File Name Research Articles

Deep Learning using Spatial Distances, Normalized Coordinates, Scaling and Visual Words for Large Datasets

Image Retrieval has become popular and crucial task and the number of digital images on (web servers) amplified, it became increasingly very difficult to classify and track images. Many methods have been used to make image exploration effective and reliable, such as search based on the file name, image tagging, etc. but none have proved a good idea to work in real scenario. Our proposed methodology applies deep learning using spatial distances, normalized coordinates, scaling and visual words for large data sets for retrieval of images with highest accuracy. The proposed methodology has three basic steps: the first is Content Analysis. The image is passed through coarser intervolving phase, second is CNN, third is RGB color evaluation, fourth is Retrieved feature vectors and fifth is results derivation. Proposed methodology was applied on the three famous datasets namely, Cifar-100, FTVL and Fashion. Experiments conducted on these datasets have shown outstanding results.

Research on the Method of Managing Personal Massive Photos Using Geodatabase

Abstract. In view of the limitations of the existing methods for personal massive photos management and browsing, a method of using geodatabase to manage and browse massive personal photos is proposed. Firstly, vector geodatabase is created and defined based on geographic information technology. Then, attribute information including the file name, photo date and time, photo point longitude, photo point latitude, location name, photo storage path and so on of each photo in the file system are extracted. Finally, based on the longitude and latitude of the photo point, the geospatial location data of each photo is generated, and written into the vector geodatabase together with the attribute information. Based on the storage path of photos in the file system, the links between the geospatial database and photos are established. Furtherly realize the attribute information and geographical space location management of massive photos, as well as the browsing and viewing of photos. Take personal photos as an example to introduce the data processing and verify the practicability of the method. The result shows that this method uses the idea of geodatabase to manage massive personal photos, which is conducive to reflect the geographical spatial distribution and density characteristics of the photos, and can use the time axis to connect the track of personal history, which is convenient for browsing and analyzing the experience.

Comparing public health-related material in print and web page versions of legacy media.

The objectives of this study were to create a database of public health content from a sample of legacy media, and to compare the prevalence of public health themes in print and web-based versions over time. A database was created from eleven nationally published magazines as a sample of legacy media content. Relevant material was extracted and coded by the title of the article, periodical, print or web edition, month of publication, item type, and 1-3 public health theme codes. Theme codes emerged as the documents were reviewed based on the primary discussion in each piece. A total of 2558 unique documents were extracted from print issues and 6440 from web-based issues. Seventeen public health themes were identified. Individual coded documents were saved with file names identical to the code string, thus creating a searchable database. Legacy media are those that existed before the internet and social media. Publishers target readership groups defined by age, gender, race, sexual orientation, and other commonalities. Although legacy media have been identified as trusted sources of health information, they have not been examined as sources of public health communication. Because both print and web-based versions exist as unstructured textual data, these are rarely examined with informatics methods. The process described can serve as a model for application of informatics approaches to similar data and assist development of targeted public health communications. Having a better understanding of what types of health content is distributed through legacy media can help to target health messages to specific demographic and interest groups in ways that are understandable and appealing to them.

Leveraging Fuzzy Match: Building an Automated Record Linkage Template in SAS Dataflux

Background ICES has conducted Probabilistic Record Linkage (PRL) for heath and non-health data for over 15 years. The PRL process has made data linkable to many ICES data holdings. However, due to the manual gray area resolution, record linkages for large datasets are time consuming with inconsistent results. ApproachAdapting from many years of experience with PRL methodology, record linkage templates were built in SAS Dataflux. By using combination of deterministic linkage and fuzzy match algorithms, the multi-pass linkage strategy is maintained by passing unlinked records in subsequent linkage comparison cycles. The new template uses personal identifiers of multiple given names, surnames, date of birth, death date (if applicable) and sex. In each pass, the pool of possible matched pairs is created by merging on low sensitive matchcodes with different conditions. Then, using a rule-based approach, possible pairs are examined, flags are assigned, and survival rules are applied to select the best matched records. ResultsBy feeding a pre-prepared linkage file along with updating the input and output file names, the record linkage job will be conducted automatically in SAS Dataflux through submitting a “run” command. It significantly reduces the turnaround time with no clerical review required, achieves a similar linkage rate as PRL consistently, and is utilized by various research projects. ConclusionThe automated SAS Dataflux record linkage template is more efficient than the traditional PRL process. It eliminates the human intervention of gray area resolution, while reducing project turnaround times, and maintaining a comparable accuracy and linkage rate.

Comparing CNN-LSTM and BERTimbau: an analysis of AI models in legal document classification

This study addresses the urgent need of the Attorney General's Office of the State of Bahia (PGE) to automate the classification of initial petitions, a challenge exacerbated by the lack of standardization in file naming. To tackle this issue, the work proposes the implementation of advanced Deep Learning models, aiming to overcome the limitations of the currently used approach based on regular expressions (Regex), which shows an average accuracy of 80%. The research compares the efficacy of a hybrid model, integrating Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM), and the BERTimbau model, with the goal of not only enhancing the precision in identifying these essential documents but also promoting procedural efficiency through automation. Preliminary results reveal that the CNN-LSTM model achieved an accuracy of 99.34%, while BERTimbau obtained 98.51%, demonstrating the great potential of both techniques in optimizing the judicial workflow in the digital era.

Automated algorithm for medical data structuring, and segmentation using artificial intelligence within secured environment for dataset creation

ObjectiveRoutinely collected electronic health records using artificial intelligence (AI)-based systems bring out enormous benefits for patients, healthcare centers, and its industries. Artificial intelligence models can be used to structure a wide variety of unstructured data. MethodsWe present a semi-automatic workflow for medical dataset management, including data structuring, research extraction, AI-ground truth creation, and updates. The algorithm creates directories based on keywords in new file names. ResultsOur work focuses on organizing computed tomography (CT), magnetic resonance (MR) images, patient clinical data, and segmented annotations. In addition, an AI model is used to generate different initial labels that can be edited manually to create ground truth labels. The manually verified ground truth labels are later included in the structured dataset using an automated algorithm for future research. ConclusionThis is a workflow with an AI model trained on local hospital medical data with output based/adapted to the users and their preferences. The automated algorithms and AI model could be implemented inside a secondary secure environment in the hospital to produce inferences.

Extract Text from Video

Abstract: The code import the YoutubeTranscriptionApi from youtube_transcription_api libray, The YouTube video ID is defined. The transcription data for the given video ID is fetched using get_transcription method. The transcription text is extracted from the data and stroed in the transcription variable. The transcriptipn is split into lines and thenjoined back into a single string. Finally the processed transcript is writen into a text file name “Love.text” with UTF-8 encoding. The commented-out code block is an alternative way to write the transcript into a text file using the open function directly. which you can use if you prefer.

EFFICIENT MULTI-AUTHORITY ACCESS CONTROL USING CIPHERTEXT POLICY -HIERARCHICAL ATTRIBUTE BASED ENCRYPTION IN CLOUD STORAGE

The goal of this research is to improve the security of cloud-based data storage systems by presenting the Cloud Secure Storage Mechanism based on Data Dispersion and Encryption (CPHABE). The User Frame, Authority Login, Cloud Server Login, and Data Owner Login are the four separate components that make up the system. By providing file names and requesting transformation keys from the authority for decryption, users start downloads. Requests for transformation keys, upload information, and key creation are handled by the authority. Owner identities, file names, encrypted content, gate types, and storage size graphs are all managed by cloud servers. Partially decrypted data, such as user identities, file names, transformation keys, data owner IDs, and partially decrypted content, is sent in response to user requests. Data owners may use the system to explore files, obtain keys, and apply hybrid encryption methods including Authenticated Encryption (AE) and Key Encapsulation Mechanism (KEM). This all-encompassing strategy guarantees strong encryption, data dispersion, and security measures, offering a stable foundation for cloud storage systems. Keywords: Cloud Storage, Security Mechanism, Encryption

APPROACH TO THE AUTOMATIC CREATION OF AN ANNOTATED DATASET FOR THE DETECTION, LOCALIZATION AND CLASSIFICATION OF BLOOD CELLS IN AN IMAGE

Context. The paper considers the problem of automating the creation of an annotated dataset for further use in a system for detecting, localizing and classifying blood cells in an image using deep learning. The subject of the research is the processes of digital image processing for object detection and localization.
 Objective. The aim of this study is to create a pipeline of digital image processing methods that can automatically generate an annotated set of blood smear images. This set will then be used to train and validate deep learning models, significantly reducing the time required by machine learning specialists.
 Method. The proposed approach for object detection and localization is based on digital image processing methods such as filtering, thresholding, binarization, contour detection, and filling. The pipeline for detection and localization includes the following steps: The given fragment of text describes a process that involves noise reduction, conversion to the HSV color model, defining a mask for white blood cells and platelets, detecting the contours of white blood cells and platelets, determining the coordinates of the upper left and lower right corners of white blood cells and platelets, calculating the area of the region inside the bounding box, saving the obtained data, and determining the most common color in the image; filling the contours of leukocytes and platelets with said color; defining a mask for red blood cells; defining the contours of red blood cells; determining the coordinates of the upper left and lower right corners of red blood cells; calculating the area of the region within the bounding box; entering data about the found objects into the dataframe; saving to a .csv file for future use. With an unlabeled image dataset and a generated .csv file using image processing libraries, any researcher should be able to recreate a labeled dataset.
 Results. The developed approach was implemented in software for creating an annotated dataset of blood smear images
 Conclusions. The study proposes and justifies an approach to automatically create a set of annotated data. The pipeline is tested on a set of unlabelled data and a set of labelled data is obtained, consisting of cell images and a .csv file with the attributes “file name”, “type”, “xmin”, “ymin”, “xmax”, “ymax”, “area”, which are the coordinates of the bounding box for each object. The number of correctly, incorrectly, and unrecognised objects is calculated manually, and metrics are calculated to assess the accuracy and quality of object detection and localisation.

Evaluating an Instructional Intervention for Research Data Management Training

Objective – At a large research university in Canada, a research data management (RDM) specialist and two liaison librarians partnered to evaluate the effectiveness of an active learning component of their newly developed RDM training program. This empirical study aims to contribute a statistical analysis to evaluate an RDM instructional intervention. Methods – This study relies on a pre- and post-test quasi-experimental intervention during introductory RDM workshops offered 12 times between February 2022 and January 2023. The intervention consists of instruction on best practices related to file-naming conventions. We developed a grading rubric differentiating levels of proficiency in naming a file according to a convention reflecting RDM best practices and international standards. We used manual content analysis to independently code each pre- and post-instruction file name according to the rubric. Results – Comparing the overall average scores for each participant pre- and post-instruction intervention, we find that workshop participants, in general, improved in proficiency. The results of a Wilcoxon signed-rank test demonstrate that the difference between the pre- and post-test observations is statistically significant with a high effect size. In addition, a comparison of changes in pre- and post-test scores for each rubric element showed that participants grasped specific elements more easily (i.e., implementing an international standard for a date format) than others (i.e., applying information related to sequential versioning of files). Conclusion – The results of this study indicate that developing short and targeted interventions in the context of RDM training is worthwhile. In addition, the findings demonstrate how quantitative evaluations of instructional interventions can pinpoint specific topics or activities requiring improvement or further investigation. Overall, RDM learning outcomes grounded in practical competencies may be achieved through applied exercises that demonstrate immediate improvement directly to participants.

Reproducibility Study on a PBPK Model of FcRn-Mediated Recycling for Large Molecules

The PBPK model of FcRn-mediated recycling of large molecules was developed and studied by \cite{de2023mechanistic} to characterize and predict Immunoglobulin G (IgG) disposition in plasma and tissues. This study investigated the large-molecule model in PK-Sim and its applicability to molecules with FcRn binding affinity in plasma. Subsequently, the model was extended to ensure a more mechanistic description of the internalization of FcRn and the FcRn-drug complex. This PBPK model has applications in autoimmune disorders such as primary immune thrombocytopenia which is mediated partly by platelet autoantibodies, resulting in thrombocytopenia, bleeding, and constitutional symptoms. Currently, there are several FcRn inhibitors in clinical development for numerous indications that can benefit from this model. We created a modular implementation of the model in MoBi, which is able to reproduce the originally published data. This Physiome paper describes how to access, run, and manipulate this model, how to parameterize the model to match data, and how to compare model predictions to data. In addition, some inconsistencies have been revealed and discussed in this paper. EDITOR'S NOTE v2: adding OMEX archive. v3: correcting file names. v4: updating publication date. v5: updating OMEX archive. v6: attaching CRBM report.

Handling Special Characters in File Naming Conventions for An Error-Free Pattern Matching Approach

Handling Special Characters in File Naming Conventions for An Error-Free Pattern Matching Approach

Sterling Integrator File Transfer Protocol Configurations

IBM Sterling Integrator supports a wide range of file transfer and communication protocols, including SFTP, Connect: Direct, and Mailbox (HTTP). While connecting with client servers, it’s imperative that these protocols and all other prerequisites for a successful file transfer, including authentication protocols, encryption, and file naming conventions, match between the IBM Sterling adapter for a connection and the client server.

Multi-Modal Deep Learning based Metadata Extensions for Video Clipping

General video search and recommendation systems primarily rely on metadata and personal information. Metadata includes file names, keywords, tags, and genres, among others, and is used to describe the video's content. The video platform assesses the relevance of user search queries to the video metadata and presents search results in order of highest relevance. Recommendations are based on videos with metadata judged to be similar to the one the user is currently watching. Most platforms offer search and recommendation services by employing separate algorithms for metadata and personal information. Therefore, metadata plays a vital role in video search. Video service platforms develop various algorithms to provide users with more accurate search results and recommendations. Quantifying video similarity is essential to enhance the accuracy of search results and recommendations. Since content producers primarily provide basic metadata, it can be abused. Additionally, the resemblance between similar video segments may diminish depending on its duration. This paper proposes a metadata expansion model that utilizes object recognition and Speech-to-Text (STT) technology. The model selects key objects by analyzing the frequency of their appearance in the video, extracts audio separately, transcribes it into text, and extracts the script. Scripts are quantified by tokenizing them into words using text-mining techniques. By augmenting metadata with key objects and script tokens, various video content search and recommendation platforms are expected to deliver results closer to user search terms and recommend related content.

Ten recommendations for organising bioimaging data for archival.

Organised data is easy to use but the rapid developments in the field of bioimaging, with improvements in instrumentation, detectors, software and experimental techniques, have resulted in an explosion of the volumes of data being generated, making well-organised data an elusive goal. This guide offers a handful of recommendations for bioimage depositors, analysts and microscope and software developers, whose implementation would contribute towards better organised data in preparation for archival. Based on our experience archiving large image datasets in EMPIAR, the BioImage Archive and BioStudies, we propose a number of strategies that we believe would improve the usability (clarity, orderliness, learnability, navigability, self-documentation, coherence and consistency of identifiers, accessibility, succinctness) of future data depositions more useful to the bioimaging community (data authors and analysts, researchers, clinicians, funders, collaborators, industry partners, hardware/software producers, journals, archive developers as well as interested but non-specialist users of bioimaging data). The recommendations that may also find use in other data-intensive disciplines. To facilitate the process of analysing data organisation, we present bandbox, a Python package that provides users with an assessment of their data by flagging potential issues, such as redundant directories or invalid characters in file or folder names, that should be addressed before archival. We offer these recommendations as a starting point and hope to engender more substantial conversations across and between the various data-rich communities.

Reproducibility Study on a PBPK Model of FcRn-Mediated Recycling for Large Molecules

The PBPK model of FcRn-mediated recycling of large molecules was developed and studied by \cite{de2023mechanistic} to characterize and predict Immunoglobulin G (IgG) disposition in plasma and tissues. This study investigated the large-molecule model in PK-Sim and its applicability to molecules with FcRn binding affinity in plasma. Subsequently, the model was extended to ensure a more mechanistic description of the internalization of FcRn and the FcRn-drug complex. This PBPK model has applications in autoimmune disorders such as primary immune thrombocytopenia which is mediated partly by platelet autoantibodies, resulting in thrombocytopenia, bleeding, and constitutional symptoms. Currently, there are several FcRn inhibitors in clinical development for numerous indications that can benefit from this model. We created a modular implementation of the model in MoBi, which is able to reproduce the originally published data. This Physiome paper describes how to access, run, and manipulate this model, how to parameterize the model to match data, and how to compare model predictions to data. In addition, some inconsistencies have been revealed and discussed in this paper. EDITOR'S NOTE v2: adding OMEX archive. v3: correcting file names.

Reproducibility Study on a PBPK Model of FcRn-Mediated Recycling for Large Molecules

The PBPK model of FcRn-mediated recycling of large molecules was developed and studied by \cite{de2023mechanistic} to characterize and predict Immunoglobulin G (IgG) disposition in plasma and tissues. This study investigated the large-molecule model in PK-Sim and its applicability to molecules with FcRn binding affinity in plasma. Subsequently, the model was extended to ensure a more mechanistic description of the internalization of FcRn and the FcRn-drug complex. This PBPK model has applications in autoimmune disorders such as primary immune thrombocytopenia which is mediated partly by platelet autoantibodies, resulting in thrombocytopenia, bleeding, and constitutional symptoms. Currently, there are several FcRn inhibitors in clinical development for numerous indications that can benefit from this model. We created a modular implementation of the model in MoBi, which is able to reproduce the originally published data. This Physiome paper describes how to access, run, and manipulate this model, how to parameterize the model to match data, and how to compare model predictions to data. In addition, some inconsistencies have been revealed and discussed in this paper. EDITOR'S NOTE v2: adding OMEX archive. v3: correcting file names.

System Search Service Implementation Based on a Custom Lexical Search

The search bar on any system is a highly employed and advantageous feature that helps make lives easier every day. Users see a tremendous improvement in their efficiencies as the search bar retrieves applications, and documents in a specific folder with just the file name. It helps avoid manual searching throughout the system. However, the existing technology does not help in the retrieval of documents where the search query is generic and about the document, and not just its name. This study presents a developed application that could be used to retrieve documents from anywhere on the system with user input keywords. These keywords are present inside the document and cannot be read by the existing technology of the search bar on the systems. The user can enter vernacular text as the search query on this application’s search bar. The application would accurately retrieve the files, order them according to relevancy, and list them as ready-to-open files with just a click. The program works with the elimination of the redundancy of reading all documents for each search query and using parallel processing to divide the files into batches. The application runs 303418.495ms, approximately 5 minutes, for the first run where it reads all the documents on the system. From the second run onwards, it takes only 20.080ms, approximately 0.02008 seconds.

Donor involvement in the packaging and transfer of born-digital material: A case study of the National Library of Ireland

This paper describes the methods used by the National Library of Ireland to determine how donors and depositors could take a more active role in packaging and transferring born-digital archival collections. The process was driven by a list of requirements and principles that evolved throughout. Three case studies are presented using different tools and workflows for packaging collections. Each case study results in more refined requirements, ultimately leading to a preferred approach of using DART by the APTrust as a packaging tool. The key findings of these case studies are that it is preferable to involve the donor in the process of packaging collections for transfer, as the generation of checksums adds to the integrity of the process. Packaging the file in a container format, such as tar and ZIP, can also preserve fragile file-system metadata that could be lost or altered, such as date values and file names. Finally, the case studies show that the packaging phase within a transfer reduces the significance of picking a specific cloud transfer tool, as the package should be in a state where cloud service intervention cannot occur. The package can be validated to ensure that the contents are identical to what is stored in the donors’ system. These findings fulfil a short-term need for robust transfer processes, and they lay the groundwork for requirements for a more advanced system, suitable for scaling up digital transfers.

A Key Based Hybrid Approach for Privacy and Integrity in Multi-Cloud

Before users store data in the cloud, many security issues must be addressed, as they will have no direct control over the data that has been outsourced to the cloud, particularly personal and sensitive data (health, finance, military, etc.). This article proposes a system based on chaotic maps for private key generation. A hybrid encryption for fast and secure cryptography. In addition to a multi-cloud storage with Pseudonymized file names to preserve user data privacy on the cloud while minimizing data loss. As well as a hash approach to check data integrity. AES in combination with RSA and fragmenting the file is used for the encryption. Integrity is cheeked using SHA-3. The experiments demonstrated that the key generation strategy may provide efficient keys in a shorter amount of time. Furthermore, the keys for the proposed approach passed NIST randomness testing. When cipher text fragmentation and encryption are combined, the average entropy value was (7.99). In addition, as file sizes grew, the total system's execution time increased only slightly.