Search

BACKGROUND: Digital models are considered the new standard in the clinical practice of orthodontics. However, they are difficult to use in the absence of a true scale for chairside use during clinical appointments. Therefore, an easy standardized method with true-scale paper print images would be of great utility. The aim of this study was to correlate and compare measurements obtained manually in true-scale paper printed images of digital models with those obtained digitally in the computer. METHODS: Sixty desktop scanned digital models (30 upper and 30 lower) were analyzed. Ortho Insight 3D software was used for generating the printed images on paper and for measuring the digital models. Intercanine width, interpremolar width (first and second), intermolar width (first), and arch length measures were performed with both methods and were correlated and compared. RESULTS: There was a high correlation between measurements performed with both methods. Values obtained from paper print images were lower and showed statistically significant differences (

[EN] In this work, we present a dataset which provides information on the scientific program of a set conferences of Machine Learning. Data were extracted from the IEEE Xplore Digital Library and the official web site of the International Conference on Machine Learning Applications (ICMLA). We include data of four different editions (from 2014 to 2017). Web scrapping techniques were used to mine the data contained in these web sites. The dataset covers 448 papers presented in the conference and every paper contains 6 attributes including information about the thematic session in which they were presented in the conference. The dataset is hosted in the Mendeley Dataset Repository., This work was partially supported by IDEIAGEOCA Research Group of the Universidad Politecnica Salesiana. This work also has been supported by the EU (FEDER) and the Spanish MINECO under grant TIN2015-69175-C4-1-R, and by Generalitat Valenciana PROMETE0112019/018.

The classification of science into disciplines is at the heart of bibliometric analyses. While most classifications systems are implemented at the journal level, their accuracy has been questioned, and paper-level classifications have been considered by many to be more precise. However, few studies investigated the difference between journal and the paper classification systems. This study addresses this gap by comparing the journal- and paper-level classifications for the same set of papers and journals. This isolates the effects of classification precision (i.e., journal- or paper-level) to reveal the extent of paper misclassification. Results show almost half of papers could be misclassified in journal classification systems. Given their importance in the construction and analysis of bibliometric indicators, more attention should be given to the robustness and accuracy of these disciplinary classifications schemes.

International audience

Publisher Summary The chapter explains new systems biology (NSB) as a cluster of methodological approaches for the analysis of dynamical behavior in networks that sits at the confluence of a number of disciplines. These disciplines are now experiencing massive increases in qualitatively new actual and potential interactions driven by the data explosions in genomics and proteomics. The developmental and evolutionary perspectives provide particularly useful tools for the analysis of life systems in NSB. Their character as systems that must develop and evolve means that they possess certain properties—in particular, evolvability, genetic and environmental robustness, and differential generative entrenchment for their parts. These properties are themselves very general and robust. They also possess virtues that help to ameliorate a problem of rapidly growing magnitude in the analysis of complex living systems: that the data produced by high-throughput methods (“gene chips”) have very high error rates. Some of these errors are undoubtedly products of a technology that is new, noisy, and needs further tuning, while some are almost certainly systematic and, by recognizing this, remediable.

The aim of this article is to outline the issues involved in the application of machine vision to the automatic extraction and registration of watermarks from continuous web paper. The correct identification and localization of watermarks are key issues in paper manufacturing. As well as requiring the position of the watermark for defect detection and classification, it is necessary to insure its position on the paper prior to the cutting process. Two paper types are discussed, with and without laid and chain lines (these lines appear as a complex periodic background to the watermark and further complicate the segmentation process). We will examine both morphological and Fourier approaches to the watermark segmentation process, concentrating specifically on those images with complex backgrounds. Finally we detail a system design suitable for real-time implementation.

Today's real-time systems are characterized by managing large volumes of data. Efficient database management algorithms for accessing and manipulating data are required to satisfy timing constraints of supported applications. Real-time database systems involve a new research area investigating possible ways of applying database systems technology to real-time systems. Management of real-time information through a database system requires the integration of concepts from both real-time systems and database systems. Some new criteria need to be developed to involve timing constraints of real-time applications in many database systems design issues, such as transaction/query processing, data buffering, CPU, and IO scheduling. In this paper, a basic understanding of the issues in real-time database systems is provided and the research efforts in this area are introduced. Different approaches to various problems of real-time database systems are briefly described, and possible future research directions are discussed. © 1995.

In this paper we use a simple neural net to model the development of spelling in children, and we describe the results of an experiment which shows that the error rates shown by children in spelling different types of word closely mirror the error scores of the model after it has learned the same words. We conclude that connectionist modelling can inform research into spelling development by focussing attention on the statistical nature of the input-output mappings that children must learn.

Building Protos, a learning apprentice system for heuristic classification, has forced us to scrutinize the usefulness of inductive learning and deductive problem solving. While these inference methods have been widely studied in machine learning, their seductive elegance in artificial domains ( e.g., mathematics) does not carry over to natural domains ( e.g., medicine). This paper briefly describes our rationale in the Protos system for relegating inductive learning and deductive problem solving to minor roles in support of retaining, indexing, and matching exemplars. The problems that arise from “lazy generalization” are described along with their solutions in Protos. Finally, an example of Protos in the domain of clinical audiology is discussed.

OOLP integrates the superior modeling capabilities of object-oriented paradigm in the declarative framework of logic programming. Method invocation in OOLP is given a precise model theoretic semantics which is consistent with that of logic programming. OOLP is extended to a practical object-oriented database language OOLP+ by adding some extra-logical features. OOLP+ allows object identity, multiple inheritance, method overriding and dynamic updating among other features. OOLP+ is implemented by translating it to Prolog. The translated programs executes without metainterpretation. This allows the use of all Prolog or Datalog optimization techniques. In this respect OOLP+ is unique among alternative proposals presented in the literature.

Real-time, closed-loop interactions between biological systems and their environments appear to be fundamental to the mechanisms that underlie natural intelligence. Such a theoretical view has given rise to neuronal models that predict a vide range of Pavlovian animal learning phenomena and to neural networks that may model instrumental conditioning phenomena. The theoretical framework that is emerging suggests an alternative to the current paradigms for neural network and artificial intelligence research.

Public transport has been identified as high risk as the corona-virus carrying droplets generated by the infected passengers could be distributed to other passengers. Therefore, predicting the patterns of droplet spreading in public transport environment is of primary importance. This paper puts forward a novel computational and artificial intelligence (AI) framework for fast prediction of the spread of droplets produced by a sneezing passenger in a bus. The formation of droplets of salvia is numerically modelled using a volume of fluid methodology applied to the mouth and lips of an infected person during the sneezing process. This is followed by a large eddy simulation of the resultant two phase flow in the vicinity of the person while the effects of droplet evaporation and ventilation in the bus are considered. The results are subsequently fed to an AI tool that employs deep learning to predict the distribution of droplets in the entire volume of the bus. This combined framework is two orders of magnitude faster than the pure computational approach. It is shown that the droplets with diameters less than 250 micrometers are most responsible for the transmission of the virus, as they can travel the entire length of the bus., Graphical Abstract ga1

With the development of computing and information processing techniques, artificial intelligence (AI) has been extensively applied in education. Artificial intelligence in education (AIEd) opens new opportunities, potentials, and challenges in educational practices. In its short history, AIEd has been undergoing several paradigmatic shifts, which are characterized into three paradigms in this position paper: AI-directed, learner-as-recipient, AI-supported, learner-as-collaborator, and AI-empowered, learner-as-leader. In three paradigms, AI techniques are used to address educational and learning issues in varied ways. AI is used to represent knowledge models and direct cognitive learning while learners are recipients of AI service in Paradigm One; AI is used to support learning while learners work as collaborators with AI in Paradigm Two; AI is used to empower learning while learners take agency to learn in Paradigm Three. Overall, the development trend of AIEd has been developing to empower learner agency and personalization, enable learners to reflect on learning and inform AI systems to adapt accordingly, and lead to an iterative development of the learner-centered, data-driven, personalized learning.

Background Hereditary hearing loss (HHL) is the most common sensory deficit, which highly afflicts humans. With gene sequencing technology development, more variants will be identified and support genetic diagnoses, which is difficult for human experts to diagnose. This study aims to develop a machine learning-based genetic diagnosis model of HHL-related variants of GJB2, SLC26A4 and MT-RNR1. Methods This case-control study included 1898 subjects, among which 1354 were HHL patients and 544 were carriers. Risk assessment models were established based on variants at 144 sites in three genes related to HHL by building six machine learning (ML) models. We compared the ML models with the genetic risk score (GRS) and expert interpretation (EI) to verify the clinical performance. Findings Among the six ML models, the support vector machine (SVM) showed the best performance. For the prediction of HHL-related gene sites in subjects with variants, the area under the receiver operating characteristic (AUC) of the SVM model was 0.803 (0.680–0.814) in the 10-fold stratified cross-validation and 0.751 (0.635–0.779) in external validation. The predicted results were better than both EI and GRS. Furthermore, 11 sites were identified as the smallest feature set that can be accurately predicted. Interpretation The developed SVM model has great potential to be an efficient and effective tool for HHL prediction when high throughput sequencing data are available. Funding This study was supported by the National Key Research and Development Program (2017YFC1001800).

This paper presents a novel evaluation approach for optical coherence tomography (OCT) image analysis of pharmaceutical solid dosage forms based on deep convolutional neural networks (CNNs). As a proof of concept, CNNs were applied to image data from both, in- and at-line OCT implementations, monitoring film-coated tablets as well as single- and multi-layered pellets. CNN results were compared against results from established algorithms based on ellipse-fitting, as well as to human-annotated ground truth data. Performance benchmarks used include, efficiency (computation speed), sensitivity (number of detections from a defined test set) and accuracy (deviation from the reference method). The results were validated by comparing the output of several algorithms to data manually annotated by human experts and microscopy images of cross-sectional cuts of the same dosage forms as a reference method. In order to guarantee comparability for all results, the algorithms were executed on the same hardware. Since modern OCT systems must operate under real-time conditions in order to be implemented in-line into manufacturing lines, the necessary steps are discussed on how to achieve this goal without sacrificing the algorithmic performance and how to tailor a deep CNN to cope with the high amount of image noise and alterations in object appearance. The developed deep learning approach outperforms static algorithms currently available in pharma applications with respect to performance benchmarks, and represents the next level in real time evaluation of challenging industrial OCT image data., Graphical abstract Unlabelled Image

Despite appealing characteristics for the clinical trials setting, Bayesian inference methods remain scarcely used, especially in randomized controlled clinical trials (RCT). This is particularly true when dealing with a survival endpoint, likely due to the additional complexities to model specifications. We propose to use Bayesian inference to estimate the treatment effect in this setting, using a proportional hazards (PH) model for right-censored data. Implementation of such an estimation process is illustrated on two working examples from cancer RCTs, the ALLOZITHRO and the CLL7-SA trials, both originally analyzed using a frequentist approach. In these two different settings, we show that Bayesian sequential analyses can provide early insight on treatment effect in RCTs. Relying on posterior distributions and predictive posterior probabilities, we find that Bayesian sequential analyses of the ALLOZITHRO trial, which was terminated early due to an unanticipated deleterious effect of the intervention on survival, allow quantifying early that the treatment effect was opposite to what was expected. Then, incorporating historical data in the sequential analyses of the CLL7-SA trial would have allowed the treatment effect to be closer to the protocol hypothesis. These post-hoc results give grounds to advocate for a wider use of Bayesian approaches in RCTs, including those with right-censored endpoints, as informative decision tools.

Publisher Summary This chapter explains techniques for increasing a layperson's view of computers and computer programming. It discusses the usefulness of five recommendations concerning the design of computer literacy curricula: (1) provide the learner with a concrete model of the computer; (2) encourage the learner to actively restate the new technical information in his or her own words; (3) assess the learner's existing intuitions about computer operation and try to build on them, or modify them, as needed; (4) provide the learner with methods for chunking statements into a larger, single, meaningful unit; and (5) provide the learner with methods for analyzing statements into smaller, meaningful parts. Each recommendation is concerned with increasing the meaningfulness of learning new computer information by novices. Information enters the human cognitive system from the outside and must go through the following steps: (1) reception, (2) availability, and (3) activation.

Publisher Summary The quantification requires the selection of one of a set of special morphemes that designates certain semantic features of whatever is being enumerated. Changes in classifiers are interesting because they provide an occasion to investigate an idea of traditional concern in linguistics—the relationship between language learning and language change. One can use shape or process classifiers for most of the things that have their own taxonomy specific classifiers. The unmarked classifiers are used in place of the more specific marked forms and also true in situations where there are intergenerational differences in use of forms. Numeral classifiers differ from phonology as they appear infrequently in spontaneous conversation and classifier forms are not among the earliest part of the language mastered because they depend not only on the mastery of number concepts but also on having a set of lexemes representing concepts to which they can be applied.

Summary: Background: Detailed evaluation of bile duct (BD) is main focus during endoscopic ultrasound (EUS). The aim of this study was to develop a system for EUS BD scanning augmentation. Methods: The scanning was divided into 4 stations. We developed a station classification model and a BD segmentation model with 10681 images and 2529 images, respectively. 1704 images and 667 images were applied to classification and segmentation internal validation. For classification and segmentation video validation, 264 and 517 videos clips were used. For man-machine contest, an independent data set contained 120 images was applied. 799 images from other two hospitals were used for external validation. A crossover study was conducted to evaluate the system effect on reducing difficulty in ultrasound images interpretation. Findings: For classification, the model achieved an accuracy of 93.3% in image set and 90.1% in video set. For segmentation, the model had a dice of 0.77 in image set, sensitivity of 89.48% and specificity of 82.3% in video set. For external validation, the model achieved 82.6% accuracy in classification. In man-machine contest, the models achieved 88.3% accuracy in classification and 0.72 dice in BD segmentation, which is comparable to that of expert. In the crossover study, trainees’ accuracy improved from 60.8% to 76.3% (P

The application of X-ray microtomography for quantitative structural analysis of pharmaceutical multi-particulate systems was demonstrated for commercial capsules, each containing approximately 300 formulated ibuprofen pellets. The implementation of a marker-supported watershed transformation enabled the reliable segmentation of the pellet population for the 3D analysis of individual pellets. Isolated translation- and rotation-invariant object cross-sections expanded the applicability to additional 2D image analysis techniques. The full structural characterisation gave access to over 200 features quantifying aspects of the pellets' size, shape, porosity, surface and orientation. The extracted features were assessed using a ReliefF feature selection method and a supervised Support Vector Machine learning algorithm to build a model for the detection of broken pellets within each capsule. Data of three features from distinct structure-related categories were used to build classification models with an accuracy of more than 99.55% and a minimum precision of 86.20% validated with a test dataset of 886 pellets. This approach to extract quantitative information on particle quality attributes combined with advanced data analysis strategies has clear potential to directly inform manufacturing processes, accelerating development and optimisation., Graphical abstract Unlabelled Image, Highlights • Coupling micro-XRT analysis with feature selection and machine learning for advanced pharmaceutical product characterisation. • Information on particle 3D-orientation were utilised to extract translation- and rotation-invariant object cross-sections. • Successful extraction of over 200 quantitative pellet descriptors linked to size, shape, porosity, surface and orientation. • Sensitivity analysis and ReliefF feature selection approach to identify predictive features for pellet classification. • Feature-based binary SVM classification model for the detection of broken pellets within the formulated system.

Publisher Summary Ever since the introduction of high-speed computers, econometricians have been able to analyze data with great ease. Although this computational revolution has been beneficial on the whole, it has had an unfortunate side effect. One is less likely to uncover erroneous observations and other anomalies in the data when using a computer than when analyzing data by hand. With large data sets, one has almost no choice but to rely entirely on well-defined programmable diagnostics and estimators. In recent years, statisticians have begun to study the existing statistical procedures to see as to which ones have this limited-sensitivity property and to develop alternative techniques where necessary. The papers by Roy Welsch and Bruce Hill provide examples. The simplest way to achieve protection against aberrant data is to use diagnostics that reveal the influential observations. Those observations which have a large effect on the results should be examined closely, keeping in mind the possibility that they were generated by a process not fully accounted for by the model.

In many robotic applications the need to represent and reason about spatial relationships is of great importance. However, our knowledge of particular spatial relationships is inherently uncertain. The most used method for handling the uncertainty is to "pre-engineer" the problem away, by structuring the working environment and using specially-suited high-precision equipment. In some advanced robotic research domains, however, such as automatic task planning, off-line robot programming, and autonomous vehicle operation, prior structuring will not be possible, because of dynamically changing environments, or because of the demand for greater reasoning flexibility. Spatial reasoning is further complicated because relationships are often not described explicitly, but are given by uncertain relative information. This is particularly true when many different frames of reference are used, producing a network of uncertain relationships. Rather than treat spatial uncertainty as a side issue in geometrical reasoning, we believe it must be an intrinsic part of spatial representations. In this paper, we describe a representation for spatial information, called the stochastic map, and associated procedures for building it, reading information from it, and revising it incrementally as new information is obtained. The map always contains the best estimates of relationships among objects in the map, and their uncertainties. The procedures provide a general solution to the problem of estimating uncertain relative spatial relationships. The estimates are probabilistic in nature, an advance over the previous, very conservative, worst-case approaches to the problem. Finally, the procedures are developed in the context of state-estimation and filtering theory, which provides a solid basis for numerous extensions.

Graphical Abstract The prediction model of oral disintegrating tablets formulations with direct compression process by artificial neural network (ANN) and deep neural network (DNN) techniques were established. 145 formulation data were extracted from Web of Science. All datasets were divided into three parts: training set (105 data), validation set (20) and testing set (20) to build prediction model.Image, graphical abstract, Oral disintegrating tablets (ODTs) are a novel dosage form that can be dissolved on the tongue within 3 min or less especially for geriatric and pediatric patients. Current ODT formulation studies usually rely on the personal experience of pharmaceutical experts and trial-and-error in the laboratory, which is inefficient and time-consuming. The aim of current research was to establish the prediction model of ODT formulations with direct compression process by artificial neural network (ANN) and deep neural network (DNN) techniques. 145 formulation data were extracted from Web of Science. All datasets were divided into three parts: training set (105 data), validation set (20) and testing set (20). ANN and DNN were compared for the prediction of the disintegrating time. The accuracy of the ANN model have reached 85.60%, 80.00% and 75.00% on the training set, validation set and testing set respectively, whereas that of the DNN model were 85.60%, 85.00% and 80.00%, respectively. Compared with the ANN, DNN showed the better prediction for ODT formulations. It is the first time that deep neural network with the improved dataset selection algorithm is applied to formulation prediction on small data. The proposed predictive approach could evaluate the critical parameters about quality control of formulation, and guide research and process development. The implementation of this prediction model could effectively reduce drug product development timeline and material usage, and proactively facilitate the development of a robust drug product.

The type of cognitive system (CS) studied here has four basic parts: (1) a set of interacting elementary productions, called lassifiers, (2) a performance algorithm that directs the action of the system in the environment, (3) a simple learning algorithm that keeps a record of each classifier's success in bringing about rewards, and (4) a more complex learning algorithm, called the genetic algorithm, that modifies the set of classifiers so that variants of good classifiers persist and new, potentially better ones are created in a provably efficient manner. Two “proof-of-principle” experiments are reported. One experiment shows CS's performance in a maze when it has only the ability to adjust the predictions about ensuing rewards of classifiers (similar to adjusting the “weight” of each classifier) vs. when the power of the genetic algorithm is added. Criterion was achieved an order of magnitude more rapidly when the genetic algorithm was operative. A second experiment examines transfer of learning. Placed in a more difficult maze, CS with experience in the simpler maze reaches criterion an order of magnitude more rapidly than CS without prior experience.

We present a new methodology for the design and development of large-scale simulations. Such simulations have often been criticized for their lack of intelligibility, modifiability, credibility, and performance. They are costly to build, to run, to interpret, and to change. Recent advances in artificial intelligence, most notably in the areas of expert systems and object-oriented languages, suggest new approaches to overcoming these limitations. We have applied this technology to the design and implementation of a new simulation language and environment called ROSS (Rule-Oriented Simulation System). Within our research system, we have implemented two military battle simulations, SWIRL (a strategic simulation) and TWIRL (a tactical simulation), which simulate the interactions and outcomes of combat between two opposing military forces. A graphics facility has been developed to visually display simulation runs dynamically. written in Franzlisp running on a VAX. Our graphics routines are written in C and loaded directly into the Franzlisp environment. Our graphics processor is an AED 512. Also we are experimenting with a network of Xerox 1100s (Lisp Machines) for our work on distributed simulation (discussed elsewhere [4]).

At EdCAAD we are interested in design as something people do. Designed artefacts, the products of designing, are interesting only in so far as they tell us something about design. An extreme expression of this position is to say that the world of design is the thoughts in the heads of designers, plus the skills of designers in externalizing their thoughts; design artifacts, once perceived and accepted in the worlds of other people, are no longer part of the world of design. We can describe design, briefly, as a process of synthesis. Design has to achieve a fusion between parts to create new parts, so that the products are recognized, as having a right and proper place in the world of people. Parts should be understood as referring to anything - physical objects, abstract ideas, aspirations. These parts occur in some design environment from which parts are extracted, designed upon and results replaced; in the example of buildings, the environment is people and results have to be judged by reference to that environment. It is characteristic of design that both the process and the product are not subject to explicit and complete criteria. This view of design differs sharply from the more orthodox understanding of scientific and technological endeavours which rely predominantly on a process of analysis. In the latter case, the approach is to decompose a problem into parts until individual parts are recognized as being amenable to known operations and results are reassembled into a solution. This process has a peripheral role in design when evaluating selected aspects of tentative design proposals, but the absence of well-defined and widely recognized criteria for design excludes it from the main stream of analytical developments.

Publisher Summary This chapter focuses on phonological analysis prepared for the third and final volume of the Linguistic Atlas of the Upper Midwest (LAUM), along with the treatment of the lexicon and the grammar in the first two volumes, adds measurably to the sociolinguistic data available not only to dialectologists but also to students and teachers of usage, to textbook writers, and to sociolinguists. Although within the 800-item corpus of the Upper Midwest worksheets more attention is given specifically to the vocabulary, the lexicon is not very significant in exhibiting social contrast. Several of the miscellaneous grammatical items recorded during the interviews provide more positive social markers than do the strong verbs. Greater inconsistency appears in the contrast between two locutions in which a numeral precedes a modified noun. Two syntactic constructions with relative clauses yield variants providing rather sharp social contrast.

Digital image processing of NTSC Color TV images by C-Matrix transform (CMT) for bandwidth compression is investigated. The effectiveness of the CMT compared to the discrete cosine transform (DCT) for image coding is evaluated. This comparison is based on various quantitative criteria and implementation aspects. Transform coding is applied. Simulation involves quantizer-coder design and bit rate reduction.

Background Seizure prediction can increase independence and allow preventative treatment for patients with epilepsy. We present a proof-of-concept for a seizure prediction system that is accurate, fully automated, patient-specific, and tunable to an individual's needs. Methods Intracranial electroencephalography (iEEG) data of ten patients obtained from a seizure advisory system were analyzed as part of a pseudoprospective seizure prediction study. First, a deep learning classifier was trained to distinguish between preictal and interictal signals. Second, classifier performance was tested on held-out iEEG data from all patients and benchmarked against the performance of a random predictor. Third, the prediction system was tuned so sensitivity or time in warning could be prioritized by the patient. Finally, a demonstration of the feasibility of deployment of the prediction system onto an ultra-low power neuromorphic chip for autonomous operation on a wearable device is provided. Results The prediction system achieved mean sensitivity of 69% and mean time in warning of 27%, significantly surpassing an equivalent random predictor for all patients by 42%. Conclusion This study demonstrates that deep learning in combination with neuromorphic hardware can provide the basis for a wearable, real-time, always-on, patient-specific seizure warning system with low power consumption and reliable long-term performance., Highlights • We use deep learning and long-term neural data to develop an automated, patient-tunable epileptic seizure prediction system. • We deploy our prediction system on a low-power neuromorphic chip to form the basis of a wearable device. Predicting and treating the debilitating seizures suffered by epileptic patients has challenged medical researchers for over fifty years. A new way forward was opened when Cook and colleagues, in 2013, collected a large longitudinal and continuous dataset recorded directly from patients' brains for one to three years. Harnessing the recent breakthroughs in deep learning techniques and in building specialized processing chips, we have demonstrated that seizures can now be predicted by a portable device. Our system automatically learns patient-specific pre-seizure signatures, and, in real time, warns of oncoming seizures.

This short paper intends first to emphasize the basic distinction between gradual truth and uncertainty, and its relevance when dealing with classification. Then, the representation capabilities of first-order possibilistic logic are pointed out, before briefly providing some hints, which may be of interest for dealing with uncertainty and handling some fuzzy features in description logic.

Publisher Summary The absolute necessity for maintaining accurate records of experiments performed and the resulting data is indisputable. Electrophoresis gels contain information critical for accurate interpretation of the outcome of a particular experiment. In both analytical and preparative settings, the information obtained by electrophoresis may be invaluable. Gels deteriorate in a relatively short time, however, and the dyes used to stain nucleic acids in gels deteriorate even more rapidly. This mandates archiving the image electronically and/or producing a tangible photographic record, as well as a photographic record of any associated X-ray films generated upon hybridization detection. A variety of systems have gained widespread acceptance and are currently in use to record and analyze the various types of images commonly encountered in a molecular biology setting. These systems fall into two broad categories: digital imaging, in which the image of the gel or X-ray film is analyzed by and stored in a computer and/or on a disk; and the traditional photograph generated on thermal paper or Polaroid film. Useful measurements that are now automated include determination of molecular weight, concentration, relative abundance, integrated optical density (IOD), and image saturation. The computer also provides a means of cataloging stored images, whereas an image analysis system most often consists of a completely self-contained system, such as the fotodyne luminary/FX workstation, which is in constant use in the laboratory for archiving the images.

Since the advent of computer-based electrocardiographic systems, it was recognized that these devices could add many features to analyze the electrocardiogram (ECG) that were beyond an individual's ability in making standard measurements from the paper version of the 12-lead ECG. These features have included the development of noise reduction techniques, such as signal averaging, and spectral measurements of frequency content using Fourier analysis. Both of these methods reveal electrocardiographic features that cannot be normally visualized or hand measured. Thus the field of high-resolution electrocardiography is defined as recording cardiac signals from the body surface that are not visible or apparent from the standard ECG. It most often implies a computer-based approach for processing the ECG. The signal-averaged ECG (SAECG) is the most common form of the high-resolution ECG but should be considered as only one approach for producing a high-resolution ECG.

With the continuous use of various new radar systems and complex radar systems, the electromagnetic environment is extremely deteriorated. The traditional emitter recognition methods have been difficult to meet the requirements of recognition performance in the rapidly changing battlefield environment. To solve this problem, a radar electronic signal recognition algorithm based on wavelet transform and deep learning is proposed in this paper. Starting from the radar reconnaissance system, the causes of signal preprocessing are analyzed, and the methods of signal denoising, signal normalization, signal intra pulse modulation recognition, multipath signal detection and suppression are deeply studied. In particular, the denoising algorithm based on threshold wavelet transform is proposed, which significantly improves the reliability of the algorithm. Aiming at the individual feature extraction of emitter signal, the extraction methods of emitter signal time domain feature, frequency domain feature, fuzzy function slice feature and cyclic spectrum feature based on wavelet transform are studied and analyzed, which provides stable and reliable classification features for emitter signal recognition. According to the characteristics of radar emitter signal, an optimized convolution neural network is designed, and the feature fusion processing is carried out at the decision-making level, which greatly improves the recognition effect and enhances the robustness of the recognition system. Experiments on radar data show that the fusion recognition rate is higher than any single feature and has strong robustness. In addition, compared with the traditional SVM and elm networks, the CNN network proposed in this paper can extract detailed features more effectively and improve the recognition rate of electronic radar.

In this paper, a new approach to time series classification is proposed. It transforms the scalar time series into a two-dimensional space of amplitude (time series values) and a change of amplitude (increment). Subsequently, it uses this representation to plot the data. One figure is produced for each time series. In consequence, the time series classification problem is converted into the visual pattern recognition problem. This transformation allows applying a wide range of algorithms for standard pattern recognition – in this domain, there are more options to choose from than in the domain of time series classification. In this paper, we demonstrated the high effectiveness of the new method in a series of experiments on publicly available time series. We compare our results with several state-of-the-art approaches dedicated to time series classification. The new method is robust and stable. It works for time series of differing lengths and is easy to extend and alter. Even with a baseline variant presented in an empirical study in this paper, it achieves a satisfying classification accuracy. Furthermore, the proposed conversion of raw time series into images that are subjected to feature extraction opens the possibility to apply standard clustering algorithms.

Ever since the first introduction of Artificial Intelligence into the field of hydrology, it has further generated immense interest in researching aspects for further improvements to hydrology. This can be seen in the rising number of related works published. This culminated further with the combination of pioneering optimization techniques. Who would have thought that the birds and the bees can offer advances in the mathematical sciences and so have the ants too? The ingenuity of humans is spelled out in the algorithms that mimic many natural activities, like pack hunting by the wolves! This review paper serves to broadcast more of the intriguing interest in newfound procedures in optimal forecasting. Reservoirs are the main and most efficient water storage facilities for managing uneven water distribution. However, due to the major global climate changes which affect rainfall trend and weather, it has been a necessity to find an alternative solution for effective conventional water balance. A multifunctional reservoir operation appears to require the operator to make wise decisions to achieve an optimal reservoir operation. One of the most important aspects of all this is the forecasting of streamflows. For this, Artificial Intelligence (AI) seems to be the best alternative solution; as in the past three decades, there has been a drastic increase in building and developing AI models for forecasting and modelling unstable patterns in various hydrological fields. Nevertheless, AI models are also required to be optimized in tandem to achieve the best result, leading thus to the desirous forming of hybrid models between a standalone AI model and optimization techniques. This comprehensive study categorizes machine learning into three main categories, together with the optimization techniques, and will next explore the various AI model used for different hydrology fields along with the most common optimization techniques. Summarization of findings under every section is provided. Some advantages and disadvantages found through literature reviews are summarized for ease of reference. Finally, future recommendations and overall conclusions drawn from the results of researchers are included. This current review focuses on papers from high-impact factor publications based on 10 years starting from (2009 to 2020).

A comprehensive review about machine learning application in power system especially in smart grid, renewable energy sector etc. is summarized in this paper. In the power sector, the power consumption is increased day by day very tremendously. So, it is very important that we have to generate the more power without disturbing the environment and whatever the generated power must be utilize effectively with minimum losses and higher efficiency. This will be possible with effective way of using the modern technology like machine learning (ML), artificial intelligence etc. This paper also describes the different types of machine learning techniques with diagram which will be very useful for many researchers who want to understand the basic fundamentals of machine learnings.

Today, power generation from clean and renewable resources such as wind and solar is of great salience. Smart grid technology efficiently responds to the increasing demand for electric power. Intelligent monitoring, control, and maintenance of wind energy facilities are indispensable to increase the performance and efficiency of smart grids (SGs). Integration of state-of-the-art machine learning algorithms and vision sensor networks approaches pave the way toward enhancing the wind farms performance. The generating power in a wind turbine farm is the most critical parameter that should be measured accurately. Produced power is highly related to weather patterns, and a new farm in a near area is also likely to have similar energy generation. Therefore, accurate and perpetual prediction models of the existing wind farms can be led to develop new stations with lower costs. The paper aims to estimate the angular velocity of turbine blades using vision sensors and signal processing. The high wind in the wind farm can cause the camera to vibrate in successive frames, and the noise in the input images can also strengthen the problem. Thanks to couples of solid computer vision algorithms, including FAST (Features from Accelerated Segment Test), SIFT (Scale-Invariant Feature Transform), SURF (Speeded Up Robust Features), BF (Brute-Force), FLANN (Fast Library for Approximate Nearest Neighbors), AE (Autoencoder), and SVM (support vector machines), this paper accurately localizes the Hub and track the presence of the Blade in consecutive frames of a video stream. The simulation results show that determining the hub location and the blade presence in sequential frames results in an accurate estimation of wind turbine angular velocity with 95.36% accuracy. (C) 2021 The Authors. Published by Elsevier Ltd.

Based on binocular stereo vision measurement and wireless sensing theory, this paper studies the measurement and analysis methods of athletes' movement displacement parameters. The main purpose is to explore the relationship between sports biomechanical parameters. The analysis reveals the laws of athletes 'movements, and provides theoretical guidance on athletes' attitude recognition and physical training. Based on the principle of binocular stereo vision, a non-contact displacement measurement system was developed. The displacement measurement system uses template matching to extract the image coordinates of the measurement points and restore the spatial coordinates of the measurement points through European 3D reconstruction, which improves the practicality of the measurement system. In the cantilever beam vibration test, the traditional displacement sensor and binocular image displacement measurement system are used to simultaneously measure the cantilever beam displacement. The experimental results show that the integrated displacement measurement system in this paper has higher accuracy and better stability.

Transfer learning using Convolution Neural Networks (CNNs) has improved the state of the art results in many research studies. Rolling element bearing fault diagnosis is a domain that has been researched extensively using different data mining and machine learning techniques. In this paper, we prove that deep CNNs, when trained on Bispectrum images of fault signals using transfer learning, provide highly accurate and reliable results for fault diagnosis that are at par with the state of the art results. These transfer learning based models are able to quickly learn patterns from visual features of a vibration signal’s bispectrum, eliminating the need for manual feature extraction. In this paper, four pretrained networks – Alexnet, VGG-19, GoogLeNet, ResNet-50 – have been fine tuned on bispectrum images prepared from vibration signals of machine ball bearing elements. Each network has been trained with 3 optimizers – Stochastic Gradient Descent (SGD), Adaptive Moment Estimation (Adam) and Adamax. These models are able to obtain high classification accuracy within a few epochs. We also visualise and analyze the feature maps associated with intermediate convolution layers for one of these models.

In today’s scenario the number of mobile devices is increasing by leaps and bounds and hence the networks are highly congested. To use the existing networks efficiently, the insight into the amount of traffic beforehand, would be highly beneficial. Mobile traffic forecasting would enable Software Defined Mobile Network (SDMN) to use network resources and bandwidth effectively. Therefore, this paper aims to forecast mobile traffic for SDMN using nature-inspired​ optimization techniques. The data taken is captured using Wireshark. In order to accurately predict network traffic, this paper considers Least Square Support Vector Machine (LSSVM) function estimation based training model with Whale Optimization Algorithm (WOA). The proposed technique increases the probability of global search by optimizing kernel parameters namely, regularization and kernel width. The parameters: Mean Square Error (MSE), True Positive Rate (TPR), True Negative Rate (TNR),​ accuracy and precision are evaluated for the proposed optimization algorithm. The results of the proposed algorithm Least Square Support Vector Machine-Enhanced Whale Optimization Algorithm (LSSVM-EWOA) for traffic forecasting are compared with Least Square Support Vector Machine-Whale Optimization Algorithm (LSSVM-WOA). The accuracy of prediction of the proposed model is 98.10%, which confirmed the effectiveness and the actual use of the proposed model.

The electric vehicle (EV) market increases due to the benefits of reducing greenhouse gas emissions using renewable energy resources. In this context, the charging scheme of electric vehicles in charging stations (CSs) is also important. Electronic devices’ charging between EV and multiple CS should consider EV’s short battery capacity, long charging time, residual energy in each CS, and time of use (ToU) for charging. In this paper, multiple CSs compete to offer electricity charging to a single EV. Based on this need, this paper proposes a deep learning-based auction which increases the charging amounts using Myerson auction while preserving truthfulness.

Facial Expression Recognition (FER) is an attractive and demanding problem in human computer interaction. Facial expressions are one of the most dominant and usual means for a human to communicate their feelings and intentions. This paper proposes the Enhanced Modified Decision Based Unsymmetric Trimmed Median Filter (EMDBUTMF) method which removes the noisy pixels from the face image. Also, this paper proposes the Local Directional Number (LDN) pattern, Dominant Gradient Local Ternary Pattern (DGLTP) descriptor for feature extraction and Support Vector Machine (SVM) classifier for classification. The histogram features are extracted from face images using the LDN and DGLTP descriptors. The experimental result shows that the proposed method gives an improved performance of 88% accuracy on two publicly available facial expression datasets JAFFE and CK.

This paper describes how a simple novel Galois Power-of-Two (GPOW2) real-time embedding scheme is used to improve the performance and accuracy of downstream NLP tasks. GPOW2 computes embeddings live on the fly (real time) in the context of target NLP tasks without the need for tabulated pre-embeddings. One excellent feature of the method is the ability to capture multilevel embeddings in the same pass. It simultaneously computes character, word and sentence embeddings on the fly. GPOW2 has been derived in the context of attempts to improve the performance of the SWAM Arabic morphological engine, which is a multipurpose tool that supports segmentation, classification, POS tagging, spell checking, word embeddings, sematic search, among other tasks. SWAM is a pattern-oriented algorithm that relies on morphological patterns and POS tagging to perform NLP tasks. The paper demonstrates how GPOW2 led to improvements in the accuracy of POS tagging and pattern matching, and accordingly the performance of the whole engine. The accuracy for pattern prediction is 99.47% and is 98.80% for POS tagging.