Character Encoding Research Articles

Behavioral Nudging With Generative AI for Content Development in SMS Health Care Interventions: Case Study.

Brief message interventions have demonstrated immense promise in health care, yet the development of these messages has suffered from a dearth of transparency and a scarcity of publicly accessible data sets. Moreover, the researcher-driven content creation process has raised resource allocation issues, necessitating a more efficient and transparent approach to content development. This research sets out to address the challenges of content development for SMS interventions by showcasing the use of generative artificial intelligence (AI) as a tool for content creation, transparently explaining the prompt design and content generation process, and providing the largest publicly available data set of brief messages and source code for future replication of our process. Leveraging the pretrained large language model GPT-3.5 (OpenAI), we generate a collection of messages in the context of medication adherence for individuals with type 2 diabetes using evidence-derived behavior change techniques identified in a prior systematic review. We create an attributed prompt designed to adhere to content (readability and tone) and SMS (character count and encoder type) standards while encouraging message variability to reflect differences in behavior change techniques. We deliver the most extensive repository of brief messages for a singular health care intervention and the first library of messages crafted with generative AI. In total, our method yields a data set comprising 1150 messages, with 89.91% (n=1034) meeting character length requirements and 80.7% (n=928) meeting readability requirements. Furthermore, our analysis reveals that all messages exhibit diversity comparable to an existing publicly available data set created under the same theoretical framework for a similar setting. This research provides a novel approach to content creation for health care interventions using state-of-the-art generative AI tools. Future research is needed to assess the generated content for ethical, safety, and research standards, as well as to determine whether the intervention is successful in improving the target behaviors.

A Chinese Nested Named Entity Recognition Model for Chicken Disease Based on Multiple Fine-Grained Feature Fusion and Efficient Global Pointer

Extracting entities from large volumes of chicken epidemic texts is crucial for knowledge sharing, integration, and application. However, named entity recognition (NER) encounters significant challenges in this domain, particularly due to the prevalence of nested entities and domain-specific named entities, coupled with a scarcity of labeled data. To address these challenges, we compiled a corpus from 50 books on chicken diseases, covering 28 different disease types. Utilizing this corpus, we constructed the CDNER dataset and developed a nested NER model, MFGFF-BiLSTM-EGP. This model integrates the multiple fine-grained feature fusion (MFGFF) module with a BiLSTM neural network and employs an efficient global pointer (EGP) to predict the entity location encoding. In the MFGFF module, we designed three encoders: the character encoder, word encoder, and sentence encoder. This design effectively captured fine-grained features and improved the recognition accuracy of nested entities. Experimental results showed that the model performed robustly, with F1 scores of 91.98%, 73.32%, and 82.54% on the CDNER, CMeEE V2, and CLUENER datasets, respectively, outperforming other commonly used NER models. Specifically, on the CDNER dataset, the model achieved an F1 score of 79.68% for nested entity recognition. This research not only advances the development of a knowledge graph and intelligent question-answering system for chicken diseases, but also provides a viable solution for extracting disease information that can be applied to other livestock species.

A Modified Hybrid Brain-Computer Interface Speller Based on Steady-State Visual Evoked Potentials and Electromyogram.

To enhance the information transfer rate (ITR) of a steady-state visual evoked potential (SSVEP)-based speller, more characters with flickering symbols should be used. Increasing the number of symbols might reduce the classification accuracy. A hybrid brain-computer interface (BCI) improves the overall performance of a BCI system by taking advantage of two or more control signals. In a simultaneous hybrid BCI, various modalities work with each other simultaneously, which enhances the ITR. In our proposed speller, simultaneous combination of electromyogram (EMG) and SSVEP was applied to increase the ITR. To achieve 36 characters, only nine stimulus symbols were used. Each symbol allowed the selection of four characters based on four states of muscle activity. The SSVEP detected which symbol the subject was focusing on and the EMG determined the target character out of the four characters dedicated to that symbol. The frequency rate for character encoding was applied in the EMG modality and latency was considered in the SSVEP modality. Online experiments were carried out on 10 healthy subjects. The average ITR of this hybrid system was 96.1 bit/min with an accuracy of 91.2%. The speller speed was 20.9 char/min. Different subjects had various latency values. We used an average latency of 0.2 s across all subjects. Evaluation of each modality showed that the SSVEP classification accuracy varied for different subjects, ranging from 80% to 100%, while the EMG classification accuracy was approximately 100% for all subjects. Our proposed hybrid BCI speller showed improved system speed compared with state-of-the-art systems based on SSVEP or SSVEP-EMG, and can provide a user-friendly, practical system for speller applications.

A Cybersecurity Threat Recognition Framework Combining GAN Networks and Semi-Supervised Learning

Abstract This paper delineates the types of threat identification in network security, designs the threat identification model architecture, analyzes the malicious code, and proposes a counter-defense strategy. The talk compares the GAN network model and semi-supervised learning technology, combines them in network security, and proposes a semi-supervised detection model utilizing GAN. Analyze the characteristics of URL network activity and design URL character encoding. Set experimental parameters and selected datasets to analyze the similarity between synthetic URLs based on GAN generators and real URLs and test the effectiveness of a GAN-based semi-supervised detection model for malicious URL recognition using different classifiers. Calculate the detection model’s classification accuracy on a mixed dataset and test its training fit. There is only a 6% difference in how well different classifiers can spot malicious URLs. This shows that the adversarial samples made by the GAN-based generator are similar to real URLs. The GAN-based semi-supervised detection model is capable of recognizing more web threats.

Notes onthe data quality ofbibliographic records from the MEDLINE database.

The US National Library of Medicine has created and maintained the PubMed® database, a collection of over 33.8 million records that contain citations and abstracts from the biomedical and life sciences literature. This database is an important resource for researchers and information service providers alike. As part of our work related to the creation of an author graph for coronaviruses, we encountered several data quality issues with records from a curated subset of the PubMed database called MEDLINE. We provide a data quality assessment for records selected from the MEDLINE database and report on several issues ranging from parsing issues (e.g. character encodings and schema definition weaknesses) to low scores for identifiers against several data quality metrics (e.g. completeness, validity and uniqueness). Database URL https://pubmed.ncbi.nlm.nih.gov.

(R)Unicode: Encoding and Sustainability Issues in Runology

In this article, the basic premises of reading a runic inscription and transferring the data into digital formats are discussed. Particular attention will be on the Runic block in the Unicode standard for digital character encoding, which currently does not suit the needs of the academic runological community. The proposed solution builds upon the existing standard without adding unnecessary additional characters, but with the ability to encode form-variants on top of the base character while retaining backwards compatibility, an approach from which other archaic scripts like Cuneiform or Khitan that suffer of similar encoding issues, could also benefit.

Modified Hierarchical-Attention Network model for legal judgment predictions

The impact of Artificial Intelligence in Legal Research has reached a high level in simulating human thought processes. Case Pendency is a long-lasting problem in many countries. The judicial system has to be more competent and reliable to provide justice on time for any developing country. Litigants and attorneys devote more time and effort to trial case preparation in the courtroom. The task of decision prediction is to automatically forecast the type of charge, law article, and term of punishment. Most of the earlier works for verdict prediction focused to work on civil law jurisdictions. Some of the challenges in the task are case facts are highly unstructured lengthy documents with a lack of annotations and mainly used machine learning techniques. While most research works ignore the information loss at the encoding stage, our proposed MHAN overcomes the above issue and long-range dependency problem using the attention model over hierarchical encoders with three tiers namely Sentence encoder, word encoder, and character encoder. To avoid information loss, a brand-new judgment prediction framework called MHAN is developed in this study effort. It is built on a modified Hierarchical-Attention network and a specially designed domain-specific word embedding model. Additionally, it emphasizes the feature extraction phase by joining features obtained using MHAN with an improved cosine similarity feature. Finally, a hybrid Self Improved RNN is employed to provide the projected results. Furthermore, the proposed model is trained on 10 types of real-time criminal cases from the Madras High Court of India and Supreme Court of India. It has outperformed prior methods in terms of verdict prediction. By applying different variations of the deep learning model and ablation tests, the proposed model achieves consistent results over baseline models.

Improving ANiTW Performance Using Bigrams Character Encoding and Identity-Based Signature

Several threats, such as misinformation and hoax, exist in social media as a frequently used technology to exchange information. These threats can be prevented if the reader can verify the message’s content integrity and source authenticity. One recent solution to overcome these threats was proposed by Ahvanooey et al. called ANiTW. ANiTW uses an invisible text watermarking scheme to verify social media message integrity and identify the message source. However, ANiTW is still vulnerable to undetected malicious text modification. Moreover, ANiTW has no tools to authenticate the extracted message source. The proposed method aims to overcome those vulnerabilities and improve ANiTW performance as a tool to verify message content integrity and message source authenticity in social media. To overcome vulnerabilities in ANITW, a part of the message hash and IBS-based signature is introduced as the watermark. The message integrity is verifiable by using part of the message hash as a watermark to detect any malicious. Moreover, implementing an IBS-based signature enables any reader to verify the message source’s authenticity easily. In addition, to improve ANITW performance in embedding capacity and invisibility, a novel bigram-based character encoding and embedding rule are also introduced. Based on the experiment and analysis result, it is proven that the proposed method can perform better than ANiTW in the security, embedding capacity, and invisibility aspects.

Естественное обобщение тьюринговой модели вычислимости

The Turing computability model is a model of algorithmic symbolic transformations that can be performed by humans. The Church-Turing thesis is a statement about the completeness of their formalisms with respect to this model. Algorithmic transformations are applicable not only to symbols, but also to physical objects. Some of these transformations can be analyzed by means of Turing formalism by way of special character encoding. At the same time, there are physical algorithms that go far beyond the standard Turing model. Examples are recipes, medical procedures, technological processes, etc. Their common feature is not only the operation of physical objects, but also the appeal to external physical processes. The general definition of an algorithm, as prescriptions for a sequence of actions to obtain the desired result, is satisfied by well-known phenomena of goal-directed behavior. Symbolic calculations are a special case of goal-directed behavior. Models of combined temporal and dynamic logic can be used to analyze goal-directed behavior. Such an analysis allows us to conclude that there are at least three types of elementary rules underlying complex purposeful behavior: 1) passively-processual – "If there is a process P , then do nothing, but wait for it to lead you to the desired goal G "; 2) constructive – "If there is a C , perform action d , the immediate result of which is the desired goal G "; 3) constructively-processual – "If C takes place, perform action d so that its immediate result R initiates process P , which will lead to the desired goal G ". The combined logic allows you to determine the conditions for the correctness of these rules. Constructively-processual rules have the property of universality, since two other types of rules are reduced to them. In the paper we define a T-machine (teleological machine) that implements complex goal-directed behavior, and conduct a comparative analysis with Turing machines. It is shown that within the framework of the new algorithmic model there are functions that are computable in it, but not computable in Turing model. In the new model, algorithms have the status of laws of living nature related to the emergence of life and evolution. The algorithmic model of goal-directed behavior can be naturally applied to describe and analyze many phenomena of the social sphere.

Multi-scaled self-attention for drug–target interaction prediction based on multi-granularity representation

BackgroundDrug–target interaction (DTI) prediction plays a crucial role in drug discovery. Although the advanced deep learning has shown promising results in predicting DTIs, it still needs improvements in two aspects: (1) encoding method, in which the existing encoding method, character encoding, overlooks chemical textual information of atoms with multiple characters and chemical functional groups; as well as (2) the architecture of deep model, which should focus on multiple chemical patterns in drug and target representations.ResultsIn this paper, we propose a multi-granularity multi-scaled self-attention (SAN) model by alleviating the above problems. Specifically, in process of encoding, we investigate a segmentation method for drug and protein sequences and then label the segmented groups as the multi-granularity representations. Moreover, in order to enhance the various local patterns in these multi-granularity representations, a multi-scaled SAN is built and exploited to generate deep representations of drugs and targets. Finally, our proposed model predicts DTIs based on the fusion of these deep representations. Our proposed model is evaluated on two benchmark datasets, KIBA and Davis. The experimental results reveal that our proposed model yields better prediction accuracy than strong baseline models.ConclusionOur proposed multi-granularity encoding method and multi-scaled SAN model improve DTI prediction by encoding the chemical textual information of drugs and targets and extracting their various local patterns, respectively.

Invisible Unicode Programming

Invisible Unicode programming (IUP) can be defined as the art and science of hiding information in data that can be read by the computer. Invisible Unicode Programming (IUP) has the explicit goal of converting traditional character encodings to invisible encoding. This paper presents a new method to hide text. This systematic method uses the binary format of invisible character to hide and extract secret information. Creating a secret message involves four main steps, first using the binary format of the original letters in the message.nextcreating the appropriate Binary Masking Value (BMV)to cover the text, and subtracting the Binary Value (BV) from the Binary Masking Value (BMV)text to get Binary Invisible Unicode (BIU), and finally masking secret text using Binary Invisible Character (BIU). This Invisible Unicode Programming (IUP) Concept uses the 54 Invisible Unicode characters to make the text invisible. The results of the experiments show that this IUP method creates highly secured invisible information using the multi-level complexity algorithm to avoid the hackers.

The History of the IT Environment of Sinology in Japan

This paper addresses the following: First, it summarizes the history of the IT environment of sinology in Japan with a focus on Chinese character processing. Then, it introduces the open-access digital archive projects in Japan as well as ICT-based research activities. An attempt was made to allow multiple Chinese characters/Chinese input from PCs in Japan beginning in the 1980s. At first, Chinese characters were implemented applying special hardware or software to JIS Chinese character encoding. After the 1990s, these approaches disappeared with the spread of Unicode and a multilingual mixed environment became more widely available. The digital archives in Japan are described focusing on databases, digital libraries, etc. Although Japan’s number of independent databases has decreased, the paper examines the current contributions to sinology studies, including a Chinese character DB that interlinks with Unicode.org and digital literature archives in Chinese characters that are held by universities and public institutions. Additionally, there are numerous research studies on humanities and oriental studies as research associations and societies have been in operation for several years.

ENCODING AND TRANSCODING OF TRANSCRIPTIONS OF THE HISTORICAL CORPUS “MANUSCRIPT”

The article considers capabilities of using Cyrillic blocks of the Unicode Standard for the purpose of creating transcriptions, which would represent graphics of medieval Slavonic manuscripts. In addition, much attention is given to the fact that the Unicode Standard provides variants of Cyrillic letters, which means that one can accurately enough record graphic features of manuscripts. However, some variants of certain letters are still missing, and that is why there exists a need to use additional agreements of character encoding, which code points are placed in special blocks and Private Use Areas and not in standard ranges of Unicode. The Manuscript - a historical corpus - is the example of a big machine-readable collection of medieval Slavonic manuscripts. It was created on the base of Oracle DBMS with the use of a specialized system of codes and fonts. Transference of the corpus to other technological platforms or usage of external software (including separate texts, parts of corpora, selections) for analysis of linguistic data would be possible only after downloaded files are recoded to the Unicode Standard. A comparative analysis of the character blocks used in the corpus and in the current version 14.0 of the Unicode Standard leads to the conclusion that recoding either results in losses of graphic features or requires usage of a supplementary set of varying characters with code points of Private Use Areas. Instances when there are two or more characters of the Unicode Standard that correspond to one recoded character of the Manuscript are analyzed. It is also stated that numerous ligatures and certain singular graphemes are missing in the standard blocks and in the blocks of Private Use Areas.

On Japanese’s quasi-characters and their representation on computer systems

Japanese’s quasi-characters iejirushi, literally ‘house sign’, are traditional marks or logos for companies in Japan. In most cases, they involve one or a few Japanese characters, combined with other, various, non-character symbols. For different reasons as explained in this article, quasi-characters have been ignored by character encodings such as unifying ones like Unicode or local standards like JIS X 0213, and thus pose an information representation issue for computer systems. In this paper, building on previous works, we first conduct a detailed ontological analysis of Japanese’s quasi-characters in order to identify their characteristics, especially their contents and structures. This is a major part of this work. Second, we derive from this ontological discussion possible representation methods for computer systems and conduct some experiments. The experimental results show significant improvements with respect to quality, practicability and flexibility over conventional approaches.

End-to-End Models to Imitate Traditional Chinese Medicine Syndrome Differentiation in Lung Cancer Diagnosis: Model Development and Validation.

BackgroundTraditional Chinese medicine (TCM) has been shown to be an efficient mode to manage advanced lung cancer, and accurate syndrome differentiation is crucial to treatment. Documented evidence of TCM treatment cases and the progress of artificial intelligence technology are enabling the development of intelligent TCM syndrome differentiation models. This is expected to expand the benefits of TCM to lung cancer patients.ObjectiveThe objective of this work was to establish end-to-end TCM diagnostic models to imitate lung cancer syndrome differentiation. The proposed models used unstructured medical records as inputs to capitalize on data collected for practical TCM treatment cases by lung cancer experts. The resulting models were expected to be more efficient than approaches that leverage structured TCM datasets.MethodsWe approached lung cancer TCM syndrome differentiation as a multilabel text classification problem. First, entity representation was conducted with Bidirectional Encoder Representations from Transformers and conditional random fields models. Then, five deep learning–based text classification models were applied to the construction of a medical record multilabel classifier, during which two data augmentation strategies were adopted to address overfitting issues. Finally, a fusion model approach was used to elevate the performance of the models.ResultsThe F1 score of the recurrent convolutional neural network (RCNN) model with augmentation was 0.8650, a 2.41% improvement over the unaugmented model. The Hamming loss for RCNN with augmentation was 0.0987, which is 1.8% lower than that of the same model without augmentation. Among the models, the text-hierarchical attention network (Text-HAN) model achieved the highest F1 scores of 0.8676 and 0.8751. The mean average precision for the word encoding–based RCNN was 10% higher than that of the character encoding–based representation. A fusion model of the text-convolutional neural network, text-recurrent neural network, and Text-HAN models achieved an F1 score of 0.8884, which showed the best performance among the models.ConclusionsMedical records could be used more productively by constructing end-to-end models to facilitate TCM diagnosis. With the aid of entity-level representation, data augmentation, and model fusion, deep learning–based multilabel classification approaches can better imitate TCM syndrome differentiation in complex cases such as advanced lung cancer.

Research on Improved Character Encoding Methods Based on QR Code*

With the popularity of mobile terminals, Quick response (QR) code, which acts as a convenient and quick way to transfer graphic information, has been widely used in various fields. QR code is a 2D matrix code which contains information in both vertical and horizontal directions. In order to promote the characters encoding efficiency, we propose the improved character encoding methods based on QR code. Specifically, we divide the types of encoding data into Chinese characters and non-Chinese characters, and thus optimizing their encoding methods separately: we apply the branch-bound algorithm to optimize the encoding pattern selection of QR code; as for Chinese characters, based on the Chinese characters use frequency generated by Url crawler system, we design a new encoding method for Chinese characters. Our approach has been shown to afford better experimental test results compared with traditional encoding methods of QR code.

WordCode using WordTrie

Computers work with text data by assigning a code for each character, called encoding. Character-encoding techniques emerged in the late 1960s, and a similar type of technique is still used to encode text data. Computers can only understand alphabets, not words. In this article, we develop an approach that enables computers to understand words. We introduce a word-based encoding of text data named WordCode. WordCode encodes the most frequent set of characters (i.e., words) found in Internet directories with a dynamic code combination. Although some dictionary-encoding techniques have been proposed, we still tend to use character encoding, such as Unicode, to encode text data. Dictionary-encoding techniques have not been adopted due to the massive size of the code page and the complexity in accessing the code page. In this article, we introduce a customised trie named WordTrie to store words for faster encoding and decoding. We generate the code combination in such a way that the size of the WordCode for a word is always smaller than the total size of the character coding. Our experimental results from encoding text files from the Gutenberg corpus, Canterbury corpus, large corpus, Calgary corpus and Silesia corpus using WordCode show an up to 19.9% reduction in file size with respect to character-based encoding. This smaller file size means that less storage space is needed and results in faster processing and communication of text data.

A Multilingual Unified Character Encoding Scheme Based on a Normative Character Set

The scheme is a unified character coding set of Sibe, Manchu, Mongolian and Todo languages, and the letters in the set are arranged in Latin alphabetical order. Compared with the system based on the nominal character encoding, this set does no need free variation selectors in Sibe and Manchu, and greatly reduce the use of the selectors in other languages. Thus, it is more in line with the general user's habits, and improve the information query, search, and transmission.

Resource Mention Extraction for MOOC Discussion Forums

In discussions hosted on discussion forums for massive online open courses (MOOCs), references to online learning resources are often of central importance. They contextualize the discussion, anchoring the discussion participants' presentation of the issues and their understanding. However, they are usually mentioned in free text, without appropriate hyperlinking to their associated resource. Automated learning resource mention hyperlinking and categorization will facilitate discussion and searching within the MOOC forums and also benefit the contextualization of such resources across disparate views. We propose the novel problem of learning resource mention identification in MOOC forums, i.e., to identify resource mentions in discussions and classify them into pre-defined resource types. As this is a novel task with no publicly available data, we first contribute a large-scale labeled dataset-dubbed the forum resource mention (FoRM) dataset-to facilitate our current research and future research on this task. The FoRM contains over 10 000 real-world forum threads in collaboration with Coursera, with more than 23 000 manually labeled resource mentions. We then formulate this task as a sequence tagging problem and investigate solution architectures to address the problem. Importantly, we identify two major challenges that hinder the applications of sequence tagging models to the task: (1) the diversity of resource mention expression and (2) long-range contextual dependencies. We address these challenges by incorporating character-level and thread context information into an LSTM-CRF model. First, we incorporate a character encoder to address the out-of-vocabulary problem caused by the diversity of mention expressions. Second, to address the context dependency challenge, we encode thread contexts using an RNN-based context encoder and apply the attention mechanism to selectively leverage useful context information during sequence tagging. The experiments on FoRM show that the proposed method improves the baseline deep sequence tagging models notably, significantly bettering performance on instances that exemplify two challenges.

Compression of Steganographed PPG Signal with Guaranteed Reconstruction Quality Based on Optimum Truncation of Singular Values and ASCII Character Encoding.

Extraction and analysis of various clinically significant features of photoplethysmogram (PPG) signals for monitoring several physiological parameters as well as for biometric authentication have become important areas of research in recent years. However, PPG signal compression; particularly quality-guaranteed compression, and steganography of patient's secret information is still lagging behind. This paper presents a robust, reliable and highly-efficient singular value decomposition (SVD) and lossless ASCII character encoding (LL-ACE)-based quality-guaranteed PPG compression algorithm. This algorithm can not only be used to compress PPG signals but also do so for steganographed PPG signals that include the patient information. It is worth mentioning that such an algorithm is being proposed for the first time to compress steganographed PPG signals. The algorithm is tested on PPG signals collected from four different databases, and its performance is assessed using both quantitative and qualitative measures. The proposed steganographed PPG compression algorithm provides a compression ratio that is much higher than that provided by other algorithms that are designed to compress the PPG signals only. (1) the clinical quality of the reconstructed PPG signal can be controlled precisely, (2) the patient's personal information is restored with no errors, (3) high compression ratio, and (4) the PPG signal reconstruction error is neither dependent on the steganographic operation nor on the size of the patient information data.