Automatic Identification Techniques Research Articles

Automatic Detection and Identification of Calcareous Nannofossils in Chalk Using Deep Learning: A Proof-of-Concept Study for Biostratigraphy and Climate Research

Calcareous nannofossils serve as crucial indicators for establishing the biostratigraphic age of chalk macrofossil specimens in natural science collections. Better age control of specimens collected several hundred years ago enables us to uncover the dark data hidden within these collections and incorporate these data into current research projects, examining ecosystem response to past climate change. However, the manual identification of these microscopic organisms is laborious and subjective, and so we are harnessing deep learning techniques for automatic nannofossil detection and identification. This approach required the construction of a robust dataset, currently comprising over 100,000 labelled images, complemented by the development of multiple specialised deep learning models. While some models focus on detecting target species, others are dedicated to species classification. Evaluation on an independent test set showcases the efficacy of our methodology, with the current detection model achieving a balanced accuracy of 93%. Similarly, the classification model demonstrates robust performance, attaining an average balanced accuracy of 96%. Furthermore, as well as assisting with our biostratigraphic studies, the dataset of accurately labelled images has enabled us to test other aspects of ecosystem response. For example, examining morphometric changes in nannofossils over geological time can provide valuable insights into the potential impact of current global warming on modern phytoplankton assemblages (Mancini et al. 2021). This is particularly important for coccolithophores (Young et al. 2005), which play a critical role as primary producers in the global carbon cycle. A decrease in their size could lead to bottom-up ecosystem impacts and reduced carbon sequestration (Poulton et al. 2007, Krumhardt et al. 2017). Using our dataset, we conducted a deep-learning-enhanced automatic morphometric analysis focusing on the nannofossil species, Tranolithus orionatus. Our analysis revealed that two key morphometric parameters, minor axis and area size, showed statistically significant differences between the Cenomanian stage (approximately 100.5 to 93.9 million years ago) and the post-Cenomanian stages of the Late Cretaceous (approximately 93.9 to 66.0 million years ago). Kolmogorov-Smirnov tests (Massey 1951) between the two samples yielded p-values of 0.039 for the minor axis and 0.031 for the area size. Understanding these morphometric changes is crucial due to the close parallels between current climate projections and the warming and greenhouse climate of the Late Cretaceous, particularly the Cenomanian-Turonian boundary event (Arthur et al. 1990). Insights into how organisms changed morphologically during past periods of environmental stress can help us more effectively predict future responses of organisms under similar conditions (Razmjooei et al. 2020). These findings underscore the effectiveness of our approach in automating the identification and recognition of chalk nannofossils, helping to unlock natural science collections and to address key questions related to marine response to past climate change.

AI-based automatic identification and processing techniques for agricultural safety information

In the context of globalization, agricultural safety is directly linked to food security and human health. Modern agriculture’s challenge is effectively monitoring and processing vast agricultural safety information in the digital era. This study aims to achieve the automatic identification and intelligent processing of agricultural safety information within a digital media environment by applying artificial intelligence (AI) technologies. Initially, the background of AI applications in agriculture is explored, followed by an analysis of the urgent need for automated processing of agricultural safety information and an overview of current research in this field. It is demonstrated that, despite progress, existing methods still lack in-depth feature extraction and real-time capabilities of the data processing systems. A method based on multi-level feature fusion for identifying agricultural product safety is proposed to address these limitations alongside a decentralized AI Internet of Things (IoT) system for processing agricultural safety information. The multi-level feature fusion method can extract and integrate essential details on agricultural products from different dimensions and levels, thus enhancing the identification accuracy. Meanwhile, the decentralized AIoT system strengthens the efficiency and reliability of data processing, ensuring timely responses to agricultural safety information. Through deep neural networks, efficient recognition and classification of agricultural product images were achieved, enabling the automatic identification of agricultural safety information in a digital media environment. Utilizing deep learning algorithms, the system could learn and understand the characteristics of different agricultural products and accurately identify potential safety issues, such as pests, diseases, or spoilage, providing timely monitoring and management for agricultural production. The innovation of this research lies in the comprehensive utilization of multi-level data features and advanced Internet of Things (IoT) technology, significantly improving the level of intelligence in agricultural safety supervision.

Fabry-Pérot laser diode spectrum switching by controllable self-injection locking to a high-quality-factor optical microresonator

We propose a technique for automatic search and identification of possible generation regimes of a commercial multimode Fabry-Pérot laser diode self-injection locked to a high-quality-factor whispering gallery mode microresonator. Such a technique provides the potential for controllable switching between regimes with different wavelengths and with a specific number of lasing modes.

Advantages of Automated License Plate Recognition Technology

Automatic Number Plate Recognition (ANPR) is a technology that can be utilized by mall and movie theater parking management as well as toll booths on roads, expressways, etc. to expedite the toll collection process. Automated systems to retain vehicle information are becoming more and more important as the number of vehicles rises. It is imperative that communication be prioritized in order to effectively manage traffic and reduce crime. Number plate recognition is a dependable technique for automatic vehicle identification. With current algorithms, which are based on the concept of learning, developing adequate outcomes takes a long time and a lot of experience. An innovative use of machine learning is Automatic Number Plate Detection, which recognizes photos and transforms them into text. Using picture segmentation, the system locates, picks up, and extracts the vehicle's image and number plate. Afterwards, optical character recognition technology is used to identify characters in the retrieved image. This technology is used in military zones, apartment buildings, and traffic surveillance.

Automatic Detection and Recognition Method of Chinese Clay Tiles Based on YOLOv4: A Case Study in Macau

ABSTRACT With the rapid growth of global urbanization and the rising demand for sustainable development, it is essential to study the performance and durability of building materials. As a traditional and widely employed building material, Chinese clay tiles play a significant role in traditional Chinese architecture. However, traditional methods for assessing structural surface damage necessitate the time-consuming and labor-intensive assessment and judgment of trained professionals. Consequently, it is crucial to employ machine learning techniques for automatic damage type identification. This study identifies the types of damage to Chinese clay tiles in Macau by employing machine learning techniques and the YOLOv4 object detection model. A total of 363 photographs of on-site Chinese clay tiles were used as training samples, and 200 epochs of the model training were performed. The primary findings of this study are as follows: (1) The machine learning method, based on the YOLOv4 model, provides an effective and precise solution for the automatic identification of Chinese clay tiles damage types, overcoming the human and time-cost constraints of conventional evaluation methods. (2) The detection accuracy of the detection model in this study is 95.42% for the detection of Chinese clay tiles cracks, 80.91% for the detection of stains, and 89.34% for the detection of surface wear, with an overall accuracy of 88.98%, which meets the basic detection requirements. (3) The experimental results demonstrate the viability and efficacy of the proposed method for identifying clay tile damage types and provide a method reference for the preservation and sustainable development of historical buildings.

ANALYSIS OF VIDEO QUALITY AND ITS IMPACT ON FACE RECOGNITION FOR AN ONLINE PROCTORING SYSTEM

Online proctoring is a monitoring tool that instantly recognizes any unlawful behavior both before and during the exam. Three different sources are used for surveillance: audio, video streams, and desktop screen record-ings. In general, a proctor, a specifically trained professional who checks to see if the system has made a mistake and looks for violations from students taking the exam, always keeps an eye on the proctoring process. Yet, it is impossi-ble for one individual to monitor more than two people at once, and it is also possible to let fraudulent students sit for the test. Determining how an online proctoring system will be very successful in preventing unfair testing by employ-ing face recognition on video samples is the focus of this paper. The development of a trainable artificial intelligence network makes it possible to employ multiple variables simultaneously. We developed a deep learning technique for automatic face identification as part of this work, employing a convolutional neural network to calculate the differ-ence between a sample and a face in a video. It was typical to employ video samples of various qualities, taken at various distances, from various angles, with various lighting conditions, and with the inclusion of accessories to get more accurate findings. The simulation results showed that, with the exception of the experiment when accessories such as a medical face mask were present, the model we trained accurately predicted the outcome for each sampling criterion. Further examples show the effectiveness of face recognition, also in the quick playback format, the percentage of face recognition reached the minimum threshold (slightly more than 75 %).

Simultaneous digital twin identification and signal-noise decomposition through modified generalized sparse identification of nonlinear dynamics

A digital twin provides a digital replication of a physical system for remote monitoring, viewing, and control objectives. It has the potential to reshape the future of industrial processes, hence paving the way for smart manufacturing. Automatic system identification techniques that are robust to measurement noise are critical for the development of high-fidelity digital twins and their applications. By establishing a sparse regression framework, the sparse identification of nonlinear dynamics (SINDy) algorithm automatically determines the parsimonious governing equations for physical systems. However, there are some major challenges associated with using SINDy to identify digital twin models. First, the SINDy is restricted to solving the ordinary differential equation (ODE) and partial differential equation (PDE) problems. Second, measurement noise may significantly deteriorate the performance of SINDy. In this paper, the generalized SINDy (GSINDy) algorithm is first introduced to enlarge the SINDy’s applicable range. Then, the modified GSINDy (MGSINDy) algorithm is proposed, in which an objective function is constructed to simultaneously identify the digital twin input time-series dynamics model and output model while separating noise from the noisy input. Two numerical examples and one industrial case study are analysed to demonstrate the advantages of applying the proposed MGSINDy to construct digital twin models. Furthermore, the proposed algorithm can be integrated with the existing SINDy-based online model-adjusting frameworks to become online-adjustable.

Improved Accuracy of Brain Tumor Detection Using VGG16

Abstract: Brain tumor is a very serious problem of human life. In recent years, brain tumors have become one of the leading causes of death among people. It is difficult to identify the tumor itself. Direct detection and classification of brain tumors has the potential to achieve high efficiency and high levels of prognosis. However, it is well known that the accuracy of automatic identification and classification techniques varies from one technique to another and depends on the nature of the image. For the diagnosis and classification of brain tumors, MRI images have been very useful in recent years. MRI images allow us to diagnose brain tumors. This paper highlights the techniques of CNN and has worked upon VGG16 model.

Assessment of hydrological response to multiyear drought: Insights from lag characteristics and shift magnitude

AbstractThe analysis of the hydrological response to meteorological drought events can lead to a deeper understanding of alterations in hydrological processes that can be used to help maintain environmental flow (e‐flow) in aquatic ecosystems. In this study, we first identified an extreme meteorological drought event and then assessed its hydrological response. Monthly precipitation anomalies were used to identify meteorological drought, while the Lyne–Hollick method (LH filter) was used alongside the baseflow recession constant (calculated using the Automatic Baseflow Identification Technique [ABIT]) to isolate baseflow in the Baiyangdian basin. Results showed that an extreme meteorological drought event occurred in August 1996, continuing for a total of 127 months, which resulted in prolonged hydrological drought (i.e., streamflow and baseflow). A time lag was generally observed between the end of the meteorological drought event and the end of the hydrological drought event, where baseflow recovery lagged behind streamflow (runoff) recovery. Additionally, drought led to an unstable shift in the precipitation‐streamflow relationship that subsequently led to a reduction in the annual streamflow of coinciding annual precipitation compared with the historical relationship. Drought also led to a longer response between precipitation and runoff events. Results from this study show that the hydrological response to meteorological drought event is important for water resource management and for addressing effects related to climate change, especially extreme drought events.

An improved method for text detection using Adam optimization algorithm

Optical Character Recognition (OCR) is an automatic identification technique which is applied in different application areas to translate documents or images into analysable and editable data. Printed or typed characters are easy to recognize as they have well defined shape and size, but this is not true in case of handwritten text. Handwriting of every individual is different so OCR face difficulty to recognize the characters. In past, researchers have been used different Machine Learning and Artificial Intelligence tools and techniques to analyse handwritten and printed documents and also worked to create an electronic format file from them. It is difficult to reuse this information as it is very difficult to search the content from these documents by lines or words. To solve this problem, OpenCV technique is used in this research work which focuses on training and testing of neural network model to conduct Document Image Analysis. The proposed model is named as J&M model for Text Detection from Hand written images. Implementation of research work is done in Python on MNIST database of handwritten digits. From this research work, 99.5% of training accuracy and 99% of testing accuracy was achieved along with training loss of 1.5%.

GreenMicro: Identifying Microservices From Use Cases in Greenfield Development

Microservices architecture is a new paradigm for developing a software system as a collection of independent services that communicate through lightweight protocols. In greenfield development, identifying the microservices is not a trivial task, as there is no legacy code lying around and no old development to start with. Thus, identification of microservices from requirements becomes an important decision during the analysis and design phase. Use cases play a vital role in the requirements analysis modeling phases in a model-driven software engineering process. It is a technique of capturing high-level user functions and scope of the system. In this paper, we propose GreenMicro, an automatic microservice identification technique that utilizes the use cases model and the database entities. Both features are the artifacts of analysis and design phase that depict complete functionality of an overall system. In essence, a collection of related use cases indicates a bounded context of the system that can be grouped in a suitable way as microservices. Therefore, our approach GreenMicro clusters close-knit use cases to recover meaningful microservices. We investigate and validate our approach on an in-house proprietary web application and three sample benchmark applications. We have mapped our approach to state-of-the-art software quality assessment attributes and have presented the results. Preliminary results are motivating and the proposed methodology works as anticipated in producing functionally cohesive and loosely coupled microservice candidate recommendations. Our approach enables the system architects to identify microservice candidates at an early analysis and design phase of development.

Catchment natural driving factors and prediction of baseflow index for Continental United States based on Random Forest technique

Baseflow plays a critical role in maintaining the aquatic environmental health. However, the driving factors and predictions of baseflow have not been rigorously investigated on a large scale, partly preventing hydrologist from deeply understanding runoff generation. To this end, the Lyne–Hollick digital filter method and the automatic baseflow identification technique were used to estimate the long-term and seasonal baseflow index (BFI) of 619 catchments across Continental United States (CONUS) from 1981 to 2014. Six natural driving factors are selected from the 31 catchment attributes about topography and location, soil, geology, land cover, and climate characteristics. The Random Forest (RF) technique was used to predict the BFI with the selected six driving factors as predictors. Results show that the long-term average BFI was 0.49, and the BFI value was different in four seasons, with the highest value of 0.55 in winter and the lowest value of 0.46 in autumn. The forest fraction, clay proportion and snow fraction were the most powerful factors affecting the long-term average BFI. The RF technique predicts the BFI across the 619 sites in CONUS with a R2 of 0.59 after Leave-One-Location cross-validation, which was more satisfactory than the multiple linear regression method. This study can provide a deep insight into the generation and variation of baseflow and guide the annual baseflow prediction for water resources management.

An automatic and efficient technique for tumor location identification and classification through breast MR images

AimThe basic objective of this paper is to develop a single structured algorithm to classify the breast tissues into normal or abnormal. Material & MethodologyFor this study, the breast MR images dataset of 448 images collected from Healthmap diagnostics centre, PGIMS, Rohtak, India. The proposed algorithm consists of several steps i.e. an integrated (Median Wiener & Median) filtering technique is used for de-noising; breast boundary region extraction via selection of nipple and mid- sternum points to make the image rotation invariant; determined the tumor region intensity by using morphological operations & hole filling; classify the normal and abnormal breast tissues by SVM using 14 texture features extracted through GLCM & 13 morphological or kinetic features; evaluated the exact location as well as area of abnormal tissues. ResultsThe proposed algorithm has been evaluated statistically as well as visually. The quality parameters achieved are accuracy, sensitivity and specificity with values 0.937, 0.956 and 0.872 respectively. The Jaccard Index coefficient achieved is 0.921, which indicates promising overlap between the predicted tumor and the manually done image by the radiologist so called ground truth image. ConclusionThis work may be taken as a second opinion by the radiologists. The evaluated results may give a basic foundation for optimization by selecting the features more precisely and also different evolutionary algorithms using multi-classifiers can be designed in future.

Automatic mass spectra recognition for Ultra High Vacuum systems using multilabel classification

In Ultra High-Vacuum (UHV) systems it is common to find a mixture of many gases originating from surface outgassing, leaks and permeation that contaminate vacuum chambers and cause issues to reach ultimate pressures. The identification of these contaminants is, in general, done manually by trained technicians from the analysis of mass spectra. This task is time consuming and can lead to misinterpretation or partial understanding of issues. The challenge resides in the rapid identification of these contaminants by using some automatic gas identification technique. This paper explores the automatic and simultaneous identification of 80 molecules, including some of the most commonly present in this kind of environment by means of multilabel classification techniques. The best performance is drawn from a dependent binary relevance method trained by extreme gradient boosting. We obtain a Hamming loss of 0.0145 in the test set. The mean binary AUC for the test set was 0.986, and the minimum test AUC was higher than 0.89. A public interactive web app has been developed to allow vacuum users to test the model with their own data.

Automatic EEG eyeblink artefact identification and removal technique using independent component analysis in combination with support vector machines and denoising autoencoder

This study proposes a novel combination of independent component analysis (ICA) in conjunction with support vector machine (SVM) and denoising autoencoder (DA), for the first time, for removal of eyeblink artefacts from the corrupted electroencephalography (EEG). At first the eyeblink corrupted EEG signals are decomposed into independent components (ICs) using ICA, the corrupted-ICs are then identified using SVM as a classifier. From the corrupted-ICs, the artefacted segment is identified with a second SVM classifier and corrected by the pre-trained DA. Finally, inverse-ICA operation is applied on the remaining ICs and the corrected ICs to obtain the artefact-free EEG signal. The proposed methodology modifies only the portion corrupted with artefacts, and does not alter the uncorrupted part, thereby preserving the neural information in the original EEG. The proposed methodology was implemented to remove eyeblinks from the EEG data collected from the publicly available EEGLab data set. The results reveal that the proposed methodology is superior to the other recently reported methods in terms of the mutual information and average correlation coefficient. Further, the proposed method is automatic and does not require any intervention of the operator, whereas the other methods require intervention of the user.

Identification of Retinal Ganglion Cells from β-III Stained Fluorescent Microscopic Images.

Optic nerve crush in mouse model is widely used for investigating the course following retinal ganglion cell (RGCs) injury. Manual cell counting from β-III tubulin stained microscopic images has been routinely performed to monitor RGCs after an optic nerve crush injury, but is time-consuming and prone to observer variability. This paper describes an automatic technique for RGC identification. We developed and validated (i) a sensitive cell candidate segmentation scheme and (ii) a classifier that removed false positives while retaining true positives. Two major contributions were made in cell candidate segmentation. First, a homomorphic filter was designed to adjust for the inhomogeneous illumination caused by uneven penetration of β-III tubulin antibody. Second, the optimal segmentation parameters for cell detection are highly image-specific. To address this issue, we introduced an offline-online parameter tuning approach. Offline tuning optimized model parameters based on training images and online tuning further optimized the parameters at the testing stage without needing access to the ground truth. In the cell identification stage, 31 geometric, statistical and textural features were extracted from each segmented cell candidate, which was subsequently classified as true or false positives by support vector machine. The homomorphic filter and the online parameter tuning approach together increased cell recall by 28%. The entire pipeline attained a recall, precision and coefficient of determination (r2) of 85.3%, 97.1% and 0.994. The availability of the proposed pipeline will allow efficient, accurate and reproducible RGC quantification required for assessing the death/survival of RGCs in disease models.

Automatic identification of knowledge related to dengue cases in the state of Piauí in public databases using Filtered-Association Rules Networks

Dengue is an endemic disease in Brazil since the 1980s and since 1996 in Piau ́ı. The number of cases increases each year, with the incidence of more severe symptoms. This research aimed to evaluate the use of an automatic knowledge identification technique in factors related to the number of dengue occurrences. We built a dataset formed by data available in the Information System for Notifiable Diseases (SINAN) and meteorological data of the municipalities of the coastal plain of Piau ́ı. The technique used was that of Filtered Association Rules Networks, which allows visual analysis of knowledge through the use of network structures and rules filtering. As a main result, we confirmed the understanding that the most significant number of cases occurs in May, as it is the moment when the rainfall indexes are decreasing, besides that socio-cultural and race factors do not interfere in the identification of the population of higher risk. This research presents the innovation of the use of a computational technique of automatic knowledge discovery that can assist in the elaboration of prevention actions by epidemiological surveillance.

Assessing the reliability of an automated system for mineral identification using LWIR Hyperspectral Infrared imagery

Application of hyperspectral infrared imagery for mineral grain identification suffers from a lack of prediction on the irregular grain’s surface along with the mineral aggregates. Here, we present an investigation to determine the reliability of automatic mineral identification in the longwave Infrared (LWIR, 7.7–11.8 μm) with an LWIR-macro lens having a spatial resolution of 100 μm. We attempt to identify eleven different mineral grains (biotite, epidote, goethite, diopside, smithsonite, tourmaline, kyanite, scheelite, pyrope, olivine, and quartz). A machine learning-based algorithm (implemented by software) compares all of the pixel-spectra to the ASTER spectral library of JPL/NASA using spectral angle mapper (SAM) and normalized cross-correlation (NCC) to create false-color maps. Then a hue-saturation-value (HSV) principle component analysis (PCA) based K-means clustering approach groups the mineral regions in different categories. The results were compared to two different ground truths (GT) (i.e. rigid-GT and observed-GT) for quantitative calculation and as an integrated step for validating our approach. Observed-GT increased the accuracy up to 1.5 times higher than rigid-GT, from 45.67% to 69.39%. The samples were also examined by micro X-ray fluorescence (μXRF) and scanning electron microscope (SEM) in order to retrieve information on the mineral aggregates and the grain’s surface. The results of μXRF imagery (aggregate map) were compared to the results of automatic mineral identification techniques, using ArcGIS software, and the results represent a promising performance for automatic identification.

A fast automatic identification method for seismic belts based on distance correlation and its earthquake case*

Earthquake prediction practice and a large number of earthquake cases show that anomalous images of small earthquake belts may appear near the epicenter before strong earthquakes. Through the research of earthquake cases, researchers have a relatively consistent method to determine the clarity of an identified seismic belt, but there is still a lack of method on seismic belt identification from the distribution of scattered points. Due to the complexity of exhaustive algorithm, the rapid automatic identification technique of seismic belts has been progressing slowly. Visual recognition is still the basic method of seismic belt identification. Based on the algorithm of distance correlation, this paper presents a fast automatic identification method of seismic belts. The effectiveness of this method was proved by 100 random earthquakes and an example of seismic belts of magnitude 4.0 before the 2005 Jiujiang M5.7 earthquake. The results show that: ① the automatic identification of seismic belts should first identify the “relational earthquake”, then identify the “suspected seismic belt”, and finally use the criterion of seismic belt clarity to determine; ② random earthquakes and real earthquakes identification results show that the distance correlation method can realize the fast automatic identification of seismic belts by computer.

Use of Machine Learning to Automate the Identification of Basketball Strategies Using Whole Team Player Tracking Data

The use of machine learning to identify and classify offensive and defensive strategies in team sports through spatio-temporal tracking data has received significant interest recently in the literature and the global sport industry. This paper focuses on data-driven defensive strategy learning in basketball. Most research to date on basketball strategy learning has focused on offensive effectiveness and is based on the interaction between the on-ball player and principle on-ball defender, thereby ignoring the contribution of the remaining players. Furthermore, most sports analytical systems that provide play-by-play data is heavily biased towards offensive metrics such as passes, dribbles, and shots. The aim of the current study was to use machine learning to classify the different defensive strategies basketball players adopt when deviating from their initial defensive action. An analytical model was developed to recognise the one-on-one (matched) relationships of the players, which is utilised to automatically identify any change of defensive strategy. A classification model is developed based on a player and ball tracking dataset from National Basketball Association (NBA) game play to classify the adopted defensive strategy against pick-and-roll play. The methodology described is the first to analyse the defensive strategy of all in-game players (both on-ball players and off-ball players). The cross-validation results indicate that the proposed technique for automatic defensive strategy identification can achieve up to 69% accuracy of classification. Machine learning techniques, such as the one adopted here, have the potential to enable a deeper understanding of player decision making and defensive game strategies in basketball and other sports, by leveraging the player and ball tracking data.