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.

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.

Digital integration is essential for efficient and sustainable management of energy resources, especially in modernizing outdated infrastructures. This involves embedding sensor and actuator devices for precise energy monitoring and control, supported by distributed computing from edge to cloud, necessary for tailored analytical and predictive decisions. Retrofit strategies incorporate these resources into older systems, enhancing existing infrastructures while adapting to technological progress. Nevertheless, systematic methodologies for sensor-actuator integration are lacking in the literature. Therefore, this article introduces the SmartLVEnergy framework, designed to modernize legacy low-voltage systems with a retrofitting approach, integrating decentralized sensing, control, distributed processing, and predictive analytics. The framework was employed to retrofit the energy distribution panel of a legacy manufacturing plant with sensor devices, which support remote monitoring and decentralized predictive analysis using 15-minute energy demand forecast models based on 2-layer Long Short-Term Memory (LSTM) networks, adhering to Artificial Intelligence of Things (AIoT) and Tiny Machine Learning (TinyML) principles. Benchmarked against non-quantized and single-layer LSTM models for the installation energy demand forecast between May 8 and July 11, 2023, our approach showed reduced prediction latency and memory consumption. The main circuit breaker exhibited a 96.67% R-squared score (R ² ) and 7.23 kW Root Mean Squared Error (RMSE), with the associated sensor showing a prediction latency of 54.55 ms and using 58.45 KB of FLASH memory. These metrics for the best-performing sensor were 97.33%, 0.39 kW, 5.55 ms, and 10.20 KB. This AIoT framework marks a significant advancement in sensor-actuator retrofitting, blending digital technology with legacy systems for intelligent energy management.

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 the 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.

Smart buildings provide opportunities for technological transformations in building environments to improve resource management, comfort, and efficiency of the systems present in these facilities. For this, Internet of Things (IoT) solutions contribute, with monitoring and remote control features, to automate these environments. However, these solutions can promote the disposal or replacement of outdated but still-needed legacy systems. Thus, a reference model that uses retrofit techniques to update pre-existing systems would be an alternative to enable smart building convergence. The lack of models that advocate this type of strategy provides an opportunity for the emergence of methods capable of filling this gap. Thus, this work presents a strategy for implementing monitoring, control, and communication resources to achieve smart building convergence in legacy building systems. This strategy consists of the use of retrofit techniques based on the adaptation of the SmartLVGrid metamodel. To validate this proposal, we developed hardware platforms and, respectively, their firmware to implement the premises established in a legacy building lighting circuit. The results obtained present a new possibility of implementing smart buildings from the retrofit of legacy infrastructures, as the pre-existing building lighting circuit obtained new functionalities and was preserved as much as possible.

The Amazon Rainforest represents one-third of the world’s tropical forest area. This makes it indispensable for maintaining global biodiversity. However, the increasing occurrences of wildfires and deforestation in the region are notorious. In this sense, it is essential to protect forests to ensure quality of life for future generations and prevent damage that affects the entire planet. In this work, a real-time monitoring device is proposed to identify attempts at deforestation through audio signals from tractors and chainsaws, using embedded artificial intelligence (AI). Additionally, it is capable of communicating with a base station, reaching distances close to 1 km in dense forest, through long-range (LoRa) communication. A user interface is also developed, providing daily alerts such as attack identification, occurrence times, device locations, and battery status. The system has an average power consumption of around 300 nA, employing power management methods defined as ultra-low power mode, sleep mode, prediction mode, and transmission mode. Hence, the device has the potential to promote the sustainable preservation of the Amazon Rainforest, helping to prevent large-scale illegal deforestation.