantification of wave attenuation for coastal defense. Additionally, the study introduces a second patent-protected REEFS configuration, isolating internal components from seawater via an elastic enveloping membrane. Challenges related to scaling, numerical modeling, and funding are thoroughly examined. The results highlight the importance of the proof-of-concept as the keystone of the development process, underscore the relevance of mixed laboratory-computational approaches and emphasize the need for a balanced equilibrium between intellectual property safeguard and scientific publishing. The REEFS development trajectory offers interesting insights for researchers and developers navigating the complex innovation seas of emerging wave energy technologies.
Engineering machinery, tools, and implements, Technological innovations. Automation
This study presents a simulation modeling of the gravity filling of a sand casting mold with gray cast iron EN-GJL-250. An analysis of the fluid flow, the nature of the filling of the casting mold, and the possibility of forming defects, such as voids and porosity due to metal shrinkage during the crystallization process, was performed. The simulation was performed using specialized software for simulating metal casting processes. The software allows the modeling of fluid dynamics and thermal conditions during the filling of the casting mold. The results obtained show the influence of the design of the sprue system, pouring temperature, and casting geometry on the movement of the fluid flow and the crystallization of the metal. The simulation also allows the visualization of turbulence and temperature gradients, helping to localize areas prone to defects. The results of this study could improve the quality of the specific casting and aid in selecting appropriate technology for the casting of a small series of high-quality castings.
Xander Küpers, Jeroen Klein Brinke, Rob Bemthuis
et al.
The construction industry faces significant challenges in optimizing equipment utilization, as underused machinery leads to increased operational costs and project delays. Accurate and timely monitoring of equipment activity is therefore key to identifying idle periods and improving overall efficiency. This paper presents the Edge-IMI framework for detecting idle construction machinery, specifically designed for integration with surveillance camera systems. The proposed solution consists of three components: object detection, tracking, and idle state identification, which are tailored for execution on resource-constrained, CPU-based edge computing devices. The performance of Edge-IMI is evaluated using a combined dataset derived from the ACID and MOCS benchmarks. Experimental results confirm that the object detector achieves an F1 score of 71.75%, indicating robust real-world detection capabilities. The logistic regression-based idle identification module reliably distinguishes between active and idle machinery with minimal false positives. Integrating all three modules, Edge-IMI enables efficient on-site inference, reducing reliance on high-bandwidth cloud services and costly hardware accelerators. We also evaluate the performance of object detection models on Raspberry Pi 5 and an Intel NUC platforms, as example edge computing platforms. We assess the feasibility of real-time processing and the impact of model optimization techniques.
Fault detection in rotating machinery is a complex task, particularly in small and heterogeneous dataset scenarios. Variability in sensor placement, machinery configurations, and structural differences further increase the complexity of the problem. Conventional deep learning approaches often demand large, homogeneous datasets, limiting their applicability in data-scarce industrial environments. While transfer learning and few-shot learning have shown potential, however, they are often constrained by the need for extensive fault datasets. This research introduces a unified framework leveraging a novel progressive neural network (PNN) architecture designed to address these challenges. The PNN sequentially estimates the fixed-size refined features of the higher order with the help of all previously estimated features and appends them to the feature set. This fixed-size feature output at each layer controls the complexity of the PNN and makes it suitable for effective learning from small datasets. The framework's effectiveness is validated on eight datasets, including six open-source datasets, one in-house fault simulator, and one real-world industrial dataset. The PNN achieves state-of-the-art performance in fault detection across varying dataset sizes and machinery types, highlighting superior generalization and classification capabilities.
Advancements in large language models (LLMs) have led to a surge of prompt engineering (PE) techniques that can enhance various requirements engineering (RE) tasks. However, current LLMs are often characterized by significant uncertainty and a lack of controllability. This absence of clear guidance on how to effectively prompt LLMs acts as a barrier to their trustworthy implementation in the RE field. We present the first roadmap-oriented systematic literature review of Prompt Engineering for RE (PE4RE). Following Kitchenham's and Petersen's secondary-study protocol, we searched six digital libraries, screened 867 records, and analyzed 35 primary studies. To bring order to a fragmented landscape, we propose a hybrid taxonomy that links technique-oriented patterns (e.g., few-shot, Chain-of-Thought) to task-oriented RE roles (elicitation, validation, traceability). Two research questions, with five sub-questions, map the tasks addressed, LLM families used, and prompt types adopted, and expose current limitations and research gaps. Finally, we outline a step-by-step roadmap showing how today's ad-hoc PE prototypes can evolve into reproducible, practitioner-friendly workflows.
Mathieu Bourdin, Anas Neumann, Thomas Paviot
et al.
Retrieval-Augmented Generation (RAG) has emerged as a powerful solution to mitigate the limitations of Large Language Models (LLMs), such as hallucinations and outdated knowledge. However, deploying RAG-based tools in Small and Medium Enterprises (SMEs) remains a challenge due to their limited resources and lack of expertise in natural language processing (NLP). This paper introduces EASI-RAG, Enterprise Application Support for Industrial RAG, a structured, agile method designed to facilitate the deployment of RAG systems in industrial SME contexts. EASI-RAG is based on method engineering principles and comprises well-defined roles, activities, and techniques. The method was validated through a real-world case study in an environmental testing laboratory, where a RAG tool was implemented to answer operators queries using data extracted from operational procedures. The system was deployed in under a month by a team with no prior RAG experience and was later iteratively improved based on user feedback. Results demonstrate that EASI-RAG supports fast implementation, high user adoption, delivers accurate answers, and enhances the reliability of underlying data. This work highlights the potential of RAG deployment in industrial SMEs. Future works include the need for generalization across diverse use cases and further integration with fine-tuned models.
Aiming at the shortcomings of the gazelle optimization algorithm, such as the imbalance between exploration and exploitation and the insufficient information exchange within the population, this paper proposes a multi-strategy improved gazelle optimization algorithm (MSIGOA). To address these issues, MSIGOA proposes an iteration-based updating framework that switches between exploitation and exploration according to the optimization process, which effectively enhances the balance between local exploitation and global exploration in the optimization process and improves the convergence speed. Two adaptive parameter tuning strategies improve the applicability of the algorithm and promote a smoother optimization process. The dominant population-based restart strategy enhances the algorithms ability to escape from local optima and avoid its premature convergence. These enhancements significantly improve the exploration and exploitation capabilities of MSIGOA, bringing superior convergence and efficiency in dealing with complex problems. In this paper, the parameter sensitivity, strategy effectiveness, convergence and stability of the proposed method are evaluated on two benchmark test sets including CEC2017 and CEC2022. Test results and statistical tests show that MSIGOA outperforms basic GOA and other advanced algorithms. On the CEC2017 and CEC2022 test sets, the proportion of functions where MSIGOA is not worse than GOA is 92.2% and 83.3%, respectively, and the proportion of functions where MSIGOA is not worse than other algorithms is 88.57% and 87.5%, respectively. Finally, the extensibility of MSIGAO is further verified by several engineering design optimization problems.
The emergence of generative AI chatbots such as ChatGPT has prompted growing public and academic interest in their role as informal mental health support tools. While early rule-based systems have been around for several years, large language models (LLMs) offer new capabilities in conversational fluency, empathy simulation, and availability. This study explores how users engage with LLMs as mental health tools by analyzing over 10,000 TikTok comments from videos referencing LLMs as mental health tools. Using a self-developed tiered coding schema and supervised classification models, we identify user experiences, attitudes, and recurring themes. Results show that nearly 20% of comments reflect personal use, with these users expressing overwhelmingly positive attitudes. Commonly cited benefits include accessibility, emotional support, and perceived therapeutic value. However, concerns around privacy, generic responses, and the lack of professional oversight remain prominent. It is important to note that the user feedback does not indicate which therapeutic framework, if any, the LLM-generated output aligns with. While the findings underscore the growing relevance of AI in everyday practices, they also highlight the urgent need for clinical and ethical scrutiny in the use of AI for mental health support.
Энторопийные принципы дают базисную основу формирования функциональных связей между многими величинами химической кинетики. Равновесная сумма энтропийных составляющих универсальной газовой постоянной, равная R/2, имеет прямую математическую связь с тангенсом геодезического угла. Аналогичное соотношение этого параметра получено по графикам Аррениуса – зависимости коэффициента скорости реакции от температуры. При движении в одном формате двух энтропийных составляющих равновесная сумма их энергий равна половине первоначальной величины энергии. Установленные принципы проявляются и в других закономерностях химической кинетике и физике, например, в энергии активации диффузионных процессов и в уравнении кинетической энергии.
Engineering machinery, tools, and implements, Motor vehicles. Aeronautics. Astronautics
Paulo Vitor Pereira de Oliveira, Lucas Zanasi Matheus, Fabio Romano Lofrano Dotto
et al.
In milling applications of CFRP (Carbon Fiber Reinforced Polymer) composites, acoustic emission sensors employing piezoelectric transducers have been used to generate acoustic maps. These maps are crucial for monitoring the condition of both the tool and the workpiece, providing a visual analysis of the tool–workpiece interaction that facilitates decision-making by the operator in case of failures. This study introduces a technique—implemented in the Matlab software—that uses the image generated by the acoustic map to perform automatic alignment during the map’s production, eliminating the need for an external synchronization signal.
AbstractIn order to suppress the electromagnetic interference in electric construction machinery, improve the stability and safety of the vehicle on the influence factors of electric construction machinery EMC system analysis, electric drive system due to the internal power electronic equipment for a long time in the high voltage, high current conditions and become the main influence factors of electric construction machinery EMC. The main methods to reduce electromagnetic interference of electric drive system grounding, shielding and filtering are expounded, which leads to the emulated research of EMC simulation of electric drive system of electric engineering machinery. The equivalent circuit model of battery, electronic control, motor and test system is established, and the low-pass filter composed of inductor and capacitor is designed. And the combined three electric system, test system, filter circuit composed of the model of simulation analysis, with or without filter input current, different frequencies of input and output voltage signals compared, the results show that adding filter can effectively improve the conducted interference, the use of RLC filter composed of four RLC components, can effectively improve the signal low frequency bias and high frequency distortion.
Franklin Chamorro, Paula Garcia-Oliveira, Sepidar Seyyedi-Mansour
et al.
The <i>Actinidia</i> genus comprises 54 species and 21 varieties of which <i>A. chinensis</i> var. <i>chinensis</i> and <i>A. chinensis</i> var. <i>deliciosa</i> are the most commercialized ones. The nutritional properties of kiwifruit have prompted their global production to nearly reach the value of 4.5 million tons per year, with Asia being one of the top producers. This increment in their production has raised a parallel augment of associated organic wastes, especially when kiwifruits are used for processed products. The most abundant by-products obtained include skins, seeds and discarded fruits. This biomass has a huge potential for its high content of bioactive compounds, such as dietary fiber or polyphenols. Therefore, it has been targeted by the food industry as a sustainable and cost-effective source of natural ingredients, highly demanded by consumers. Indeed, kiwi skins and seeds have been pointed out as a relevant source of pectin followed by the kiwi pulp. Pectin is a recognized ingredient due to the organoleptic properties it may confer but also for its prebiotic capacities. The recovery of pectin has been mainly performed via the application of extraction techniques that implied the use of chemical reagents such as acids. Nowadays, the use of chemicals is negatively regarded for their associated side effects. Indeed, customers’ claims for chemical-free food ingredients have triggered the development and application of green extraction techniques: ultrasonic, microwave, enzyme, supercritical fluid or electrical pulse. Pectin has been successfully extracted with these green techniques both in terms of yield and quality, improving results obtained with traditional extraction techniques. Therefore, the main objective of this work is to review the wide variability of green techniques applied to extract pectin along with the comparison of the optimal parameters as a basis for the future development of an optimized extraction method. In addition, this work also aims to disclose the potential of kiwifruit by-products as a source of pectin and their industrial applications for the development of functional foods, nutraceuticals, food additives or cosmetics.
Asset management decision support tools determine which action (maintenance, rehabilitation, or reconstruction) is applied to each facility in a transportation network and when. Sophisticated tools recognize uncertainties and consider emerging priorities. However, these tools are often computationally complex and lack transparency, the models are difficult to evaluate, and the outputs challenging to validate. This paper explores computational complexity, transparency, and realism in transportation asset management decision support tools to better understand how to select the right tools for a particular context. The results provide direction for agencies when selecting decision support tools, and for researchers and tool developers working towards developing the right tool for an application.
Additive manufacturing (AM), also known as three-dimensional (3D) printing, is the process of building a solid object in a layer-wise manner. Cybersecurity is a prevalent issue that appears more and more frequently as AM becomes popular. This paper focuses on the effect of fan speed on the printing quality and presents a plugin called Fan Speed Attack Detection (FSAD) that predicts and monitors fan speeds throughout the printing process. The goal of the plugin is to prevent cybersecurity attacks, specifically targeting fan speed. Using the proposed FSAD, any fan speed changes during the printing process are evaluated to see whether the printer can sustain the abnormal fan speed change and still maintain good print quality.
Engineering machinery, tools, and implements, Technological innovations. Automation
Feng-Ming Yeh, Liang-Ying Huang, Chao-Kai Chang
et al.
Currently, many swimming goggle lenses use optical plates to maintain zero refractive power in air and water. However, people’s widespread use of 3C products has increased myopia significantly, so lenses have a demand for refractive power. Lenses will have different refractive power problems in water and air media. Therefore, we solved the refractive power change in air and water by using a plane Fresnel lens with a diopter to replace plano-concave lenses. In this study, a first-order design was created and then the microstructure of the Fresnel lens was optimized using optical software. The Fresnel lens simulation results showed that the error was within 5%, which was compared with the data using the lensmaker’s equation calculation. For swimming goggles, this error value is tolerable for human vision.
Ianna Moris Kanyi, Thomas Stephen Ijimdiya, Adrian Oshioname Eberemu
et al.
The strength of lateritic soil bio-treated with a <i>Bacillus thuringiensis</i> (Bt)-induced calcite precipitate was investigated using a pocket penetrometer (PPT). The effect of bacterial (Bt) and cementation solution concentration (C<sub>s</sub>) on the strength of the microbial-induced calcite precipitate (MICP) worked soil was also evaluated. Soil samples were treated with Bt and C<sub>s</sub> using three mix ratios (i.e., 25% Bt: 75% C<sub>s</sub>, 50% Bt: 50% C<sub>s</sub>, and 75% Bt: 25% C<sub>s</sub>) based on the natural soil liquid limit (LL = 36.0%). Bt suspension densities of 0, 1.5 × 10<sup>8</sup>, 6.0 × 10<sup>8</sup>, 1.2 × 10<sup>9</sup>, 1.8 × 10<sup>9</sup>, and 2.4 × 10<sup>9</sup> cells/mL were applied to the soil with four varying C<sub>s</sub> concentrations (i.e., 0.25, 0.5, 0.75, and 1 M). The prepared specimens were allowed to homogenise and equilibrate at laboratory conditions. A pocket penetrometer (PPT) was used to test the unconfined compressive strength (UCS) of the prepared specimens at 3, 5, and 7 days after bio-treatment to evaluate the strength of the MICP worked soil at different moisture contents. The results obtained show that the UCS values increased with higher Bt and C<sub>s</sub> as well as with a reduction in moisture content as the bio-treated soil equilibrated with the environment. The recorded UCS values for the mix ratios considered were in the order: 50% Bt: 50% C<sub>s</sub> > 25% Bt: 75% C<sub>s</sub> > 75% Bt: 25% C<sub>s</sub>. Therefore, a PPT can be used to determine the approximate unconfined compressive strength of treated soil.
Coronavirus (COVID-19) is a fast-spreading virus-related disease. On 28 March 2022, Worldometer (COVID-19 live update) reported that there were about 482,338,923 COVID-19 cases and 6,149,387 fatalities worldwide. Moreover, there were about 416,884,712 recovered patients. The primary clinical mechanism currently utilized for COVID-19 identification is the Reverse Transcription–Polymerase Chain Reaction (RT-PCR). Hospitals only have small quantities of COVID-19 test kits available due to the daily increase in cases. As an alternative diagnosis possibility, an automatic detection system was implemented. A vigorous technique for the automatic COVID-19 identification is the deep learning approach. Chest X-ray (CXR) imaging is a modest tool that can be an alternate for diagnosing COVID-19-infected patients. With the use of deep learning, deep layer characteristics that are hidden from human sight may be observed using CXR imaging. One of the largest public databases, the “COVID-19 Radiography Database”, comprises 21,164 CXR images and was taken from Kaggle. To achieve the best accuracy in this work, data cleansing and the balanced dataset approach were applied. The primary goal of data cleansing is to remove duplicate CXR images from the database. The accuracy of three distinct pre-trained Convolutional Neural Networks (CNNs) was compared and then analyzed (Xception, InceptionV3, and MobileNetV2). Among other models, Xception achieved the best testing accuracy of 94.13% with plain lung CXR pictures. The Gabor filtering image enhancement approach was also employed to identify COVID-19. Only for the MobileNetV2 model did enhance CXR images perform significantly better for classification than plain lung CXR images. This study attempts to enhance the system’s accuracy to 100%, outperforming previous tests.