Automation Of Processing Research Articles

Review on positional significance of LSTM and CNN in the multilayer deep neural architecture for efficient sentiment classification

The deep learning revolution in the current decade has transformed the artificial intelligence industry. Eventually, deep learning techniques have become essential for many computational modeling tasks. Nevertheless, deep neural models provide a high degree of automation for natural language processing (NLP) applications. Deep neural models are extensively used to decode public reviews subjective to specific products, services, and other social activities. Further, to improve sentiment classification accuracy, several neural architectures have been developed. Convolutional neural networks (CNN) and Long-short term memory (LSTM) are the popular deep models employed in ensemble architectures for sentiment classification tasks. This review article extensively compares the competence of CNN and LSTM-based ensemble models to improve the sentiment accuracy for online review datasets. Further, this article also provides an empirical study on various ensemble models concerning the position of LSTM and CNN for efficient sentiment classification. This empirical study provides deep learning researchers with insights into building effective multilayer LSTM and CNN models for many sentiment analysis tasks.

Prevalence of Foodborne Bacterial Pathogens and Antibiotic Resistance Genes in Sweets from Local Markets in Iran.

This study aimed to investigate the prevalences of some important antibiotic-resistance genes (ARGs) and foodborne bacterial pathogens in sweet samples collected from local markets in Iran. Forty sweet samples were collected. Foodborne pathogens and ARGs were detected in the sweet samples by conventional and multiplex PCR assays using species-specific primers. Staphylococcus aureus, Cronobacter sakazakii, Shigella spp., Campylobacter jejuni, and Campylobacter coli were detected and identified in 47.5%, 20%, 45%, 5%, and 30% of the sweet samples, respectively. We found S. aureus and Shigella spp. were the most prevalent bacterial pathogens. S. aureus was found to be the most frequent pathogenic bacteria profiled in these samples. We also found a significant correlation between the presence of C. coli and Cr. sakazakii. We detected the blaSHV resistance gene in 97.5% of the sweet samples; however, blaTEM was detected in only one sample (2.5%). Regarding these results, we suggest preventive strategies such as implementing automation of food processing; monitoring the personal hygiene and health of food handlers, and testing regularly for antibiotic resistance in raw materials and products.

Automated invoice processing: Machine learning-based information extraction for long tail suppliers

Automation of incoming invoices processing promises to yield vast efficiency improvements in accounting. Until a universal adoption of fully electronic invoice exchange formats has been achieved, machine learning can help bridge the adoption gaps in electronic invoicing by extracting structured information from unstructured invoice formats. Machine learning especially helps the processing of invoices of suppliers who only send invoices infrequently, as the models are able to capture the semantic and visual cues of invoices and generalize them to previously unknown invoice layouts. Since the population of invoices in many companies is skewed toward a few frequent suppliers and their layouts, this research examines the effects of training data taken from such populations on the predictive quality of different machine-learning approaches for the extraction of information from invoices. Comparing the different approaches, we find that they are affected to varying degrees by skewed layout populations: The accuracy gap between in-sample and out-of-sample layouts is much higher in the Chargrid and random forest models than in the LayoutLM transformer model, which also exhibits the best overall predictive quality. To arrive at this finding, we designed and implemented a research pipeline that pays special attention to the distribution of layouts in the splitting of data and the evaluation of the models.

Image Segmentation of the Sudd Wetlands in South Sudan for Environmental Analytics by GRASS GIS Scripts

This paper presents the object detection algorithms GRASS GIS applied for Landsat 8-9 OLI/TIRS data. The study area includes the Sudd wetlands located in South Sudan. This study describes a programming method for the automated processing of satellite images for environmental analytics, applying the scripting algorithms of GRASS GIS. This study documents how the land cover changed and developed over time in South Sudan with varying climate and environmental settings, indicating the variations in landscape patterns. A set of modules was used to process satellite images by scripting language. It streamlines the geospatial processing tasks. The functionality of the modules of GRASS GIS to image processing is called within scripts as subprocesses which automate operations. The cutting-edge tools of GRASS GIS present a cost-effective solution to remote sensing data modelling and analysis. This is based on the discrimination of the spectral reflectance of pixels on the raster scenes. Scripting algorithms of remote sensing data processing based on the GRASS GIS syntax are run from the terminal, enabling to pass commands to the module. This ensures the automation and high speed of image processing. The algorithm challenge is that landscape patterns differ substantially, and there are nonlinear dynamics in land cover types due to environmental factors and climate effects. Time series analysis of several multispectral images demonstrated changes in land cover types over the study area of the Sudd, South Sudan affected by environmental degradation of landscapes. The map is generated for each Landsat image from 2015 to 2023 using 481 maximum-likelihood discriminant analysis approaches of classification. The methodology includes image segmentation by ‘i.segment’ module, image clustering and classification by ‘i.cluster’ and ‘i.maxlike’ modules, accuracy assessment by ‘r.kappa’ module, and computing NDVI and cartographic mapping implemented using GRASS GIS. The benefits of object detection techniques for image analysis are demonstrated with the reported effects of various threshold levels of segmentation. The segmentation was performed 371 times with 90% of the threshold and minsize = 5; the process was converged in 37 to 41 iterations. The following segments are defined for images: 4515 for 2015, 4813 for 2016, 4114 for 2017, 5090 for 2018, 6021 for 2019, 3187 for 2020, 2445 for 2022, and 5181 for 2023. The percent convergence is 98% for the processed images. Detecting variations in land cover patterns is possible using spaceborne datasets and advanced applications of scripting algorithms. The implications of cartographic approach for environmental landscape analysis are discussed. The algorithm for image processing is based on a set of GRASS GIS wrapper functions for automated image classification.

Investigating the Joint Amplitude and Phase Imaging of Stained Samples in Automatic Diagnosis.

The diagnosis of many diseases relies, at least on first intention, on an analysis of blood smears acquired with a microscope. However, image quality is often insufficient for the automation of such processing. A promising improvement concerns the acquisition of enriched information on samples. In particular, Quantitative Phase Imaging (QPI) techniques, which allow the digitization of the phase in complement to the intensity, are attracting growing interest. Such imaging allows the exploration of transparent objects not visible in the intensity image using the phase image only. Another direction proposes using stained images to reveal some characteristics of the cells in the intensity image; in this case, the phase information is not exploited. In this paper, we question the interest of using the bi-modal information brought by intensity and phase in a QPI acquisition when the samples are stained. We consider the problem of detecting parasitized red blood cells for diagnosing malaria from stained blood smears using a Deep Neural Network (DNN). Fourier Ptychographic Microscopy (FPM) is used as the computational microscopy framework to produce QPI images. We show that the bi-modal information enhances the detection performance by 4% compared to the intensity image only when the convolution in the DNN is implemented through a complex-based formalism. This proves that the DNN can benefit from the bi-modal enhanced information. We conjecture that these results should extend to other applications processed through QPI acquisition.

PBIS: A Pre-Batched Inspection Strategy for spent nuclear fuel inspection robot

Nuclear power plants play a pivotal role in the global energy infrastructure, fulfilling a substantial share of the world's energy requirements in a sustainable way. The management of these facilities, especially the handling of spent nuclear fuel (SNF), necessitates meticulous inspections to guarantee operational safety and efficiency. However, the prevailing inspection methodologies lean heavily on human operators, which presents challenges due to the potential hazards of the SNF environment. This study introduces the design of a novel Pre-Batched Inspection Strategy (PBIS) that integrates robotic automation and image processing techniques to bolster the inspection process. This methodology deploys robotics to undertake tasks that could be perilous or time-intensive for humans, while image processing techniques are used for precise identification of SNF targets and regulating the robotic system. The implementation of PBIS holds considerable promise in minimizing inspection time and enhancing worker safety. This paper elaborates on the structure, capabilities, and application of PBIS, underlining its potential implications for the future of nuclear energy inspections.

CCP-EM 2.0: software tools for efficient, accurate and reproducible management and automation of cryo-EM processing from images to structures

<i>CCP-EM 2.0</i>: software tools for efficient, accurate and reproducible management and automation of cryo-EM processing from images to structures

The Problem оf the Research Methods оf the Value-Motivational Sphere оf Personality in the Times оf Transformations

Our country is currently in a very dynamic situation. Rapid changes in a society demand prompt and timely diagnostics of the psychological condition of large and small social groups, that, in turn, makes the problem of toolkit relevant. In the article the comparative analysis of two various types of techniques used in the studies of motivation and value orientations — the traditional method and the reflexive one — is carried out. The advantages and disadvantages of each type of techniques are highlighted. The important advantage of reflexive techniques is that they minimize the problem of equivalence of meanings of the researcher and the respondents. Reflexive techniques also allow for the integration of qualitative and quantitative data analysis. Traditional techniques and methodologies are focused on a quantitative analysis of results. They are easy to create and use. Automation of data processing is possible. Conclusions are made, that use of techniques of reflective type is necessary during crises and rapid changes; and the development of traditional techniques should be based on the results received by qualitative methods.

Materials Characterisation and Structural Health Monitoring of Composite Structures Using Ultrasonic Guided Wave

The ultrasonic guided waves are employed to develop a sensor system that can be permanently attached to the aerospace composite components for the purpose of continuous or intermittent monitoring of the health of the structure. The system is capable of detecting impact and dis-bond damages that occur during the service of the aircraft. The sensor patch design, sensor reliability, low footprint sensor electronics, data processing and evaluation automation, wireless communication, energy requirements, etc. will be discussed in this paper.

Strategies for MALDI-MS method development to investigate different pharmaceutical drug modalities

High-throughput screening (HTS) is an ultra-high throughput tool that allows the identification of diverse, pharmaceutically active compounds in the early stages of drug discovery, by enabling chemists to screen reactions at micromole/nanomole scales. To eliminate the bottleneck arising from analysis of large libraries, Matrix Assisted Laser Desorption Ionization Mass Spectrometry (MALDI-MS) can be utilized as a compatible, ultra-fast, label-free, analysis tool. Upon integrating this technique with suitable liquid handling robots that can accurately spot matrices and analytes on a MALDI plate, chemical reactions can be screened at a sampling rate of <1 s per sample. While earlier efforts to improve MALDI-HTS applications were geared towards the development of automation and data processing tools, a systematic method development study across different drug modalities was needed to understand the contribution of different parameters such as MALDI matrices, choice of matrices, additives, and solvent composition, on MALDI-MS signal intensities of analytes. The current study will demonstrate the importance of initial MALDI-MS method development on small molecules, peptides, antibodies, and antibody drug conjugates. This study is designed as a starting point for MALDI-MS signal optimization, which can eventually lead to the development of effective MALDI-HTS methods for various modalities, thus paving the way for a wide range of applications, including but not limited to conformational analysis.

INNOVATIVE ANALYTICAL AND STATISTICAL TECHNOLOGIES AS A TOOL FOR MONITORING AND COUNTERACTING CORRUPTION

The article focuses on exploring the directions for implementing innovative analytical-statistical technologies as a tool for monitoring and detecting corruption in the state. To achieve this goal, the author clarifies the content of key concepts, defines the essence of innovative analytical-statistical technologies, and analyzes the applications of these technologies as elements of the state’s anti-corruption policy. It is determined that modern analytical-statistical technologies are integral to information technologies, which have emerged as a separate branch of production known as the information industry. Information technologies, including analytical-statistical ones, are realized through information systems, which combine technical tools (computers, communication devices and channels, peripherals, input/output devices, etc.) with software applications that facilitate the functioning of the technical components and analytical aspects, including the mathematical component (statistics). The use of analytical-statistical technologies as a tool to counter corruption at the state level is driven by the specificity of the corruption identification process. The application of relevant technologies is possible when perceiving corruption as a form of fraud. Therefore, the search for corruption in modern society requires a comprehensive approach, utilizing mathematical, analytical, and psychophysical research methods. This approach enables not only the identification but also the prediction of probable instances of abuse. Five directions for implementing innovative analytical-statistical technologies in anti-corruption activities are identified: 1) automation of data collection and processing; 2) automation of communication and office processes; 3) automation of direct management processes; 4) automation of decision-making processes and development; 5) development of expert systems. It is noted that analytical-statistical technologies find the most implementation in four of the identified directions: data collection/processing, direct management, decision support, and expert support.

Critical Review of Nanoindentation-Based Numerical Methods for Evaluating Elastoplastic Material Properties

It is well known that the elastoplastic properties of materials are important indicators to characterize their mechanical behaviors and are of guiding significance in the field of materials science and engineering. In recent years, the rapidly developing nanoindentation technique has been widely used to evaluate various intrinsic information regarding the elastoplastic properties and hardness of various materials such as metals, ceramics, and composites due to its high resolution, versatility, and applicability. However, the nanoindentation process of indenting materials on the nanoscale provides the measurement results, such as load-displacement curves and contact stiffness, which is challenging to analyze and interpret, especially if contained in a large amount of data. Many numerical methods, such as dimensionless analysis, machine learning, and the finite element model, have been recently proposed with the indentation techniques to further reveal the mechanical behavior of materials during nanoindentation and provide important information for material design, property optimization, and engineering applications. In addition, with the continuous development of science and technology, automation and high-throughput processing of nanoindentation experiments have become a future trend, further improving testing efficiency and data accuracy. This paper critically reviewed various numerical methods for evaluating elastoplastic constitutive properties of materials based on nanoindentation technology, which aims to provide a comprehensive understanding of the application and development trend of the nanoindentation technique and to provide guidance and reference for further research and applications.

Automation for data collection, processing and analysis on the LiX beamline

Automation for data collection, processing and analysis on the LiX beamline

An Exploration into Human–Computer Interaction: Hand Gesture Recognition Management in a Challenging Environment

Scientists are developing hand gesture recognition systems to improve authentic, efficient, and effortless human–computer interactions without additional gadgets, particularly for the speech-impaired community, which relies on hand gestures as their only mode of communication. Unfortunately, the speech-impaired community has been underrepresented in the majority of human–computer interaction research, such as natural language processing and other automation fields, which makes it more difficult for them to interact with systems and people through these advanced systems. This system’s algorithm is in two phases. The first step is the Region of Interest Segmentation, based on the color space segmentation technique, with a pre-set color range that will remove pixels (hand) of the region of interest from the background (pixels not in the desired area of interest). The system’s second phase is inputting the segmented images into a Convolutional Neural Network (CNN) model for image categorization. For image training, we utilized the Python Keras package. The system proved the need for image segmentation in hand gesture recognition. The performance of the optimal model is 58 percent which is about 10 percent higher than the accuracy obtained without image segmentation.

Automation of data processing and monitoring of the state of the environment during the construction of the "Pojate-Preljina" highway

The aim of the paper is to present the way of solving and the problems we encounter in the everyday digitization and automation of data. As the amount of data that is collected during monitoring the state of the environment medium is very large, it was necessary to find an adequate way to digitize, store and process the data. Digitization is the process of converting analog data into digital form using computers and other digital technologies. This process facilitates the storage, distribution, and analysis of data. Data is information recorded and stored on some type of digital media. The paper presents an example of data digitization in the field of environmental protection during the construction of the "Pojate - Preljina" highway using the "d.Hub" storage and visual presentation platform. d.Hub is a data transformation platform that helps users simplify data management to gain better insight into the real situation and make real-time decisions more easily. Within the Arup system, d.Hub currently has end users from different parts of Europe, so its current coverage only covers this region. Being a cloud-based solution, the ability of the system to keep up with the growth of user needs and to grow with those needs of this application depends on AWS (Amazon Web Services).

Optimizing robot grasping using soft origami zigzag gripper with artificial intelligence

The covid-19 pandemic leads to an increased need for automation in food industries. Current soft robots require cast moulding, high assembly effort, large actuators, and upfront actuation awareness due to the absence of artificial intelligence. Soft origami structures exhibit high levels of compliance. We developed a 3D print-in-place under-actuated soft origami zigzag gripper using TPU with artificial intelligence object pose estimation to grasp objects with high repeatability of success under different conditions. A self-designed 3D robot arm is used for object grasping. Grasping performance tests were conducted using different gripper designs, robot arm speed, and gripping force on objects with different masses and morphology. The soft origami zigzag gripper has better-grasping performance than the hard gripper as analyzed by paired t-test. The logistic model of the soft origami zigzag gripper’s grasping performance achieved an accuracy of 0.940 and AUC=0.911. Jetson Nano running AI CNN Resnet18, enhanced grasping performance with vision object classification achieved an accuracy of 0.923 and F1 score of 0.956. The AI CNN MobileNetV2 is used for object classification and experimental results showed it had lower accuracy as compared to the AI CNN Resnet18. The object classification using artificial intelligence optimized the robot grasping to improve automation in food processing and food handling to avoid contamination. All these can be used in the automation process in the food industry to overcome health and safety challenges.

Insurance Industry and Block Chain Technology: An Analysis of Opportunities and Challenges

Blockchain is incorporated into our distributed platform design as a system service to facilitate the execution of transactions in insurance procedures. The insurance sector is highly reliant on several procedures between parties engaged in a transaction for opening, retaining, and closing various types of policies. Our view of data management and security has undergone a paradigm shift as a result of the emergence of blockchain technology. Blockchain technology is essential to the insurance industry for optimization of claims processing and policy automation, resulting in lower costs and greater efficiency. Additionally, the ability of blockchain to increase transparency and reduce fraudulent activity promotes credibility and trust between the insured and insurer. This paper explains how the insurance sector might profit from blockchain technology investments. We review the fundamentals of blockchain technology, major platforms currently in use, and offer a simple explanation of the insurance sub-processes that blockchain might enhance. This paper also discuss about the challenges that must be overcome for blockchain solutions to be completely adopted in the insurance industry.

FAIRness through automation: development of an automated medical data integration infrastructure for FAIR health data in a maximum care university hospital

BackgroundSecondary use of routine medical data is key to large-scale clinical and health services research. In a maximum care hospital, the volume of data generated exceeds the limits of big data on a daily basis. This so-called “real world data” are essential to complement knowledge and results from clinical trials. Furthermore, big data may help in establishing precision medicine. However, manual data extraction and annotation workflows to transfer routine data into research data would be complex and inefficient. Generally, best practices for managing research data focus on data output rather than the entire data journey from primary sources to analysis. To eventually make routinely collected data usable and available for research, many hurdles have to be overcome. In this work, we present the implementation of an automated framework for timely processing of clinical care data including free texts and genetic data (non-structured data) and centralized storage as Findable, Accessible, Interoperable, Reusable (FAIR) research data in a maximum care university hospital.MethodsWe identify data processing workflows necessary to operate a medical research data service unit in a maximum care hospital. We decompose structurally equal tasks into elementary sub-processes and propose a framework for general data processing. We base our processes on open-source software-components and, where necessary, custom-built generic tools.ResultsWe demonstrate the application of our proposed framework in practice by describing its use in our Medical Data Integration Center (MeDIC). Our microservices-based and fully open-source data processing automation framework incorporates a complete recording of data management and manipulation activities. The prototype implementation also includes a metadata schema for data provenance and a process validation concept. All requirements of a MeDIC are orchestrated within the proposed framework: Data input from many heterogeneous sources, pseudonymization and harmonization, integration in a data warehouse and finally possibilities for extraction or aggregation of data for research purposes according to data protection requirements.ConclusionThough the framework is not a panacea for bringing routine-based research data into compliance with FAIR principles, it provides a much-needed possibility to process data in a fully automated, traceable, and reproducible manner.

A novel hybrid deep learning method for early detection of lung cancer using neural networks

Lung cancer is a fatal disease with a high mortality rate in diseased patients. Early diagnosis of this disease and accurately identifying the lung cancer stage can save the patients’ lives. Several image processing, biomarker-based and machine automation approaches are used to identify lung cancer, but accuracy and early diagnosis are challenging for medical practitioners. The Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) are utilized in this study to extract the CT scan images. In conventional methods, manual CT images are supplied to visualize whether the person has lung cancer. This research article proposes a novel method for an early and accurate diagnosis called Cancer Cell Detection using Hybrid Neural Network (CCDC-HNN). The features are extracted from the CT scan images using deep neural networks. The accuracy in feature extraction is very important to detect the cancerous cells at early stages to save the patient from this fatal disease. In this study, an advanced 3D-convolution neural network (3D-CNN) is also utilized to improve the accuracy of diagnosis. The suggested approach also enables the distinction between benign and malignant tumors. The results are evaluated using standard statistical techniques, and the results confirm the viability of the proposed hybrid deep learning (DL) technique for early diagnosis of the lung cancer.

Tool Wear Condition Monitoring Method Based on Deep Learning with Force Signals.

Tool wear condition monitoring is an important component of mechanical processing automation, and accurately identifying the wear status of tools can improve processing quality and production efficiency. This paper studied a new deep learning model, to identify the wear status of tools. The force signal was transformed into a two-dimensional image using continuous wavelet transform (CWT), short-time Fourier transform (STFT), and Gramian angular summation field (GASF) methods. The generated images were then fed into the proposed convolutional neural network (CNN) model for further analysis. The calculation results show that the accuracy of tool wear state recognition proposed in this paper was above 90%, which was higher than the accuracy of AlexNet, ResNet, and other models. The accuracy of the images generated using the CWT method and identified with the CNN model was the highest, which is attributed to the fact that the CWT method can extract local features of an image and is less affected by noise. Comparing the precision and recall values of the model, it was verified that the image obtained by the CWT method had the highest accuracy in identifying tool wear state. These results demonstrate the potential advantages of using a force signal transformed into a two-dimensional image for tool wear state recognition and of applying CNN models in this area. They also indicate the wide application prospects of this method in industrial production.