Search

Producción Científica, This study addresses the issue of automatic pronunciation assessment (APA) and its contribution to the teaching of second language (L2) pronunciation. Several attempts have been made at designing such systems, and some have proven operationally successful. However, the automatic assessment of the pronunciation of short words in segmental approaches has still remained a significant challenge. Free and off-the-shelf automatic speech recognition (ASR) systems have been used in integration with other tools with the hopes of facilitating improvement in the domain of computer-assisted pronunciation training (CAPT). The use of ASR in APA stands on the premise that a word that is recognized is intelligible and well-pronounced. Our goal was to explore and test the functionality of Google ASR as the core component within a possible automatic British English pronunciation assessment system. After testing the system against standard and non-standard (foreign) pronunciations provided by participating pronunciation experts as well as non-expert native and non-native speakers of English, we found that Google ASR does not and cannot simultaneously meet two necessary conditions (here defined as intrinsic and derived) for performing as an APA system. Our study concludes with a synthetic view on the requirements of a reliable APA system.

A robust inverse method for the complex wavenumber space (complex k-space) extraction is essential for structural vibration and damping analysis of two-dimensional structures. Most existing methods suffer from extracting the reliable complex k-space of plates in the presence of realistic uncertainties, especially for plates with low damping properties. To this end, this paper presents a new method for extracting the dispersion and damping characteristics of two-dimensional periodic structures using only the full-field displacement fields as input. The proposed method, the Algebraic K-Space Identification 2D technique (AKSI 2D), is an extension of the Algebraic Wavenumber Identification technique to solve two-dimensional problems. The optimised formulas are developed within the algebraic identification framework, which allows the extraction of all the properties of the complex k-space in a comprehensive way. The proposed method is validated numerically and experimentally, and its performances are compared with other popular k-space identification methods under different uncertainty conditions. The test cases cover analytically solved isotropic fields to numerically solve orthotropic fields and finally experimental measurements. The different cases show promising results and demonstrate that the proposed method is a robust tool to characterise the wave propagation of two-dimensional structures under stochastic structural and constitution conditions., QC 20240927

Graphical security models constitute a well-known, user-friendly way to represent the security of a system. These classes of models are used by security experts to identify vulnerabilities and assess the security of a system. The manual construction of these models can be tedious, especially for large enterprises. Consequently, the research community is trying to address this issue by proposing methods for the automatic generation of such models. In this work, we present a survey illustrating the current status of the automatic generation of two popular kinds of graphical security models: Attack Trees and Attack Graphs. The goal of this survey is to present the current methodologies used in the field, compare them, and present the challenges and future directions to the research community.

Precision viticulture is increasingly being applied to automate and optimize grape production in the vineyard. This paper describes the development of a method for automatic selection of regions of interest from hyperspectral images obtained of a row of vines and intended for prediction of soluble solids content. For this purpose, a dataset consisting of hyperspectral images of a row of ‘Sangiovese’ wine grapes was adopted. Hyperspectral images were acquired directly in the field by means of a hyperspectral imaging Vis/NIR system (400–1000 nm) mounted on a ground-based vehicle. The analyses were carried out on 17 different days, under clear or partly cloudy conditions, in the period between post-veraison and harvest. The vineyard row of Sangiovese vines was divided into 11 sections and a hyperspectral image for each section for each day of analysis was acquired. The regions of interest of the hyperspectral images, comprising the areas representing the grapes, were selected using a PLS-DA-based method. The best PLS-DA model provided excellent results, with sensitivity and specificity values of 0.991 and 0.996, respectively. The mean spectra of the selected regions of interest (ROI) were finally used to predict the soluble solids content (SSC) of the grapes by PLS regression to a primary reference analysis. The results of SSC predictions using the automatic selection of ROIs (R2CV = 0.74 and RMSECV = 0.86 °Brix) were on par with similar regression based on carefully manual selection of ROIs (R2CV = 0.73 and RMSECV = 0.87 °Brix).

Loop-efficient automatic parallelization has become increasingly relevant due to the growing number of cores in current processors and the programming effort needed to parallelize codes in these systems efficiently. However, automatic tools fail to extract all the available parallelism in irregular loops with indirections, race conditions or potential data dependency violations, among many other possible causes. One of the successful ways to automatically parallelize these loops is the use of speculative parallelization techniques. This paper presents a new model and the corresponding C++ library that supports the speculative automatic parallelization of loops in shared memory systems, seeking competitive performance and scalability while keeping user effort to a minimum. The primary speculative strategy consists of redundantly executing chunks of loop iterations in a duplicate fashion. Namely, each chunk is executed speculatively in parallel to obtain results as soon as possible and sequentially in a different thread to validate the speculative results. The implementation uses C++11 threads and it makes intensive use of templates and advanced multithreading techniques. An evaluation based on various benchmarks confirms that our proposal provides a competitive level of performance and scalability.

Annotated corpora are indispensable tools to train computational models in Artificial Intelligence and Natural Language Processing. However, manual annotation is a costly, arduous, and time-consuming task, especially when the annotation is semantically complex. To address the problem, this work applies a methodology for semi-automatic annotation of datasets based on the Human-in-the-Loop paradigm. The methodology supports the building a resource, that benefits from a fine-grained annotation, to aid in the detection of Spanish violent messages sourced from social media (Twitter/X). After implementing the proposed methodology for semi-automatic violence annotation, a high quality resource was obtained (hereafter referred to as VILLANOS). The methodology consists of annotating the dataset incrementally, which delivers an increase in annotator efficiency, thereby validating the suitability of the proposal. Annotation time was reduced by 52% compared to manual annotation and performance, by training a model with the VILLANOS dataset, obtains an F 1 of 85.2%. These results demonstrate the efficiency and effectiveness of the methodology, evidencing its validity.

Fishery products, especially capture fisheries, must be safe and high-quality. The treatment of captured fish from capture to consumption is crucial to maintaining its quality. Temperature impacts fish quality. Fish putrefaction can be prevented at a specific temperature. Maintaining optimal fish quality requires temperature monitoring at the holding hatch of fish captured on board. Indonesia requires hatches with fish storage to have automatic temperature recorders and monitors. Inspections by authorities who issued certifications of acceptable fish handling practices found many breaches on Indonesian fishing vessels without automatic temperature monitoring systems. Indonesian fishery exports to the EU have been rejected due to the lack of automatic temperature recording systems on fishing vessels. Existing automatic temperature recording equipment for fishing vessels does not meet technical and legal requirements. The lack of autonomous temperature monitoring devices on fishing vessels was solved via design thinking in an exploratory study. Thus, fishing vessel temperature recording devices were designed using Internet of Things technology. Literature is utilized to choose resources. Hatch temperature recorder, MAX 31865 module, and PT100 thermocouple sensor use ESP 32 as a microprocessor. Raspberry Pi4 controls, displays, and stores data. This fish hatch temperature recorder has a GPS module for coordinates. This utility manages display and storage with Home Assistant software. Commercial low-temperature recorders are utilized for comparison testing. Before calibration, the pesuotokapi tool had a variance coefficient of 9.39%, whereas the comparison tool had 12.09%. The pesuotokapi tool has a coefficient of variation of 11.96% after calibration, whereas the comparison tool had 13.28%. The pesuotokapi tool regularly yields a lower coefficient of variation than the comparison tool. This shows that the pesuotokapi tool generates data with less divergence from the a

Objective: Robotic assistants are becoming a very helpful tool for surgeons. As for the suturing procedure, several commercial devices assist the physician in suturing. However, such devices have not yet been coupled to a robot assistant in order to perform sutures fully automatically. This could contribute to a procedure that is often routinely performed but requires time and dexterity. Materials and methods: This article presents the adaptation of a commercial manual suture gripper, the Medtronic Endo Stitch, to a Universal Robots UR3 robot. The gripper was modeled in SolidWorks, as well as a motorized coupling device, which were simulated in CoppeliaSim. Once its proper functioning was verified, the device was fabricated in a 3D printer and coupled to a UR3 robot, then its operation was tested in the tracking of a suture trajectory with displacement. Results: The trajectories planned in Matlab are sent to the UR3 robot via ROS. It was possible to verify the good performance of the suture movement with displacement, carried out by the printed device and by the Endo Stitich gripper. The opening and closing of the gripper was also obtained under the action of the motors included in the device. Conclusions: The motorized device together with the Endo Stitch gripper, coupled to the UR3 robot, is capable of following the trajectories required for automatic suturing. Future work will test suturing with thread on a test phantom in order to measure its true potential for automatic suturing., Objetivo: Los asistentes robóticos se están convirtiendo en una herramienta de gran ayuda para los cirujanos. En cuanto al procedimiento de sutura, aunque existen varios dispositivos comerciales que le ayudan al médico a realizarla, todavía no se han acoplado dichos dispositivos a un robot asistente con el fin de realizar suturas de manera completamente automática. De esta manera se contribuiría con un procedimiento que muchas veces es rutinario pero que requiere tiempo y destreza. Materiales y métodos: Este artículo presenta la adecuación de una pinza manual de sutura comercial, la Endo Stitch de Medtronic, a un robot UR3 de Universal Robots. La pinza fue modelada en SolidWorks, así como un dispositivo de acople motorizado, los cuales fueron simulados en CoppeliaSim. Una vez verificado su buen funcionamiento, el dispositivo fue fabricado en una impresora 3D y acoplado a un robot UR3, probándose entonces su funcionamiento en el seguimiento de una trayectoria de sutura con desplazamiento. Resultados: Las trayectorias planificadas en Matlab son enviadas al robot UR3 vía ROS. Se pudo comprobar el buen desempeño del movimiento de sutura con desplazamiento, efectuado por el dispositivo impreso y por la pinza Endo Stitich. Igualmente se obtuvo la apertura y cerrado de la pinza bajo el accionar de los motores incluidos en el dispositivo. Conclusiones: El dispositivo motorizado junto con la pinza Endo Stitch, y acoplado al robot UR3, es capaz de seguir las trayectorias necesarias para la realización de una sutura automática. Trabajos futuros realizarán pruebas de sutura con hilo sobre un phantom de prueba con el fin de medir su verdadero potencial para realizar suturas de manera automática.

This study aimed to develop a rapid, 1 mm3 isotropic resolution, whole-brain MRI technique for automatic lesion segmentation and multi-parametric mapping without using contrast by continuously applying balanced steady-state free precession with inversion pulses throughout incomplete inversion recovery in a single 6 min scan. Modified k-means clustering was performed for automatic brain tissue and lesion segmentation using distinct signal evolutions that contained mixed T1/T2/magnetization transfer properties. Multi-compartment modeling was used to derive quantitative multi-parametric maps for tissue characterization. Fourteen patients with contrast-enhancing gliomas were scanned with this sequence prior to the injection of a contrast agent, and their segmented lesions were compared to conventionally defined manual segmentations of T2-hyperintense and contrast-enhancing lesions. Simultaneous T1, T2, and macromolecular proton fraction maps were generated and compared to conventional 2D T1 and T2 mapping and myelination water fraction mapping acquired with MAGiC. The lesion volumes defined with the new method were comparable to the manual segmentations (r = 0.70, p < 0.01; t-test p > 0.05). The T1, T2, and macromolecular proton fraction mapping values of the whole brain were comparable to the reference values and could distinguish different brain tissues and lesion types (p < 0.05), including infiltrating tumor regions within the T2-lesion. Highly efficient, whole-brain, multi-contrast imaging facilitated automatic lesion segmentation and quantitative multi-parametric mapping without contrast, highlighting its potential value in the clinic when gadolinium is contraindicated.

Cryogenic electron tomography (cryoET) is capable of determining in situ biological structures of molecular complexes at near-atomic resolution by averaging half a million subtomograms. While abundant complexes/particles are often clustered in arrays, precisely locating and seamlessly averaging such particles across many tomograms present major challenges. Here, we developed TomoNet, a software package with a modern graphical user interface to carry out the entire pipeline of cryoET and subtomogram averaging to achieve high resolution. TomoNet features built-in automatic particle picking and three-dimensional (3D) classification functions and integrates commonly used packages to streamline high-resolution subtomogram averaging for structures in 1D, 2D, or 3D arrays. Automatic particle picking is accomplished in two complementary ways: one based on template matching and the other using deep learning. TomoNet's hierarchical file organization and visual display facilitate efficient data management as required for large cryoET datasets. Applications of TomoNet to three types of datasets demonstrate its capability of efficient and accurate particle picking on flexible and imperfect lattices to obtain high-resolution 3D biological structures: virus-like particles, bacterial surface layers within cellular lamellae, and membranes decorated with nuclear egress protein complexes. These results demonstrate TomoNet's potential for broad applications to various cryoET projects targeting high-resolution in situ structures.

The challenge hybrid system power sources face is switching from one source to another. This transfer is required to anticipate the depletion of energy sources in the battery owing to unfavorable weather, such that the solar panels do not receive sufficient sunlight. An automatic switching process with minimal time lag is required to maintain the continuity of the electrical energy flow. In addition, there is a growing need to analyze the energy consumption in certain areas and periods. This project designed and built an Internet of Things (IoT) based Automatic Transfer Switch (ATS) system. The ATS prototype uses the Arduino MEGA 2560 microcontroller to switch the power source and the ESP32 DevKit V1 microcontroller to send the data logger to the IoThingsHub cloud platform for monitoring systems that are useful for sustainable ecosystems. The sensor exhibited accuracies of 99.8% for voltage and 96.5% for current readings. The ATS prototype could switch between power sources with an average time lag of 47 ms. The results of the field trials show that the ATS prototype design utilized solar photovoltaic for approximately 26% of the usage, with a 100 Ah 12V battery system and three 100 Wp solar panels in sunny/partly cloudy conditions for 50 W lamp loads.

Background: For bone morphology and biomechanics analysis, landmarks are essential to define position, orientation, and shape. These landmarks define bone and joint coordinate systems and are widely used in these research fields. Currently, no method is known for automatically identifying landmarks on virtual 3D bone models of the radius and ulna. This paper proposes a knowledge-based method for locating landmarks and calculating a coordinate system for the radius, ulna, and combined forearm bones, which is essential for measuring forearm function. This method does not rely on pre-labeled data. Validation: The algorithm is validated by comparing the landmarks placed by the algorithm with the mean position of landmarks placed by a group of experts on cadaveric specimens regarding distance and orientation. Results: The median Euclidean distance differences between all the automated and reference landmarks range from 0.4 to 1.8 millimeters. The median angular differences of the coordinate system of the radius and ulna range from -1.4 to 0.6 degrees. The forearm coordinate system's median errors range from -0.2 to 2.0 degrees. The median error in calculating the rotational position of the radius relative to the ulna is 1.8 degrees. Conclusion: The automatic method's applicability depends on the use context and desired accuracy. However, the current method is a validated first step in the automatic analysis of the three-dimensional forearm anatomy.

BACKGROUND AND OBJECTIVES: Dual process models of addiction suggest that controlled, goal-directed processes prevent drug-use, whereas impulsive, stimulus-driven processes promote drug-use. The most frequently used measure of automatic smoking-related processes, the implicit association test (IAT), has yielded mixed results. We examine the validity of two alternative implicit measures: 1) the affect misattribution procedure (AMP), a measure of automatic evaluations, and 2) the relational responding task (RRT), a measure of implicit beliefs.METHODS: Smokers and non-smokers performed smoking-related versions of the AMP and the RRT and filled in questionnaires for smoking dependence. Smokers participated in two sessions: once after they just smoked, and once after being deprived for 10 h. Smokers also kept a smoking diary for a week after the second session.RESULTS: We found significant differences between smokers and non-smokers on the RRT, t (86) = 2.86, p = .007, d = 0.61, and on the AMP, F (1, 85) = 6.22, p = .015, pƞ 2 = 0.07. Neither the AMP nor the RRT were affected by the deprivation manipulation. Smoking dependence predicted smoking behavior in the following week; the AMP and RRT did not explain additional variance. LIMITATIONS: Possibly, our manipulation was not strong enough to affect the motivational state of participants in a way that it changed their implicit cognitions. Future research should examine the sensitivity of implicit measures to (motivational) context.CONCLUSIONS: We found limited evidence for the validity of the smoking-AMP and the smoking-RRT, highlighting the need for a critical view on implicit measures.

Fiction is a challenging genre for automatic theme identification. Unlike other types of documents, such as physics academic papers, fiction does not always name the concepts it addresses, but rather implies them through subtle clues. Fiction also uses metaphors intentionally to convey deeper meanings. To make Swedish LGBTQ+ fiction more accessible, the Queerlit database (https://queerlit.dh.gu.se/) provides subject indexing by information professionals. They use the QLIT thesaurus (based on Homosaurus) for LGBTQ+ themes and Swedish Subject Headings (SAO – Svenska Ämnesord) for non-LGBTQ+ themes. The indexing is comprehensive and retrospective, assigning terms to previously published Swedish fiction. This work aims to determine to what degree and under which conditions is it possible to automatically assign subject index terms from QLIT, in order to estimate the usefulness of automatic tools to support subject indexing conducted by information professionals. This process may require a large number of training documents which are not available (the entire Queerlit database has about 2000 works indexed and QLIT has about 800 terms, while SAO is much bigger). Therefore, another approach will be explored – whether automatically extracted terms from the texts provide the potential to complement existing, professionally assigned terms from QLIT and SAO. We experiment with zero-shot classification transformers and topic modeling. The proposed paper will present the intermediate results of different methods applied to available texts from the QLIT database. It is important to note that the project is currently in an exploratory phase and that the presentation is intended to showcase how different approaches have both failed and succeeded. We also intend to highlight areas of possible applicability specifically from the perspective afforded by the QLIT thesaurus, i.e., the appropriateness of the methods for Swedish LGBTQ+ fiction. We will also discuss the challenges and limi

With this thesis, we aim to automate the creation of DJ mixes. A DJ mix consists of an uninterrupted sequence of music, constructed by playing tracks one after the other, to improve the listening experience for the audience. Thus, to be able to build mixes automatically, we first need to understand the tracks we want to mix. This is done by extracting information from the audio signal. Specifically, we retrieve two pieces of information that are essential for DJs: cue points and drum transcription. In the field of music information retrieval, the two associated tasks are cue point detection and automatic drum transcription. With cue point detection, we identify the positions in the tracks that can be used to create pleasant transitions in the mix. DJs have a good intuition on how to detect these positions. However, it is not straightforward to transform their intuition into a computer program because of the semantic gap between the two. To solve this problem we propose multiple approaches based on either expert knowledge or machine learning. Further, by interpreting the resulting models from our approaches, we also reflect on the musical content that is linked to the presence of cue points. With automatic drum transcription, we aim to retrieve the position and the instrument of the notes played on the drumkit, to characterize the musical content of the tracks. To create the transcription, the most promising method is based on supervised deep learning. That is, models trained on labeled datasets. However, because of the difficulty of creating the annotations, the datasets available for training are usually limited in size or diversity. Thus, we propose novel methods to create better training data, either with real-world or synthetic music tracks. Further, by investigating thoroughly the performance of the models resulting from the training data, we deduce the most relevant characteristics of a dataset that help train models. The solutions we proposed for both tasks o

This thesis explores the adoption of semi-automatic functions in wheel loaders by novice operators with three years of experience, highlighting the design's role in enhancing operator engagement and efficiency in short-cycle loading tasks. Research findings demonstrate that hands-on, practical learning of semi-automatic functions is significantly more effective than theoretical approaches, although both remain crucial. The study identifies a major barrier to adopting semi-automatic functions: the lack of familiarity and previous exposure to these functions, leading to a preference for manual control due to the operator’s traditional method’s comfort and perceived simplicity. To address these challenges, this thesis proposes a design solution that includes clear, easy-to-understand instructions and real-time feedback to help operators recognize the semi-automatic function’s ergonomic and efficiency benefits. Demonstrating the practical advantages of these functions in action has proven to shift operators’ attitudes positively. Furthermore, the operators’ perceptions of their usability and usefulness significantly influence the adoption of semi-automatic functions. The design recommendations advocate for an intuitive interface that offers step-by-step guidance and interactive tutorials, making the semi-automatic functions more accessible and encouraging novice operators to transition more smoothly to semi-automation. Overall, the thesis underscores the importance of a user-centered design approach that facilitates the initial adoption of semi-automatic functions and supports the ongoing development of operator skills and the optimization of work practices in the construction industry., Denna uppsats utforskar användningen av semi-automatiska funktioner i hjullastare av nybörjaroperatörer med tre års erfarenhet, och lägger vikt på rollen som design spelar för att kunna öka operatörens engagemang och effektivitet under kortcykellastning. Resultatet av forskningen visar att praktisk inlärning av semi-automatiska funktioner är betydligt mer effektiv än teoretiska tillvägagångssätt, även om båda är viktiga. Studien har identifierat ett stort hinder för att använda semi-automatiska funktioner: bristen på bekantskap och tidigare exponering för dessa funktioner, vilket leder till en preferens för manuell kontroll på grund av bekvämlighet och enkelheten av sina traditionella metoder. För att möta dessa utmaningar föreslår denna uppsats en designlösning som inkluderar tydliga, lättförståeliga instruktioner och realtidsfeedback för att hjälpa operatörer att känna igen de ergonomiska och effektivitetsfördelar som halvautomatiska funktioner erbjuder. Att demonstrera de praktiska fördelarna med dessa funktioner under manövrering med fordonet har visat sig positivt påverka operatörernas attityder. Dessutom påverkar operatörernas uppfattningar om användbarheten och nyttan avsevärt användningen av semi-automatiska funktioner. Designrekommendationerna förespråkar ett intuitivt gränssnitt som erbjuder steg- för-stegvägledning vilket gör de semi-automatiska funktionerna mer tillgängliga och uppmuntrar nybörjaroperatörer att övergå smidigare till semi-automatik. Slutligen understryker uppsatsen vikten av en användarcentrerad designmetod som inte bara underlättar den initiala användningen av semi-automatiska funktioner, utan också stödjer den kontinuerliga utvecklingen av operatörers färdigheter och optimeringen av arbetsmetoder inom byggnadsindustrin.

The automatic control subject has several connections to sustainability and can play an important role in the strive towards a more sustainable society. An example of how sustainability is included in a basic course in automatic control is presented, where the links between the degree requirements, sustainability and the subject are illustrated using The Global Goals for Sustainable Development (SGDs). The key idea is to present real world application examples where automatic control is a vital component and there are clear connections to the SDGs. The examples are inspired and illustrated using videos and images taken from the internet. Several times during the course a part of the lecture time is used to show a video, describe how the control subject comes in, and how the use of feedback control via the application can contribute to the fulfillment of the SDG

Background Identifying hate speech (HS) is a central concern within online contexts. Current methods are insufficient for efficient preemptive HS identification. In this study, we present the results of an analysis of automatic HS identification applied to popular alt-right YouTube videos. Methods This essay describes methodological challenges of automatic HS detection. The case study concerns data on a formative segment of contemporary radical right discourse. Our purpose is twofold. (1) To outline an interdisciplinary mixed-methods approach for using automated identification of HS. This bridges the gap between technical research on the one hand (such as machine learning, deep learning, and natural language processing, NLP) and traditional empirical research on the other. Regarding alt-right discourse and HS, we ask: (2) What are the challenges in identifying HS in popular alt-right YouTube videos? Results The results indicate that effective and consistent identification of HS communication necessitates qualitative interventions to avoid arbitrary or misleading applications. Binary approaches of hate/non-hate speech tend to force the rationale for designating content as HS. A context-sensitive qualitative approach can remedy this by bringing into focus the indirect character of these communications. The results should interest researchers within social sciences and the humanities adopting automatic sentiment analysis and for those analysing HS and radical right discourse. Conclusions Automatic identification or moderation of HS cannot account for an evolving context of indirect signification. This study exemplifies a process whereby automatic hate speech identification could be utilised effectively. Several methodological steps are needed for a useful outcome, with both technical quantitative processing and qualitative analysis being vital to achieve meaningful results. With regard to the alt-right YouTube material, the main challenge is indirect framing. Identific

The automatic projection filter is a recently developed numerical method for projection filtering that leverages sparse-grid integration and automatic differentiation. However, its accuracy is highly sensitive to the accuracy of the cumulant-generating function computed via the sparse-grid integration, which in turn is also sensitive to the choice of the bijection from the canonical hypercube to the state space. In this article, we propose two new adaptive parametric bijections for the automatic projection filter. The first bijection relies on the minimization of Kullback-Leibler divergence, whereas the second method employs the sparse-grid Gauss-Hermite quadrature. The two new bijections allow the sparse-grid nodes to adaptively move within the high-density region of the state space, resulting in a substantially improved approximation while using only a small number of quadrature nodes. The practical applicability of the methodology is illustrated in three simulated nonlinear filtering problems.

The implementation of a blockchain system for the automatic generation of academic credentials in a higher education institution can be considered as a safeguard against potential instances of abuse and counterfeiting of diplomas. However, the utilization of blockchain technology in the field of education, particularly within higher education institutions, appears to be limited in scope. This article aims to elucidate the advantages and constraints associated with the use of blockchain technology in higher education organizations. In addition, we present the ideas towards developing a blockchain-based prototype model that targets the automatic generation of diplomas using smart contracts and ensures the fast and secure verification of diplomas. In order to provide a more comprehensive understanding of the blockchain system, we aim to expand on its description via the use of graphical representations in the form of use case diagrams for each actor involved in the system. Additionally, we provide use case scenarios, as well as outline the functional as well as the nonfunctional requirements that are essential for the proper functioning of such a system.

Catfish breeding using an automatic feeding system involves four crucial stages to achieve success in this endeavor. The first stage in this process is the survey stage, which involves a field survey by visiting the Aisyiyah Children's Social Welfare Institution (LKSA). The second stage is the tool preparation stage. This process begins with purchasing the necessary equipment based on the results of the survey that has been conducted. The third stage is the tool installation stage. This stage begins with the land preparation, including leveling the land where the catfish ponds will be installed. As a further step, bricks are used around the perimeter of the catfish pond to support the pond foundation and prevent collapse. Then, an automatic feed device was installed to support the automatic feeding system according to a predetermined schedule. The last stage is the equipment handover stage. This stage marks the completion of the installation and preparation process and signifies the start of the active phase in catfish farming using the automatic feed system. Success in the implementation of each of these stages has direct implications for the success and sustainability of the catfish farming business at LKSA Aisyiyah.

The aim of this study was to preoperatively asses the feasibility of drilling a bony recess for the fixation of a cochlear implant in the temporal bone. Even though complications are rare with cochlear implantations, drilling at the site of implantation have resulted in hematoma or cerebrospinal fluid leakage. Mainly in cases with a reduced temporal bone thickness, the risk for complications has increased, such as in paediatric patients.Methods An in-house designed semi-automatic algorithm was developed to analyse a 3D model of the skull. The feasibility of drilling the recess was determined by a gradient descent method to search for the thickest part of the temporal bone. Feasibility was determined by the residual bone thickness which was calculated after a simulated drilling of the recess at the thickest position. An initial validation of the algorithm was performed by measuring the accuracy of the algorithm on five 3D models with known thickest locations for the recess. The accuracy was determined by a part comparison between the known position and algorithm provided position.Results In four of the five validation models a standard deviation for accuracy below the predetermined cut-off value of 4.2 mm was achieved between the actual thickest position and the position determined by the algorithm. Furthermore, the residual thickness calculated by the algorithm showed a high agreement (max. 0.02 mm difference) with the actual thickness.Conclusion With the developed algorithm, a semi-automatic method was created to analyse the temporal bone thickness within a specified region of interest on the skull. Thereby, providing indications for surgical feasibility, potential risks for anatomical structures and impact on procedure time of cochlear implantation. This method could be a valuable research tool to objectively assess feasibility of drilling a recess in patients with thin temporal bones preoperatively.

Automatic plant sprinklers aim to replace manual work into automatic, as for the benefits obtained from this tool is that it can facilitate human work in watering onion plants. This tool uses a soil moisture sensor that functions as a soil moisture detector and sends commands to Arduino uno to turn on the relay so that the pump can turn on and splash water according to soil needs automatically. The design of this tool utilizes the nature of water, which is to fill empty space, and is always flat, this automatic plant sprinkler uses a water reservoir before water is splashed on the ground. Output holes applied to water reservoirs of the same height and diameter allow watering of the soil evenly. The results of the automatic plant sprinkler design test obtained after three tests, have a difference in the amount of water released from water hole one and water hole two, which ranges from 0-7%, which means it is still within the tolerance limit for onion plants, onion plants need soil moisture between 70-80%, which means it has a moisture tolerance between 10%.

Reading comprehension tests are used in a variety of applications, reaching from education to assessing the comprehensibility of simplified texts. However, creating such tests manually and ensuring their quality is difficult and time-consuming. In this paper, we explore how large language models (LLMs) can be used to generate and evaluate multiple-choice reading comprehension items. To this end, we compiled a dataset of German reading comprehension items and developed a new protocol for human and automatic evaluation, including a metric we call text informativity, which is based on guessability and answerability. We then used this protocol and the dataset to evaluate the quality of items generated by Llama 2 and GPT-4. Our results suggest that both models are capable of generating items of acceptable quality in a zero-shot setting, but GPT-4 clearly outperforms Llama 2. We also show that LLMs can be used for automatic evaluation by eliciting item reponses from them. In this scenario, evaluation results with GPT-4 were the most similar to human annotators. Overall, zero-shot generation with LLMs is a promising approach for generating and evaluating reading comprehension test items, in particular for languages without large amounts of available data.

Established surgical navigation systems for pedicle screw placement have been proven to be accurate, but still reveal limitations in registration or surgical guidance. Registration of preoperative data to the intraoperative anatomy remains a time-consuming, error-prone task that includes exposure to harmful radiation. Surgical guidance through conventional displays has well-known drawbacks, as information cannot be presented in-situ and from the surgeon's perspective. Consequently, radiation-free and more automatic registration methods with subsequent surgeon-centric navigation feedback are desirable. In this work, we present a marker-less approach that automatically solves the registration problem for lumbar spinal fusion surgery in a radiation-free manner. A deep neural network was trained to segment the lumbar spine and simultaneously predict its orientation, yielding an initial pose for preoperative models, which then is refined for each vertebra individually and updated in real-time with GPU acceleration while handling surgeon occlusions. An intuitive surgical guidance is provided thanks to the integration into an augmented reality based navigation system. The registration method was verified on a public dataset with a median of 100% successful registrations, a median target registration error of 2.7 mm, a median screw trajectory error of 1.6°and a median screw entry point error of 2.3 mm. Additionally, the whole pipeline was validated in an ex-vivo surgery, yielding a 100% screw accuracy and a median target registration error of 1.0 mm. Our results meet clinical demands and emphasize the potential of RGB-D data for fully automatic registration approaches in combination with augmented reality guidance.

Children imitate others for different reasons: To learn from others and to reach social goals such as affiliation or prosociality. So far, imitative acts have been measured using diverging methods in children and adults. Here, we investigated whether school-aged children’s imitation can be measured via their automatic imitation with a classical imitation-inhibition task (Brass et al., 2000) as has been used in adults. To this end, we measured automatic imitation in N = 94 7–8-year-olds and N = 10 adults. The results were similar in children and adults: Observing actions that are incongruent with participants’ actions interferes with their responses resulting in increased reaction times and error rates. This shows that assessing automatic imitation via the imitation-inhibition task is feasible in children, and creates the basis for future studies to compare the behaviour of different age groups with the same imitation task.

Objective. Accurate extraction of mitral valve shape from clinical tomographic images acquired in patients has proven useful for planning surgical and interventional mitral valve treatments. However, manual extraction of the mitral valve shape is laborious, and the existing automatic extraction methods have not been sufficiently accurate. In this paper, we propose a fully automated method of extracting mitral valve shape from computed tomography (CT) images for the all phases of the cardiac cycle. Approach. This method extracts the mitral valve shape based on DenseNet using both the original CT image and the existence probability maps of the mitral valve area inferred by U-Net as input. A total of 1585 CT images from 204 patients with various cardiac diseases including mitral regurgitation were collected and manually annotated for mitral valve region. The proposed method was trained and evaluated by 10-fold cross validation using the collected data and was compared with the method without the existence probability maps. Main results. The mean error of shape extraction error in the proposed method is 0.88 mm, which is an improvement of 0.32 mm compared with the method without the existence probability maps. Significance. We present a novel fully automatic mitral valve extraction method from input to output for all phases of 4D CT images. We suggest that the accuracy of mitral valve shape extraction is improved by using existence probability maps., Objective. Accurate extraction of mitral valve shape from clinical tomographic images acquired in patients has proven useful for planning surgical and interventional mitral valve treatments. However, manual extraction of the mitral valve shape is laborious, and the existing automatic extraction methods have not been sufficiently accurate. In this paper, we propose a fully automated method of extracting mitral valve shape from computed tomography (CT) images for the all phases of the cardiac cycle. Approach. This method extracts the mitral valve shape based on DenseNet using both the original CT image and the existence probability maps of the mitral valve area inferred by U-Net as input. A total of 1585 CT images from 204 patients with various cardiac diseases including mitral regurgitation were collected and manually annotated for mitral valve region. The proposed method was trained and evaluated by 10-fold cross validation using the collected data and was compared with the method without the existence probability maps. Main results. The mean error of shape extraction error in the proposed method is 0.88 mm, which is an improvement of 0.32 mm compared with the method without the existence probability maps. Significance. We present a novel fully automatic mitral valve extraction method from input to output for all phases of 4D CT images. We suggest that the accuracy of mitral valve shape extraction is improved by using existence probability maps.

DWI/FLAIR mismatch assessment for ischemic stroke patients shows promising results in determining if patients are eligible for recombinant tissue-type plasminogen activator (r-tPA) treatment. However, the mismatch criteria suffer from two major issues: binary classification of a non-binary problem and the subjectiveness of the assessor. In this article, we present a simple automatic method for segmenting stroke-related parenchymal hyperintensities on FLAIR, allowing for an automatic and continuous DWI/FLAIR mismatch assessment. We further show that our method’s segmentations have comparable inter-rater agreement (DICE 0.820, SD 0.12) compared to that of two neuro-radiologists (DICE 0.856, SD 0.07), that our method appears robust to hyper-parameter choices (suggesting good generalizability), and lastly, that our methods continuous DWI/FLAIR mismatch assessment correlates to mismatch assessments made for a cohort of wake-up stroke patients at hospital submission. The proposed method shows promising results in automating the segmentation of parenchymal hyperintensity within ischemic stroke lesions and could help reduce inter-observer variability of DWI/FLAIR mismatch assessment performed in clinical environments as well as offer a continuous assessment instead of the current binary one. Keywords: DWI/FLAIR mismatch; ischemic stroke; wake-up stroke; r-tPA; MRI, DWI/FLAIR mismatch assessment for ischemic stroke patients shows promising results in determining if patients are eligible for recombinant tissue-type plasminogen activator (r-tPA) treatment. However, the mismatch criteria suffer from two major issues: binary classification of a non-binary problem and the subjectiveness of the assessor. In this article, we present a simple automatic method for segmenting stroke-related parenchymal hyperintensities on FLAIR, allowing for an automatic and continuous DWI/FLAIR mismatch assessment. We further show that our method’s segmentations have comparable inter-rater agreement (DICE 0.820, SD 0.12) compared to that of two neuro-radiologists (DICE 0.856, SD 0.07), that our method appears robust to hyper-parameter choices (suggesting good generalizability), and lastly, that our methods continuous DWI/FLAIR mismatch assessment correlates to mismatch assessments made for a cohort of wake-up stroke patients at hospital submission. The proposed method shows promising results in automating the segmentation of parenchymal hyperintensity within ischemic stroke lesions and could help reduce inter-observer variability of DWI/FLAIR mismatch assessment performed in clinical environments as well as offer a continuous assessment instead of the current binary one.

Significance: Near-infrared fluorescence imaging still lacks a standardized, objective method to evaluate fluorescent dye efficacy in oncological surgical applications. This results in difficulties in translation between preclinical to clinical studies with fluorescent dyes and in the reproduction of results between studies, which in turn hampers further clinical translation of novel fluorescent dyes. Aim: Our aim is to develop and evaluate a semi-automatic standardized method to objectively assess fluorescent signals in resected tissue. Approach: A standardized imaging procedure was designed and quantitative analysis methods were developed to evaluate non-targeted and tumor-targeted fluorescent dyes. The developed analysis methods included manual selection of region of interest (ROI) on white light images, automated fluorescence signal ROI selection, and automatic quantitative image analysis. The proposed analysis method was then compared with a conventional analysis method, where fluorescence signal ROIs were manually selected on fluorescence images. Dice similarity coefficients and intraclass correlation coefficients were calculated to determine the inter- and intraobserver variabilities of the ROI selections and the determined signal- and tumor-to-background ratios. Results: The proposed non-targeted fluorescent dyes analysis method showed statistically significantly improved variabilities after application on indocyanine green specimens. For specimens with the targeted dye SGM-101, the variability of the background ROI selection was statistically significantly improved by implementing the proposed method. Conclusion: Semi-automatic methods for standardized quantitative analysis of fluorescence images were successfully developed and showed promising results to further improve the reproducibility and standardization of clinical studies evaluating fluorescent dyes.

BACKGROUND: Cystic fibrosis (CF) lung disease is characterised by progressive airway wall thickening and widening. We aimed to validate an artificial intelligence-based algorithm to assess dimensions of all visible bronchus-artery (BA) pairs on chest CT scans from patients with CF.METHODS: The algorithm fully automatically segments the bronchial tree; identifies bronchial generations; matches bronchi with the adjacent arteries; measures for each BA-pair bronchial outer diameter (B out), bronchial lumen diameter (B in), bronchial wall thickness (B wt) and adjacent artery diameter (A); and computes B out/A, B in/A and B wt/A for each BA pair from the segmental bronchi to the last visible generation. Three datasets were used to validate the automatic BA analysis. First BA analysis was executed on 23 manually annotated CT scans (11 CF, 12 control subjects) to compare automatic with manual BA-analysis outcomes. Furthermore, the BA analysis was executed on two longitudinal datasets (Copenhagen 111 CTs, ataluren 347 CTs) to assess longitudinal BA changes and compare them with manual scoring results. RESULTS: The automatic and manual BA analysis showed no significant differences in quantifying bronchi. For the longitudinal datasets the automatic BA analysis detected 247 and 347 BA pairs/CT in the Copenhagen and ataluren dataset, respectively. A significant increase of 0.02 of B out/A and B in/A was detected for Copenhagen dataset over an interval of 2 years, and 0.03 of B out/A and 0.02 of B in/A for ataluren dataset over an interval of 48 weeks (all p<0.001). The progression of 0.01 of B wt/A was detected only in the ataluren dataset (p<0.001). BA-analysis outcomes showed weak to strong correlations (correlation coefficient from 0.29 to 0.84) with manual scoring results for airway disease. CONCLUSION: The BA analysis can fully automatically analyse a large number of BA pairs on chest CTs to detect and monitor progression of bronchial wall thic

While the data science ecosystem is dominated by programming languages that do not feature a strong type system, it is widely agreed that using strongly typed programming languages leads to more maintainable and less error-prone code and ultimately more trustworthy results. We believe Scala 3 would be an excellent contender for data science in a strongly typed language, but it lacks a general automatic differentiation library, e.g., for gradient-based learning.We present ScalaGrad, a general and type-safe automatic differentiation library designed for Scala. It builds on and improves a novel approach from the functional programming community using immutable duals, which is conceptually simple, asymptotically optimal and allows differentiation of higher-order code. We demonstrate the ease of use, robust performance, and versatility of ScalaGrad through its applications to deep learning, higher-order optimization, and gradient-based sampling. Specifically, we show an execution speed comparable to PyTorch for a simple deep learning use case, capabilities for higher-order differentiation, and opportunities to design more specialized libraries decoupled from ScalaGrad. As data science challenges evolve in complexity, ScalaGrad provides a pathway to harness the inherent advantages of strongly typed languages, ensuring both robustness and maintainability.

This paper explores an automatic news generation and fact-checking system based on language processing, aimed at enhancing the efficiency and quality of news production while ensuring the authenticity and reliability of the news content. With the rapid development of Natural Language Processing (NLP) and deep learning technologies, automatic news generation systems are capable of extracting key information from massive data and generating well-structured, fluent news articles. Meanwhile, by integrating fact-checking technology, the system can effectively prevent the spread of false news and improve the accuracy and credibility of news. This study details the key technologies involved in automatic news generation and fact-checking, including text generation, information extraction, and the application of knowledge graphs, and validates the effectiveness of these technologies through experiments. Additionally, the paper discusses the future development directions of automatic news generation and fact-checking systems, emphasizing the importance of further integration and innovation of technologies. The results show that with continuous technological optimization and practical application, these systems will play an increasingly important role in the future news industry, providing more efficient and reliable news services.

[Absctract]: Central Serous Chorioretinopathy (CSC) is a retinal disorder caused by the accumulation of fluid, resulting in vision distortion. The diagnosis of this disease is typically performed through Optical Coherence Tomography (OCT) imaging, which displays any fluid buildup between the retinal layers. Currently, these fluid regions are manually detected by visual inspection a time-consuming and subjective process that can be prone to errors. A series of six deep learning-based automatic segmentation architectural configurations of different levels of complexity were trained and compared in order to determine the best model intended for the automatic segmentation of CSC-related lesions in OCT images. The best performing models were then evaluated in an external validation study. Furthermore, an intra- and inter-expert analysis was conducted in order to compare the manual segmentation performed by expert ophthalmologists with the automatic segmentation provided by the models. Test results of the best performing configuration achieved a mean Dice of in the internal dataset. In the external validation set, these models achieved a level of agreement with human experts of up to 0.960 in terms of Kappa coefficient, contrasting with a value of 0.951 for agreement between human experts. Overall, the models reached a better agreement with either of the human experts than these experts with each other, suggesting that automatic segmentation models for the detection of CSC-related lesions in OCT imaging can be useful tools for assessing this disease, reducing the workload of manual inspection and leading to a more robust and objective diagnosis method.

This thesis examines the relationship between dominance and prestige, and risk aversion and automatic cognition. Dominance and prestige are integrated as self-concepts, and expressed as distinct strategies to power. They cause differences in how one accepts and interacts with power. Power has many effects on cognition, including but not limited to lowered risk aversion and increased automatic cognitions. These effects and the mechanisms of powre are described with the approach-inhibition thereory, where power causes approach, and with it a sleugh of cognitive effects. The research questions focus on uncovering wether or not prestige and dominance have an impact on how power is integrated and processed; more specifically, if there are correlations between prestige, dominance, reaction time and risk aversion. This was done using the Dominance-Prestige Questionnaire (DPQ), the Balloon Analogue Risk Task (BART) as well as a conscequential power priming design. The findings are not very significant but do suggest some interesting trends, namely that there can be effects of dominance and prestige onto automatic thinking. Prestige is indeed correlated with more automatic thinking. But further research is needed for more definitive findings on risk aversion.

This study assessed the influence of speaker similarity and sample length on the performance of an automatic speaker recognition (ASR) system utilizing the SpeechBrain toolkit. The dataset comprised recordings from 20 male identical twin speakers engaged in spontaneous dialogues and interviews. Performance evaluations involved comparing identical twins, all speakers in the dataset (including twin pairs), and all speakers excluding twin pairs. Speech samples, ranging from 5 to 30 s, underwent assessment based on equal error rates (EER) and Log cost-likelihood ratios (Cllr). Results highlight the substantial challenge posed by identical twins to the ASR system, leading to a decrease in overall speaker recognition accuracy. Furthermore, analyses based on longer speech samples outperformed those using shorter samples. As sample size increased, standard deviation values for both intra and inter-speaker similarity scores decreased, indicating reduced variability in estimating speaker similarity/dissimilarity levels in longer speech stretches compared to shorter ones. The study also uncovered varying degrees of likeness among identical twins, with certain pairs presenting a greater challenge for ASR systems. These outcomes align with prior research and are discussed within the context of relevant literature.

Emergent manufacturing paradigms, including ubiquitous manufacturing, social manufacturing, and agile manufacturing, facilitate the advancement of the manufacturing industry. However, these paradigms suffer from the difficulty of interoperability due to the heterogeneity of field devices and diverse communication protocols. The OLE for Process Control Unified Architecture (OPC UA) technique, which is featured with cross-platform, is considered as the pivotal technology for addressing this issue. However, there still exist a large number of heterogeneous devices which do not support OPC UA protocol. The communication protocols of these heterogeneous devices need to be converted into OPC UA based on information model, nevertheless, the manual construction of OPC UA information model is cumbersome and inefficient. In this paper, an integrated architecture based on reasoning over the OPC UA information model is proposed to realize rapid integration of heterogeneous devices to achieve interoperability. To realize the proposed integrated architecture, an automatic device information model construction method is developed simultaneously. The method first identifies the type of the newly accessed device based on the character-level TextCNN (CTCNN) model, which utilizes the word sequence extracted from the corresponding device data frame as input. Subsequently an open-world knowledge completion model is adopted to link the unseen entities in the device data frame to the information model knowledge graph(KG) to support the information model automatic construction for unknown device. For evaluation purpose, two industrial datasets are constructed and the results demonstrate the feasibility and effectiveness of the proposed method., QC 20240229

The purpose of this paper is to investigate the economic sustainability implications of reconfigurable modularization and changeability in semi-automatic assembly systems using a system dynamics perspective. Through our applied research, using a multiple case study approach, we assess the potential and drawbacks of reconfigurable modularization to advance sustainable practices in the manufacturing industry with the purpose of improving overall long-term resource allocation in product realization processes. The traditional approach of developing and industrializing one product at a time is becoming obsolete due to factors such as more frequent product introductions, technological innovations, and sustainability requirements. This is due to the increasing trends of product variety and customization, which often necessitate costly modifications to production systems throughout their life cycles. To address these challenges, scholars advocate for the adoption of reconfigurable modular architectures in product and production system designs, facilitated through product platforming. However, when it comes to studies of the long-term economic impacts from the effects in operations, meaning the economic sustainability implications for the production system throughout its life cycle, there is limited research examining the economic rationale for this approach. Therefore, this paper proposes a systematic examination of the economic sustainability implications of reconfigurable modularization in semi-automatic assembly systems using a system dynamics perspective. By leveraging a system dynamics simulation, we structure and investigate the potential economic short- and long-term tradeoffs between the benefits and drawbacks of reconfigurable modularization derived from empirical findings across four case studies. The novelty of this study highlights not only the investment costs and related engineering implications and their costs but also the estimated operation costs encompassi, CC BY 4.0Correspondence: gary.linneusson@his.seThis research was funded by the Swedish Knowledge and Competence Foundation grant number 20200051 during 2020 to 2023, and grant number 20200018 during 2023 to 2024.

While automatic translation technology is advancing rapidly and can be useful in certain contexts, it seems to fall behind when it comes to the translation of literary texts. This thesis explores to what extent three approaches to fully automated literary translation – commercial machine translation models, literature-specific translation models and large language models – are suitable for the translation of literary texts, and how existing translation and literary quality assessment methods compare when assessing machine-translated literary texts. In the experiment, excerpts from eight literary texts are translated by a commercial machine translation model (DeepL), a literary-adapted model (Combo) and a large-language model (GPT-3) and assessed using an automated assessment metric (BLEU), human assessment (PIE), corpus-based evaluation (lexical density and type-token ratio) and a literariness assessment (literary vector space). After analysing the results of these assessments, the literary-adapted machine translation model seems to provide the most promising results. None of the employed assessment metrics appear to be ideal for the assessment of machine translated literary texts, and further research into other types of assessment metrics is desirable.

This research discusses the development of a prototype of an automatic door and fire alarm system based on the Internet of Things (IoT) utilizing IR sensors to detect people, servo motors to automate door opening, flame detectors for fire detection, MQ-2 sensors for smoke detection, and Telegram as a notification medium. The integration of these technologies aims to enhance security and automation in home or office environments. IR sensors are used to detect people approaching the door, while servo motors provide a solution for door automation. Flame detectors and MQ-2 are employed to detect potential fires by issuing early warnings. This system communicates through the Telegram application to notify users. Testing conducted indicates that IR sensors can detect the presence of people up to a distance of 5cm to activate the micro servo opening the door. The flame detector effectively detects fire up to a distance of 30cm, while the MQ-2 sensor detects smoke up to a distance of 20cm; both generate output signals to activate the micro servo, LED, and buzzer for fire alarms, as well as sending notifications via Telegram to the building owner. With this approach, it is hoped to create an effective, efficient, and reliable system to enhance security and response to emergency situations., Penelitian ini membahas pengembangan prototipe sistem pintu otomatis dan alarm kebakaran berbasis Internet of Things (IoT) yang menggunakan sensor IR untuk mendeteksi orang, motor servo untuk otomatisasi pembukaan pintu, detector api untuk deteksi kebakaran, sensor MQ-2 untuk deteksi asap, dan Telegram sebagai media pemberitahuan. Integrasi teknologi ini bertujuan untuk meningkatkan keamanan dan otomatisasi di lingkungan rumah atau kantor. Sensor IR digunakan untuk mendeteksi orang yang mendekati pintu, sedangkan motor servo memberikan solusi untuk otomatisasi pintu. Detector api dan MQ-2 digunakan untuk mendeteksi potensi kebakaran dengan memberikan peringatan dini. Sistem ini berkomunikasi melalui aplikasi Telegram untuk memberi tahu pengguna. Pengujian yang dilakukan menunjukkan bahwa sensor IR dapat mendeteksi keberadaan orang hingga jarak 5cm untuk mengaktifkan mikro servo membuka pintu. Detector api efektif mendeteksi api hingga jarak 30cm, sedangkan sensor MQ-2 mendeteksi asap hingga jarak 20cm; keduanya menghasilkan sinyal keluaran untuk mengaktifkan mikro servo, LED, dan buzzer sebagai alarm kebakaran, serta mengirimkan pemberitahuan melalui Telegram kepada pemilik bangunan. Dengan pendekatan ini, diharapkan dapat menciptakan sistem yang efektif, efisien, dan dapat diandalkan untuk meningkatkan keamanan dan respons terhadap situasi darurat.

Quantitative analysis of complex mixtures, including compounds having similar chemical properties, is demonstrated using an automatic and high throughput approach to microcrystal electron diffraction (MicroED). Compositional analysis of organic and inorganic compounds can be accurately executed without the need of diffraction standards. Additionally, with sufficient statistics, small amounts of compounds in mixtures can be reliably detected. These compounds can be distinguished by their crystal structure properties prior to structure solution. In addition, if the crystals are of good quality, the crystal structures can be generated on the fly, providing a complete analysis of the sample. MicroED is an effective method for analyzing the structural properties of sub-micron crystals, which are frequently found in small-molecule powders. By developing and using an automatic and high throughput approach to MicroED, and with the use of SerialEM for data collection, data from thousands of crystals allow sufficient statistics to detect even small amounts of compounds reliably.

Humans seem to arbitrate between automatic and controlled processing by optimizing a trade-off between cognitive effort and performance. Previous research has described ways of how these costs and benefits can be quantified and how the trade-off between them can be performed. However, it remains unclear how the costs should be weighed relative to the benefits and how the cost of the arbitration mechanism itself factors in. Here, we derive measures for these separate factors from a single objective: the variational free energy. We demonstrate that by minimizing this objective, the trade-off between automatic and controlled processing as well as meta-control is optimized implicitly. As a proof of concept, we show that the congruency and proportion congruency effects in the Stroop task directly result from this optimization, given an environment with specific statistical regularities.

A new automatic shoreline detection method by using a bidirectional Long Short-Term Memory (bi-LSTM) Network that processes images column by column is presented. The model is trained on manually extracted shorelines from time-exposure video-images and is very robust against the selection of images for training. Thanks to the novelty of working with image columns, instead of with the whole image, the amount of labelled images for training is limited to a few tens or even less if the conditions are good. Moreover, this column approach makes the model to be robust to variable illuminated images and more easily interpretable, light and fast. There is a wide range of configuration parameters for the bi-LSTM layer by which the system works correctly, which facilitate to use the same network in different video stations. The highest accuracy is obtained by using CIELAB colour space. Without pre-processing the raw colour channels or defining a region of interest and without post-processing the obtained shorelines, the model demonstrates impressive accuracy with mean errors of 2.8 pixels (1.4 meters) in Castelldefels and 1.7 pixels (0.85 meters) in Barcelona.The method could also be effective for satellite shoreline detection by using as input channel the water index of the satellite detection techniques., This work has been funded by the Spanish government through the research project RTI2018-093941-B-C33 (MINECO/FEDER)., Peer Reviewed, Postprint (published version)

Background and objectives: This study aims to develop and evaluate NeuNN, a system based on convolutional neural networks (CNN) and generative adversarial networks (GAN) for the automatic identification of normal neutrophils and those containing several types of inclusions or showing hypogranulation. Methods: From peripheral blood smears, a set of 5605 digital images was obtained with neutrophils belonging to seven categories: Normal neutrophils (NEU), Hypogranulated (HYP) or containing cryoglobulins (CRY), Döhle bodies (DB), Howell-Jolly body-like inclusions (HJBLI), Green-blue inclusions of death (GBI) and phagocytosed bacteria (BAC). The dataset utilized in this study has been made publicly available. The class of GBI was augmented using synthetic images generated by GAN. The NeuNN classification model is based on an EfficientNet-B7 architecture trained from scratch. Results: NeuNN achieved an overall performance of 94.3% accuracy on the test data set. Performance metrics, including sensitivity, specificity, precision, F1-Score, Jaccard index, and Matthews correlation coefficient indicated overall values of 94%, 99.1%, 94.3%, 94.3%, 89.6%, and 93.6%, respectively. Conclusions: The proposed approach, combining data augmentation and classification techniques, allows for automated identification of morphological findings in neutrophils, such us inclusions or hypogranulation. The system can be used as a support tool for clinical pathologists to detect these specific abnormalities with clinical relevance., Peer Reviewed, Postprint (published version)

Tesi en modalitat de compendi de publicacions, (English) Clinical pathologists focus on detailed morphological analysis of peripheral blood (PB) cells for the recognition of abnormal cells and contribute to the diagnosis of hematological diseases. While this traditional method is often precise, it requires significant expertise, is time-consuming, and is subject to variability, especially when discerning subtle cell characteristics. In light of these challenges, this dissertation proposes the innovative use of deep learning, specifically convolutional neural networks (CNNs) and generative adversarial networks (GANs), to add objectivity in morphological examination of PB cells. The research is developed through a three-fold strategy. First, a novel GAN-based model standardizes PB cell image visualization across varied staining techniques. Second, optimized CNN architectures are tailored for precise classification of the selected PB cell types, with emphasis on reactive and malignant blood cells. Results indicate that the introduced Stain Normalization Model effectively manages staining variations while preserving cell morphology. Furthermore, CNN models, based on these normalized data, contribute significantly to the automatic recognition of malignant cells. And third, a modular GAN system generates synthetic PB images to enrich model training, particularly of low-prevalence cell data with special diagnostic interest. This research emphasizes the transformative impact of combining the expertise of clinical pathologists with advanced computational strategies. While these systems serve as potent support tools, it is imperative to note that the clinical pathologist retains the ultimate authority in decision-making. The fusion of traditional expertise and modern technology is a promising trend in the present and near future, enhancing both objectivity and efficiency. This study signifies an advance towards the establishment of an integrated system for an automated screening tool for hematological diseases., (Català) Els patòlegs clínics depenen de l'anàlisi morfològica detallada de les cèl·lules de sang perifèrica (PB) per a un diagnòstic precís de malalties hematològiques. Encara que aquest mètode tradicional és sovint precís, requereix una gran experiència, és laboriós i està subjecte a variabilitat, especialment quan es tracta de discernir característiques subtils de les cèl·lules. Davant d'aquests desafiaments, aquesta tesi doctoral introdueix l'ús innovador de l'aprenentatge profund, específicament xarxes neuronals convolucionals (CNN) i xarxes generatives antagonistes (GAN), per transformar l'examen morfològic de les cèl·lules de la sang. La recerca es desenvolupa a través d'una estratègia de tres vessants: Primer, un model nou basat en GAN estandarditza la visualització de les imatges a través de diverses tècniques de tinció. En segon lloc, s'adapten arquitectures de CNN optimitzades per a una classificació precisa dels tipus principals de cèl·lules sanguínies, amb èmfasi en els limfòcits reactius i les cèl·lules malignes. En tercer lloc, un sistema GAN modular genera imatges sintètiques de les cèl·lules, especialment en casos de cèl·lules de baixa prevalença per enriquir l'entrenament del model. Els resultats indiquen que el Model de Normalització de Tinció introduït gestiona eficaçment les variacions de tinció sense afectar la morfologia cel·lular. A més, els models CNN, construïts amb aquestes dades normalitzades, excel·leixen en la detecció de cèl·lules malignes. El model SyntheticCellGAN enriqueix encara més el conjunt de dades d'entrenament amb cèl·lules sintètiques diagnòsticament rellevants. Aquesta recerca destaca l'impacte transformador de combinar l'experiència dels patòlegs clínics amb eines computacionals avançades. Tot i que aquests sistemes serveixen com a eines de suport, és imperatiu tenir en compte que el patòleg clínic reté la màxima autoritat en la presa de decisions. La fusió de l'experiència tradicional i la tecnologia moderna promet revolu, (Español) Los patólogos clínicos dependen del análisis morfológico detallado de las células de sangre periférica (PB) para un diagnóstico preciso de enfermedades hematológicas. Aunque este método tradicional es a menudo preciso, requiere una gran experiencia, es laborioso y está sujeto a variabilidad, especialmente cuando se trata de discernir características sutiles de las células. Ante estos desafíos, esta tesis doctoral introduce el uso innovador del aprendizaje profundo, específicamente redes neuronales convolucionales (CNN) y redes generativas antagónicas (GAN), para transformar el examen morfológico de las células PB. La investigación se desarrolla a través de una estrategia triple. Primero, un modelo novedoso basado en GAN estandariza la visualización de imágenes de células PB a través de diversas técnicas de tinción. En segundo lugar, se adaptan arquitecturas de CNN optimizadas para una clasificación precisa de los tipos principales de células sanguíneas, con énfasis en los linfocitos reactivos y las células malignas. En tercer lugar, un sistema GAN modular genera imágenes sintéticas de PB, especialmente en el caso de células de baja prevalencia, para enriquecer el entrenamiento del modelo. Los resultados indican que el Modelo de Normalización de Tinción introducido gestiona eficazmente las variaciones de tinción sin afectar la morfología celular. Además, los modelos CNN, construidos con estos datos normalizados, sobresalen en la detección de células malignas. El modelo SyntheticCellGAN enriquece aún más el conjunto de datos de entrenamiento con células sintéticas con relevancia diagnóstica. Esta investigación destaca el impacto transformador de combinar la experiencia de los patólogos clínicos con herramientas computacionales avanzadas. Si bien estos sistemas sirven como herramientas de apoyo, es imperativo tener en cuenta que el patólogo clínico mantiene la máxima autoridad en la toma de decisiones. La fusión de la experiencia tradicional y la tecnología m, Postprint (published version)