Tag Features Research Articles

Online Attendance System with Geolocation Tagging Feature based on Progressive Web Apps (PWA) on CV Trivia Oktana Mandiri

Online Attendance System with Geolocation Tagging Feature based on Progressive Web Apps (PWA) on CV Trivia Oktana Mandiri

Photo-induced preparation of Ce-doped terbium aluminum garnet and its luminescent properties

Ce(III) activated terbium aluminum garnet (Tb3Al5O12:Ce, TAG:Ce) powder as a luminescent phosphor was synthesized by the photo-induced method. The irradiation of an aqueous solution containing formate anions and soluble salts of both metal ions by UV light led to the precipitation of an amorphous solid phase. Subsequent heat treatment at 1200 °C resulted in the crystallization of the TAG:Ce phase-pure garnet structure. The structure and morphology of the products were investigated by X-ray powder diffraction (XRPD) and by scanning electron microscopy (SEM). The particle size, evaluated by transmission electron microscopy (TEM), ranges from 50 to 150 nm. The manufactured Ce-doped TAG features intensive luminescence corresponding to Ce(III) 5d–4f transitions at 559 nm. Due to its high density, chemical stability, non-toxic character, and excellent scintillation efficiency, the application of Ce-doped TAG nano-powder in photodynamic therapy and preparation of optical ceramics was suggested.

A satellite-linked tag for the long-term monitoring of diving behavior in large whales

Despite spending most time underwater, the technology in use to track whales over large geographic ranges via satellite has been largely limited to locational data, with most applications focusing on characterizing their horizontal movements. We describe the development of the RDW tag, a new Argos-based satellite telemetry device that incorporates sensors for monitoring the movements and dive behavior of large whales over several months without requiring recovery. Based on an implantable design, the tag features a saltwater conductivity switch, a tri-axial accelerometer, and an optional pressure transducer, along with onboard software for data processing and detection of behavioral events or activities of interest for transmission. We configured the software to detect dives and create per-dive summaries describing behavioral events associated with feeding activities in rorqual whales. We conducted a validation by proxy of the dive summary and event detection algorithms using field data from a medium-duration archival tag. We also conducted a simulation exercise to examine how the expected data recovery would vary under different dive behavior scenarios and compared those results to empirical values from field deployments of the RDW tag on blue (Balaenoptera musculus) and humpback (Megaptera novaeangliae) whales. The dive summary algorithm accurately reported dive depth and duration, while the accuracy of the lunge-feeding event detection algorithm was dependent on the precision of the accelerometer data that was used, with a predicted accuracy of 0.74 for correctly classifying feeding dives from 1/64-G precision data and 0.95 from 1-mG precision data. Simulated data recovery was lower with sparser transmission schedules, shorter mean dive durations, and lower rates of successfully received transmissions. Empirical data recovery was lower than expected from the simulation, suggesting the effect of additional factors, such as data gaps. By measuring key aspects of the per-dive behavior of large whales over multi-month timescales of movement, the RDW tags provide the ability to monitor previously unobservable behaviors across entire geographic ranges, extending the applications of satellite telemetry devices to new areas of whale physiology, behavior, ecology, and conservation.

Exploratory Research on the Practice of College English Classroom Teaching Based on Internet and Artificial Intelligence

With the rapid development of cloud computing and mobile Internet technology, the information of optional services in the network is exploding and the problem of information overload is becoming more and more serious. The recommendation system can recommend suitable English online classes for students according to their interests and needs, effectively reduce the data load, help students extract effective information from the mass of information, and make accurate recommendations. Aiming at the problems of data sparsity and cold start in the recommendation system, this paper proposes a recommendation method to improve the collaborative recommendation algorithm in college English online classroom teaching practice. Based on the extracted student tag feature information, this method uses spectral clustering algorithm to cluster similar students and transforms the original high-dimension scoring matrix into several lower-dimension subscoring matrices. Then, the implicit meaning model is used to locally predict the missing score in the subscore matrix. Finally, after obtaining the missing score, the improved neighborhood-based collaborative recommendation algorithm is used to predict the global score of the target student. Experiments are performed on commonly used public data sets. Compared with the traditional recommendation algorithm, the proposed algorithm has higher recommendation accuracy and better RMSE performance.

Leveraging Part-of-Speech Tagging Features and a Novel Regularization Strategy for Chinese Medical Named Entity Recognition

Chinese Medical Named Entity Recognition (Chinese-MNER) aims to identify potential entities and their categories from the unstructured Chinese medical text. Existing methods for this task mainly incorporate the dictionary knowledge on the basis of traditional BiLSTM-CRF or BERT architecture. However, the construction of high-quality dictionaries is typically time consuming and labor-intensive, which may also damage the robustness of NER models. What is more, the limited amount of annotated Chinese-MNER data can easily lead to the over-fitting problem while training. With the aim of dealing with the above problems, we put forward a BERT-BiLSTM-CRF model by integrating the part-of-speech (POS) tagging features and a Regularization method (BBCPR) for Chinese-MNER. In BBCPR, we first leverage a POS fusion layer to incorporate external syntax knowledge. Next, we design a novel REgularization mothod with Adversarial training and Dropout (READ) to improve the model robustness. Specifically, READ focuses on reducing the difference between the predictions of two sub-models through minimizing the bidirectional KL divergence between the adversarial output and original output distributions for the same sample. Comprehensive evaluations on two public data sets, namely, cMedQANER and cEHRNER from the Chinese Biomedical Language Understanding Evaluation benchmark (ChineseBLUE), demonstrate the superiority of our proposal in Chinese-MNER. In addition, ablation study shows that READ can effectively improve the model performance. Our proposal does well in exploring the technical terms and identifying the word boundary.

OWGC-HMC: An Online Web Genre Classification Model Based on Hierarchical Multilabel Classification

Web genre plays an important role in focused crawling, web link analysis, and contextual advertising. In this paper, web genre is defined as the functional purpose and the information type contained in the website. The intelligent classification of web genre can predict the content and functional type of website. However, there are several critical challenges to solve the web genre classification problem: lack of web genre classification dataset and efficient web genre classification mechanism. To improve web genre classification performance, we crawled Chinese websites of different web genres and converted crawled data into a hierarchical multilabel classification dataset. A website knowledge graph is constructed based on the relationship of website and meta tag features. Using entity features extracted from the knowledge graph, we propose an online web genre classification model based on hierarchical multilabel classification (OWGC-HMC) to mine the functional purpose of the corresponding website. Experimental results show that our OWGC-HMC model can mine hierarchical multilabel structure of web genre and outperform other web genre classification methods.

How Can We Provide Additively Manufactured Parts with a Fingerprint? A Review of Tagging Strategies in Additive Manufacturing.

Additive manufacturing (AM) is rapidly evolving from “rapid prototyping” to “industrial production”. AM enables the fabrication of bespoke components with complicated geometries in the high-performance areas of aerospace, defence and biomedicine. Providing AM parts with a tagging feature that allows them to be identified like a fingerprint can be crucial for logistics, certification and anti-counterfeiting purposes. Whereas the implementation of an overarching strategy for the complete traceability of AM components downstream from designer to end user is, by nature, a cross-disciplinary task that involves legal, digital and technological issues, materials engineers are on the front line of research to understand what kind of tag is preferred for each kind of object and how existing materials and 3D printing hardware should be synergistically modified to create such tag. This review provides a critical analysis of the main requirements and properties of tagging features for authentication and identification of AM parts, of the strategies that have been put in place so far, and of the future challenges that are emerging to make these systems efficient and suitable for digitalisation. It is envisaged that this literature survey will help scientists and developers answer the challenging question: “How can we embed a tagging feature in an AM part?”.

Clutter Suppression for Indoor Self-Localization Systems by Iteratively Reweighted Low-Rank Plus Sparse Recovery.

Self-localization based on passive RFID-based has many potential applications. One of the main challenges it faces is the suppression of the reflected signals from unwanted objects (i.e., clutter). Typically, the clutter echoes are much stronger than the backscattered signals of the passive tag landmarks used in such scenarios. Therefore, successful tag detection can be very challenging. We consider two types of tags, namely low-Q and high-Q tags. The high-Q tag features a sparse frequency response, whereas the low-Q tag presents a broad frequency response. Further, the clutter usually showcases a short-lived response. In this work, we propose an iterative algorithm based on a low-rank plus sparse recovery approach (RPCA) to mitigate clutter and retrieve the landmark response. In addition to that, we compare the proposed approach with the well-known time-gating technique. It turns out that RPCA outperforms significantly time-gating for low-Q tags, achieving clutter suppression and tag identification when clutter encroaches on the time-gating window span, whereas it also increases the backscattered power at resonance by approximately 12 dB at 80 cm for high-Q tags. Altogether, RPCA seems a promising approach to improve the identification of passive indoor self-localization tag landmarks.

Graph-LSTM with Global Attribute for Scene Graph Generation

Lots of machine learning tasks require dealing with graph data, and among them, scene graph generation is a challenging one that calls for graph neural networks’ potential ability. In this paper, we present a definition of graph neural network (GNN) consists of node, edge and global attribute, as well as their corresponding update and aggregate functions. Based on this, we then propose a realization of GNN model called Graph-LSTM and use it in scene graph generation. The model first extracts the item features in the image as the initial states of the node-LSTM representing subject/object and edge-LSTM representing predicate. Two LSTMs update the states via LSTM’s timestep and aggregate information via message passing. Repeat the update-aggregate until convergence. Meanwhile, the tag feature, i.e., the generated probability distribution of image’s semantic concepts is sent to the LSTM through a semantic compositional network (SCN). The SCN-LSTM is trained in an ensemble style, and hence allows the tag feature to serve as the global attribute providing context information to all individuals. The LSTMs’ final states are input to inference modules and generate the triplet (subject, predicate, object) of the scene graph. Experimental results show that Graph-LSTM outperforms the Message Passing and the attention Graph Covolutional Network methods, proving the effectiveness of the proposed scheme.

RETRACTED ARTICLE: Coastal soil pollution detection and business English teaching index construction based on deep feature fusion

This paper proposes a deep learning model, which classifies web pages based on deep feature fusion. The model has the function of using Text CNN to extract the text of important tags in the web page. It also has the function of using XL Net to extract the text of other tags in the web page. The two parts of the function in the webpage are combined together, which effectively solves the problem of feature collinearity and vector sparseness in the process of network deep feature fusion. This article discusses a deep merging mechanism that can improve the merging of the semantic features of important tags with the semantic features of other web pages. Experimental results show that this method is based on a deep fusion deep learning model and can be used for efficient and high-precision classification of website text. At the same time, the development index of an effective English language model for business research and index system is established in the study. The research is based on theoretical analysis, concept deduction, teaching reform projects, textbook drafts, teaching materials, teacher training basic knowledge, and teaching competitions. Theoretical model of English teaching development index. In addition, this article also introduces the actual soil of a certain area of China as the research object, and 16 kinds of phthalate esters were tested in the soil of this area. By determining the physical and chemical properties of soil enzymes, the effects of phthalate microbial communities, and soil microbial communities on different planting methods were analyzed. This paper uses deep functional fusion technology to detect soil pollution and display the concentration of phthalate pollutants in the soil, as well as the response of business English to the construction of teaching index.

MenuNER: Domain-Adapted BERT Based NER Approach for a Domain with Limited Dataset and Its Application to Food Menu Domain

Entity-based information extraction is one of the main applications of Natural Language Processing (NLP). Recently, deep transfer-learning utilizing contextualized word embedding from pre-trained language models has shown remarkable results for many NLP tasks, including Named-entity recognition (NER). BERT (Bidirectional Encoder Representations from Transformers) is gaining prominent attention among various contextualized word embedding models as a state-of-the-art pre-trained language model. It is quite expensive to train a BERT model from scratch for a new application domain since it needs a huge dataset and enormous computing time. In this paper, we focus on menu entity extraction from online user reviews for the restaurant and propose a simple but effective approach for NER task on a new domain where a large dataset is rarely available or difficult to prepare, such as food menu domain, based on domain adaptation technique for word embedding and fine-tuning the popular NER task network model ‘Bi-LSTM+CRF’ with extended feature vectors. The proposed NER approach (named as ‘MenuNER’) consists of two step-processes: (1) Domain adaptation for target domain; further pre-training of the off-the-shelf BERT language model (BERT-base) in semi-supervised fashion on a domain-specific dataset, and (2) Supervised fine-tuning the popular Bi-LSTM+CRF network for downstream task with extended feature vectors obtained by concatenating word embedding from the domain-adapted pre-trained BERT model from the first step, character embedding and POS tag feature information. Experimental results on handcrafted food menu corpus from customers’ review dataset show that our proposed approach for domain-specific NER task, that is: food menu named-entity recognition, performs significantly better than the one based on the baseline off-the-shelf BERT-base model. The proposed approach achieves 92.5% F1 score on the YELP dataset for the MenuNER task.

Improving Scalability, Sparsity and Cold Start User Issues in Collaborative Tagging with Incremental Clustering and Trust

Background: Due to huge data in web sites, recommending users for every product is impossible. For this problem Recommender Systems (RS) are introduced. RS is categorized into Content-Based (CB), collaborative Filtering (CF) and Hybrid RS. Based on these techniques recommendations are done to user. In this, CF is the recent technique used in RS in which tagging feature also provided. Objective: Three main issues occur in RS are scalability problem which occurs when there is a huge data, sparsity problem occurs when rating data is missing and cols start user or item problem occurs when new user or new item enters in the system. To avoid these issues here we have proposed Incremental clustering and Trust in Collaborative Tagging. Methods: Here we have proposed a method Collaborative Tagging (CT) with Incremental Clustering and Trust which enhances the recommendation quality by removing the issues of scalability with the help of Incremental Clustering and sparsity and cold start user or item problems are resolved with the help of Trust. Results: Here we have compared the results of Collaborative tagging with Incremental Clustering and Trust (CFT-EDIC-TS) with the baseline approaches of CT with Cosine similarity (CFT-CS), CT with Euclidian Distance and Incremental Clustering (CFT-EDIC) and CT with Trust (CFT-TS). Conclusion: Here we have compare the proposed approach with the baseline approaches and the metrics are used MAE, prediction percentage, Precision and Recall. Based on these metrics for every split CFT-EDICTS shown best results as compared to other baseline approaches.

Multichannel Attendance Management System using QR Code and Location

With the advent of technologies and multiple options available, it’s very essential to rethink and optimize the current manual process by utilizing technologies, like web, mobile together. At present mobile phones play a vital role in our day-to-day life, and it also became a mode of identity. Using the mobile and its geo tagging feature we can precisely locate and validate once presence. The inbuilt ability of mobile can be very well leveraged to modernize the current manual attendance system. QR Code scanning is one of such features of mobile phones that enables them to quickly capture and process the data. Smartphones can be used to speed up the process of taking attendance. This project ‘Multichannel Attendance Management system using QR Code and Location’ focuses on simplifying & solving the problem of manual process of taking attendance. The project proposes a system that is based on using a QR code. QR stands for ‘Quick Response’. They can be read quickly by a cell phone. It stores information such as the lecture number, date, name of the professor, etc, which is used in this proposed system.

AutoBOT: evolving neuro-symbolic representations for explainable low resource text classification

Learning from texts has been widely adopted throughout industry and science. While state-of-the-art neural language models have shown very promising results for text classification, they are expensive to (pre-)train, require large amounts of data and tuning of hundreds of millions or more parameters. This paper explores how automatically evolved text representations can serve as a basis for explainable, low-resource branch of models with competitive performance that are subject to automated hyperparameter tuning. We present autoBOT (automatic Bags-Of-Tokens), an autoML approach suitable for low resource learning scenarios, where both the hardware and the amount of data required for training are limited. The proposed approach consists of an evolutionary algorithm that jointly optimizes various sparse representations of a given text (including word, subword, POS tag, keyword-based, knowledge graph-based and relational features) and two types of document embeddings (non-sparse representations). The key idea of autoBOT is that, instead of evolving at the learner level, evolution is conducted at the representation level. The proposed method offers competitive classification performance on fourteen real-world classification tasks when compared against a competitive autoML approach that evolves ensemble models, as well as state-of-the-art neural language models such as BERT and RoBERTa. Moreover, the approach is explainable, as the importance of the parts of the input space is part of the final solution yielded by the proposed optimization procedure, offering potential for meta-transfer learning.

Fine-scale behaviour of the Lusitanian toadfish assessed in situ with the AccelTag

BackgroundThree-axis acceleration sensor acoustic transmitters (AccelTag) programmed to identify specific acceleration patterns associated with particular behaviours (e.g., burrowing, attack) were used to study some aspects of the ecology of the Lusitanian toadfish Halobatrachus didactylus (Bloch & Schneider 1801). The AccelTag combines the features of archival tags (records acceleration in all three directions measuring also roll-independent pitch/tilt angle and roll around the fish’s axis) and acoustic transmitters. Therefore, this tag can autonomously identify and record specific signatures (i.e., behaviour patterns) of different movements transmitting autonomously and periodically the data to an acoustic biotelemetry receiver. Lusitanian toadfish is a subtropical marine teleost confined to estuaries in its northern limit of distribution due to thermal constraints. During 2010 (August and October), 24 toadfish were captured, tagged with the AccelTag and released in the Mira estuary, SW coast of Portugal, where an array of underwater automatic acoustic biotelemetry receivers was deployed.ResultsAround 40% of AccelTag transmissions from tagged fish that stayed in the study area were logged by the acoustic receiver array. The Lusitanian toadfish exhibited low activity during late summer and early autumn (< 3% of time active). The tidal stage and time of day were important factors that influenced the species behaviour and activity. Increased burrowing and re-burrowing movements were registered during spring tides, while attacks prevailed on neap tides and during the night. The tidal cycle only influenced toadfish behaviour and activity in interaction with time of day, with more attacks and higher levels of activity during nocturnal high tides.ConclusionsHigher activity levels and attacks displayed by the Lusitanian toadfish during the night, at high tide periods and during Spring tides are considered to be associated with increased activity and vulnerability of its prey during these periods. The AccelTag proved to be a powerful tool to assess and monitor the activity and fine-scale behaviour of fish in situ. This technology is particularly suited for fish species with biological and ecological features similar to Lusitanian toadfish, i.e., resident species with low activity levels and behaviours with a distinct 3D acceleration signature.

A novel design of surface acoustic wave‐based chipless radio frequency identification tag based on multiphysics modeling

AbstractRadio frequency identification (RFID) technique is a kind of wireless, automatic identification technology that is being widely used. Compared to other identification methods such as bar code and two‐dimensional code (quick response code or QR code), the RFID technique has several remarkable merits, such as long reading distance, strong penetrating ability, pollution resistance, high reading efficiency, small size, and large information storage. However, the technique involves high cost and cannot be accepted by cost‐sensitive commodities or applications. To reduce its cost, chipless RFID tags were proposed in recent years using surface acoustic wave (SAW) to read and store the information is one such RFID tags. The tags feature small size, high flexibility, strong radiation resistance, high consistency and repeatability, as well as high temperature stability. In this paper, we propose a novel design for the SAW‐based RFID tags by using the commercial software COMSOL and analyze the performance of SAW tags with different structures.

Image Tag Recommendation based on Ranked Categorical Nearest Neighbors and Weighted Tag Features

Image Tag Recommendation based on Ranked Categorical Nearest Neighbors and Weighted Tag Features

Event Geoparser with Pseudo-Location Entity Identification and Numerical Argument Extraction Implementation and Evaluation in Indonesian News Domain

Geoparser is a fundamental component of a Geographic Information Retrieval (GIR) geoparser, which performs toponym recognition, disambiguation, and geographic coordinate resolution from unstructured text domain. However, geoparsing of news articles which report several events across many place-mentions in the document are not yet adequately handled by regular geoparser, where the scope of resolution is either toponym-level or document-level. The capacity to detect multiple events and geolocate their true coordinates along with their numerical arguments is still missing from modern geoparsers, much less in Indonesian news corpora domain. We propose an event geoparser model with three stages of processing, which tightly integrates event extraction model into geoparsing and provides precise event-level resolution scope. The model casts the geotagging and event extraction as sequence labeling and uses LSTM-CRF inferencer equipped with features derived using Aggregated Topic Model from a large corpus to increase the generalizability. Throughout the proposed workflow and features, the geoparser is able to significantly improve the identification of pseudo-location entities, resulting in a 23.43% increase for weighted F1 score compared to baseline gazetteer and POS Tag features. As a side effect of event extraction, various numerical arguments are also extracted, and the output is easily projected to a rich choropleth map from a single news document.

Bidirectional Gated Recurrent Unit Neural Network for Chinese Address Element Segmentation

Chinese address element segmentation is a basic and key step in geocoding technology, and the segmentation results directly affect the accuracy and certainty of geocoding. However, due to the lack of obvious word boundaries in Chinese text, the grammatical and semantic features of Chinese text are complicated. Coupled with the diversity and complexity in Chinese address expressions, the segmentation of Chinese address elements is a substantial challenge. Therefore, this paper proposes a method of Chinese address element segmentation based on a bidirectional gated recurrent unit (Bi-GRU) neural network. This method uses the Bi-GRU neural network to generate tag features based on Chinese word segmentation and then uses the Viterbi algorithm to perform tag inference to achieve the segmentation of Chinese address elements. The neural network model is trained and verified based on the point of interest (POI) address data and partial directory data from the Baidu map of Beijing. The results show that the method is superior to previous neural network models in terms of segmentation performance and efficiency.

An improved hidden behavioral pattern mining approach to enhance the performance of recommendation system in a big data environment

The proposed work aims to solve data sparsity problem in the recommendation system. It handles two-level pre-processing techniques to reduce the data size at the item level. Additional resources like items genre, tag, and time are added to learn and analyse the behaviour of the user preferences in-depth. The advantage of the proposed method is to recommend the item, based on user interest pattern and avoid recommending the outdated items. User information are grouped based on similar item genre and tag feature. This effectively handle overlapping conditions that exist on item’s genre, as it has more than one genre at initial level. Further, based on time, it analyses the user non-static interest. Overall it reduces the dimensions which is an initial way to prepare data, to analyse hidden pattern. To enhance the performance, the proposed method utilized Apache’s spark Mllib FP-Growth and association rule mining approach in a distributed environment. To reduce the computation cost of constructing tree in FP-Growth, the candidate data set is stored in matrix form. The experiments were conducted using MovieLens data set. The observed results shows that the proposed method achieves 4% increase in accuracy when compared to earlier methods.