Sustainable Engineering and Innovation (SEI - E-Journal)
Not a member yet
142 research outputs found
Sort by
Integrating Lean Six Sigma into waste management evaluation to enhance supply chain productivity: A case study
Full text linkThis study investigates how waste management performance at community-based 3R waste management facilities (CWMFs) can be improved to enhance environmental sustainability and supply chain productivity. As urban waste continues to increase, effective community-based systems are critical to reducing landfill dependency. The research, conducted at TPS3R DR Indonesia, employed Lean Six Sigma tools such as SIPOC (Supplier-Input-Process-Output-Customer), process flow mapping, and fishbone analysis, to identify inefficiencies and their root causes. The analysis revealed that waste management efficiency reached only 60%, leaving approximately 2,400 kg of waste unprocessed daily. Key bottlenecks were found in equipment maintenance, work methods, staff awareness, and monitoring systems. Implementing structured improvement approaches such as 5S, 5W1H, and standardized operating procedures (SOPs) could enhance recovery efficiency by up to 20%. These interventions not only reduce residual waste but also improve workflow consistency and environmental performance. The study’s scientific contribution lies in demonstrating the applicability of Lean Six Sigma within community-based waste systems, providing a replicable model for integrating process improvement methodologies into local sustainability practices
Estimating different velocities in wrist movements from information contained in surface electromyography: Application of a machine learning technique
Full text linkThe study of surface electromyography (sEMG) has several approaches. It is used to classify upper and lower extremity movements by identifying the muscle groups that have been excited to generate movements. In general, movements have certain properties related to the type of movement, the force, and the speed at which they are performed. The hypothesis of this study is that information about different speeds is contained in sEMG signals. Participants performed wrist movements at different speeds, following verbal instructions to alternate between fast and slow movements. Our objective was to estimate whether there is information in the sEMG signal that can be associated with the different speed conditions; therefore, binary differencing (two classes) was chosen to test this. These two conditions (fast and slow) were used as classes for analysis and classification based on surface electromyography signals. The moving window method was used to extract sEMG envelopes at two different speeds performed by the test subjects. A linear discriminant analysis model was created to estimate the velocities with the resulting model. Finally, cross-validation was performed to estimate sensitivity (76.67%), specificity (91.2%), and accuracy (approximately 87%)
Modeling the interaction of virtual agents in distributed artificial intelligence systems
Full text linkModern distributed artificial intelligence (AI) systems utilize a significant number of virtual agents that must work collaboratively to solve complex tasks. However, existing technologies for organizing their interaction are characterized by certain shortcomings: high computational complexity, simplified operating conditions, poor adaptability to changes, and significant problems in accounting for the diversity of virtual agents and their emotional reactions during decision-making. The purpose of the study is to develop a new approach for organizing virtual agent operations in distributed AI systems that aims to improve their cooperation, coordination efficiency, and adaptability. The methodological foundation of the study was an innovative approach that combined a specialized emotion model containing 100 virtual agents in a two-dimensional space with a complex network of connections between them, with machine learning methods to enhance virtual agent coordination. Computer modeling methods were applied using experiments in the Python programming environment. The research results demonstrate that effective communication methods between virtual agents significantly improve their coordination, and conflicts during task execution are substantially reduced through adaptive mechanisms. The innovative emotion model can achieve high accuracy levels and contribute to the formation of new system behavior that includes sharp changes in collective decision-making processes. It also identifies essential parameters of virtual agent cooperation to ensure stable system operation. The comprehensive approach based on combining rule-based logic with machine learning can effectively improve virtual agent coordination, especially under conditions of their diversity. The AI system demonstrates real capacity for large-scale changes, but is imperfect in reflecting negative emotional states. Such AI system research results are essential for developing autonomous systems, intelligent networks, and collaboration platforms for virtual agents
A semi-systematic review and bibliometric analysis of life cycle assessment in solar desalination technologies (2004–2024)
Full text linkWater harvesting for human consumption faces growing challenges due to extreme climatic events, leading to the exploration of alternative sources such as groundwater and seawater. Desalination has become a viable solution despite technical and environmental limitations. Life Cycle Analysis (LCA) is widely used to assess the environmental impacts of desalination technologies, positioning solar desalination as a promising option for coastal areas. However, differences in LCA methodologies limit the identification of consistent trends. This study presents a bibliometric analysis using VOSviewer and the SCOPUS database to update the state of the art in LCA applications for desalination systems, with emphasis on solar desalination. A total of 165 documents published between 2004 and 2024 were analyzed in two periods. A significant increase in publications was observed from 2015, particularly in Asia and the Arabian Peninsula, aligning with high solar potential and financial capability. From the 29 selected papers, 12 were directly related to LCA methodologies, covering scope, typologies, impact categories, and tools. Although no single method dominates, ReCiPe has gained attention, while IMPACT 2002+ and IPCC-2013 remain in use. Commonly assessed impact categories include Global Warming Potential (GWP100a), Acidification Potential (AP), and Eutrophication Potential (EP)
Using artificial intelligence in software development processes: achievements and challenges
Full text linkThis study consolidates contemporary methodologies for applying artificial intelligence in software engineering. Using the PRISMA protocol, an analysis of 60 peer-reviewed publications was conducted. Findings indicate that the use of generative tools (such as GitHub Copilot), AI-based testing platforms (like Testim.io and Diffblue), and DevOps automation systems (e.g., Harness.io) can lead to a 20–40% reduction in development time, while also enhancing code quality and minimizing errors. A key academic contribution of the research is the introduction of a three-tier classification of integration barriers – technical, organizational, and legal – that hinder the seamless adoption of AI technologies within the Software Development Life Cycle (SDLC), as well as the lack of standardized methodologies. The recommendations provided in this work are particularly relevant to software engineers, IT project leaders, and academic researchers, as they address crucial concerns related to model interpretability, system instability, the absence of unified standards, and regulatory ambiguity. The practical relevance of the study lies in presenting actionable strategies for the responsible, scalable, and ethically grounded deployment of AI-driven tools in industrial, academic, and research settings
Smart water quality regulation in sustainable aquaponics using PID control and long-term performance analysis
Full text linkThis study evaluates the reliability and suitability of long-term water quality data collected from a sustainable aquaponics system equipped with a pH, dissolved oxygen, and temperature regulation control strategy based on a PID algorithm. Although PID control was implemented to maintain parameters within optimal biological ranges, natural fluctuations and out-of-range measurements were recorded, particularly in pH. Rather than being considered anomalies, these deviations represent realistic environmental variations that must be captured for comprehensive system analysis. A thorough data validation process was conducted, including descriptive statistics, outlier detection, correlation analysis, principal component analysis (PCA), and temporal stability evaluation. Results confirmed the absence of missing data, the presence of controlled variability in dissolved oxygen and temperature, and meaningful correlations between parameters, with pH showing the highest variability. Autocorrelation and long-term trend analyses indicated stable measurement patterns that reflect real-world aquaponic dynamics. The validated dataset provides a robust foundation for future studies, particularly for the development of artificial intelligence (AI)-based predictive models aimed at early detection of fish distress or mortality
AI-based monkeypox detection model using Raspberry Pi 5 AI Kit
Full text linkMonkeypox is a zoonotic disease that originated from monkeys and then spread to humans; this disease recently popped up globally with increased risks of spreading from human to human and clinical presentation similar to other pox-like diseases. Quick and right identification is fundamental for containment and treatment that will minimize the spread of the disease. The current conventional diagnostic techniques include PCR which takes time, and money, and often needs sophisticated laboratories that cannot be easily accessed in developing countries. This work describes the creation and application of a monkeypox detection algorithm orchestrated on the Raspberry Pi 5 AI Kit. Developed based on convolutional neural networks (CNNs), the model enables one to distinguish actual monkeypox lesions in the images. The Raspberry Pi 5 AI Kit allows for edge computing solutions to be implemented, making the entire solution mobile, affordable, and perfect for locations with low connectivity. Extensive data collection and data preprocessing were performed, and the final dataset with monkeypox and skin lesion images consisted of more than 5000 verified images. 94% accuracy was obtained by the model, making it superior to the model available in literature. The implementation proves that powerful AI technologies can be applied to low-cost hardware to become a valuable weapon in the monkeypox frontline workers’ arsenal and advance the efforts against monkeypox infections
Assessing the impact of artificial intelligence integration on educational processes in higher education institutions of Ukraine and Kazakhstan
Full text linkThe study focuses on assessing the impact of artificial intelligence on educational processes in higher education institutions. It considers aspects of administrative task automation, personalization of learning, and ethical challenges. The topic's relevance is driven by global trends in the digital transformation of education and the need to adapt systems to modern challenges. A descriptive approach was used, using secondary data from scientific publications, statistical reports, and analytical studies. The data were analyzed using statistical and correlation methods, allowing us to identify the key patterns of implementing artificial intelligence in higher education in Ukraine and Kazakhstan. Integration of artificial intelligence increases the efficiency of administrative processes by 40%, reducing the time spent on routine tasks. Personalized learning contributes to the growth of students' academic performance by 7-30%. Using AI to monitor educational processes can reduce the risk of expulsions by up to 15%. At the same time, the risks of reduced social interaction and possible ethical issues, such as the opacity of algorithms and the risk of data leakage, have been identified. Artificial intelligence has significant potential for optimizing educational processes, provided ethical standards are met. Technological solutions must be combined with a socially oriented approach, particularly through integrating hybrid learning models. It is recommended that Ukraine use Kazakhstan's experience in centralizing solutions, investing in analytical tools, and training teachers
New microstrip bandpass filter design with sharp roll-off based on rectangular split resonators
Full text linkThis paper presents a compact bandpass filter (BPF) with a triple rectangular split resonator optimized for high performance at a central frequency of 3.682 GHz. The filter achieves an exceptional voltage standing wave ratio (VSWR) of 1.088 and a return loss of 27.48 dB, demonstrating superior impedance matching. Additionally, the filter exhibits minimal insertion loss with S21?=0.38dB, ensuring efficient signal transmission. The design boasts a sharp roll-off rate of 87 and a narrow transition band of 0.196 GHz, making it suitable for high-selectivity applications. The compact size of the filter, measuring only 24?mm×24?mm, enhances its applicability in modern communication systems with limited space requirements
Estimating survival rates using artificial intelligence combined with the Aalen–Johansen estimator in multi-state models
Full text linkAccurate survival prediction is essential for clinical decision-making, health economics, and treatment planning. Traditional methods like the Kaplan-Meier and Cox models are widely used but have limitations when applied to complex multi-state processes or individualized predictions. The Aalen–Johansen estimator, a non-parametric approach suited for multi-state Markov models, improves population-level inference but lacks the ability to incorporate covariates or capture nonlinear relationships. In this study, we propose a hybrid framework that combines the Aalen–Johansen estimator with artificial intelligence (AI) techniques, specifically gradient boosting machines (GBM) and long short-term memory (LSTM) networks. By transforming transition probabilities into subject-level pseudo-observations, AI models can learn personalized survival functions based on individual covariates. We validate our approach on both simulated and real-world clinical datasets. The hybrid model outperforms traditional estimators in predictive accuracy, as measured by calibration and discrimination metrics such as Brier score and area under the curve (AUC). This AI–Aalen–Johansen framework enhances risk stratification and clinical decision-making by providing more accurate, scalable, and interpretable survival predictions. Our results support its potential as a valuable tool in modern healthcare analytics, contributing to the advancement of precision medicine