Search Results (7)

Color consistency when reading colorimetric sensors is a key factor for this technology. Here, we demonstrate how the usage of machine-readable patterns, like QR codes, can be used to solve the problem. We present our approach of using back-compatible color QR codes as colorimetric sensors, which are common QR codes that also embed a set of hundreds of color references as well as colorimetric indicators. The method allows locating the colorimetric sensor within the captured scene and to perform automated color correction to ensure color consistency regardless of the hardware used. To demonstrate it, a $C{O}_2$-sensitive colorimetric indicator was printed on top of a paper-based substrate using screen printing. This indicator was formulated for Modified Atmosphere Packaging (MAP) applications. To verify the method, the sensors were exposed to several environmental conditions (both in gas composition and light conditions). And, images were captured with an 8M pixel digital camera sensor, similar to those used in smartphones. Our results show that the sensors have a relative error of 9% when exposed with a $C{O}_2$ concentration of 20%. This is a good result for low-cost disposable sensors that are not intended for permanent use. However, as soon as light conditions change (2500–6500 K), this error increases up to ${\mathsf{ϵ}}_{\mathbf{20}}$ = 440% (rel. error at 20% $C{O}_2$ concentration) rendering the sensors unusable. Within this work, we demonstrate that our color QR codes can reduce the relative error to ${\mathsf{ϵ}}_{\mathbf{20}}$ = 14%. Furthermore, we show that the most common color correction, white balance, is not sufficient to address the color consistency issue, resulting in a relative error of ${\mathsf{ϵ}}_{\mathbf{20}}$ = 90%. Full article

We present the application of QR Codes as carriers for colorimetric dyes, whereby this refined version of machine-readable patterns applied to colorimetric sensing also allows us to maintain the data from the QR Code standard in a back-compatible way, which means that the QR Code is still able to encode digital data (readable with a standard QR Code decoder) alongside a hundred colorimetric references and the dyes. Also, we discuss in detail the effectiveness of different color correction methods in attaining color accuracy levels suited for sensing via colorimetry. Moreover, we illustrate how color correction techniques can be applied to take advantage of having hundreds of color references, with an exemplary case of a CO₂ printed sensor used to monitor the integrity of modified atmosphere packaging (MAP). Full article

The increased complexity of modern systems is calling for an integrated and comprehensive approach to system design and development and, in particular, a shift toward Model-Based Systems Engineering (MBSE) approaches for system design. The requirements that serve as the foundation for these intricate systems are still primarily expressed in Natural Language (NL), which can contain ambiguities and inconsistencies and suffer from a lack of structure that hinders their direct translation into models. The colossal developments in the field of Natural Language Processing (NLP), in general, and Large Language Models (LLMs), in particular, can serve as an enabler for the conversion of NL requirements into machine-readable requirements. Doing so is expected to facilitate their standardization and use in a model-based environment. This paper discusses a two-fold strategy for converting NL requirements into machine-readable requirements using language models. The first approach involves creating a requirements table by extracting information from free-form NL requirements. The second approach consists of an agile methodology that facilitates the identification of boilerplate templates for different types of requirements based on observed linguistic patterns. For this study, three different LLMs are utilized. Two of these models are fine-tuned versions of Bidirectional Encoder Representations from Transformers (BERTs), specifically, aeroBERT-NER and aeroBERT-Classifier, which are trained on annotated aerospace corpora. Another LLM, called flair/chunk-english, is utilized to identify sentence chunks present in NL requirements. All three language models are utilized together to achieve the standardization of requirements. The effectiveness of the methodologies is demonstrated through the semi-automated creation of boilerplates for requirements from Parts 23 and 25 of Title 14 Code of Federal Regulations (CFRs). Full article

Air pollution is a pressing concern in urban areas, necessitating the critical monitoring of air quality to understand its implications for public health. Internet of Things (IoT) devices are widely utilized in air pollution monitoring due to their sensor capabilities and seamless data transmission over the Internet. Artificial intelligence (AI) and machine learning techniques play a crucial role in classifying patterns derived from sensor data. Environmental stations offer a multitude of parameters that can be obtained to uncover hidden patterns showcasing the impact of pollution on the surrounding environment. This paper focuses on utilizing the CO parameter as an indicator of pollution in two datasets collected from wireless environmental monitoring devices in the greater Port area and the Town Hall of Igoumenitsa City in Greece. The datasets are normalized to facilitate their utilization in classification algorithms. The k-means algorithm is applied, and the elbow method is used to determine the optimal number of clusters. Subsequently, the datasets are introduced to the grammatical evolution algorithm to calculate the percentage fault. This method constructs classification programs in a human-readable format, making it suitable for analysis. Finally, the proposed method is compared against four state-of-the-art models: the Adam optimizer for optimizing artificial neural network parameters, a genetic algorithm for training an artificial neural network, the Bayes model, and the limited-memory BFGS method applied to a neural network. The comparison reveals that the GenClass method outperforms the other approaches in terms of classification error. Full article

Part design is the principal source of communicating design intent to manufacturing and inspection. Design data are often communicated through computer-aided design (CAD) systems. Modern analytics tools and artificial intelligence integration into manufacturing have significantly advanced machine recognition of design specification and manufacturing constraints. These algorithms require data to be uniformly structured and easily consumable; however, the design data are represented in a graphical structure and contain a nonuniform structure, which limits the use of machine learning algorithms for a variety of tasks. This paper proposes an algorithm for extracting dimensional data from three-dimensional (3D) part designs in a structured manner. The algorithm extracts face dimensions and their relationships with other faces, enabling the recognition of underlying patterns and expanding the applicability of machine learning for various tasks. The extracted part dimensions can be stored in a dimension-based numeric extensible markup language (XML) file, allowing for easy storage and use in machine-readable formats. The resulting XML file provides a dimensional representation of the part data based on their features. The proposed algorithm reads and extracts dimensions with respect to each face of the part design, preserving the dimensional and face relevance. The uniform structure of the design data facilitates the processing of data by machine learning algorithms, enabling the detection of hidden patterns and the development of pattern-based predictive algorithms. Full article

The explosion of omics data availability in cancer research has boosted the knowledge of the molecular basis of cancer, although the strategies for its definitive resolution are still not well established. The complexity of cancer biology, given by the high heterogeneity of cancer cells, leads to the development of pharmacoresistance for many patients, hampering the efficacy of therapeutic approaches. Machine learning techniques have been implemented to extract knowledge from cancer omics data in order to address fundamental issues in cancer research, as well as the classification of clinically relevant sub-groups of patients and for the identification of biomarkers for disease risk and prognosis. Rule induction algorithms are a group of pattern discovery approaches that represents discovered relationships in the form of human readable associative rules. The application of such techniques to the modern plethora of collected cancer omics data can effectively boost our understanding of cancer-related mechanisms. In fact, the capability of these methods to extract a huge amount of human readable knowledge will eventually help to uncover unknown relationships between molecular attributes and the malignant phenotype. In this review, we describe applications and strategies for the usage of rule induction approaches in cancer omics data analysis. In particular, we explore the canonical applications and the future challenges and opportunities posed by multi-omics integration problems. Full article

We present a systematic methodology to generate machine-readable patterns embodying all the elements needed to carry out colorimetric measurements with conventional color cameras in an automated, robust and accurate manner. Our approach relies on the well-stablished machine-readable features of the QR Codes, to detect the pattern, identify the color reference elements and the colorimetric spots, to calibrate the color of the image and to conclude a quantitative measurement. We illustrate our approach with a NH3 colorimetric indicator operating at distinct color temperature ambient lights, demonstrating that with our design, consistent measurements can be achieved, with independence on the illumination conditions. Full article