Search

RESUMO Objetivo: As atividades que os profissionais Bibliotecários desempenham estão se adaptando às novas formas de comunicação e às demandas modernas dos usuários. Dentre essas atividades, tem-se a indexação. O presente artigo possui o objetivo de descrever o panorama de produção científica e as tendências de pesquisa sobre os estudos voltados para a indexação automática, semiautomática e auxiliada por computador, indexada na Base de Dados Referencial de Artigos de Periódicos em Ciência da Informação (Brapci), no período de no período de 1972 a 2021. Método: Caracteriza-se como exploratória e bibliográfica com fins descritivos, uma vez que descreve e detalha a produção científica sobre os temas “indexação automática”, “indexação semiautomática” e “indexação auxiliada por máquina” indexada na Brapci. Resultado: Por meio da análise desse corpus, foi possível identificar os pesquisadores que mais produziram sobre a temática em questão, bem como os periódicos que mais tratam da referida temática, além disso, perceberam-se os períodos de tempo mais fecundos à produção de trabalhos relacionados com a automação da indexação e as palavras-chave utilizadas à indexação do corpus analisado, as quais, juntamente com os resumos, sinalizaram as tendências de estudos nessa vertente. Conclusões: Há uma tendência de estudos voltados à indexação totalmente automática, dando ênfase aos métodos semânticos e não apenas estatísticos, fazendo uso de recursos advindos da Inteligência Artificial. Poucas propostas de indexação semiautomática foram evidenciadas. Propostas promissoras na prática da representação temática da informação de forma automática em curtos espaços de tempo se apresentam hodiernamente. ABSTRACT Objective: The activities that professional Librarians perform are adapting to new forms of communication and the modern demands of users. Among these activities, there is indexing. This article aims to describe the panorama of scientific production and research trends on studies aimed at automatic, semi-automatic and computer-aided indexing, indexed in the Reference Database for Journal Articles in Information Science (Brapci), in the period from 1972 to 2021. Methods: It is characterized as exploratory and bibliographical with descriptive purposes, since it describes and details the scientific production on the topics "automatic indexing", "semi-automatic indexing" and "machine-aided indexing" indexed in Brapci. Results: Through the analysis of this corpus, it was possible to identify the researchers who produced the most on the subject in question, as well as the journals that most deal with that subject, in addition, the most fruitful periods of time for the production of related works with the automation of indexing and the keywords used to index the analyzed corpus, which, together with the abstracts, signaled the trends of studies in this area. Conclusions: There is a tendency for studies aimed at fully automatic indexing, emphasizing semantic and not just statistical methods, making use of resources derived from Artificial Intelligence. Few proposals for semi-automatic indexing were evidenced. Promising proposals in the practice of thematic representation of information automatically in short spaces of time are presented today.

Seabed inspection is one of the most sought-after applications for Autonomous Underwater Vehicles (AUVs). In particular, acoustic sensors, as Side Scan Sonars (SSSs) and Forward-Looking Sonars (FLSs), are commonly favored over optical cameras to carry out such a task being not influenced by the illumination conditions and providing high-range data. However, acoustic images are often hard to interpret with conventional automatic techniques, forcing human operators to analyze thousands of collected images to identify the so-called Objects of Potential Interest (OPIs). In this perspective, this paper reports the development of an Automatic Target Recognition (ATR) methodology to identify and localize OPIs in FLS imagery; such detections have been then exploited to realize a world model with the Probabilistic Multiple Hypothesis Anchoring (PMHA) data association algorithm. Both the ATR and world modeling systems were on-field tested at the Naval Support and Experimentation Centre (Centro di Supporto e Sperimentazione Navale - CSSN) basin, in La Spezia, Italy, in a multi-vehicle architecture by employing an acoustic channel between FeelHippo AUV and an autonomous moving buoy.

In this paper, we build and compare multiple speech systems for the automatic evaluation of the severity of a speech impairment due to oral cancer, based on spontaneous speech. To be able to build and evaluate such systems, we collected a new spontaneous oral cancer speech corpus from YouTube consisting of 124 utterances rated by 100 non-expert listeners and one trained speech-language pathologist, which we made publicly available. We evaluated the systems in two scenarios: a scenario where transcriptions were available (reference-based) and a scenario where transcriptions might not be available (reference-free). The results of extensive experiments showed that (1) when transcriptions were available, the highest correlation with the human severity ratings was obtained using an automatic speech recognition (ASR) retrained with oral cancer speech. (2) When transcriptions were not available, the best results were achieved by a LASSO model using modulation spectrum features. (3) We found that naive listeners’ ratings are highly similar to the speech pathologist's ratings for speech severity evaluation. (4) The use of binary labels led to lower correlations of the automatic methods with the human ratings than using severity scores.

IT技術の発展に伴うソースコードの複雑化により，デバッグ作業が困難となっている．そのため，自動プログラム修正が注目されている．注目されている自動プログラム修正の方法の1つである遺伝的アルゴリズムを用いたGenProgでは評価値にテスト通過率のみを用いているため，修正結果の可読性が保証されていない．そこで本研究では，GenProgに対して可読性が高いソースコードとの類似度を考慮することで修正結果の可読性向上を図る．提案手法では，生成個体を可読性の高いソースコードにすることを目標とする．, Debugging has become difficult due to the increasing complexity of source code with the development of information technology. For this reason, automatic program modification has been attracting attention. GenProg, which uses a genetic algorithm as one of the methods of automatic program modification, uses only the test pass rate as the evaluation ground, and thus does not guarantee the readability of the modification results. Therefore, this study aims to improve the readability of modification results by considering the degree of similarity with the source code, which has high readability compared to GenProg. The proposed method aims to make the generated individuals highly readable source code.

This review aims to summarize and describe research on the topic of automatic group emotion recognition. In recent years, the topic of emotion analysis of groups or crowds has gained interest, with studies performing emotion detection in different contexts, using different datasets and modalities (such as images, video, audio, social media messages), and taking different approaches. Articles are included after an innovative search method, including Dense Query Extraction and automatic cross-referencing. Discussed are the types of groups and emotion models considered in automatic emotion recognition research, common datasets for all modalities, general approaches taken, and reported performances. These performances are discussed, followed by an analysis of the application possibilities of the discussed methods. To ensure clear, replicable, and comparable studies, we suggest research should test on multiple, common datasets and report on multiple metrics, when possible. Implementation details and code should be made available where possible. An area of interest for future work is to build systems with more real-world application possibilities, coping with changing group sizes, different emotional subgroups, and changing emotions over time, while having a higher robustness and working with datasets with reduced biases.

Background and Objectives: Combining knowledge of clinical pathologists and deep learning models is a growing trend in morphological analysis of cells circulating in blood to add objectivity, accuracy, and speed in diagnosing hematological and non-hematological diseases. However, the variability in staining protocols across different laboratories can affect the color of images and performance of automatic recognition models. The objective of this work is to develop, train and evaluate a new system for the normalization of color staining of peripheral blood cell images, so that it transforms images from different centers to map the color staining of a reference center (RC) while preserving the structural morphological features. Methods: The system has two modules, GAN1 and GAN2. GAN1 uses the PIX2PIX technique to fade original color images to an adaptive gray, while GAN2 transforms them into RGB normalized images. Both GANs have a similar structure, where the generator is a U-NET convolutional neural network with ResNet and the discriminator is a classifier with ResNet34 structure. Digitally stained images were evaluated using GAN metrics and histograms to assess the ability to modify color without altering cell morphology. The system was also evaluated as a pre-processing tool before cells undergo a classification process. For this purpose, a CNN classifier was designed for three classes: abnormal lymphocytes, blasts and reactive lymphocytes. Results: Training of all GANs and the classifier was performed using RC images, while evaluations were conducted using images from four other centers. Classification tests were performed before and after applying the stain normalization system. The overall accuracy reached a similar value around 96% in both cases for the RC images, indicating the neutrality of the normalization model for the reference images. On the contrary, it was a significant improvement in the classification performance when applying the stain normalization to the other centers. Reactive lymphocytes were the most sensitive to stain normalization, with true positive rates (TPR) increasing from 46.3% - 66% for the original images to 81.2% - 97.2% after digital staining. Abnormal lymphocytes TPR ranged from 31.9% - 95.7% with original images to 83% - 100% with digitally stained images. Blast class showed TPR ranges of 90.3% - 94.4% and 94.4% - 100%, for original and stained images, respectively. Conclusions: The proposed GAN-based normalization staining approach improves the performance of classifiers with multicenter data sets by generating digitally stained images with a quality similar to the original images and adaptability to a reference staining standard. The system requires low computation cost and can help improve the performance of automatic recognition models in clinical settings. This work is part of a research project funded by the Ministry of Science and Innovation of Spain, with reference PID2019-104087RB-I00.

Objective. Fetal heart rate (fHR) evaluation is fundamental to guarantee timely medical intervention in case of pregnancy complications. Due to the limitations of traditional cardiotocography, multichannel electrophysiological recording was proposed as a viable alternative, which requires Blind Source Separation (BSS) techniques. Yet effective and reliable separation of the fetal ECG remains challenging due to multiple noise sources and the effects of varying fetal position. In this work, we demonstrate that the adopted electrode configuration plays a key role in the effectiveness of BSS and propose guidelines for optimal electrode positioning. Moreover, a model is proposed to automatically predict the most suited configuration for accurate BSS-based fHR estimation with a minimal number of leads, to facilitate practical implementation. Methods. We compared fHR estimation accuracy with different electrode configurations on in-silico data, identifying the optimal configuration for a recent BSS method. Based on features extracted from raw signals, we proposed a support vector regression model to automatically identify the best electrode configuration in terms of fHR estimation accuracy and to dynamically adjust it to varying fetal presentation. Evaluation was performed on real and synthetic data. Results. Guidelines for the optimal electrode configuration are proposed by using 4 leads. Prediction of configuration quality shows 80.9% accuracy; the optimal configuration is recognized in 92.2% of the subjects. Conclusion. The proposed method successfully predicts the quality of the configurations, demonstrating the impact of the electrode configuration on the BSS performance. Significance. The method holds potential for long-term fetal monitoring, by dynamically choosing the optimal configuration.

人工肛門脱出は人工肛門造設後の合併症の一つであり，疼痛や出血，パウチ貼付困難といった症状が出現すると手術が必要になる．ところが，人工肛門脱出に対する標準的な手術や治療法は確立していないのが現状である．過去の文献では自動縫合器を用いた手術の報告が散見され，良好な治療経過をえている．今回，われわれは人工肛門脱出に対して自動縫合器を用いて非開腹下に手術を施行した．症例１は81歳の男性．原因不明のS状結腸狭窄に対して横行結腸で双孔式人工肛門を造設した．術後１か月目から口側腸管から人工肛門脱出を認めた．さらに１か月経過し増悪するため手術を施行した．症例2は82歳の女性．閉塞性S状結腸癌に対して横行結腸で双孔式人工肛門を造設した．術後3か月目に肛門側から人工肛門脱出を認め，手術を施行した．自動縫合器を用いた術式では，縫合部が直視困難な位置に自然に還納するため，縫合部出血の確認と止血を念頭に置き切離前から縫合部を牽引して術野に牽引しておくことが重要であると考えられた．, Stoma prolapse is one of the complications after colostomy, and we have to operate it if symptoms such as pain, bleeding, and difficulty in attaching the pouch occur. However, we have no standard surgery or treatment for stoma prolapse. In the past literature, there have been some reports of surgery using automatic sutures. We performed non-laparotomy surgery using automatic sutures for incarcerated colostomy. Case 1 was an 81-year-old man. A biperal colostomy was constructed in the transverse colon for sigmoid colon stenosis of unknown cause. From the first month after surgery, a stoma prolapse was observed from the mouth intestinal tract. After another month, we performed operation for worsen the disease. Case 2 was an 82-year-old woman. A biperal colostomy was constructed in the transverse colon for obstructive sigmoid colon cancer. Three months after surgery, a stoma prolapse was observed from the side. And we performed operation. While the usefulness of surgery using automatic sutures has been found in some places, it may also be useful in incarcerated cases. In this surgical procedure, since the suture is naturally returned to a position where it is difficult to see directly, it is important to tow the proboscis suture to the surgical field before dissection, keeping in mind the confirmation of suture bleeding and hemostasis.

Speech intelligibility is an essential though complex construct for evaluating dysarthric speech. Various procedures can be used to measure speech intelligibility, most of which are based on subjective ratings assigned by experts. Since these procedures are subjective and laborious, automatic speech recognition (ASR) has been proposed to obtain objective metrics of intelligibility. Although promising results have been reported, ASR for dysarthric speech generally requires large amounts of data consisting of recorded and annotated speech. In the present study, we explored the possibility of using dysarthric speech resources from the dominant language variety to improve the performance of ASR systems on the dysarthric speech of the non-dominant variety of the same pluricentric language. Dutch is used as an example of a pluricentric language, with Netherlandic Dutch considered the dominant and Flemish Dutch the non-dominant variety. The performance of ASR is evaluated by using two types of intelligibility metrics: orthographic transcriptions and global intelligibility assessments, both obtained from experts. Overall, the results show that dysarthric speech data from the dominant language variety can contribute to improving automatic transcriptions and to developing objective, automatic global measures of speech intelligibility only when no data from the non-dominant variety are available for training ASR models.

The need for accurate and up-to-date spatial data by decision-makers in public and private administrations is increasing gradually. In recent decades, in the management of disasters and smart cities, fast and accurate extraction of roads, especially in emergencies, is quite important in terms of transportation, logistics planning, and route determination. In this study, automatic road extraction analyses were carried out using the Unmanned Aerial Vehicle (UAV) data set, belonging to the Yildiz Technical University Davutpasa Campus road route. For this purpose, this paper presents a comparison between performance analysis of rule-based classification and U-Net deep learning method for solving automatic road extraction problems. Objects belonging to the road and road network were obtained with the rule-based classification method with overall accuracy of 95%, and with the deep learning method with an overall accuracy of 86%. On the other hand, the performance metrics including accuracy, recall, precision, and F1 score were utilized to evaluate the performance analysis of the two methods. These values were obtained from confusion matrices for 4 target classes consisting of road and road elements namely road, road line, sidewalk, and bicycle road. Finally, integration of classified image objects with ontology was realized. Ontology was developed by defining four target class results obtained as a result of the rule-based classification method, conceptual class definition and properties, rules, and axioms.

The so-called ‘mismatch’ is a factor which experts in the forensic voice comparison field encounter regularly. Therefore, we decided to explore to what extent the automatic-speaker-recognition system’s and the earwitness’ ability to identify speakers is influenced when recordings are acquired in different languages and at different times. 100 voices in a database of 300 recordings (100 speakers recorded in three mutually mismatched sessions) were compared with an automatic-speaker-recognition software VOCALISE based on i-vectors and x-vectors, and by 39 respondents in simulated voice parades. Both the automatic and perceptual approach seem to have yielded similar results in that the less complex the mismatch type, the more successful the identification. The results point to the superiority of the x-vector approach, and also to varying identification abilities of listeners.

This article deals with model predictive control (MPC) design for automatic transmission (AT) upshift inertia phase, which aims to optimally coordinate the actions of oncoming (ONC) and off- going (OFG) clutches and engine and to facilitate calibration. The designed MPC strategy accounts for clutch actuation dynamics and constraints, while setting the tradeoff between three key and conflicting shift quality criteria: comfort ; duration ; and efficiency. The shift comfort and duration are ensured by minimizing output shaft torque and ONC clutch slip speed tracking errors, and the shift efficiency is reflected in clutch energy loss minimization on a prediction horizon. This allows for the calibration of the MPC performance through setting the inertia phase duration, the output shaft torque reference, cost function weighting coefficients, and constraints, rather than optimizing the shift control profiles themselves. The MPC problem is formulated as a constrained quadratic programming problem and efficiently solved online by an interior-point solver. The proposed MPC strategy is applicable to other transmissions with multiple actuators, such as parallel hybrid transmissions. The MPC system is examined through nonlinear powertrain model simulations for one to three shift and its performance is compared with an offline, multiobjective optimization-based control strategy. The MPC design flexibility and ease of calibration are demonstrated for different shift comfort and duration targets, as well as cost function tuning, and robustness with respect to clutch actuation parameter uncertainties is examined.

To develop and validate a tool for automatic selection of the slice of minimal hiatal dimensions (SMHD) and segmentation of the urogenital hiatus (UH) in transperineal ultrasound (TPUS) volumes.Manual selection of the SMHD and segmentation of the UH was performed in TPUS volumes of 116 women with symptomatic pelvic organ prolapse (POP). These data were used to train two deep-learning algorithms. The first algorithm was trained to provide an estimation of the position of the SMHD. Based on this estimation, a slice was selected and fed into the second algorithm, which performed automatic segmentation of the UH. From this segmentation, measurements of the UH area (UHA), anteroposterior diameter (APD) and coronal diameter (CD) were computed automatically. The mean absolute distance between manually and automatically selected SMHD, the overlap (dice similarity index (DSI)) between manual and automatic UH segmentation and the intraclass correlation coefficient (ICC) between manual and automatic UH measurements were assessed on a test set of 30 TPUS volumes.The mean absolute distance between manually and automatically selected SMHD was 0.20 cm. All DSI values between manual and automatic UH segmentations were above 0.85. The ICC values between manual and automatic UH measurements were 0.94 (95% CI, 0.87-0.97) for UHA, 0.92 (95% CI, 0.78-0.97) for APD and 0.82 (95% CI, 0.66-0.91) for CD, demonstrating excellent agreement.Our deep-learning algorithms allowed reliable automatic selection of the SMHD and UH segmentation in TPUS volumes of women with symptomatic POP. These algorithms can be implemented in the software of TPUS machines, thus reducing clinical analysis time and simplifying the examination of TPUS data for research and clinical purposes. © 2021 The Authors. Ultrasound in Obstetricsamp; Gynecology published by John Wileyamp; Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

L-systems have long been used to generate computer graphics of trees, and much research has been conducted to generate music based on L-systems．That is, L-system generates sequences of symbols, symbols are interpreted as musical data or x-y coordinates of tree shapes and are interpreted as musical data such as pitches of notes．We developed an intuitively understandable method to map from the face of growth to musical data．Then we created the movies of trees with music. In order to check whether it is possible to generate various types of music we generated some movies with di_erent musical instruments and tempos．We had participants appreciate the movies and veri_ed that they satis_ed a relationship between the movies and their situations of use.

L-systems have long been used to generate computer graphics of trees, and much research has been conducted to generate music based on L-systems．That is, L-system generates sequences of symbols, symbols are interpreted as musical data or x-y coordinates of tree shapes and are interpreted as musical data such as pitches of notes．We developed an intuitively understandable method to map from the face of growth to musical data．Then we created the movies of trees with music. In order to check whether it is possible to generate various types of music we generated some movies with di_erent musical instruments and tempos．We had participants appreciate the movies and veri_ed that they satis_ed a relationship between the movies and their situations of use.

LLC resonant converters are used in renewable energy applications to achieve high power efficiency conversions between different energy sources, buses, and energy storage elements. The traditional design methods for LLC resonant converters are based on a simple frequency-domain analysis (FDA). However, the accuracy of FDA is not satisfactory, especially at wide voltage range applications. To overcome the drawbacks of the traditional FDA method in wide-range applications, in this article, the time-domain analysis (TDA) is adopted to achieve accurate analysis of LLC converters. Efficiency is normally selected as the optimization objective, where the circuit components and accurate power loss models are required beforehand. To achieve a more general optimal design method for LLC converters, a simple root-mean-square (rms) current and TDA-based optimal design method is proposed. The optimal design is achieved by minimizing the converter rms current and ensuring some key design considerations. Moreover, an automatic design tool for the proposed rms-current-based optimal design method is developed, and advanced optimization algorithms are introduced to improve the optimization speed. A 2.5-kW experimental prototype is built using the optimal circuit parameters. Experimental results under different operating conditions are demonstrated, and the results are consistent with the theoretical analysis. Efficiency comparisons between the proposed optimal design method and conventional design method are made. The proposed optimal design method can improve the converter efficiency by a maximum value of 2.14%.

The applicability of machine learning (ML) techniques has recently been expanding to include automatic real estate valuation models. The main advantage of this technique is that it can better capture complexity in the value determination process. Therefore, the performance of these techniques is shown to be superior to conventional models. In this paper, the latest ML algorithms (i.e., support vector machine, random forest, XGBoost, LightGBM, and CatBoost algorithms) are examined as automatic valuation models, and several combination methods are proposed to improve the models’ predictive power. We applied ML models to approximately 57,000 records on apartment transactions, which were provided by South Korea’s Ministry of Land, Infrastructure, and Transport, that occurred in Seoul in 2018. The results are as follows. First, ML-based predictors (especially, the latest decision tree-based algorithms) are more performative than conventional models. Second, the prediction error from a model can be partially offset by another model’s error, which implies that an efficient averaging of the predictors improves their predictive accuracy. Third, the models’ relative performance may be relearned by the ML algorithms, which means that they can also be used to recommend which algorithm should be selected for making predictions.

The problem of determining the components of the structural-automatic model is solved by creating a graph of states and transitions. The purpose of the process is to form a formalized expression of the object of study in the form of a structural-machine model of the process of firing a mobile armored vehicle with a series of three shots with fragmentation-beam projectiles of directional action. This model can be further practically implemented during the development of the latest samples of fire resistance in order to reduce errors at the stage of system design. This approach reduces the cost of design and production of prototypes by up to 25%. This paper considers the process involving interrelated elements of the components of a system while accounting for all possible variants of its behavior from the moment of detection to the failure of a single target in armor protection to perform tasks as intended. The execution of a fire task is considered as a set of certain procedures characterized by the average value of their duration. The explosive destruction of the hull of each fragmentation-beam projectile is characterized by the self-propagation of the reaction of explosive transformations based on tabular data on an armored combat vehicle. Appropriate procedures (phases) of firing a single target in armor protection are advisable to formalize to create preconditions for obtaining the value of a statistical indicator of the effectiveness of causing damage to the target and to study further alternative options for this process. For the proposed structural-automatic model of the process of firing a single target in armor protection with a series of fragmentation-beam projectiles of directional action, validation and verification were carried out, which demonstrated the convergence of the results that exceeded 60%. The use of the structural-automatic model's components proposed in this work increases the probability of performing a fire task for the first shot from 0.23 to 0.88, for the second – from 0.35 to 0.95, for the third – from 0.45 to 0.98

This work presents a beam-steered infrared light communication (BS-ILC) system that enables high data rate wireless optical transmission to individual mobile users. The BS-ILC system comprises arrayed waveguide grating router-based optical antennas, camera-based user localization, and optical receivers (each integrated with an infrared tag). A high-speed photodetector has typically a small active area to minimize its junction capacitance, but this small size will result in a very limited field of view (FoV), which is detrimental to an optical wireless system aimed to provide some degree of mobility to users. Thus, the desired BS-ILC system requires precise and automatic alignment to establish a high-performance optical link between users and optical antennas. In this work, we propose an optical wireless receiver that can automatically align its orientation with respect to the optical antenna to ensure the light angle of incidence within the receiver's FoV. The automatic receiver consists of a motorized actuator and an optimization control algorithm. The actuator controls the orientation of the receiver, and the optimization algorithm is developed to accelerate the searching process of the actuator. In an indoor laboratory system setup, the amount of less than 200 ms has been demonstrated to establish gigabit-per-second optical link, and seamless transmission has also been realized for the mobile receiver while on the move with the FoV of ± 0.6°.

This study investigated on constructing a low cost solar irradiance meter that can be protected by automatic closing system. It determined the needed features of the device, the difference between the measurements recorded by the constructed device as compared to the PASCO/ IR Light Sensor, the experiments that may be performed using the constructed device and the evaluation of the experts and professionals on the device as to functionality, and design & marketability. The instruments used underwent expert validation. The study employed experimental and descriptive methods. The data were gathered from 30 experts who evaluated the constructed device in terms of features and marketability. On the other hand, 30 students of EARIST Manila evaluated the constructed device in terms of functionality and marketability. Results revealed that the Low Cost Solar Irradiance Meter with Automatic Closing System has an innovative design and has new features based on the evaluation. It can measure solar irradiance or intensity efficiently. The measurement of the device is comparable to the result of the IR Light Sensor of the PASCO. There is no significant difference between the result of the calibrated device and the PASCO IR Light Sensor. The constructed device is more affordable compared to the commercial solar irradiance meter.

In this paper, a dual-mode step-down DC-DC converter with an automatic mode-switching circuit is implemented in a 28 nm digital CMOS process and embedded in an RF transceiver chip to power the digital part. The proposed automatic mode-switching circuit includes a frequency-voltage conversion circuit that is designed according to the principle of charge redistribution on capacitance. The converter can switch modes according to the load without external intervention. This converter, along with a PMU sequencer, can also provide a solution for low-power design for system-on-chip applications. The IC occupies a total die area of 0.378 mm2. The input voltage of the converter is 3.3 V, the output voltage is 1.05 V, and the maximum load current can reach 1 A. The converter shows a conversion efficiency of not less than 81% at a full load range and can achieve a peak conversion efficiency of 91% when the load current is 100 mA. The load range of the PWM mode is 1 A to 50 mA, and that of the PFM mode is 100 mA to 1 mA. The combination of zero-crossing detection circuitry and freewheel switches can reduce energy loss and eliminate additional electromagnetic interference.

Color similarity has been a key feature for content-based image retrieval by contemporary search engines, such as Google. In this study, we compare the visual content information of images, obtained through color histograms, with their corresponding hashtag sets in the case of Instagram posts. In previous studies, we had concluded that less than 25% of Instagram hashtags are related to the actual visual content of the image they accompany. Thus, the use of Instagram images' corresponding hashtags for automatic image annotation is questionable. In this study, we are answering this question through the computational comparison of images' low-level characteristics with the semantic and syntactic information of their corresponding hashtags. The main conclusion of our study on 26 different subjects (concepts) is that color histograms and filtered hashtag sets, although related, should be better seen as a complementary source for image retrieval and automatic image annotation.

In view of the limitations of traditional statistical methods in dealing with multifactor and nonlinear data and the inadequacy of classical machine learning algorithms in dealing with and predicting data with high dimensions and large sample sizes, this paper proposes an operational risk prediction model based on an automatic encoder and convolutional neural networks. First, we use an automatic encoder to extract features of motion risk factors and obtain feature components that can highly represent risk. Secondly, based on the causal relationship between sports risk and risk characteristics, a convolutional neural network with a dual convolution layer and dual pooling layer topology is constructed. Finally, the sports risk prediction model is established by combining the auto-coded feature components with the topology of the convolutional neural network. Compared with other algorithms, the proposed method can effectively analyze and extract risk characteristics and has a high prediction accuracy. At the same time, it promotes the integration of sports science and computer science and provides a basis for the application of machine learning in the field of sports risk prediction.

There is a large interest in the annotation of speech addressed to infants. Infant-directed speech (IDS) has acoustic properties that might pose a challenge to automatic speech recognition (ASR) tools developed for adult-directed speech (ADS). While ASR tools could potentially speed up the annotation process, their effectiveness on this speech register is currently unknown. In this study, we assessed to what extent open-source ASR tools can successfully transcribe IDS. We used speech data from 21 Dutch mothers reading picture books containing target words to their 18- and 24-month-old children (IDS) and the experimenter (ADS). In Experiment 1, we examined how the ASR tool Kaldi-NL performs at annotating target words in IDS vs. ADS. We found that Kaldi-NL only found 55.8% of target words in IDS, while it annotated 66.8% correctly in ADS. In Experiment 2, we aimed to assess the difficulties in annotating IDS more broadly by transcribing all IDS utterances manually and comparing the word error rates (WERs) of two different ASR systems: Kaldi-NL and WhisperX. We found that WhisperX performs significantly better than Kaldi-NL. While there is much room for improvement, the results show that automatic transcriptions provide a promising starting point for researchers who have to transcribe a large amount of speech directed at infants.

The automatic collection of key milestone nodes in the process of aircraft turnaround plays an important role in the development needs of airport collaborative decision-making. This article exploits a computer vision-based framework to automatically recognize activities of the flight in/off-block and docking/undocking and record corresponding key milestone nodes. The proposed framework, which seamlessly integrates state-of-the-art algorithms and techniques in the field of computer vision, comprises two modules for the preprocessing and collection of key milestones. The preprocessing module extracts the spatiotemporal information of the executor of key milestone nodes from the complex background of the airport ground. In the second module, aiming at two categories of key milestone nodes, namely, single-target-based nodes represented by in-block and off-block and interaction-of-two-targets-based nodes represented by docking and undocking stairs, two methods for the collection of key milestone are designed, respectively. Two datasets are constructed for the training, testing, and evaluation of the proposed framework. Results of field experiments demonstrate how the proposed framework can contribute to the automatic collection of these key milestone nodes by replacing the manual recording method routinely used today.

This dissertation investigated the role of mental habits in well-being. There has been extensive research on how people form behavioural habits related to their physical health (e.g., diet and exercise), but there have been fewer theoretical and empirical attempts to understand how the same habitual processes might underlie mental health. By better understanding the role of habits in mental health, particularly habitual thinking, clinicians and researchers might be able to improve the treatments offered for mental health concerns (e.g., depression and anxiety). In the three studies presented in this dissertation, I aimed to integrate habit research with the study of mental health by examining the extent to which thoughts can be considered habitual. In Study 1, we conducted a scoping review to describe and summarize the existing literature on mental habits (as they relate to mental health). We screened 2817 articles and included 20 in the review. Of these 20 articles, we examined 24 separate studies and 4 commentaries on mental habits. When defining habits, researchers emphasized the importance of automaticity (described in 80% of articles) as a key factor in differentiating mental habits from other thinking processes. Most research studies used correlational research designs (71%) with university student samples (75%) measuring various constructs including negative self-thinking, worry, self-critical thinking, self-stigma, negative body image thinking, and emotion regulation. We found no articles that measured positive mental habits. Lastly, the concept of mental habits has been poorly integrated with related psychological constructs (e.g., automatic thinking, repetitive negative thinking). In Study 2, we developed two new measures of mental habits, the Positive Thought Automaticity Index (PTAI) and Negative Thought Automaticity Index (NTAI), that integrated the strengths of existing mental habit and automatic thought questionnaires. We then used these two measures to tease apart the roles of automaticity and frequency in predicting well-being outcomes. Based on two samples of participants from the United Kingdom and Canada, these new measures demonstrated predictive and concurrent validity, internal consistency reliability, and test-retest reliability. Positive and negative thought automaticity predicted well-being outcomes over and above thought frequency. Thought automaticity partially mediated the relationship between thought frequency and how much participants believe thoughts to be true. Overall, the results of Study 2 provided evidence of the utility of automaticity as a distinct thinking process compared to frequency. In Study 3, we examined a key component of mental habits that has been under-explored in the literature: the cues that precede automatic thoughts. Participants from the United Kingdom completed a questionnaire about the recent and past cues that have preceded their automatic thoughts. We analyzed the results using both qualitative and quantitative methods. Using thematic analysis, we coded participants responses using the PERMA (Positive Emotion, Engagement, Relationships, Meaning, and Achievement) framework. We coded 92% of situations preceding negative thoughts and 97% of situations preceding positive thoughts as fitting within the PERMA framework. Participants described multiple cues preceding the same thought, with a median of five cues reported for both positive and negative thoughts. Participants also endorsed experiencing internal (e.g., emotions) and external (e.g., situations) cues as preceding thoughts in similar proportions. The results from Study 3 contribute to the mental habit literature by providing important information about the nature of the events preceding automatic thinking. Overall, this program of research connects several disparate areas of study (e.g., mental habits, automatic thinking) and provides new insights about how the conceptual framework of mental habits may be useful to both clinicians and researchers. By summarizing the existing research on mental habits (Study 1), distinguishing automatic from frequent thinking (Study 2), and better understanding the cues that precede automatic thoughts (Study 3), this dissertation attempts to clarify the role of habitual thinking in mental health. My intention is that the ideas in this dissertation will stimulate further discussions amongst habit researchers and clinicians, which will improve our understanding of mental health problems and how we treat them.

International Journal of Intelligent Engineering and Systems is an OPEN ACCESS international journal An Automatic Generation Control (AGC) is considered a substantial stage in power systems to ensure that the area-frequency response and the tie-line power of an interchanging steady state errors are acceptable values especially at the transient state. Whiles, several techniques have been designed for the AGC, Fuzzy logic control is commonly used. However, it is faced a longer processing time issues to adjust the accurate single in the transient state. In this paper, a Single Input Fuzzy Logic Gain Scheduling PID Controller (SIFL-PID) is designed as a supplementary loop for AGC of two area interconnected power system to reduce the processing time. The lower number of rules and the simple parameters of the SIFL-PID will contribute to minimise the design time required for the Fuzzy Logic Gain Scheduling FL-PID. The SIFL-PID also reduced the signed distance technique when it is generated one input variable simple mathematical model of the system. In comparison with the FL-PID, the number of rules controlling system can be significantly reduced. The main outcome of this work is that it is assessed the effectiveness of the SIFL-PID for two power systems that are interconnected when it is compared with the FL-PID using the MATLAB/SIMULINK environment. The results prove that, the simple design of the SIFL-PID control is validated under various condition tests. Performance analysis standards are also performed. The results of all simulations demonstrate that the suggested controller provides better performances such as like as minimum Performance analysis standards, frequency deviation power deviations and low overshoot and undershoot

In order to prevent the illegal export of paintings abroad, a museum examination using various methods for studying a work of art is carried out. At the same time, an analysis is also made of historical, art history, financial and other information and documents confirming the painting’s authenticity — provenance. Automation of such examination is hampered by the need to take into account numerical values of visual features, quality indicators, and verbal descriptions from provenance. In this paper, we consider the problem of automatic multi-task classification of paintings for museum expertise. A system architecture is proposed that checks provenance, implements a fine-grained image analysis (FGIA) of visual image features, and automatically classifies a painting by authorship, genre, and time of creation. Provenance is contained in a knowledge graph; for its vectorization, it is proposed to use a graph2vec type encoder with an attention mechanism. Fine-grained image analysis is proposed to be performed using searching discriminative regions (SDR) and learning discriminative regions (LDR) allocated by convolutional neural networks. To train the classifier, a generalized loss function is proposed. A data set is also proposed, including provenance and images of paintings by European and Ukrainian artists. Для запобігання незаконному вивезенню картин за кордон прово- диться музейна експертиза з використанням різних методів дослідження твору мистецтва, зокрема аналіз історичних, мистецтвознавчих, фінансових та інших відомостей і документів, що підтверджують справжність картин – провенансу. Автоматизація такої експертизи ускладнюється необхідністю враховувати числові значення візуальних ознак, показників якості та словесні описи з провенансу. Розглянуто завдання автоматичної багатозадачної класифікації картин під час музейної експертизи. Запропоновано архітектуру системи, яка перевіряє провенанс, реалізує детальний аналіз (FGIA) візуальних ознак зображення та виконує автоматичну класифікацію картини за авторством, жанром та часом створення. Провенанс міститься у графі знань, для векторизації якого запропоновано використовувати енкодер типу graph2vec з механізмом уваги, а детальний аналіз пропонується виконувати за допомогою пошукових відмітних регіонів (SDR) та навчальних відмітних регіонів (LDR), що виділяються згортковими нейронними мережами. Для навчання класифікатора запропоновано узагальнену функцію втрат, а також набір даних, що включає провенанс та зображення картин європейських та українських художників.

We investigated the relationship between the head size and radiation dose in pediatric brain computed tomography (CT) to evaluate the validity of automatic exposure control (AEC). Phantom experiments were performed to assess image noise with and without AEC, and indicated that AEC decreased differences in noise between slices of different section sizes. Retrospective analysis was conducted on 980 pediatric brain CT scans where the tube current was determined using AEC. The water equivalent diameter (WED) was employed as an index of the head size, and mean WED for each image set (WEDmean) and WED for each slice (WEDslice) were used for analysis. For the image-set-based analysis, volume CT dose index (CTDIvol) was compared to WEDmean. For the slice-based analysis, the tube current was compared to WEDslice using 20 of the 980 sets. Additionally, CTDIvol and WEDmean were compared between male and female patients matched for age, weight, or WEDmean. CTDIvol increased with increasing WEDmean, and an exponential curve was closely fitted to the relationship. Tube current changed similarly to the change in WEDslice for each image set, and an exponential curve was well-fitted to the plots of tube current against WEDslice when data from the 20 sets were pooled together. Although CTDIvol and WEDmean were slightly but significantly larger for male than female patients after matching for age or weight, a sex-dependent difference in CTDIvol was not found after matching for WEDmean. This study indicated successful dose modulation using AEC according to the head size for each patient and each slice location. The application of AEC to pediatric brain CT is recommended for radiation dose optimization.

Using automatic identification system (AIS) data, this article first has extended the definition of three widely used roadway congestion indices to maritime transportation systems (MTS), traffic speed index (TSI), traffic rate index (TRI), and dwell time index (DTI). Next, a methodology is developed to measure the indices based on AIS data, considering various factors, including path geometry, time of day, and the type and size of vessels, and finally the method has been applied to the AIS data of the Houston Ship Channel (HSC) to evaluate the applicability in real cases. The results show that although average TSI and TRI cannot represent waterway congestion, the real-time values (rather than the average) at the micro level can help finding location, time, and severity of traffic congestion. Besides, while TSI and TRI have shortcomings, both average and real-time dwell time index (DTI) can quantify traffic congestion and highlight severity in different waterway segments for different types of vessels. When congestion happens at some narrow waterways, vessels need to wait at sea buoy or docks, thus dwell time index (DTI) can quantify traffic congestion better than in-transit indices such as travel speed, TSI. According to HSC DTI, most tankers experience long waiting times at the sea buoy and Galveston Bay, while cargo vessels experience delays at Bayport and Barbour's Cut terminals. This paper helps the decision-makers quantify congestion in different sections of a waterway and provides measures to compare congestion for national competing projects at different waterways.

Reading comprehension is one of the essential skills for students as they make a transition from learning to read to reading to learn. Over the last decade, the increased use of digital learning materials for promoting literacy skills (e.g., oral fluency and reading comprehension) in K-12 classrooms has been a boon for teachers. However, instant access to reading materials, as well as relevant assessment tools for evaluating students’ comprehension skills, remains to be a problem. Teachers must spend many hours looking for suitable materials for their students because high-quality reading materials and assessments are primarily available through commercial literacy programs and websites. This study proposes a promising solution to this problem by employing an artificial intelligence (AI) approach. We demonstrate how to use advanced language models (e.g., OpenAI’s GPT-2 and Google’s T5) to automatically generate reading passages and items. Our preliminary findings suggest that with additional training and fine-tuning, open-source language models could be used to support the instruction and assessment of reading comprehension skills in the classroom. For both automatic story and item generation, the language models performed reasonably; however, the outcomes of these language models still require a human evaluation and further adjustments before sharing them with students. Practical implications of the findings and future research directions are discussed.

Plants need water to grow well, so watering must follow the plant's needs. Parameters that affect the process of watering plants are air temperature and soil moisture, thus, we need a control system that can make decisions in the form of watering time to meet plant water needs according to their needs, namely an automatic watering system. Fuzzy method can be used for human-like decision making in a control system. This study uses the Sugeno fuzzy method which is integrated into the Microcontroller as the controller. Testing of this system is carried out on eggplant plants which are regulated based on how long the watering time is so that the air temperature and soil moisture are following the plant's needs. The test resulted that the effective watering time interval so that the eggplant soil moisture was maintained at 40-60% was 21 seconds. It can be concluded that the fuzzy inference embedded in the design has been able to overcome the problem of watering eggplant plants, where the test shows that after the watering process, the soil moisture value can be maintained at an average value of 55% so that the soil moisture is following the needs of the plant.

Kampung Gadog Desa Sukamahi merupakan sebuah kampung yang terletak di Cianjur Jawa Barat. Topologi Kampung Gadog dikelilingi oleh persawahan sehingga mayoritas masyarakat berprofesi sebagai petani. Pendapatan masyarakat yang rendah mengakibatkan kondisi masyarakat kurang sejahtera. Untuk membantu masyarakat meningkatkan perekonomiannya dan melihat potensi air yang melimpah serta menerapkan IPTEK di kampung Gadog, maka tim akan membangun kolam budidaya ikan lele. Yang perlu diperhatikan untuk budidaya ikan lele adalah waktu pemberian pakan tepat waktu, sedangkan masyarakat menghabiskan waktu seharian jika bercocok tanam di sawah / di ladang karena posisi yang jauh. Untuk memfasilitasi hal tersebut maka pemberian pakan akan menggunakan automatic fish feeder yang sudah dilengkapi dengan photovoltaic di bagian atas alat.. Sedangkan penerapan IPTEK menggunakan pompa air DC berbasis energi surya, dimana pompa air ini akan digunakan untuk proses pengairan kolam. Untuk fish feeder dalam pemberian pakan dapat di setting sesuai dengan kebutuhan, dimana dalam hal ini settingan waktu yang dibuat adalah dalam setiap 5 jam sekali. Kolam yang digunakan adalah kolam konvensional dengan ukuran panjang x lebar x tinggi adalah 3m x 2m x1m, dengan jumlah 4 unit kolam yang terbagi menjadi 1 kolam untuk pembibitan, 1 kolam untuk pertumbuhan dan 2 kolam lainnya untuk kolam panen. Dan untuk pompa air yang digunakan untuk menguras dan atau mengisi kembali air ke kolam digunakan pompa Air DC dengan kapasitas output pompa sebesar 180 Watt ,12 Volt. Untuk panen ikan di lakukan setelah ikan berusia 3 bulan dari sejak pembibitan pada usia 15 hari.

The Netherlands is known for a lenient party drug policy climate and for high ecstasy (MDMA) use prevalence. In 2020, ecstasy use prevalence in The Netherlands was higher than in any other European country. This topic deserves investigation, as recently the question whether the illegal yet widely used party drug should be regulated instead of banned is recurring in political, public and scientific contexts. In this paper, recent Dutch current affairs television programs are analyzed to untangle the reputation of ecstasy in The Netherlands. Research about ecstasy in historical media debates has shown that Automatic Speech Recognition or ASR (speech-to-text) enrichment can be used to explore radio debates in a way that is comparable to how newspaper debates can be researched using Optical Character Recognition metadata, offering great potential for cross-media public debate research: topics can be researched in their socio-historical context across print news and radio news. Now, the CLARIAH Media Suite is unlocking the Dutch digitized public television archive for similar research with searchable ASR metadata. The television programs can be analyzed using techniques such as keyword search, timeline visualization and word frequency lists. This raises a methodological question to go with the question about ecstasy’s reputation: how can the coverage of ecstasy use in a fundamentally visual data archive be effectively explored with search techniques that are based exclusively on the spoken word? Answers are sought by comparing the results of close analysis of relevant television programs with the findings based on ASR metadata analysis., Research fellowship 'Exploring ASR-enriched Television Debates' is funded by CLARIAH (www.clariah.nl)

This paper addresses the issue of the automatic identification of river reaches and their planform type given the (observed) set of geomorphic elements and units. It introduces further advances with respect to the original proposal by Nardini and Brierley, and it explores explicitly the ability of the algorithm and associated tools to work properly on significantly different rivers while adopting a given same parametrization. This was indeed an envisaged ability speculated as a challenging conclusion of the previous work. The Duqueco, Laja, and Biobío rivers (Chile) were analyzed for this purpose. The conclusion is definitely positive, which opens future promising application horizons.

This study aims to evaluate and compare the performance of automatic transcription systems for the ToBI (Tones and Breaks Indices) and ToDI (Transcription of Dutch Intonation) frameworks. Specifically, the focus is on matching or surpassing the results achieved by previous systems using a relatively small data set for training. By employing recent advancements in Natural Language Processing (NLP), this research demonstrates the potential to achieve comparable or superior performance in generating ToDI transcriptions of intonational phonology with limited labelled data available for boundary detection and boundary classification, while, for accent detection and accent classification, no results substantially better than the majority class baseline were obtained., This paper was written as a BA thesis.

Automatic modulation classification (AMC) is an important component in non-cooperative wireless communication networks to identify the modulation schemes of the received signals. In this paper, considering the multipath effect in practical propagation environments, a distributed cooperative AMC (Co-AMC) network based on machine learning is proposed to identify the modulation scheme in non-cooperative wireless communication networks. Specifically, feature vectors are first obtained by applying a cyclic spectrum to facilitate the feature extraction of the received signal. Then, a classifier based on the K-nearest neighbor (KNN) method is designed to obtain the local decision for modulation classification at each distributed node. Meanwhile, the reliability of the local decision is estimated by applying two loss functions to assess the quality of the local decision. Finally, the unified classification result is obtained to fuse the local decisions according to their reliabilities by applying a designed decision fusion algorithm based on the distributed weighted average alternating direction method of multipliers (DWA-ADMM). The simulation results demonstrate that the proposed Co-AMC network achieves superior classification accuracy compared to existing AMC methods across a range of modulation schemes and SNRs. More importantly, the proposed Co-AMC exhibits great flexibility and practicability since it is adaptive to wireless networks with various scales and topologies.

Low-power consumption and long-distance transmission are two problems that have to be solved by the application of broadband power line communication for the automatic meter reading system. To reduce the power consumption of the communication module, based on the analysis of the composition of the power consumption, some methods are proposed. From the communication chip level and the module circuit level, the design scheme of low-power consumption is given. To solve the problem of transmission distance, a frequency band of 2.44 MHz~5.6 MHz is used as the main working frequency band. The communication module supports multiple frequency bands. Using this feature, the optimal frequency band is adaptively selected for communication and automatic switching, which further improve the transmission distance. Field application shows that the above methods effectively decrease the power consumption of the communication module and extend the transmission distance.

The automatic fluency assessment of spontaneous speech without reference text is a challenging task that heavily depends on the accuracy of automatic speech recognition (ASR). Considering this scenario, it is necessary to explore an assessment method that combines ASR. This is mainly due to the fact that in addition to acoustic features being essential for assessment, the text features output by ASR may also contain potentially fluency information. However, most existing studies on automatic fluency assessment of spontaneous speech are based solely on audio features, without utilizing textual information, which may lead to a limited understanding of fluency features. To address this, we propose a multimodal automatic speech fluency assessment method that combines ASR output. Specifically, we first explore the relevance of the fluency assessment task to the ASR task and fine-tune the Wav2Vec2.0 model using multi-task learning to jointly optimize the ASR task and fluency assessment task, resulting in both the fluency assessment results and the ASR output. Then, the text features and audio features obtained from the fine-tuned model are fed into the multimodal fluency assessment model, using attention mechanisms to obtain more reliable assessment results. Finally, experiments on the PSCPSF and Speechocean762 dataset suggest that our proposed method performs well in different assessment scenarios.

In a cluster of news texts on the same event, two sentences from different documents might express different multi-document phenomena (redundancy, complementarity, and contradiction). Cross-Document Structure Theory (CST) provides labels to explicitly represent these phenomena. The automatic identification of the multi-document phenomena and their correspondent CST relations is definitely handy for Automatic Multi-Document Summarization since it helps computers understand text meaning. In this paper, we evaluated a typology of (textual) signals for the automatic detection of the CST relations of complementarity (i.e., Historical background, Follow-up and Elaboration) in a multi-document corpus of news texts in Brazilian Portuguese. Using algorithms from different machine-learning paradigms, we obtained classifiers that achieved high general accuracy (higher than 90%), indicating the potential of the signals. Em uma coleção de notícias sobre um mesmo evento, duas sentenças de textos distintos podem expressar diferentes fenômenos multidocumento (redundância, complementaridade e contradição). A Cross-Document Structure Theory (CST) provê rótulos para representar esses fenômenos. A identificação automática dos fenômenos multidocumento e das relações CST correspondentes é central à Sumarização Automática Mutidocumento, pois ajuda a máquina a entender o conteúdo textual. Neste artigo, avaliou-se uma tipologia de sinais (textuais) para a detecção automática das relações CST de complementaridade (Historical background, Follow-up e Elaboration) em um corpus multidocumento de notícias em Português do Brasil. Utilizando algoritmos de diferentes paradigmas de Aprendizado de Máquina, obtiveram-se classificadores que atingiram alto índice de acurácia geral (superior a 90%), indicando o potencial dos sinais.

Recent advances in optical remote sensing, especially with the development of machine learning models have made it possible to automatically classify different crop types based on their unique spectral characteristics. In this article, a simple feed-forward artificial neural network (ANN) was implemented for the automatic classification of various crop types. A DJI Mavic air drone was used to simultaneously collect about 549 images of a mixed-crop farmland belonging to Federal University of Technology Minna, Nigeria. The images were annotated and the ANN algorithm was implemented using custom-designed Python programming scripts with libraries such as NumPy, Label box, and Segmentation Mask, for the classification. The algorithm was designed to automatically classify maize, rice, soya beans, groundnut, yam and a non-crop feature into different land spectral classes. The model training performance, using 70% of the dataset, shows that the loss curve flattened down with minimal over-fitting, showing that the model was improving as it trained. Finally, the accuracy of the automatic crop-type classification was evaluated with the aid of the recorded loss function and confusion matrix, and the result shows that the implemented ANN gave an overall training classification accuracy of 87.7% from the model and an overall accuracy of 0.9393 as computed from the confusion matrix, which attests to the robustness of ANN when implemented on high-resolution image data for automatic classification of crop types in a mixed farmland. The overall accuracy, including the user accuracy, proved that only a few images were incorrectly classified, which demonstrated that the errors of omission and commission were minimal.

Annotated datasets for automatic white balance (AWB) are used for the evaluation and, when necessary, the training, of AWB methods. Relying on such datasets requires awareness of the potential bias in their content and characteristics: some methods are designed to rely on the presence of particular elements, such as human skin, while other methods learn implicit relationships between image content and light properties from training data. The dependency on these relationships makes it fundamental to understand whether the available datasets are actually representative of common application scenarios, such as the presence of human subjects, the diversity of composition, or the illumination conditions. In this paper we overview the most common datasets for Automatic White Balance, including those for single as well as multiple illuminant estimation, providing a critical analysis on their characteristics. Furthermore, we identify a number of existing methods for single illuminant estimation, as a representative pool of approaches to the problem with various levels of complexity. We investigate how the performance of these correlate to the image content of common datasets.

Background: Black-box skepticism is one of the main hindrances impeding deep-learning-based automatic sleep scoring from being used in clinical environments. Methods: Towards interpretability, this work proposes a sequence-to-sequence sleep-staging model, namely SleepTransformer. It is based on the transformer backbone and offers interpretability of the model's decisions at both the epoch and sequence level. We further propose a simple yet efficient method to quantify uncertainty in the model's decisions. The method, which is based on entropy, can serve as a metric for deferring low-confidence epochs to a human expert for further inspection. Results: Making sense of the transformer's self-attention scores for interpretability, at the epoch level, the attention scores are encoded as a heat map to highlight sleep-relevant features captured from the input EEG signal. At the sequence level, the attention scores are visualized as the influence of different neighboring epochs in an input sequence (i.e. the context) to recognition of a target epoch, mimicking the way manual scoring is done by human experts. Conclusion: Additionally, we demonstrate that SleepTransformer performs on par with existing methods on two databases of different sizes. Significance: Equipped with interpretability and the ability of uncertainty quantification, SleepTransformer holds promise for being integrated into clinical settings., This article has been published in IEEE Transactions on Biomedical Engineering

Many studies have been conducted using obstacle hazard values, called potential method, for connected autonomous vehicle. However, most studies were conducted for static obstacles, and those for dynamic obstacles assumed an environment without oncoming or crossing vehicles. In this study, we devise an algorithm for generating potential values considering time series characteristics using information that can be obtained through inter-vehicle communication and propose a path ?nding algorithm that uses these potential values. As an evaluation of the usefulness of the proposed method, we compare it with existing potential methods. The results show that, in some situations, the route derived by the proposed method is superior to the route derived by the existing potential method in terms of safety and timer to reach the destination.

This paper describes a novel automatic control toolbox, designed for non-experienced practitioners. Fractional order (FO) controllers are easily tuned with the main purpose of easy practical implementation. Experimental step data are required for the automatic FO controller tuning. An embedded system identification algorithm uses the step data to obtain a process model as a second order plus dead-time (SOPDT) system. Finally, the FO controller is computed based on the previously estimated SOPDT model in order to fulfil a set of user-imposed frequency domain performance specifications: phase margin, gain crossover frequency and gain margin maximization. Experimental step response data from a strongly nonlinear vertical take-off and landing unit have been used to design an FO controller using the toolbox. The experimental closed loop results validate the proposed toolbox. The end result is a user-friendly automatic fractional order controller tuning with endless possibilities of real-world applicability.

The Design-Build-Test-Learn cycle is the main approach of synthetic biology to re-design and create new biological parts and systems, targeting the solution for complex and challenging paramount problems. The applications of the novel designs range from biosensing and bioremediation of water pollutants (e.g. heavy metals) to drug discovery and delivery (e.g. cancer treatment) or biofuel production (e.g. butanol and ethanol), amongst others. Standardisation, predictability and automation are crucial elements for synthetic biology to efficiently attain these objectives. Mathematical modelling is a powerful tool that allows us to understand, predict, and control these systems, as shown in many other disciplines such as particle physics, chemical engineering, epidemiology and economics. Yet, the inherent difficulties of using mathematical models substantially slowed their adoption by the synthetic biology community. Researchers might develop different competing model alternatives in absence of in-depth knowledge of a system, consequently being left with the burden of with having to find the best one. Models also come with unknown and difficult to measure parameters that need to be inferred from experimental data. Moreover, the varying informative content of different experiments hampers the solution of these model selection and parameter identification problems, adding to the scarcity and noisiness of laborious-to-obtain data. The difficulty to solve these non-linear optimisation problems limited the widespread use of advantageous mathematical models in synthetic biology, broadening the gap between computational and experimental scientists. In this work, I present the solutions to the problems of parameter identification, model selection and experimental design, validating them with in vivo data. First, I use Bayesian inference to estimate model parameters, relaxing the traditional noise assumptions associated with this problem. I also apply information-theoretic approaches to evaluate the amount of information extracted from experiments (entropy gain). Next, I define methodologies to quantify the informative content of tentative experiments planned for model selection (distance between predictions of competing models) and parameter inference (model prediction uncertainty). Then, I use the two methods to define efficient platforms for optimal experimental design and use a synthetic gene circuit (the genetic toggle switch) to substantiate the results, computationally and experimentally. I also expand strategies to optimally design experiments for parameter identification to update parameter information and input designs during the execution of these (on-line optimal experimental design) using microfluidics. Finally, I developed an open-source and easy-to-use Julia package, BOMBs.jl, automating all the above functionalities to facilitate their dissemination and use amongst the synthetic biology community.

The resting behavior of rearing pigs provides information about their perception of the current temperature. A pen that is too cold or too warm can impact the well-being of the animals as well as their physical development. Previous studies that have automatically recorded animal behavior often utilized body posture. However, this method is error-prone because hidden animals (so-called false positives) strongly influence the results. In the present study, a method was developed for the automated identification of time periods in which all pigs are lying down using video recordings (an AI-supported camera system). We used velocity data (measured by the camera) of pigs in the pen to identify these periods. To determine the threshold value for images with the highest probability of containing only recumbent pigs, a dataset with 9634 images and velocity values was used. The resulting velocity threshold (0.0006020622 m/s) yielded an accuracy of 94.1%. Analysis of the testing dataset revealed that recumbent pigs were correctly identified based on velocity values derived from video recordings. This represents an advance toward automated detection from the previous manual detection method.

ispartof: ECOLOGICAL INFORMATICS vol:75 status: accepted