Recent advancements in Artificial Intelligence (AI), deep learning (DL), and computer vision have revolutionized various industrial processes through image classification and object detection. State-of-the-art Optical Character Recognition (OCR) and object detection (OD) technologies, such as YOLO and PaddleOCR, have emerged as powerful solutions for addressing challenges in recognizing textual and non-textual information on printed stickers. However, a well-established framework integrating these cutting-edge technologies for industrial applications still needs to be discovered. In this paper, we propose an innovative framework that combines advanced OCR and OD techniques to automate visual inspection processes in an industrial context. Our primary contribution is a comprehensive framework adept at detecting and recognizing textual and non-textual information on printed stickers within a company, harnessing the latest AI tools and technologies for sticker information recognition. Our experiments reveal an overall macro accuracy of 0.88 for sticker OCR across three distinct patterns. Furthermore, the proposed system goes beyond traditional Printed Character Recognition (PCR) by extracting supplementary information, such as barcodes and QR codes present in the image, significantly streamlining industrial workflows and minimizing manual labor demands.

Advancements in Artificial Intelligence and Deep Learning have impacted numerous fields, particularly through innovations like You Only Look Once for object detection and PaddleOCR for optical character recognition in computer vision. These technologies are pivotal in automating and enhancing the accuracy of tasks, such as detecting and extracting characters from identification badges, which have traditionally been prone to manual effort, time consumption, and errors. This study introduces an automated method for detecting and extracting textual data from identification badges, achieving notable efficiency and precision. Our results indicate a Character Error Rate of 0.028 for name recognition and a flawless score for registration number extraction, with a precision rate of 0.992 for the identification badge detection model. By highlighting the importance of automating character extraction and badge detection, this study showcases the ability of Artificial Intelligence and Deep Learning to revolutionize and improve data extraction processes with digital identification systems in professional environments.

Many industrial sectors still lack automation resources to optimize their production processes, aiming to make manufacturing leaner and offer better working conditions to operators. Without these improvements, workers can suffer physical and even psychological damage from the ergonomic risks of the activities performed. Thus, the aim of this paper is to present the ergonomic evaluation of packaging tapes workstation before and after the implementation of an automatic packaging machine, called Guzzetti. In the Guzzetti context, the paper shows the implementation of an electrical system based on controlling a mechanical device powered by servomotors and controlled by a PLC is necessary. For ergonomic evaluation, the paper presents the application of three methods: Suzanne Rodger, Strain Index, called Moore and Garg and REBA (Rapid Entire Body Assessment). With the results collection, was possible to obtain improvements in ergonomic risks that changed from the intermediate level to low level in all methods.

The rapid evolution of intelligent chatbots has been largely driven by the advent of Large Language Models (LLMs), which have greatly enhanced natural language understanding and generation. However, the fast-paced advancements in generative Artificial Intelligence (AI) and LLM technologies present challenges for developers to stay up-to-date and to select optimal architectures or approaches from a wide range of available options. This survey article addresses these challenges by providing a overview of cutting-edge techniques and architectural application choices in modern generative chatbot development. We explore various approaches involving retrieval strategies, chunking methods, context management, embeddings, and the utilization of LLMs. Furthermore, we analyze paradigms such as naive Retrieval-Augmented Generation (RAG) compared to Graph-Based RAG, as well as single-agent versus multi-agent systems. We examine agent-based methodologies, comparing single-agent systems with multi-agent architectures, and analyze how multi-agent systems can proficiently handle intricate tasks, enhance scalability, and mitigate faults such as hallucinations through collaborative efforts. Additionally, we review tools and frameworks such as LangGraph that facilitate the implementation of stateful, multi-agent LLM applications. By categorizing and analyzing these modern techniques, this survey aims to present the current landscape and future directions in chatbot development.

Monitoring vast and remote areas like forests using Wireless Sensor Networks (WSNs) presents significant challenges, such as limited energy resources and signal attenuation over long distances due to natural obstacles. Traditional solutions often require extensive infrastructure, which is impractical in such environments. To address these limitations, we introduce the “FloatingBlue” architecture. This architecture, known for its superior energy efficiency, combines Bluetooth Low Energy (BLE) technology with Delay Tolerant Networks (DTN) and data mules. It leverages BLE’s low power consumption for energy-efficient sensor broadcasts while utilizing DTN-enabled data mules to collect data from dispersed sensors without constant network connectivity. Deployed in a remote agricultural area in the Amazon region, “FloatingBlue” demonstrated significant improvements in energy efficiency and communication range, with a high Packet Delivery Ratio (PDR). The developed BLE beacon sensor achieved state-of-the-art energy consumption levels, using only 2.25 µJ in sleep mode and 11.8 µJ in transmission mode. Our results highlight “FloatingBlue” as a robust, low-power solution for remote monitoring in challenging environments, offering an energy-efficient and scalable alternative to traditional WSN approaches.

This work contributes with a new approach for tuning hyperparameters of machine learning models, based on sequences of optimization studies based on an initial range of hyperparameters. Through the proposed methodology, each sequence of studies allows the delimitation of an optimal range of hyperparameters to be inserted and evaluated by a Bayesian optimization framework, Optuna, in search of better performance metrics for the model used. The technique developed in this work was applied for short-term electrical energy prediction, with 15-minute and 1-hour data, using energy consumption data from a steel industry. We used ensemble and decision tree learning models as predictors, including Random Forest Regressor, Support Vector Regressor and Cubist Regressor, which have already been used in the literature to predict energy consumption using the same database. In an unprecedented way, we used the XGBoost model as a predictor of energy consumption in the proposed context. The results obtained from each model surpassed the performance metrics previously obtained in the literature for the same prediction scenarios, even without the use of specific feature selection techniques or pre-processing. To predict the 15-minute and 1-hour energy consumption, we obtained a Root Mean Square Error of 0.175 kWh and 1.341 kWh for the test set, respectively, using the Cubist Regressor model.