Search

Over the last few years, there has been a rapid growth in digital data. Images with quotes are spreading virally through online social media platforms. Misquotes found online often spread like a forest fire through social media, which highlights the lack of responsibility of the web users when circulating poorly cited quotes. Thus, it is important to authenticate the content contained in the images being circulated online. So, there is a need to retrieve the information within such textual images to verify quotes before its usage in order to differentiate a fake or misquote from an authentic one. Optical Character Recognition (OCR) is used in this paper, for converting textual images into readable text format, but none of the OCR tools are perfect in extracting information from the images accurately. In this paper, a method of post-processing on the retrieved text to improve the accuracy of the detected text from images has been proposed. Google Cloud Vision has been used for recognizing text from images. It has also been observed that using post-processing on the extracted text improved the accuracy of text recognition by 3.5% approximately. A web-based text similarity approach (URLs and domain name) has been used to examine the authenticity of the content of the quoted images. Approximately, 96.26% accuracy has been achieved in classifying quoted images as verified or misquoted. Also, a ground truth dataset of authentic site names has been created. In this research, images with quotes by famous celebrities and global leaders have been used. A comparative analysis has been performed to show the effectiveness of our proposed algorithm.

Safety is critical for autonomous vehicle, therefore quality management system method is crucial for the risks that may impact human beings. Quality management system help identify customer requirements and finally meet them. Customer requirements also include other aspects that customers or stakeholders are most concerned. Although many researches on customer perception had been done, they do not include all aspect of the requirements toward autonomous vehicle. Furthermore, they are most in text format or will be transfer to text format that convenient to store and read. In front of the large amount text data, classifying them become time and costs consuming. The customer requirements on autonomous vehicle are summarized and allocated in different categories. The natural language processing method is applied in this paper. This method shows its efficiency on dealing with customer requirements. The results provide valuable reference for autonomous vehicle developer and top managemen

Short Message Service (SMS) is a technology that provides service for sending and receiving messages between cell phones. Every individual, government, private or educational institution cannot be separated from using SMS as one of the information media. One of them is meeting notification information. But SMS technology can only carry limited data. SMS Gateway is a system that bridges mobile phones with the system that becomes a server with SMS as the information. In the SMS Gateway work system, the user's cellular phone sends an SMS containing the written format to access the information needed through the GSM network. The SMS will be received by the SMS Gateway cellular phone which will then be retrieved by the PC using the mfbus protocol via a data cable. Up to the PC, the text format will be processed by the SMS Gateway application program to produce information that will be sent to the SMS Gateway cellular phone using the mfbus protocol via a data cable. After that the information is sent by the SMS Gateway cellular phone to the user's cellular phone. With the SMS Gateway-based meeting notification application, it can provide detailed and concurrent notification of meeting information so that each meeting member can follow according to his schedule.

This chapter provides a technical description of several tools used to facilitate spectrum management operations. It includes hardware and infrastructure requirements, software used, and capabilities of spectrum management tools. Tools that promote the flow of information between spectrum stakeholders reduce the planning cycle leading to quicker decisions. Spectrum managers are able to perform the core SMO functions much more efficiently when tools comply with the net‐centric environment. Standard Frequency Action Format is a line oriented text format used by DOD, and by U.S. allies and unified action partners who use Spectrum XXI. Joint spectrum interference resolution online collaboration portal is the preferred tool for reporting EMI occurrences. It is a Web‐based, centralized application containing data and correspondence for reported EMI, intrusion, and jamming incidents dating back to 1970. The Defense Spectrum Organization provides direct on‐line data access to the joint spectrum data repository and provides customized reports.

In the face of the growing incidence of malignant tumors (about 3.929 million, data issued in January 2019) and the death rate (about 2.338 million, data issued in January 2019) and the limitation of the application of informatics in cancer treatment, this paper tried to use TRIZ theory to deduce new ideas about cancer treatments, perform literature analysis on schemes, and make retrieval strategy for meta-analyses on cancer therapy. By using TRIZ theory and information to analyze the fields of cancers, the research schemes for selecting documents on cancer therapy were presented. After retrieving the documents, we exported all those articles in text format. We further analyzed the research status with the software CiteSpace and Bibliographic Information Mining System (BICOMS) by using different keywords, regions, countries, schools, authors, geography, institutes, etc. We also performed the cluster analysis by using Statistical Package for the Social Sciences (SPSS) software and performed two-way cluster analysis by using Gluto software. The hot areas of research and their tendency or distribution were analyzed. The search strategy was set and the retrieving results were tried.

In stated-preference research, the conventional approach to describing study attributes is through text, often with easy-to-understand graphics. More recently, researchers have begun to present attribute descriptions and content in videos. Some experts have expressed concern regarding internalization and retention of information conveyed via video. Our study aimed to compare respondents’ understanding of attribute information provided via text versus video. Potential respondents were randomized to receive a text or video version of the survey. In the text version, all content was provided in text format along with still graphics. In the video version, text content was interspersed with four video clips, providing the same information as the text version. In both versions, 10 questions were embedded to assess respondents’ understanding of the information presented relating to ovarian cancer treatments. Half of the questions were on treatment benefits and the other half were on treatment-related risks. Some questions asked about the decision context and definitions of treatment features, and others asked about the graphic presentation of treatment features. Preferences for ovarian cancer treatments were also compared between respondents receiving text versus video versions. Overall, 150 respondents were recruited. Of the 95 who were eligible and completed the survey, 54 respondents received the text version and 41 received the video version. Median times to completion were 24 and 30 min in the video and text arms, respectively (p

The current COVID-19 crisis has revealed the crucial role of online communication technologies in providing unique opportunities to carry out qualitative research in online user-based testing. The ability to provide a shared common space for participants living in different parts of the world and to record discursive data in text format accurately, makes these tools crucial in gathering qualitative data for research studies (Turney & Pocknee, 2005). Although the accessibility of the online communication platforms is improving, they still present significant challenges for all users, especially when running synchronous meeting sessions with participants in remote settings (Dodds & Hess, 2020).

The report discusses the use of Text Mining algorithms such as semantic analysis of text and search for keywords to solve the problem of categorizing data entering the information system in the form of short messages in text format. An example of the application of such algorithms in the information system for processing user messages is given.

Eye movements in reading can provide important information about readers' perception of texts and, with appropriate algorithms, about the level of their understanding of what is written. Both digital learning and professional training require processing of large volumes of information, mostly in the text format. Management and control of students' or trainees' levels of perception in reading can be accomplished with the use of technology, assessing attention, engagement, understanding, cognitive load and tiredness of readers. These metrics can potentially be inferred from eye tracking data during reading a text. For this task it is important to utilize features of mass-market consumer devices. For example, the latest version of iPad Pro with a standard iOS operating system has an embedded eye tracker, and thus it provides opportunities for mass adoption in the educational and training settings. Authors of this work built a stable algorithm for detecting saccades and fixations in noisy eye tracking data recorded by iPad Pro 11″ and achieved certain progress in applying a machine-learning algorithm for classifying eye movement patterns in reading. The results could be used for creating an interactive reader's assistant in the format of an iOS application.

Audio file size is relatively larger when compared to files with text format. Large files can cause various obstacles in the form of large space requirements for storage and a long enough time in the shipping process. File compression is one solution that can be done to overcome the problem of large file sizes. Arithmetic coding is one algorithm that can be used to compress audio files. The arithmetic coding algorithm encodes the audio file and changes one row of input symbols with a floating point number and obtains the output of the encoding in the form of a number of values greater than 0 and smaller than 1. The process of compression and decompression of audio files in this study is done against several wave files. Wave files are standard audio file formats developed by Microsoft and IBM that are stored using PCM (Pulse Code Modulation) coding. The wave file compression ratio obtained in this study was 16.12 percent with an average compression process time of 45.89 seconds, while the average decompression time was 0.32 seconds.

Nowadays, recognition of machine printed or hand printed document is essential part in applications. Optical character recognition is one of the techniques which are used to convert the printed or hand written file into its corresponding text format. Tamil is the south Indian language spoken widely in Tamil Nadu. It has the longest unbroken literary tradition amongst Dravidian language. Tamil character recognition (TCR) is one of the challenging tasks in optimal character recognition. It is used for recognizing the characters from scanned input digital image and converting them into machine editable form. Recognition of handwritten in Tamil character is very difficult, due to variations in size, style and orientation angle. Character editing and reprinting of text document that were printed on paper are time consuming and low accuracy. In order to overcome this problem, the proposed technique utilizes effective Tamil character recognition. The proposed method has four main process such as preprocessing process, segmentation process, feature extraction process and recognition process. For preprocessing, the input image is fed to Gaussian filter, Binarization process and skew detection technique. Then the segmentation process is carried out, here line and character segmentation is done. From the segmented output, the features are extracted. After that the feature extraction, the Tamil character is recognized by means of optimal artificial neural network. Here the traditional neural network is modified by means of optimization algorithm. In neural network, the weights are optimized by means of Elephant Herding Optimization. The performance of the proposed method is assessed with the help of the metrics namely Sensitivity, Specificity and Accuracy. The proposed approach is experimented and its results are analyzed to visualize the performance. The proposed approach will be implemented in MATLAB.

Although current computer-aided software engineering tools support developers in composing a program, there is no doubt that more flexible supportive tools are needed to address the increases in the complexity of programs. This need can be met by automating the intellectual activities that are carried out by humans when composing a program. This paper aims to automate the composition of a programming language code from pseudocode, which is viewed here as a translation process for a natural language text, as pseudocode is a formatted text in natural English language. Based on this view, a new automatic code generator is developed that can convert pseudocode to C# programming language code. This new automatic code generator (ACG), which is called CodeComposer, uses natural language processing (NLP) techniques such as verb classification, thematic roles, and semantic role labeling (SRL) to analyze the pseudocode. The resulting analysis of linguistic information from these techniques is used by a semantic rule-based mapping machine to perform the composition process. CodeComposer can be viewed as an intelligent computer-aided software engineering (I_CASE) tool. An evaluation of the accuracy of CodeComposer using a binomial technique shows that it has a precision of 88%, a recall of 91%, and an F-measure of 89%.

Classical Chinese poetry is a kind of formatted text with phonological patterns. It has been a big challenge for the classical Chinese poetry generation. Because deep learning technology has made great progress in image and text processing, we present a classical Chinese poetry generation model based on Transformer-XL that can capture longer-term dependency than the original transformer. Our model creates the first character according to the title specified by a user and then concatenates the generated character as the input to predict the next character until reaches the predefined number of characters. Experimental results show that our model can generate poems that have good format, consistency and rhythm.

The arrival of COVID-19 has ushered in a new era of distance learning. Since schools and universities have closed, learning has transferred to apps like Google Meet, Microsoft Teams, Zoom, and others. Almost all colleges have changed their curricula to reflect the current reality. Students' practical knowledge deteriorated as a result of the virtual form of learning, and they began attending lectures only for the purpose of attending them. With all of this, their grades and scores should ideally be declining, but the findings came as a shock. It was a fantastic turnaround. Many students outperformed their average score. This is due to the fact that there has never been a way to perform an organized evaluation without using unequal means in the online-mode of education. To address the existing problem, a system that can assist in analysing unfair tactics used by students is required. The employment of proctoring procedures is a big difficulty for the research community when it comes to online examinations. In this paper, we present how to create a complete multi-model system utilising computer vision to prevent the presence of humans throughout the examination. We propose a system that includes a variety of features that students may exploit throughout the test, such as eye gaze tracking, mouth open or close detection, object identification, and head posture estimate using facial landmarks and face detection. Our system can also transform the student's voice into a text format, which might be useful for keeping track of the words said by the student. This might aid the examiner in determining whether or not the student is speaking with someone close. In summary, this research reveals how to prevent cheating in online tests using semi-automated proctoring based on vision and audio capabilities and monitor multiple students at a time.

Life without vision is filled with hardships. We have proposed a system to aid visually impaired persons in their day-to-day navigation by providing them information about their surroundings using audio output (voice feedback) in real-time. The execution of this system is divided into three steps. The first is object detection using the You Only Look Once version 3 (YOLOv3) algorithm. Although multiple objects as detected in each frame, it is not practical to relay each object to the (visually impaired) user. There is a need to find the closest and most relevant object for the user. This is done in the second stage by estimating the depth and finding the closest object with the help of a depth map and comparing the size of bounding boxes in real-time. The output of the first two steps is generated in text format. The last step is to convert the text into audio output using the Text-To-Speech (TTS) API. As this system is intended to be inexpensive and readily available, this system is implemented on Android smartphones and has no additional hardware requirements.

Artificial intelligence can assist in interpreting chest X-ray radiography (CXR) data, but large datasets require efficient image annotation. The purpose of this study is to extract CXR labels from diagnostic reports based on natural language processing, train convolutional neural networks (CNNs), and evaluate the classification performance of CNN using CXR data from multiple centers We collected the CXR images and corresponding radiology reports of 74,082 subjects as the training dataset. The linguistic entities and relationships from unstructured radiology reports were extracted by the bidirectional encoder representations from transformers (BERT) model, and a knowledge graph was constructed to represent the association between image labels of abnormal signs and the report text of CXR. Then, a 25-label classification system were built to train and test the CNN models with weakly supervised labeling. In three external test cohorts of 5,996 symptomatic patients, 2,130 screening examinees, and 1,804 community clinic patients, the mean AUC of identifying 25 abnormal signs by CNN reaches 0.866 ± 0.110, 0.891 ± 0.147, and 0.796 ± 0.157, respectively. In symptomatic patients, CNN shows no significant difference with local radiologists in identifying 21 signs (p > 0.05), but is poorer for 4 signs (p 0.05), but is poorer at classifying nodules (p = 0.013). In community clinic patients, CNN shows no significant difference for 12 signs (p > 0.05), but performs better for 6 signs (p

Weapon detection is a very serious and intense issue as far as the security and safety of the public in general, no doubt it’s a hard and difficult task furthermore, its troublesome when you need to do it automatically or with some of the AI model. Different object detection models are available but in case of weapons detection it is difficult to detect the weapons of distinctive size and shapes along with the different colors of the background. Currently, a great deal of Convolutional Neural Network (CNN) based deep learning approaches are proposed for the recognition and classification in real-time. In this paper, we have done the comparative analysis of the two versions which is a state of the art model called YOLOV3 and YOLOV4 for weapons detection. For training purpose, we create weapons dataset and the images are collected from google images along with a portion of different assets. We annotate the images one by one manually in different formats in light of fact that YOLO needs annotation file in text format and some other models need annotation file in XML format. We trained both the versions on a large data set of weapons and afterward tested their results for comparative analysis. We explained in the paper that YOLOV4 performs obviously superior to the YOLOV3 in terms of processing time and sensitivity yet we can compare these two in precision metric. The implementation details and trained models are made public at this link:https://cutt.ly/5kBEPhM.

An Introduction to the Digital Analysis of Stationary Signals: A Computer Illustrated Text directly illustrates the various techniques required to make accurate measurements of the properties of fluctuating signals. Emphasis is on qualitative ideas rather than detailed mathematical analysis for which the computer illustrated text format is ideally suited. The author reinforces normal figures and diagrams with computer-generated graphical displays produced dynamically by the student. This package of text and accompanying software is not specific to any particular microcomputer.

Digital health systems contain large amounts of patient records, doctor notes, and prescriptions in text format. This information summarized over the electronic clinical information will lead to an improved quality of healthcare, the possibility of fewer medical errors, and low costs. Besides, seafarers are more vulnerable to have accidents, and prone to health hazards because of work culture, climatic changes, and personal habits. Therefore, text mining implementation in seafarers’ medical documents can generate better knowledge of medical issues that often happened onboard. Medical records are collected from digital health systems of Centro Internazionale Radio Medico (C.I.R.M.) which is an Italian Telemedical Maritime Assistance System (TMAS). Three years (2018–2020) patient data have been used for analysis. Adoption of both lexicon and Naive Bayes’ algorithms was done to perform sentimental analysis and experiments were conducted over R statistical tool. Visualization of symptomatic information was done through word clouds and 96% of the correlation between medical problems and diagnosis outcome has been achieved. We validate the sentiment analysis with more than 80% accuracy and precision.

Data can be represented in various languages, such as Hindi, Marathi and English in social media and also in various knowledge resources. The data is open to users in a different format. Information comprehension is very difficult for uneducated individuals. Often it is difficult for people to read or comprehend meaningful data available on social media. Thus, researchers used NLP to develop different machine translation techniques, such as rule-based, statistical-based and some hybrid machine translation. Natural language is incredibly rich in form and composition and highly vague. Natural language comprehension is much harder compared to natural language development. We present the MVET (Marathi video to English Text translation) technique in this research manuscript which helps to translate Marathi Video content into English text format. That will be very useful for people who really aren’t Marathi. Sometimes so many people have lost valuable information because of the regional language crisis. We have developed the MVET machine translation technique to solve this problem, which will achieve more precision compared to existing methods such as statistical, rule-based and hybrid.

SummaryCytogenetics data, or karyotypes, are among the most common clinically used forms of genetic data. Karyotypes are stored as standardized text strings using the International System for Human Cytogenomic Nomenclature (ISCN). Historically, these data have not been used in large-scale computational analyses due to limitations in the ISCN text format and structure. Recently developed computational tools such as CytoGPS have enabled large-scale computational analyses of karyotypes. To further enable such analyses, we have now developed RCytoGPS, an R package that takes JSON files generated from CytoGPS.org and converts them into objects in R. This conversion facilitates the analysis and visualizations of karyotype data. In effect this tool streamlines the process of performing large-scale karyotype analyses, thus advancing the field of computational cytogenetic pathology.Availability and ImplementationFreely available at https://CRAN.R-project.org/package=RCytoGPSSupplementary informationSupplementary data are available at Bioinformatics online.

The sentiment analysis of the Bengali language is converting into a trendy research topic nowadays. Sentiment analysis is a useful technique in opinion mining, emotion extraction, and trend predictions. By sentiment analysis, the actual sentiment of a text review can be extracted. Every day, every second's people use the internet for different purposes and leave their opinions or perspective views in various places on the internet as a text format. The opinion or review on the internet can contain the author's positive, negative, and neutral views of the statement. This study proposed a machine learning-based model to predict a user's sentiment (positive, neutral, and negative) of a Bangla text review. We have applied five machine learning algorithms in our dataset, which we manually gathered from a Bangladeshi e-commerce site called “Daraz.” We have experimented with Random Forest classifier, Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and XGBoost algorithms with our dataset. KNN performs great among all these five algorithms in all the performance measures of accuracy, precision, recall, and f1-score. KNN shows 96.25% accuracy, 0.96 in each of precision, recall, and f1-score.

Automated monitoring of websites that trade wildlife is increasingly necessary to inform conservation and biosecurity efforts. However, e-commerce and wildlife trading websites can contain a vast number of advertisements, an unknown proportion of which may be irrelevant to researchers and practitioners. Given that many wildlife-trade advertisements have an unstructured text format, automated identification of relevant listings has not traditionally been possible, nor attempted. Other scientific disciplines have solved similar problems using machine learning and natural language processing models, such as text classifiers. Here, we test the ability of a suite of text classifiers to extract relevant advertisements from wildlife trade occurring on the Internet. We collected data from an Australian classifieds website where people can post advertisements of their pet birds (n = 16.5k advertisements). We found that text classifiers can predict, with a high degree of accuracy, which listings are relevant (ROC AUC ≥ 0.98, F1 score ≥ 0.77). Furthermore, in an attempt to answer the question ‘how much data is required to have an adequately performing model?’, we conducted a sensitivity analysis by simulating decreases in sample sizes to measure the subsequent change in model performance. From our sensitivity analysis, we found that text classifiers required a minimum sample size of 33% (c. 5.5k listings) to accurately identify relevant listings (for our dataset), providing a reference point for future applications of this sort. Our results suggest that text classification is a viable tool that can be applied to the online trade of wildlife to reduce time dedicated to data cleaning. However, the success of text classifiers will vary depending on the advertisements and websites, and will therefore be context dependent. Further work to integrate other machine learning tools, such as image classification, may provide better predictive abilities in the context of streamlining data processing for wildlife trade related online data.

The procedure of translating images of handwritten, typewritten, or typed text into a format recognized by computers is called Optical Character Recognition (OCR). Editing, indexing, searching, and storage space reduction are the uses of Optical Character Recognition. This is done by scanning the picture of the text character-by-character first, then processing the scanned image and eventually converting the image of the character into character codes, such as ASCII. To translate text in an image into text format, the Optical Character Recognition system is used. There are three key aspects of OCR approach: pre-processing, character recognition, character segmentation and presentation of data. Convolutional Neural Network is a deep learning method which is used for character recognition. In this paper, CNN layers, architecture and implementation of CNN architecture are discussed. Here the CNN (VGG-16) model is trained over Telugu character data set which covers maximum of 1600 characters and its accuracy is measured.

Extracting valuable and relevant information from a potential employee’s CV to ease the hiring process for employers, automating data extraction, parsing documents of multiple formats, and storing data in a standardized relational database model. The user uploads a single resume or multiple resumes into the program, the program accepts multiple formats (.pdf, .doc, .rtf, etc.) and converts it into a standard text format which is later parsed for the required information, and the extracted data is organized in a standard defined format. The user can then download the extracted information in the .CSV format.

Fake news, hate speech, crude language, ethnic and racial slurs and more have been spreading widely every day, yet in Sri Lanka, there is no definite solution to save our society from such profanities. The method we propose detects racist, sexist and cursing objectionable content of Sinhala, Tamil and English languages. To selectively filter out the potentially objectionable audio content, the input audio is first preprocessed, converted into text format, and then such objectionable content is detected with a machine learning filtering mechanism. In order to validate its offensive nature, a preliminary filtering model was created which takes the converted sentences as input and classifies them through a binary classification. When the text is classified as offensive, then secondary filtering is carried out with a separate multi-class text classification model which classifies each word in the sentence into sexist, racist, cursing, and non-offensive categories. The models in preliminary filtering involve the Term Frequency–Inverse Document Frequency (TF-IDF) vectorizer and Support Vector Machine algorithm with varying hyperparameters. As for the multi-class classification model for Sinhala language, the combination of Logistic Regression (LR) and Countvectorizer was used while the Multinomial Naive Bayes and TF-IDF vectorizer model was found suitable for Tamil. For English, LR with Countvectorizer model was chosen to proceed. The system has an 89% and 77% accuracy of detection for Sinhala and Tamil respectively. Finally, the detected objectionable content is replaced in the audio with a predetermined audio input.

Optical character recognition (OCR) is an image analysis technique in the document where digital images (scanned) that contain handwritten script or machine printed script is used as input into a system to convert it to editable machine readable text format. In the current era, OCRs development for regional script is an active field of cutting edge as research, such as Odia, Telugu and Bengali. Particularly, in Odia language, it is a great challenge to an OCR inventor due to various categories of character in the alphabet. Further it is also required to combine the different letter in Odia, and many characters are roundish similar in loop. In this paper, WEKA software has been used to build classification model for offline character recognition. Hence, this research work has been attempted toward development of a novel algorithm for classification of offline handwritten Odia character recognition using Naive Bayes and decision table in WEKA environment.

This chapter proposes a new and innovative method of smart optical character recognition (OCR) for translation (SOT) from an English image to Bangla and Hindi language. For translation, this OCR system can take any picture from any documents which contain printed English sentences. SOT can translate the image into text within two languages. The translated text from SOT can also be copied and kept for further use. SOT can convert the full image in a text format and then can translate some of the portions of an image by cropping. Google translator has been used here for the OCR. This API can translate the image into a printed text or a machine-encoded text. But the translated text cannot be kept for further use which is an immense disparity between SOT and Google translator. Moreover, many APIs also deploy, which can translate the image into a text format but cannot ferry the limit of copying text which is collected after translating text from the image. SOT can be beneficiary among all the OCR as it struck the limit of copying text.

For realizing automatic data collecting of the touch probing system on the CNC machine tool and practicing the application technology of big data from the CNC machining process, a special NC program was developed on the Siemens 840D SL controller to record data with a defined text format, and they were uploaded onto the host computer automatically. With the help of DB management software in the host PC, data obtained were sent into the MES database regularly, and then automatic data collecting of manufacturing process information was realized. With the big data technology, three applications based on big data technology have been listed. They are duo active error detection on the probing system, geometrical accuracy monitoring, and management of the cutting parameter and tool life. Tests of cutting on the platen of an injection molding machine with a PAMA SR3000 floor-type CNC boring-milling machine proved that the new technology achieves its design objectives.

Nowadays modern Internet technologies play an important role in our life. The present article deals with the peculiarities of hashtags as new text format used in social network. The article presents characteristic features of hashtag text, classification of hashtag functions, types of hashtags according to their construction and the position of hashtags in the post. Different types of hashtags were subjected to the analysis. Continuous sampling method, descriptive qualitative and quantitative analysis allowed the authors to come to the conclusion about hashtags as linguistic tools. As a result, five hashtag functions and six hashtag types were identified. These findings would help to understand modern online discourse and to prove the idea that hashtags are considered as meaningful elements of social network communication.

Speech acts as a barrier to communication between two individuals and helps them in expressing their feelings, thoughts, emotions, and ideologies among each other. The process of establishing a communicational interaction between the machine and mankind is known as Natural Language processing. Speech recognition aids in translating the spoken language into text. We have come up with a Speech Recognition model that converts the speech data given by the user as an input into the text format in his desired language. This model is developed by adding Multilingual features to the existent Google Speech Recognition model based on some of the natural language processing principles. The goal of this research is to build a speech recognition model that even facilitates an illiterate person to easily communicate with the computer system in his regional language.

The textual data of insulation status contains the original records of the on-site partial discharge detection. In order to improve the data utilization rate and mine the relevant information that affects the insulation status of the equipment, it needs to be processed and stored uniformly. Knowledge graph technology is used to process the insulation status text data, and the insulation status text format is identified, and then the data storage based on the graph database is completed. By comparison with relational databases, it is found that graph databases have more efficient query performance for complex relationships. Graph database is more suitable for storing textual data of insulation status with complex relationships.

Power companies have accumulated a large amount of maintenance data of power equipment in text format. To extract valuable information, text mining is expected. Text similarity is an important method for text mining; however, the feature dimensions increase for long texts. In this paper, the SimHash algorithm is used to map the original text into a 64-bit binary fingerprint, and the similarity between texts is then determined with Hamming distance. With this method, the recommendation model of maintenance measures is established. The verification results show that the recommendation model has good predictions based on the SimHash and Hamming distance algorithm, and is potential to apply in the practical field.

Companies generate their reports in the form of PDF files. For further data analysis, the statistics or quantitative data in these reports have to be converted to CSV (.csv) or Excel (.xlsx) files. This is done manually by companies. This consumes a lot of time and manual work which can be reduced for better utilization of resources. Forecomp is a web application to automatically convert the tables in the PDF to CSV files. The tables could be present in text format or as an image. The web application is built keeping flexibility in mind such that the user can select the process used to convert the PDF into CSV files based on the tables in their PDF. Different technologies used in this application include YOLO model for machine learning, Tesseract OCR, Tabula, and an inbuilt snipping tool. This paper introduces the concepts behind Forecomp focussing on the methodology employed and the various results obtained.

A database containing the titles of the records of all seismic events recorded by the network of stations of the Geophysical Institute “Vladikavkaz” and “Karmadon Parametric Test Site” was created. The application of the event sampling procedure makes it possible to select records registered simultaneously by several stations for their subsequent analysis and processing. To process the received data of the Karmadon parametric test site network, a special program for editing events in the SEV format was developed. It allows calling utility programs for their subsequent processing. Utilities for viewing and editing adb file headers, adb file converter to text format. Such data structuring allows not only finding the necessary records from the data bank, but also performing more complex operations using SQL queries. The created replenished database of seismic records and events when it is filled with a large amount of data can become an object that belongs to the category of big data.

Analyzing correlations between research groups has been increasingly appealing in recent years. The identification of proximity between different research projects can not only contribute to triggering new partnerships, but also optimize resources and share results. In Brazil, the Lattes Curriculum System of the Brazilian National Council for Scientific and Technological Development is a rich source of information about the academic and professional life of professors, researchers, and students. Lattes curricula present information, much of it up-to-date, in a semi-structured text format. This paper intends to identify correlations between Brazilian research groups in Information Science through the analysis of keywords contained in the informative summaries and in the descriptions of the research projects found in the Lattes curricula of the participants of these groups. The analysis presented below was made with the application of text mining techniques to the Lattes curricula of researchers linked to 27 graduate programs in Information Science from 24 Brazilian institutions of higher education, totaling 399 curricula analyzed. Among the results obtained, it was possible to identify some existing research trends between the groups and link them to the areas of Information Science, Archivology, Library Science, and Museology. It was also possible to identify the most used research terms at the moment. In addition, the analysis of the occurrence of the terms allowed to identify the areas that concentrate most of the research in Information Science in Brazil, as well as to realize that there is a propensity of researchers to use certain terms to describe their research and their informative summaries.

Sign System for Bahasa Indonesia (SIBI) is the official sign language authorised by The Ministry of Education and Culture of Indonesia and being used as one of the communication media by School for Children with Special Needs (SLB) for people with hearing impairments in the process of learning. For people who have a lack of knowledge about SIBI gestures certainly will have difficulty to communicate with people with hearing impairments. Thus, a translation system from SIBI gestures to sentences in Bahasa Indonesia or vice versa is needed. This research is the initial stage of a translation system from sentences in Bahasa Indonesia to SIBI Gestures. The focus of this research is to generate sign gestures in the form of 3D Animation from a sentence input in text format and deployed on the smartphone device. The generation process starts from deconstructing the input sentence into its word components using a look-up table that consists of affixes, root words, and a “slang” dictionary. Then, this word components are referred to their corresponding gesture animations. The gesture data are recorded with motion-capture sensor “Perception Neuron v2” and use the official SIBI Dictionary as the reference. The animation is rendered in Unity engine and to create a smooth transition between one gesture animation to another, a LERP (Linear Interpolation) based method is implemented using Animancer API. Based on evaluation results, produced gestures correctly represent smooth SIBI gestures with the most significant accuracy score of 97.56% with a user satisfaction score of Very Satisfied is 84%, Satisfied is 14%, and Fair is 2%.

Purpose: Viet Nam currently relies on a manual paper-based system to track and monitor 28 major infectious diseases. This inefficient system takes 2 or more months to complete. Method: We designed and pilot tested the use of text messaging to report certain infectious disease symptoms in rural areas of northern Viet Nam. The project was divided into three 6-month phases carried out in two provinces. The current analysis focuses on the implementation of a two-way feedback system between Phases II and III, which aims at (1) evaluating whether this system improves efficiency by determining the number of correctly (vs. incorrectly) formatted text messages; (2) assessing this system's influence on accuracy by comparing text messages with their respective official paper-based documented forms; and (3) determining whether the amount of information required to report through text messages influences the efficiency and accuracy of the text messages. Results: Between Phases II and III, results revealed a significant improvement in correctly formatted texts in comparison to incorrectly formatted texts. As the number of fields required to report increased, the number of correctly formatted texts (efficiency) as well as the number of matched text messages (accuracy) decreased. Conclusion: Our research demonstrates that an automated error bidirectional feedback system can significantly improve both the efficiency and accuracy of a Short Message Service-based method for disease surveillance. Also, our data may suggest that two-way communication has better engaged health care staff to follow reporting protocols as well as to maintain accuracy from their clinic's own data.

The paper is all about the system and interface developed, that allows deaf mutes to make use of various voice automated virtual assistants with help of Sign Language. Majority of Virtual Assistants work on basis of audio inputs and produces audio outputs which in turn makes it impossible to be used by people with hearing and speaking disabilities. The project makes various voice controlled virtual assistants respond to hand gestures and also produces results in form of text outputs. It makes use of concepts like Deep Learning, Convolutional Neural Network, Tensor Flow, Python Audio Modules. A webcam first captures the hand gestures, then Convolutional Neural Network interprets the images produced and produces rational languages. These languages are then mapped to pre-defined datasets using Deep learning. For this purpose, Neural Networks are linked with Tensor flow library. The designed system will then produce audio input for the Digital Assistant, using one of the Python text to speech module. The final audio output of the Digital Assistant will be converted into text format using one of the Python speech to text module which will be displayed on the viewing screen.

The technology of natural language processing in the task of constructing a psychological portrait is considered. An algorithm for machine learning based on a recurrent neural network is proposed, which allows you to automatically determine the psychological portrait from a person’s speech, translated into text format.

An essential prerequisite of an effective recommender system is providing helpful information regarding users and items to generate high-quality recommendations. Written customer review is a rich source of information that can offer insights into the recommender system. However, dealing with the customer feedback in text format, as unstructured data, is challenging. In this research, we extract those features from customer reviews and use them for similarity evaluation of the users and ultimately in recommendation generation. To do so, we developed a glossary of features for each product category and evaluated them for removing irrelevant terms using Latent Dirichlet Allocation. Then, we employed a deep neural network to extract deep features from the reviews-characteristics matrix to deal with sparsity, ambiguity, and redundancy. We applied matrix factorization as the collaborative filtering method to provide recommendations. As the experimental results on the Amazon.com dataset demonstrate, our methodology improves the performance of the recommender system by incorporating information from reviews and produces recommendations with higher quality in terms of rating prediction accuracy compared to the baseline methods.

The development in Information Technology (IT) has encouraged the use of Igbo Language in text creation, online news reporting, online searching and articles publications. As the information stored in text format of this language is increasing, there is need for an intelligent text-based system for proper management of the data. The selection of optimal set of features for processing plays vital roles in text-based system. This paper analyzed the structure of Igbo text and designed an efficient feature selection model for an intelligent Igbo text-based system. It adopted Mean TF-IDF measure to select most relevant features on Igbo text documents represented with two word-based n-gram text representation (unigram and bigram) models. The model is designed with Object-Oriented Methodology and implemented with Python programming language with tools from Natural Language Toolkits (NLTK). The result shows that bigram represented text gives more relevant features based on the language semantics.

Recent inspection findings from audit regulators around the world suggest that auditors fail to use sufficient professional skepticism when auditing complex estimates. In an experiment using audit managers and partners as participants, we examine factors that influence auditors’ deficiencies in this area. We find that the presentation format of management-provided evidence significantly affects auditors’ skepticism. In particular, auditors are less skeptical of aggressive assumptions underlying complex estimates when reviewing evidence presented in a text format rather than a graph format. However, we find that priming auditors to consider how management derived its assumptions effectively enhances auditors’ skepticism by encouraging them to consider the often ignored information that is inconsistent with management’s assumptions. Further, auditors are most skeptical when this simple intervention is combined with evidence that is presented graphically. These results should be important to practitioners, regulators, and researchers, as they provide insight into how two factors affect a significant deficiency noted in the audits of complex estimates.

TI Workbench is a software package that serves as a control and analysis center for cellular imaging and electrophysiological experiments. It is unique among general-purpose software packages where it integrates the control of cellular imaging and electrophysiological devices, as well as sophisticated data analyses, which provides superior usability in imaging experiments combined with electrophysiology. During the development over the last 20 years, the range of supported image acquisition devices has expanded from cooled charge-coupled device (CCD) cameras to multi-photon microscope systems. In this review, I outline the concept of TI Workbench together with its unique functions and features derived from ideas emerging during daily experiments in my own lab and in those of my collaborators over the last 20 years. TI Workbench includes standard functions required for time-lapse multicolor fluorescence imaging and electrophysiological experiments, in addition to specialized functions such as random-scan or conventional raster-scan two-photon microscopy packages and fluorescence life time imaging (FLIM) utilities. Data analysis modules, e.g. digital data filters for temporal waveforms of time-lapse image data and electrophysiology and for 2-D image data, and fluorescence correlation spectroscopy (FCS) analysis functions, are well integrated with data acquisition functions. A notebook function holds formatted text, graphs, image and movie data altogether, which are linked to the actual data files. TI Workbench uses Igor Pro software as a back-end output for publishing. In addition, TI Workbench imports several different formats of image and electrophysiology data, serving as a general-purpose data analysis software package.

The actor-partner interdependence model (APIM) is widely used for analyzing dyadic data. Although dyadic research has become immensely popular, its statistical complexity might be a barrier. To remedy this, a free user-friendly web application, called APIM_SEM, has been developed. This app automatically performs the statistical analyses (i.e., structural equation modeling) of both simple and more complex APIMs. It allows the researcher to analyze distinguishable or indistinguishable dyads, to examine dyadic patterns, to estimate actor and partner effects of one or two predictors, and to control for covariates. Results are provided in software and text format, complemented by summary tables and figures. As an illustration, the effect of romantic appraisal on relational satisfaction is assessed by fitting APIMs with varying complexity.

Summary Oligator is software designed to assist scientists in their exploration of MS/MS experiments, especially for oligosaccharides bearing unreferenced chemical substitutions. Through a graphical interface, users have the total flexibility to build a candidate glycan structure and produce the corresponding theoretical MS/MS spectrum in accordance with the usual ion nomenclature. The structural information is saved using standard notations, in text format, which facilitates the capitalization and exchange of data as well as any other processing of the information. Availability and implementation Source code and user manual are freely available at https://github.com/vlollier/oligator. Supplementary information Supplementary data are available at Bioinformatics online.

Until now, lot of companies that already have data that is so large and the development of data is so quickly and with the plurality of data formats. Not only in units hundreds of Mega or Giga again but have reached the realm of Tera data countless. Besides the diversity of the data format itself, today not just formatted text but can be video or image as well as the format of other data. With the trend of data continues to grow, sometimes aspect of data security was often overlooked and even ignored.

Nowadays online reviews play a significant role in influencing the decision of consumers. Consumers show their experience and information about product quality in their reviews. Product Reviews from Amazon to Restaurant Reviews from Yelp are facing problems with fake reviews and fake numeric ratings. Online reviews typically consist of qualitative (text format) and quantitative (rating) formats. In the case of Google Play store fake numeric ratings can play a big role in the success of apps. People tend to believe that a high-star rating may be significantly attached with a good review. However, user star level rating information does not usually match with text format of review. Despite many efforts to resolve this issue, Apple App Store and Google Play Store are still facing this problem. This study proposes a novel Google App numeric reviews & ratings contradiction prediction framework using Deep Learning approaches. The framework consists of two phases. In the first phase, the polarity of reviews are predicted using sentiment analysis tool to build ground truth. In the second phase, star ratings are predicted from text format of reviews after training deep learning models on ground truth obtained in the first phase. Experimental results demonstrate that based on actual user reviews the proposed framework significantly predicts unbiased star rating of app.