Search Results (6)

The growing energy demands and increasing environmental concerns in industrial manufacturing necessitate innovative solutions to reduce fuel consumption and lower carbon emissions. This paper presents Sustain AI, a multi-modal deep learning framework that integrates Convolutional Neural Networks (CNNs) for defect detection, Recurrent Neural Networks (RNNs) for predictive energy consumption modeling, and Reinforcement Learning (RL) for dynamic energy optimization to enhance industrial sustainability. The framework employs IoT-based real-time monitoring and AI-driven supply chain optimization to optimize energy use. Experimental results demonstrate that Sustain AI achieves an 18.75% reduction in industrial energy consumption and a 20% decrease in CO₂ emissions through AI-driven processes and scheduling optimizations. Additionally, waste heat recovery efficiency improved by 25%, and smart HVAC systems reduced energy waste by 18%. The CNN-based defect detection model enhanced material efficiency by increasing defect identification accuracy by 42.8%, leading to lower material waste and improved production efficiency. The proposed framework also ensures economic feasibility, with a 17.2% reduction in operational costs. Sustain AI is scalable, adaptable, and fully compatible with Industry 4.0 requirements, making it a viable solution for sustainable industrial practices. Future extensions include enhancing adaptive decision-making with deep RL techniques and incorporating blockchain-based traceability for secure and transparent energy management. These findings indicate that AI-powered industrial ecosystems can achieve carbon neutrality and enhanced energy efficiency through intelligent optimization strategies. Full article

Requirement traceability links are an essential part of requirement management software and are a basic prerequisite for software artifact changes. The manual establishment of requirement traceability links is time-consuming. When faced with large projects, requirement managers spend a lot of time in establishing relationships from numerous requirements and codes. However, existing techniques for automatic requirement traceability link recovery are limited by the semantic disparity between natural language and programming language, resulting in many methods being less accurate. In this paper, we propose a fine-grained requirement-code traceability link recovery approach based on query expansion, which analyzes the semantic similarity between requirements and codes from a fine-grained perspective, and uses a query expansion technique to establish valid links that deviate from the query, so as to further improve the accuracy of traceability link recovery. Experiments showed that the approach proposed in this paper outperforms state-of-the-art unsupervised traceability link recovery methods, not only specifying the obvious advantages of fine-grained structure analysis for word embedding-based traceability link recovery, but also improving the accuracy of establishing requirement traceability links. The experimental results demonstrate the superiority of our approach. Full article

The path toward energy transition requires many metals, some of which are scarce in nature or their supply is controlled by a few countries. The European and Spanish situations are particularly vulnerable because of the scarcity of crucial geological mineral resources, especially those known as critical. In this context, the recovery of metals from waste electric and electronic equipment (WEEE) presents an important opportunity to partly alleviate this situation because this region produces most of the WEEE per capita. In this study, 43 different categories of EEE placed in the Spanish market between 2016 and 2021 were assessed, considering the composition of up to 57 elements, with 34 being critical. The results show the great opportunities for urban mining: 1.4 million tons of metals valued at USD 2.43 billion, representing 80% of the mass and 25% of the price of the primary extraction in Spain during that period. In addition, 20,000 tons corresponded to critical metals. However, the short life of EEE and the low traceability and low recovery of metals, especially critical and precious (94% and 87% of their values are lost, respectively), make it necessary to overcome major challenges to develop a new industry capable of moving toward a deeper circular economy. Full article

The waste generated by small-scale ultra-fresh juice producers, such as bistros and restaurants, has been little studied so far, mainly because it is unevenly distributed and dissipated in the economic ecosystem and would require high costs associated with transportation and subsequent recovery of bio composites. The present article seeks to offer solutions by providing sustainable methods to reduce their waste losses to a minimum and transform them into valuable products, with affordable equipment and techniques. The study focuses on the preliminary phase of quantitative analysis of fruit and vegetable by-products generated on a small scale, the results showing a mean 55% productivity in fresh juices. Due to the high amount of remnant water content in waste, a new process of mechanically pressing the resulting squeezed pulp was introduced, generating an additional yield in juice, ranging from 3.98 to 51.4%. Due to the rising trend in healthier lifestyle, the by-products were frozen or airdried for conservation in each of the processing stages, and the total phenolic compounds and antioxidant activity were analyzed in order to assess the traceability of these bioactive compounds to help maximize their transfer into future final products. The polyphenols transferred into by-products varied between 7 and 23% in pulps and between 6 and 20% in flours. The highest DPPH potential was found in flours, up to three-fold in comparison with the raw material, but the high dry substance content must be accounted for. The results highlight the potential of reusing the processing waste as a reliable source of bioactive compounds. Full article

This document describes the development of a tracing system for the buffalo supply chain, namely an online computer system in which farmers, dairies, and brokers must maintain records of the production of milk through to the production of derivatives. The system is jointly used throughout the Italian national territory by the Istituto Zooprofilattico Sperimentale del Mezzogiorno (IZSM) and the Sistema Informativo Agricolo Nazionale Italiano (SIAN), after being made mandatory and regulated with the publication of the Ministerial Decree of 9 September 2014. Farmers are obligated to communicate their daily production of bulk milk, the number of animals milked, the number of the delivery note of the sale, and the name of the purchaser; within the first week of the month, they must communicate the milk production of each animal milked. Dairies are required to communicate the milk and the processed product (mozzarella, yogurt, etc.) purchased on a daily basis. The intermediaries are required to communicate the daily milk purchased, both fresh and frozen, the semi-finished product, and the sale of the same. The tracing system linked to the project authorized by the Ministry of Health, called “Development, validation and verification of the applicability of an IT system to be used for the management of traceability in the buffalo industry”, provides operators with the monitoring of production and sales in real time through alerts and access logs. Currently, there are 1531 registered farmers, 601 non-PDO dairies, 102 PDO dairies, 68 non-PDO intermediaries, and 17 PDO intermediaries in Italy. The system provides support for the recovery of the buffalo sector; from the analysis of the data extrapolated from the tracing system of the buffalo supply chain for the years 2016 to 2019, this paper highlights that the application of the Ministerial Decree No. 9406 of 9 September 2014 and the tracing of the supply chain have increased the price of buffalo milk at barns from EUR 1.37/kg to EUR 1.55/kg from 2016 to 2019. Full article

Maintaining traceability links of software systems is a crucial task for software management and development. Unfortunately, dealing with traceability links are typically taken as afterthought due to time pressure. Some studies attempt to use information retrieval-based methods to automate this task, but they only concentrate on calculating the textual similarity between various software artifacts and do not take into account the properties of such artifacts. In this paper, we propose a novel traceability link recovery approach, which comprehensively measures the similarity between use cases and source code by exploring their particular properties. To this end, we leverage and combine machine learning and logical reasoning techniques. On the one hand, our method extracts features by considering the semantics of the use cases and source code, and uses a classification algorithm to train the classifier. On the other hand, we utilize the relationships between artifacts and define a series of rules to recover traceability links. In particular, we not only leverage source code’s structural information, but also take into account the interrelationships between use cases. We have conducted a series of experiments on multiple datasets to evaluate our approach against existing approaches, the results of which show that our approach is substantially better than other methods. Full article