Search results for: information retrieval (ir)

Authors: H. S. Saini, K. Vijayalakshmi, Rishi Sayal

Abstract:

Network-based education has been growing rapidly in size and quality. Knowledge clustering becomes more important in personalized information retrieval for web-learning. A personalized-Learning service after the learners’ knowledge has been classified with clustering. Through automatic analysis of learners’ behaviors, their partition with similar data level and interests may be discovered so as to produce learners with contents that best match educational needs for collaborative learning. We present a specific mining tool and a recommender engine that we have integrated in the online learning in order to help the teacher to carry out the whole e-learning process. We propose to use sequential pattern mining algorithms to discover the most used path by the students and from this information can recommend links to the new students automatically meanwhile they browse in the course. We have Developed a specific author tool in order to help the teacher to apply all the data mining process. We tend to report on many experiments with real knowledge so as to indicate the quality of using both clustering and sequential pattern mining algorithms together for discovering personalized e-learning systems.

Keywords: e-learning, cluster, personalization, sequence, pattern

Procedia PDF Downloads 428

Authors: Nihad Karim Chowdhury, Mohammad Sanaullah Chowdhury, Muhammed Jamshed Alam Patwary, Rubel Biswas

Abstract:

In content-based 3D shape retrieval system, achieving high search performance has become an important research problem. A challenging aspect of this problem is to find an effective shape descriptor which can discriminate similar shapes adequately. To address this problem, we propose a new shape descriptor for 3D shape models by combining multi-resolution with multi-block center-symmetric local binary pattern operator. Given an arbitrary 3D shape, we first apply pose normalization, and generate a set of multi-viewed 2D rendered images. Second, we apply Gaussian multi-resolution filter to generate several levels of images from each of 2D rendered image. Then, overlapped sub-images are computed for each image level of a multi-resolution image. Our unique multi-block CS-LBP comes next. It allows the center to be composed of m-by-n rectangular pixels, instead of a single pixel. This process is repeated for all the 2D rendered images, derived from both ‘depth-buffer’ and ‘silhouette’ rendering. Finally, we concatenate all the features vectors into one dimensional histogram as our proposed 3D shape descriptor. Through several experiments, we demonstrate that our proposed 3D shape descriptor outperform the previous methods by using a benchmark dataset.

Keywords: 3D shape retrieval, 3D shape descriptor, CS-LBP, overlapped sub-images

Procedia PDF Downloads 445

Authors: Bo Wang

Abstract:

This paper proposes a method that can estimate PM2.5 by the images of GF-1 Satellite that called WFOV images (Wide Field of View). AOD (Aerosol Optical Depth) over land surfaces was retrieved in Shanghai area based on DDV (Dark Dense Vegetation) method. PM2.5 information, gathered from ground monitoring stations hourly, was fitted with AOD using different polynomial coefficients, and then the correlation coefficient between them was calculated. The results showed that, the GF-1 WFOV images can meet the requirement of retrieving AOD, and the correlation coefficient between the retrieved AOD and PM2.5 was high. If more detailed and comprehensive data is provided, the accuracy could be improved and the parameters can be more precise in the future.

Keywords: remote sensing retrieve, PM 2.5, GF-1, aerosol optical depth

Procedia PDF Downloads 244

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 170

Authors: Aman Berhe, Camille Guinaudeau, Claude Barras

Abstract:

In order to facilitate information seeking in large collections of multimedia documents with long and progressive content (such as broadcast news or TV series), one can extract the semantic links that exist between semantically coherent parts of documents, i.e., scenes. The links can then create a coherent collection of scenes from which it is easier to perform content analysis, topic extraction, or information retrieval. In this paper, we focus on TV series structuring and propose two approaches for scene linking at different levels of granularity (episode and season): a fuzzy online clustering technique and a graph-based community detection algorithm. When evaluated on the two first seasons of the TV series Game of Thrones, we found that the fuzzy online clustering approach performed better compared to graph-based community detection at the episode level, while graph-based approaches show better performance at the season level.

Keywords: multimedia collection structuring, progressive content, scene linking, fuzzy clustering, community detection

Procedia PDF Downloads 100

Authors: Suleiman Musa, Shuaibu Sidi Safiyanu

Abstract:

This study examined the digital preservation in Nigeria university libraries. A comparison between the university of Nigeria Nsukka (UNN) and Ahmadu Bello University Zaria (ABU, Zaria). The study utilized primary source of data obtained from two selected institution librarians. Finding revealed varying results in terms of skills acquired by librarians before and after digitization of the two institutions. The study reports that journals publication, text book, CD-ROMS, conference papers and proceedings, theses, dissertations and seminar papers are among the information resources available for digitization. The study further documents that copyright issue, power failure, and unavailability of needed materials are among the challenges facing the digitization of library of the institution. On the basis of the finding, the study concluded that digitization of library enhances efficiency in organization and retrieval of information services. The study therefore recommended that software should be upgraded with backup, training of the librarians on digital process, installation of antivirus and enhancement of technical collaboration between the library and MIS.

Keywords: digitalization, preservation, libraries, comparison

Procedia PDF Downloads 339

Authors: Jeanne Gallee, Sofia Vallila-Rohter

Abstract:

Technology-based applications are increasingly being utilized in aphasia rehabilitation as a means of increasing intensity of treatment and improving accessibility to treatment. These interactive therapies, often available on tablets, lead individuals to complete language and cognitive rehabilitation tasks that draw upon skills such as the ability to name items, recognize semantic features, count syllables, rhyme, and categorize objects. Tasks involve visual and auditory stimulus cues and provide feedback about the accuracy of a person’s response. Research has begun to examine the efficacy of tablet-based therapies for aphasia, yet much remains unknown about how individuals interact with these therapy applications. Thus, the current study aims to examine the efficacy of a tablet-based therapy program for anomia, further examining how strategy training might influence the way that individuals with aphasia engage with and benefit from therapy. Individuals with aphasia are enrolled in one of two treatment paradigms: traditional therapy or strategy therapy. For ten weeks, all participants receive 2 hours of weekly in-house therapy using Constant Therapy, a tablet-based therapy application. Participants are provided with iPads and are additionally encouraged to work on therapy tasks for one hour a day at home (home logins). For those enrolled in traditional therapy, in-house sessions involve completing therapy tasks while a clinician researcher is present. For those enrolled in the strategy training group, in-house sessions focus on limiting cue use in order to maximize lexical retrieval attempts and naming opportunities. The strategy paradigm is based on the principle that retrieval attempts may foster long-term naming gains. Data have been collected from 7 participants with aphasia (3 in the traditional therapy group, 4 in the strategy training group). We examine cue use, latency of responses and accuracy through the course of therapy, comparing results across group and setting (in-house sessions vs. home logins).

Keywords: aphasia, speech-language pathology, traumatic brain injury, language

Procedia PDF Downloads 203

Authors: Neziha Jaouedi, Noureddine Boujnah, Mohamed Salim Bouhlel

Abstract:

In the framework of human machine interaction systems enhancement, we focus throw this paper on human behavior analysis and action recognition. Human behavior is characterized by actions and reactions duality (movements, psychological modification, verbal and emotional expression). It’s worth noting that many information is hidden behind gesture, sudden motion points trajectories and speeds, many research works reconstructed an information retrieval issues. In our work we will focus on motion extraction, tracking and action recognition using wavelet network approaches. Our contribution uses an analysis of human subtraction by Gaussian Mixture Model (GMM) and body movement through trajectory models of motion constructed from kalman filter. These models allow to remove the noise using the extraction of the main motion features and constitute a stable base to identify the evolutions of human activity. Each modality is used to recognize a human action using wavelets of derived beta distributions approach. The proposed approach has been validated successfully on a subset of KTH and UCF sports database.

Keywords: feautures extraction, human action classifier, wavelet neural network, beta wavelet

Procedia PDF Downloads 411

Authors: Kien Vu, Jien Min Soh, Mohamed Jahangir Abubacker, Piyawut Pattamanon, Soojin Lee, Suvro Banerjee

Abstract:

Recent advances in Generative Artificial Intelligence (GenAI), in particular Large Language Models (LLMs) have shown promise to disrupt multiple industries at scale. However, LLMs also present unique challenges, notably, these so-called "hallucination" which is the generation of outputs that are not grounded in the input data that hinders its adoption into production. Common practice to mitigate hallucination problem is utilizing Retrieval Agmented Generation (RAG) system to ground LLMs'response to ground truth. RAG converts the grounding documents into embeddings, retrieve the relevant parts with vector similarity between user's query and documents, then generates a response that is not only based on its pre-trained knowledge but also on the specific information from the retrieved documents. However, the RAG system is not suitable for tabular data and subsequent data analysis tasks due to multiple reasons such as information loss, data format, and retrieval mechanism. In this study, we have explored a novel methodology that combines planning-and-execution and code generation agents to enhance LLMs' data analysis capabilities. The approach enables LLMs to autonomously dissect a complex analytical task into simpler sub-tasks and requirements, then convert them into executable segments of code. In the final step, it generates the complete response from output of the executed code. When deployed beta version on DataSense, the property insight tool of PropertyGuru, the approach yielded promising results, as it was able to provide market insights and data visualization needs with high accuracy and extensive coverage by abstracting the complexities for real-estate agents and developers from non-programming background. In essence, the methodology not only refines the analytical process but also serves as a strategic tool for real estate professionals, aiding in market understanding and enhancement without the need for programming skills. The implication extends beyond immediate analytics, paving the way for a new era in the real estate industry characterized by efficiency and advanced data utilization.

Keywords: large language model, reasoning, planning and execution, code generation, natural language processing, prompt engineering, data analysis, real estate, data sense, PropertyGuru

Procedia PDF Downloads 87

Authors: Renukswamy Chikkamath, Vishvapalsinhji Ramsinh Parmar, Christoph Hewel, Markus Endres

Abstract:

Given a patent document, identifying distinct semantic annotations is an interesting research aspect. Text annotation helps the patent practitioners such as examiners and patent attorneys to quickly identify the key arguments of any invention, successively providing a timely marking of a patent text. In the process of manual patent analysis, to attain better readability, recognising the semantic information by marking paragraphs is in practice. This semantic annotation process is laborious and time-consuming. To alleviate such a problem, we proposed a dataset to train machine learning algorithms to automate the highlighting process. The contributions of this work are: i) we developed a multi-class dataset of size 150k samples by traversing USPTO patents over a decade, ii) articulated statistics and distributions of data using imperative exploratory data analysis, iii) baseline Machine Learning models are developed to utilize the dataset to address patent paragraph highlighting task, and iv) future path to extend this work using Deep Learning and domain-specific pre-trained language models to develop a tool to highlight is provided. This work assists patent practitioners in highlighting semantic information automatically and aids in creating a sustainable and efficient patent analysis using the aptitude of machine learning.

Keywords: machine learning, patents, patent sentiment analysis, patent information retrieval

Procedia PDF Downloads 90

Authors: Peter U. Eze, P. Udaya, Robin J. Evans

Abstract:

Data hiding can be achieved by Steganography or invisible digital watermarking. For digital watermarking, both accurate retrieval of the embedded watermark and the integrity of the cover image are important. Medical image security in Teleradiology is one of the applications where the embedded patient record needs to be extracted with accuracy as well as the medical image integrity verified. In this research paper, the Constant Correlation Spread Spectrum digital watermarking for medical image tamper detection and accurate embedded watermark retrieval is introduced. In the proposed method, a watermark bit from a patient record is spread in a medical image sub-block such that the correlation of all watermarked sub-blocks with a spreading code, W, would have a constant value, p. The constant correlation p, spreading code, W and the size of the sub-blocks constitute the secret key. Tamper detection is achieved by flagging any sub-block whose correlation value deviates by more than a small value, ℇ, from p. The major features of our new scheme include: (1) Improving watermark detection accuracy for high-pixel depth medical images by reducing the Bit Error Rate (BER) to Zero and (2) block-level tamper detection in a single computational process with simultaneous watermark detection, thereby increasing utility with the same computational cost.

Keywords: Constant Correlation, Medical Image, Spread Spectrum, Tamper Detection, Watermarking

Procedia PDF Downloads 194

Authors: Gaurav Kumar

Abstract:

An information literate person is one who uses information effectively in all its forms. When presented with questions or problems, an information literate person would know what information to look for, how to search efficiently and be able to access relevant sources. In addition, an information literate person would have the ability to evaluate and select appropriate information sources and to use the information effectively and ethically to answer questions or solve problems. Information literacy has become an important element in higher education. The information literacy movement has internationally recognized standards and learning outcomes. The step-by-step process of achieving information literacy is particularly crucial in an era where knowledge could be disseminated through a variety of media. What is the relationship between information literacy as we define it in higher education and information literacy among non-academic populations? What forces will change how we think about the definition of information literacy in the future and how we will apply the definition in all environments?

Keywords: information literacy, human beings, visual media and computer network etc, information literacy

Procedia PDF Downloads 339

Authors: Farzaneh Badinlou, Reza Kormi-Nouri, Monika Knopf, Kamal Kharazi

Abstract:

Research into long-term memory has demonstrated that the richness of the knowledge base cues in memory tasks improves retrieval process, which in turn influences learning and memory performance. The present research investigated the idea that adding cues connected to knowledge can affect memory performance in the context of action memory in children. In action memory studies, participants are instructed to learn a series of verb–object phrases as verbal learning and experience-based learning (learning by doing and learning by observation). It is well established that executing action phrases is a more memorable way to learn than verbally repeating the phrases, a finding called enactment effect. In the present study, a total of 410 students from four grade groups—2nd, 4th, 6th, and 8th—participated in this study. During the study, participants listened to verbal action phrases (VTs), performed the phrases (SPTs: subject-performed tasks), and observed the experimenter perform the phrases (EPTs: experimenter-performed tasks). During the test phase, cued recall test was administered. Semantic relational cues (i.e., well-integrated vs. poorly integrated items) were manipulated in the present study. In that, the participants were presented two lists of action phrases with high semantic integration between verb and noun, e.g., “write with the pen” and with low semantic integration between verb and noun, e.g., “pick up the glass”. Results revealed that experience-based learning had a better results than verbal learning for both well-integrated and poorly integrated items, though manipulations of semantic relational cues can moderate the enactment effect. In addition, children of different grade groups outperformed for well- than poorly integrated items, in flavour of older children. The results were discussed in relation to the effect of knowledge-based information in facilitating retrieval process in children.

Keywords: action memory, enactment effect, knowledge-based cues, school-aged children, semantic relational cues

Procedia PDF Downloads 275

Authors: Aicha Aggoune, Abdelkrim Bouramoul, Mohamed Khiereddine Kholladi

Abstract:

Recent research shows that user profile as important element can improve heterogeneous information retrieval with its content. In this context, we present our indexing model for heterogeneous multimedia documents. This model is based on the combination of user profile to the indexing process. The general idea of our proposal is to operate the common concepts between the representation of a document and the definition of a user through his profile. These two elements will be added as additional indexing entities to enrich the heterogeneous corpus documents indexes. We have developed IRONTO domain ontology allowing annotation of documents. We will present also the developed tool validating the proposed model.

Keywords: indexing model, user profile, multimedia document, heterogeneous of sources, ontology

Procedia PDF Downloads 348

Authors: Feras Hanandeh, Izzat Alsmadi, Muhammad M. Kwafha

Abstract:

Prefix trees or tries are data structures that are used to store data or index of data. The goal is to be able to store and retrieve data by executing queries in quick and reliable manners. In principle, the structure of the trie depends on having letters in nodes at the different levels to point to the actual words in the leafs. However, the exact structure of the trie may vary based on several aspects. In this paper, we evaluated different structures for building tries. Using datasets of words of different sizes, we evaluated the different forms of trie structures. Results showed that some characteristics may impact significantly, positively or negatively, the size and the performance of the trie. We investigated different forms and structures for the trie. Results showed that using an array of pointers in each level to represent the different alphabet letters is the best choice.

Keywords: data structures, indexing, tree structure, trie, information retrieval

Procedia PDF Downloads 452

Authors: Hiroshi Yamaguchi, Phillip C. Y. Sheu, Ryo Fujita, Shigeo Tsujii

Abstract:

In this paper, the secure BioSemantic Scheme is presented to bridge biological/biomedical research problems and computational solutions via semantic computing. Due to the diversity of problems in various research fields, the semantic capability description language (SCDL) plays and important role as a common language and generic form for problem formalization. SCDL is expected the essential for future semantic and logical computing in Biosemantic field. We show several example to Biomedical problems in this paper. Moreover, in the coming age of cloud computing, the security problem is considered to be crucial issue and we presented a practical scheme to cope with this problem.

Keywords: biomedical applications, private information retrieval (PIR), semantic capability description language (SCDL), semantic computing

Procedia PDF Downloads 390

Authors: Sameut Bouhaik Mostafa

Abstract:

Information Act is the Canadian law gives the right of access to information for the institution of government. It declares the availability of government information to the public, but that exceptions should be limited and the necessary right of access to be specific, and also states the need to constantly re-examine the decisions on the disclosure of any government information independently from the government. By 1982, it enacted a dozen countries, including France, Denmark, Finland, Sweden, the Netherlands and the United States (1966) newly legally to access the information. It entered access to Canadian information into force of the Act of 1983, under the government of Pierre Trudeau, allowing Canadians to recover information from government files, and the development of what can be accessed from the information, and the imposition of timetables to respond. It has been applied by the Information Commissioner in Canada.

Keywords: law, information, management, legal

Procedia PDF Downloads 415

Authors: Muhammad Sollehhuddin A. Jalil, Mohd Ibrahim Shapiai, Rubiyah Yusof

Abstract:

Nowadays, ontology is common in many areas like artificial intelligence, bioinformatics, e-commerce, education and many more. Ontology is one of the focus areas in the field of Information Retrieval. The purpose of an ontology is to describe a conceptual representation of concepts and their relationships within a particular domain. In other words, ontology provides a common vocabulary for anyone who needs to share information in the domain. There are several ontology domains in various fields including engineering and non-engineering knowledge. However, there are only a few available ontology for engineering knowledge. Fuzzy logic as engineering knowledge is still not available as ontology domain. In general, fuzzy logic requires step-by-step guidelines and instructions of lab experiments. In this study, we presented domain ontology for Fuzzy Logic Control (FLC) knowledge. We give Table of Content (ToC) with middle strategy based on the Uschold and King method to develop FLC ontology. The proposed framework is developed using Protégé as the ontology tool. The Protégé’s ontology reasoner, known as the Pellet reasoner is then used to validate the presented framework. The presented framework offers better performance based on consistency and classification parameter index. In general, this ontology can provide a platform to anyone who needs to understand FLC knowledge.

Keywords: engineering knowledge, fuzzy logic control ontology, ontology development, table of content

Procedia PDF Downloads 299

Authors: Rujia Chen, Akbar Ghobakhlou, Ajit Narayanan

Abstract:

This study investigates the task of identifying musical instruments in polyphonic compositions using Convolutional Neural Networks (CNNs) from spectrogram inputs, focusing on binary classification. The model showed promising results, with an accuracy of 97% on solo instrument recognition. When applied to polyphonic combinations of 1 to 10 instruments, the overall accuracy was 64%, reflecting the increasing challenge with larger ensembles. These findings contribute to the field of Music Information Retrieval (MIR) by highlighting the potential and limitations of current approaches in handling complex musical arrangements. Future work aims to include a broader range of musical sounds, including electronic and synthetic sounds, to improve the model's robustness and applicability in real-time MIR systems.

Keywords: binary classifier, CNN, spectrogram, instrument

Procedia PDF Downloads 77

Authors: Ziad Abdallah, Mohamad Oueidat, Ali El-Zaart

Abstract:

Image Multi-label Classification (IMC) assigns a label or a set of labels to an image. The big demand for image annotation and archiving in the web attracts the researchers to develop many algorithms for this application domain. The existing techniques for IMC have two drawbacks: The description of the elementary characteristics from the image and the correlation between labels are not taken into account. In this paper, we present an algorithm (MIML-HOGLPP), which simultaneously handles these limitations. The algorithm uses the histogram of gradients as feature descriptor. It applies the Label Priority Power-set as multi-label transformation to solve the problem of label correlation. The experiment shows that the results of MIML-HOGLPP are better in terms of some of the evaluation metrics comparing with the two existing techniques.

Keywords: data mining, information retrieval system, multi-label, problem transformation, histogram of gradients

Procedia PDF Downloads 374

Authors: Parveen Kumar

Abstract:

This article discusses institute information resources. Information, in its most restricted technical sense, is a sequence of symbols that can be interpreted as message information can be recorded as signs, or transmitted as signals. Information is any kind of event that affects the state of a dynamic system. Conceptually, information is the message being conveyed. This concept has numerous other meanings in different contexts. Moreover, the concept of information is closely related to notions of constraint, communication, control, data, form, instruction, knowledge, meaning, mental stimulus, pattern, perception, representation, and especially entropy.

Keywords: institutions, information institutions, information services for mission-oriented institute, pattern

Procedia PDF Downloads 376

Authors: Issam Ben Jami

Abstract:

Information retrieval in digital libraries is very important because most famous historical documents occupy a significant value. The word spotting in historical documents is a very difficult notion, because automatic recognition of such documents is naturally cursive, it represents a wide variability in the level scale and translation words in the same documents. We first present a system for the automatic recognition, based on the extraction of interest points words from the image model. The extraction phase of the key points is chosen from the representation of the image as a synthetic description of the shape recognition in a multidimensional space. As a result, we use advanced methods that can find and describe interesting points invariant to scale, rotation and lighting which are linked to local configurations of pixels. We test this approach on documents of the 15th century. Our experiments give important results.

Keywords: feature matching, historical documents, pattern recognition, word spotting

Procedia PDF Downloads 274

Authors: Dilini Bodhinayaka, Aunsha Sajeewanie Rubasinghe

Abstract:

The library of the University of Kelaniya plays a significant role in supporting the academic work of the university. As at July, 2016 the library of the University of Kelaniya comprised of 250301 printed books, 2157 CD-ROMs, 1203 theses and 800 non-book materials. Furthermore, the library is subscribed to about 60 local journals, access to over 12,500 full text academic journals and around 100,000 e-books. The library provides the services and resources that support in teaching, doing research and learning. On the other hand, undergraduate students have adopted and continued to use the online information retrieval for their academic and research work. This study aims to compare the usage of internet and the usage of library among undergraduates in the faculties of Humanities, Social Sciences, Science and Commerce & Management in the University of Kelaniya. Also, the research attempts to determine the factors of enthusiasm or the disinterest in the students in using library and Internet. All the undergraduate students in the University (8440 students at the time of the study) were taken as the population of the study and the sample of 15% was selected out of the population using stratified sampling method. A total of 1266 questionnaires were distributed among undergraduates of the above mentioned faculties. The qualitative data were analyzed using Descriptive Statistical Method. Findings, of the study indicated that undergraduate students of the faculties of Humanities, Social Sciences, Science and Commerce & Management use both the library and the internet to fulfill their information needs. But, the students in the faculty of Science and Commerce & Management use the internet sources more than the library. The undergraduates in the faculties of Humanities and Social Sciences frequently use the university library than the internet. Although, majority agreed that the internet is the most preferred source of information they have no an adequate awareness about the available internet resources in the E-library of the University of Kelaniya.

Keywords: university libraries, University of Kelaniya, online resources, undergraduates in Sri Lanka

Procedia PDF Downloads 238

Authors: Gokulan Vethanayakam, Daniel Aston

Abstract:

Introduction: The ReSPECT process supports healthcare professionals when making patient-centered decisions in the event of an emergency. It has been widely adopted by the NHS in England and allows patients to express thoughts and wishes about treatments and outcomes that they consider acceptable. It includes (but is not limited to) cardiopulmonary resuscitation decisions. ReSPECT conversations should ideally occur prior to ICU admission and should be documented in the eight sections of the nationally-standardised ReSPECT form. This audit evaluated the use of ReSPECT on a busy cardiothoracic ICU in an NHS Trust where established policies advocating its use exist. Methods: This audit was a retrospective review of ReSPECT forms for a sample of high-risk patients admitted to ICU at the Royal Papworth Hospital between January 2021 and March 2022. Patients all received one of the following interventions: Veno-Venous Extra-Corporeal Membrane Oxygenation (VV-ECMO) for severe respiratory failure (retrieved via the national ECMO service); cardiac or pulmonary transplantation-related surgical procedures (including organ transplants and Ventricular Assist Device (VAD) implantation); or elective non-transplant cardiac surgery. The quality of documentation on ReSPECT forms was evaluated using national standards and a graded ranking tool devised by the authors which was used to assess narrative aspects of the forms. Quality was ranked as A (excellent) to D (poor). Results: Of 230 patients (74 VV-ECMO, 104 transplant, 52 elective non-transplant surgery), 43 (18.7%) had a ReSPECT form and only one (0.43%) patient had a ReSPECT form completed prior to ICU admission. Of the 43 forms completed, 38 (88.4%) were completed due to the commencement of End of Life (EoL) care. No non-transplant surgical patients included in the audit had a ReSPECT form. There was documentation of balance of care (section 4a), CPR status (section 4c), capacity assessment (section 5), and patient involvement in completing the form (section 6a) on all 43 forms. Of the 34 patients assessed as lacking capacity to make decisions, only 22 (64.7%) had reasons documented. Other sections were variably completed; 29 (67.4%) forms had relevant background information included to a good standard (section 2a). Clinical guidance for the patient (section 4b) was given in 25 (58.1%), of which 11 stated the rationale that underpinned it. Seven forms (16.3%) contained information in an inappropriate section. In a comparison of ReSPECT forms completed ahead of an EoL trigger with those completed when EoL care began, there was a higher number of entries in section 3 (considering patient’s values/fears) that were assessed at grades A-B in the former group (p = 0.014), suggesting higher quality. Similarly, forms from the transplant group contained higher quality information in section 3 than those from the VV-ECMO group (p = 0.0005). Conclusions: Utilisation of the ReSPECT process in high-risk patients is yet to be well-adopted in this trust. Teams who meet patients before hospital admission for transplant or high-risk surgery should be encouraged to engage with the ReSPECT process at this point in the patient's journey. VV-ECMO retrieval teams should consider ReSPECT conversations with patients’ relatives at the time of retrieval.

Keywords: audit, critical care, end of life, ICU, ReSPECT, resuscitation

Procedia PDF Downloads 66

Authors: Saad M. Darwish, Mohamed A. El-Iskandarani, Guitar M. Shawkat

Abstract:

Nowadays, the amount of available multimedia data is continuously on the rise. The need to find a required image for an ordinary user is a challenging task. Content based image retrieval (CBIR) computes relevance based on the visual similarity of low-level image features such as color, textures, etc. However, there is a gap between low-level visual features and semantic meanings required by applications. The typical method of bridging the semantic gap is through the automatic image annotation (AIA) that extracts semantic features using machine learning techniques. In this paper, a multi-label image annotation system guided by Firefly and Bayesian method is proposed. Firstly, images are segmented using the maximum variance intra cluster and Firefly algorithm, which is a swarm-based approach with high convergence speed, less computation rate and search for the optimal multiple threshold. Feature extraction techniques based on color features and region properties are applied to obtain the representative features. After that, the images are annotated using translation model based on the Net Bayes system, which is efficient for multi-label learning with high precision and less complexity. Experiments are performed using Corel Database. The results show that the proposed system is better than traditional ones for automatic image annotation and retrieval.

Keywords: feature extraction, feature selection, image annotation, classification

Procedia PDF Downloads 586

Authors: Yasamin Rahimi, Ali Kamandi, Abbas Hoseini, Hesam Haddad

Abstract:

Online/offline chat is a convenient approach in the electronic markets of second-hand products in which potential customers would like to have more information about the products to fill the information gap between buyers and sellers. Online peer in peer market is trying to create artificial intelligence-based systems that help customers ask more informative questions in an easier way. In this article, we introduce a method for the question/answer system that we have developed for the top-ranked electronic market in Iran called Divar. When it comes to secondhand products, incomplete product information in a purchase will result in loss to the buyer. One way to balance buyer and seller information of a product is to help the buyer ask more informative questions when purchasing. Also, the short time to start and achieve the desired result of the conversation was one of our main goals, which was achieved according to A/B tests results. In this paper, we propose and evaluate a method for suggesting questions and answers in the messaging platform of the e-commerce website Divar. Creating such systems is to help users gather knowledge about the product easier and faster, All from the Divar database. We collected a dataset of around 2 million messages in Persian colloquial language, and for each category of product, we gathered 500K messages, of which only 2K were Tagged, and semi-supervised methods were used. In order to publish the proposed model to production, it is required to be fast enough to process 10 million messages daily on CPU processors. In order to reach that speed, in many subtasks, faster and simplistic models are preferred over deep neural models. The proposed method, which requires only a small amount of labeled data, is currently used in Divar production on CPU processors, and 15% of buyers and seller’s messages in conversations is directly chosen from our model output, and more than 27% of buyers have used this model suggestions in at least one daily conversation.

Keywords: smart reply, spell checker, information retrieval, intent detection, question answering

Procedia PDF Downloads 187

Authors: Haider Javed Uppal, Javed Yunas Uppal

Abstract:

In today's globalized world, it is necessary to develop a form of music that is able to evoke equal emotional responses among people from diverse cultural backgrounds. Indigenous cultures throughout history have developed their own music cognition, specifically in terms of the connections between music and mood. With the advancements in artificial intelligence technologies, it has become possible to analyze and categorize music features such as timbre, harmony, melody, and rhythm and relate them to the resulting mood effects experienced by listeners. This paper presents a model that utilizes a screenshot translator to convert music from different origins into waveforms, which are then analyzed using machine learning and information retrieval techniques. By connecting these waveforms with Thayer's matrix of moods, a mood classifier has been developed using fuzzy logic algorithms to determine the emotional impact of different types of music on listeners from various cultures.

Keywords: cognition, world music, artificial intelligence, Thayer’s matrix

Procedia PDF Downloads 81

Authors: Tannistha Dasgupta

Abstract:

This study explores the aspects of second language (L2) spoken fluency that are related to L2 linguistic knowledge and processing skill. It draws on Levelt’s ‘blueprint’ of the L2 speaker which discusses the cognitive issues underlying the act of speaking. However, L2 speaking assessments have largely neglected the underlying mechanism involved in language production; emphasis is given on the relationship between subjective ratings of L2 speech sample and objectively measured aspects of fluency. Hence, in this study, the relation between L2 linguistic knowledge and processing skill i.e. Cognitive Fluency (CF), and objectively measurable aspects of L2 spoken fluency i.e. Utterance Fluency (UF) is examined. The participants of the study are L2 learners of English, studying at high school level in Hyderabad, India. 50 participants with intermediate level of proficiency in English performed several lexical retrieval tasks and attention-shifting tasks to measure CF, and 8 oral tasks to measure UF. Each aspect of UF (speed, pause, and repair) were measured against the scores of CF to find out those aspects of UF which are reliable indicators of CF. Quantitative analysis of the data shows that among the three aspects of UF; speed is the best predictor of CF, and pause is weakly related to CF. The study suggests that including the speed aspect of UF could make L2 fluency assessment more reliable, valid, and objective. Thus, incorporating the assessment of psycholinguistic mechanisms into L2 spoken fluency testing, could result in fairer evaluation.

Keywords: attention-shifting, cognitive fluency, lexical retrieval, utterance fluency

Procedia PDF Downloads 711

Authors: Chong-Yang Qiao, Teeravarunyou Sakol

Abstract:

Current production-oriented factories need maintenance operators to work in shifts monitoring and inspecting complex systems and different equipment in the situation of mechanical breakdown. Augmented reality (AR) is an emerging technology that embeds data into the environment for situation awareness to help maintenance operators make decisions and solve problems. An application was designed to identify the problem of steam generators and inspection centrifugal pumps. The objective of this research was to find the best medium of AR and type of problem solving strategies among analogy, focal object method and mean-ends analysis. Two scenarios of inspecting leakage were temperature and vibration. Two experiments were used in usability evaluation and future innovation, which included decision-making process and problem-solving strategy. This study found that maintenance operators prefer build-in magnifier to zoom the components (55.6%), 3D exploded view to track the problem parts (50%), and line chart to find the alter data or information (61.1%). There is a significant difference in the use of analogy (44.4%), focal objects (38.9%) and mean-ends strategy (16.7%). The marked differences between maintainers and operators are of the application of a problem solving strategy. However, future work should explore multimedia information retrieval which supports maintenance operators for decision-making.

Keywords: augmented reality, situation awareness, decision-making, problem-solving

Procedia PDF Downloads 230

Authors: Anthony Proschka, Deepak Mishra, Merlyn Ramanan, Zurab Baratashvili

Abstract:

Small and medium-sized businesses receive over 160 billion invoices every year. Since these documents exhibit many subtle differences in layout and text, extracting structured fields such as sender name, amount, and VAT rate from them automatically is an open research question. In this paper, existing work in template-based document extraction is extended, and a system is devised that is able to reliably extract all required fields for up to 70% of all documents in the data set, more than any other previously reported method. The approaches are described for 1) detecting through visual features which template a given document belongs to, 2) automatically generating extraction rules for a given new template by composing regular expressions from multiple components, and 3) computing confidence scores that indicate the accuracy of the automatic extractions. The system can generate templates with as little as one training sample and only requires the ground truth field values instead of detailed annotations such as bounding boxes that are hard to obtain. The system is deployed and used inside a commercial accounting software.

Keywords: data mining, information retrieval, business, feature extraction, layout, business data processing, document handling, end-user trained information extraction, document archiving, scanned business documents, automated document processing, F1-measure, commercial accounting software

Procedia PDF Downloads 130