The Internet of Things (IoT) paradigm allows the connection and exchange of information between millions of smart devices. This paradigm grows and develops exponentially as do the risks and attacks on IoT infrastructures. Security, privacy, reliability, and autonomy are the most important requirements in IoT Systems. If these issues are not guaranteed, the IoT system could be susceptible to malicious users and malicious use. In centralized IoT systems, attacks and risks are greater, especially when data is transmitted between devices and shared with other organizations. To avoid these types of situations, this work presents a decentralized system that guarantees the autonomy and security of an IoT system. The proposed methodology helps to protect data integrity and availability based on the security advantages provided by blockchain and the use of cryptographic tools. The accuracy of the proposed methodology was measured on a temperature and humidity sensing IoT-based Wireless Sensor Network (WSN). The obtained results prove that the proposal fulfils the main requirements of an IoT system. It is autonomous, secure to share and send information between devices and users, has privacy, it is reliable, and the information is available in the infrastructure. Furthermore, this research demonstrates that the proposal is less susceptible to the most frequent attacks against IoT systems, such as linking attack, man in the middle, and Distributed Denial of Service (DDoS) attack.
The evaluation of the Resistance Spot Welding (RSW) that guarantees satisfactory performance of mechanical characteristics without altering physical properties can be reached by modeling the input parameters such as current, welding time, and applied force from which each unit has been built and correlating with digital images of the surface and infrared images that allows to identify variations on the parameters that modify the quality of the welding spot [1]. With this, mechanical and surface characteristics can be detected without the need for a mechanical test that modifies the structure of the unit. The database serves as a comprehensive record of the welding spot process, including the monitor of crucial input parameters such as current and force. The constructions and documentation of the testing platform through the instrumentation of a resistance welding will assess the variability of the input parameters and their impact on the output in surface and thermographic imaging, welding nugget diameter and it's mechanical strength. Additionally, it documents characteristics of the material used as thickness and material type and its output as the mechanical resistance and nugget diameter, along with its corresponding classification. Thus, the database not only captures the details of the welding process, but it also provides a valuable resource for analyzing and evaluating the performance of the welding operation.
Quality assessment of the resistance spot welding process (RSW) is vital during manufacturing. Evaluating the quality without altering the joint material’s physical and mechanical properties has gained interest. This study uses a trained computer vision model to propose a cheap, non-destructive quality-evaluation methodology. The methodology connects the welding input and during-process parameters with the output visual quality information. A manual resistance spot welding machine was used to monitor and record the process input and output parameters to generate the dataset for training. The welding current, welding time, and electrode pressure data were correlated with the welding spot nugget’s quality, mechanical characteristics, and thermal and visible images. Six machine learning models were trained on visible and thermographic images to classify the weld’s quality and connect the quality characteristics (pull force and welding diameter) and the manufacturing process parameters with the visible and thermographic images of the weld. Finally, a cross-validation method validated the robustness of these models. The results indicate that the welding time and the angle between electrodes are highly influential parameters on the mechanical strength of the joint. Additionally, models using visible images of the welding spot exhibited superior performance compared to thermal images.
Dementia is a neurodegenerative disorder characterized by progressive cognitive impairment that significantly affects daily living. Early detection of Alzheimer’s disease—the most common form of dementia—remains essential for prompt intervention and treatment, yet clinical diagnosis often requires extensive and resource-intensive procedures. This article explores the effectiveness of automated Natural Language Processing (NLP) methods for identifying Alzheimer’s indicators from audio transcriptions of the Cookie Theft picture description task in the PittCorpus dementia database. Five NLP approaches were compared: a classical Tf–Idf statistical representation and embeddings derived from large language models (GloVe, BERT, Gemma-2B, and Linq-Embed-Mistral), each integrated with a logistic regression classifier. Transcriptions were carefully preprocessed to preserve linguistically relevant features such as repetitions, self-corrections, and pauses. To compare the performance of the five approaches, a stratified 5-fold cross-validation was conducted; the best results were obtained with BERT embeddings (84.73% accuracy) closely followed by the simpler Tf–Idf approach (83.73% accuracy) and the state-of-the-art model Linq-Embed-Mistral (83.54% accuracy), while Gemma-2B and GloVe embeddings yielded slightly lower performances (80.91% and 78.11% accuracy, respectively). Contrary to initial expectations—that richer semantic and contextual embeddings would substantially outperform simpler frequency-based methods—the competitive accuracy of Tf–Idf suggests that the choice and frequency of the words used might be more important than semantic or contextual information in Alzheimer’s detection. This work represents an effort toward implementing user-friendly software capable of offering an initial indicator of Alzheimer’s risk, potentially reducing the need for an in-person clinical visit.
Modern outdoor self-localizing computer vision applications require descriptors more than repeatability. The descriptors need to be invariant to light conditions and transformation changes to give support for efficient classification. This paper investigates a new framework based on the genetic algorithm to create and optimize extensible modular descriptors for specific outdoor environments. The algorithm returns descriptors with improved efficiency and classification performance. It controls the image processing and machine learning parameters and optimizes the descriptor size by activating the necessary modules. To show the strength of the descriptor, we compared it with the most commonly used standard descriptors on speed, accuracy, and invariance to light conditions, image resolution changes, scale, affine transformation, rotation, and classification. The results show that it has an average result in transformation invariance, and its description ability in sparse areas is significantly better than that of the most-used descriptors. The descriptor was also integrated into an augmented reality algorithm to create a self-regulating segmentation application.
22 September 2016 in Pattern Analysis and Applications