Search results for: embedding model

Authors: Ganfeng Yu, Yuefeng Ma, Shanliang Yang

Abstract:

The word discovery is a key problem in text information retrieval technology. Methods in new word discovery tend to be closely related to words because they generally obtain new word results by analyzing words. With the popularity of social networks, individual netizens and online self-media have generated various network texts for the convenience of online life, including network words that are far from standard Chinese expression. How detect network words is one of the important goals in the field of text information retrieval today. In this paper, we integrate the word embedding model and clustering methods to propose a network word discovery framework based on sentence semantic similarity (S³-NWD) to detect network words effectively from the corpus. This framework constructs sentence semantic vectors through a distributed representation model, uses the similarity of sentence semantic vectors to determine the semantic relationship between sentences, and finally realizes network word discovery by the meaning of semantic replacement between sentences. The experiment verifies that the framework not only completes the rapid discovery of network words but also realizes the standard word meaning of the discovery of network words, which reflects the effectiveness of our work.

Keywords: text information retrieval, natural language processing, new word discovery, information extraction

Procedia PDF Downloads 100

Authors: Ebipatei Victoria Tunyan, T. A. Cao, Cheol Young Ock

Abstract:

Detecting subjectively biased statements is a vital task. This is because this kind of bias, when present in the text or other forms of information dissemination media such as news, social media, scientific texts, and encyclopedias, can weaken trust in the information and stir conflicts amongst consumers. Subjective bias detection is also critical for many Natural Language Processing (NLP) tasks like sentiment analysis, opinion identification, and bias neutralization. Having a system that can adequately detect subjectivity in text will boost research in the above-mentioned areas significantly. It can also come in handy for platforms like Wikipedia, where the use of neutral language is of importance. The goal of this work is to identify the subjectively biased language in text on a sentence level. With machine learning, we can solve complex AI problems, making it a good fit for the problem of subjective bias detection. A key step in this approach is to train a classifier based on BERT (Bidirectional Encoder Representations from Transformers) as upstream model. BERT by itself can be used as a classifier; however, in this study, we use BERT as data preprocessor as well as an embedding generator for a Bi-LSTM (Bidirectional Long Short-Term Memory) network incorporated with attention mechanism. This approach produces a deeper and better classifier. We evaluate the effectiveness of our model using the Wiki Neutrality Corpus (WNC), which was compiled from Wikipedia edits that removed various biased instances from sentences as a benchmark dataset, with which we also compare our model to existing approaches. Experimental analysis indicates an improved performance, as our model achieved state-of-the-art accuracy in detecting subjective bias. This study focuses on the English language, but the model can be fine-tuned to accommodate other languages.

Keywords: subjective bias detection, machine learning, BERT–BiLSTM–Attention, text classification, natural language processing

Procedia PDF Downloads 131

Authors: Walid Moudani, Ahmad Shahin

Abstract:

This research presents a study to handle the recruitment services system. It aims to enhance a business intelligence system by embedding data mining in its core engine and to facilitate the link between job searchers and recruiters companies. The purpose of this study is to present an intelligent management system for supporting recruitment services based on data mining methods. It consists to apply segmentation on the extracted job postings offered by the different recruiters. The details of the job postings are associated to a set of relevant features that are extracted from the web and which are based on critical criterion in order to define consistent clusters. Thereafter, we assign the job searchers to the best cluster while providing a ranking according to the job postings of the selected cluster. The performance of the proposed model used is analyzed, based on a real case study, with the clustered job postings dataset and classified job searchers dataset by using some metrics.

Keywords: job postings, job searchers, clustering, genetic algorithms, business intelligence

Procedia PDF Downloads 329

Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang

Abstract:

Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.

Keywords: t-SNE, UMAP, fashion MNIST, neural networks

Procedia PDF Downloads 199

Authors: Entisar A. Elgmati

Abstract:

Recurrent infant diarrhea is studied using daily data collected in Salvador, Brazil over one year and three months. A logistic regression model is fitted instead of Aalen's additive model using the same covariates that were used in the analysis with the additive model. The model gives reasonably similar results to that using additive regression model. In addition, the problem with the estimated conditional probabilities not being constrained between zero and one in additive model is solved here. Also martingale residuals that have been used to judge the goodness of fit for the additive model are shown to be useful for judging the goodness of fit of the logistic model.

Keywords: additive model, cumulative probabilities, infant diarrhoea, recurrent event

Procedia PDF Downloads 636

Authors: Hamza A. A. Al-Sewadi, Adnan H. M. Al-Helali, Samaa A. K. Khamis

Abstract:

Ownership proofs of multimedia such as text, image, audio or video files can be achieved by the burial of watermark is them. It is achieved by introducing modifications into these files that are imperceptible to the human senses but easily recoverable by a computer program. These modifications would be in the time domain or frequency domain or both. This paper presents a procedure for watermarking by mixing amplitude modulation with frequency transformation histogram; namely a specific value is used to modulate the intensity component Y of the YIQ components of the carrier image. This scheme is referred to as histogram embedding technique (HET). Results comparison with those of other techniques such as discrete wavelet transform (DWT), discrete cosine transform (DCT) and singular value decomposition (SVD) have shown an enhance efficiency in terms of ease and performance. It has manifested a good degree of robustness against various environment effects such as resizing, rotation and different kinds of noise. This method would prove very useful technique for copyright protection and ownership judgment.

Keywords: authentication, copyright protection, information hiding, ownership, watermarking

Procedia PDF Downloads 565

Authors: Hamza A. Ali, Adnan H. M. Al-Helali

Abstract:

Generally, a watermark is information that identifies the ownership of multimedia (text, image, audio or video files). It is achieved by introducing modifications into these files that are imperceptible to the human senses but easily recoverable by a computer program. These modifications are done according to a secret key in a descriptive model that would be either in the time domain or frequency domain or both. This paper presents a procedure for watermarking by mixing amplitude modulation with frequency transformation histogram; namely a specific value is used to modulate the intensity component Y of the YIQ components of the carrier image. This scheme is referred to as histogram embedding technique (HET). Results comparison with those of other techniques such as discrete wavelet transform (DWT), discrete cosine transform (DCT) and singular value decomposition (SVD) have shown an enhance efficiency in terms of ease and performance. It has manifested a good degree of robustness against various environment effects such as resizing, rotation and different kinds of noise. This method would prove very useful technique for copyright protection and ownership judgment.

Keywords: watermarking, ownership, copyright protection, steganography, information hiding, authentication

Procedia PDF Downloads 368

Authors: Haodong Huang, Zida Zhao, Shilong Sun, Chiyao Li, Wenfu Xu

Abstract:

The control methods for legged robots based on deep reinforcement learning have seen widespread application; however, the inherent black-box nature of neural networks presents challenges in understanding the decision-making motives of the robots. To address this issue, we propose a fully interpretable deep reinforcement learning training method to elucidate the underlying principles of legged robot motion. We incorporate the dynamics of legged robots into the policy, where observations serve as inputs and actions as outputs of the dynamics model. By embedding the dynamics equations within the multi-layer perceptron (MLP) computation process and making the parameters trainable, we enhance interpretability. Additionally, Bayesian optimization is introduced to train these parameters. We validate the proposed fully interpretable motion control algorithm on a legged robot, opening new research avenues for motion control and learning algorithms for legged robots within the deep learning framework.

Keywords: deep reinforcement learning, interpretation, motion control, legged robots

Procedia PDF Downloads 23

Authors: Fabio T. Costa, Sergio E. Moya, Marcelo H. Sousa

Abstract:

Nanocomposites designed by embedding magnetic nanoparticles into a polymeric matrix stand out as ideal magnetic-hybrid and magneto-responsive materials as sorbents for removal of pollutants in environmental applications. Covalent coupling is often desired for the immobilization of species on these nanocomposites, in order to keep them permanently bounded, not desorbing or leaching over time. Moreover, unwanted adsorbates can be separated by successive washes/magnetic separations, and it is also possible to recover the adsorbate covalently bound to the nanocomposite surface through detaching/cleavage protocols. Thus, in this work, we describe the preparation and characterization of highly-magnetizable chloromethylated polystyrene-based nanocomposite beads for selective covalent coupling in environmental applications. For synthesis optimization, acid resistant core-shelled maghemite (γ-Fe₂O₃) nanoparticles were coated with oleate molecules and directly incorporated into the organic medium during a suspension polymerization process. Moreover, the cross-linking agent ethylene glycol dimethacrylate (EGDMA) was utilized for co-polymerization with the 4-vinyl benzyl chloride (VBC) to increase the resistance of microbeads against leaching. After characterizing samples with XRD, ICP-OES, TGA, optical, SEM and TEM microscopes, a magnetic composite consisting of ~500 nm-sized cross-linked polymeric microspheres embedding ~8 nm γ-Fe₂O₃ nanoparticles was verified. This nanocomposite showed large room temperature magnetization (~24 emu/g) due to the high content in maghemite (~45 wt%) and resistance against leaching even in acidic media. Moreover, the presence of superficial chloromethyl groups, probed by FTIR and XPS spectroscopies and confirmed by an amination test can selectively adsorb molecules through the covalent coupling and be used in molecular separations as shown for the selective removal of 4-aminobenzoic acid from a mixture with benzoic acid.

Keywords: nanocomposite, magnetic nanoparticle, covalent separation, pollutant removal

Procedia PDF Downloads 112

Authors: Mohammed Jamal Al-Mansor, Kok Beng Gan

Abstract:

This paper develops an optimized embedding of payload in medical image by using genetic optimization. The goal is to preserve region of interest from being distorted because of the watermark. By using this developed system there is no need of manual defining of region of interest through experts as the system will apply the genetic optimization to select the parts of image that can carry the watermark with guaranteeing less distortion. The experimental results assure that genetic based optimization is useful for performing steganography with less mean square error percentage.

Keywords: AES, DWT, genetic algorithm, watermarking

Procedia PDF Downloads 411

Authors: Mechlouch Ridha Fethi

Abstract:

This paper presents a recent mathematical model in political sciences concerning democracy. The model is represented by a logarithmic equation linking the Relative Index of Democracy (RID) to Participation Ratio (PR). Firstly the meanings of the different parameters of the model were presented; and the variation curve of the RID according to PR with different critical areas was discussed. Secondly, the model was applied to a virtual group where we show that the model can be applied depending on the gender. Thirdly, it was observed that the model can be extended to different language models of democracy and that little use to assess the state of democracy for some International organizations like UNO.

Keywords: democracy, mathematic, modelization, quantification

Procedia PDF Downloads 369

Authors: R. Kiruthika, A. Kannan

Abstract:

Steganography is the problem of hiding secret messages in 'innocent – looking' public communication so that the presence of the secret message cannot be detected. This paper introduces a steganographic security in terms of computational in-distinguishability from a channel of probability distributions on cover messages. This method first splits the cover image into two separate blocks using Douglas – Peucker algorithm. The text message and the image will be hided in the Least Significant Bit (LSB) of the cover image.

Keywords: steganography, lsb, embedding, Douglas-Peucker algorithm

Procedia PDF Downloads 364

Authors: Le Kang

Abstract:

On the research question of 'how to achieve USR', this contribution reflects the concept of university social responsibility, identify three achievement models of USR as the society - diversified model, the university-cooperation model, the government - compound model, also conduct a case study to explore characteristics of Chinese achievement model of USR. The contribution concludes with discussion of how the university, government and society balance demands and roles, make necessarily strategic adjustment and innovative approach to repair the shortcomings of each achievement model.

Keywords: modern university, USR, achievement model, compound model

Procedia PDF Downloads 759

Authors: M. Naidoo

Abstract:

Artificial intelligence often requires large amounts of good quality data. Within important fields, such as healthcare, the training of AI systems predominately relies on health and personal data; however, the usage of this data is complicated by various layers of law and ethics that seek to protect individuals’ privacy rights. This research seeks to establish the challenges AI and data sciences pose to (i) informational rights, (ii) privacy rights, and (iii) data protection. To solve some of the issues presented, various methods are suggested, such as embedding values in technological development, proper balancing of rights and interests, and others.

Keywords: artificial intelligence, data science, law, policy

Procedia PDF Downloads 106

Authors: Zhou Jianhong

Abstract:

Model averaging is a desirable approach to deal with model uncertainty, which, however, has rarely been explored for Poisson regression. In this paper, we propose a model averaging procedure based on an unbiased estimator of the expected Kullback-Leibler distance for the Poisson regression. Simulation study shows that the proposed model average estimator outperforms some other commonly used model selection and model average estimators in some situations. Our proposed methods are further applied to a real data example and the advantage of this method is demonstrated again.

Keywords: model averaging, poission regression, Kullback-Leibler distance, statistics

Procedia PDF Downloads 520

Authors: Wagneur Edouard

Abstract:

Tropical algebra is the algebra constructed over an idempotent semifield S. We show here that every m-dimensional tropical module M over S with strongly independent basis can be embedded into Sm, and provide an algebraic invariant -the Γ-matrix of M- which characterises the isomorphy class of M. The strong independence condition also yields a significant improvement to the Whitney embedding for tropical torsion modules published earlier We also show that the strong independence of the basis of M is equivalent to the unique representation of elements of M. Numerous examples illustrate our results.

Keywords: classification, idempotent semi-modules, strong independence, tropical algebra

Procedia PDF Downloads 371

Authors: Eduardo Álvarez, Gerardo Quiroga, Jorge Orozco, Gabriel Chavira

Abstract:

AmI proposes a new way of thinking about computers, which follows the ideas of the Ubiquitous Computing vision of Mark Weiser. In these, there is what is known as a Disappearing Computer Initiative, with users immersed in intelligent environments. Hence, technologies need to be adapted so that they are capable of replacing the traditional inputs to the system by embedding these in every-day artifacts. In this work, we present an approach, which uses Radiofrequency Identification (RFID) and Near Field Communication (NFC) technologies. In the latter, a new form of interaction appears by contact. We compare both technologies by analyzing their requirements and advantages. In addition, we propose using a combination of RFID and NFC.

Keywords: touching interaction, ambient intelligence, ubiquitous computing, interaction, NFC and RFID

Procedia PDF Downloads 508

Authors: Yuntao Liu, Lei Wang, Haoran Xia

Abstract:

Machine learning has shown extensive applications in the development of classification models for autism spectrum disorder (ASD) using neural image data. This paper proposes a fusion multi-modal classification network based on a graph neural network. First, the brain is segmented into 116 regions of interest using a medical segmentation template (AAL, Anatomical Automatic Labeling). The image features of sMRI and the signal features of fMRI are extracted, which build the node and edge embedding representations of the brain map. Then, we construct a dynamically updated brain map neural network and propose a method based on a dynamic brain map adjacency matrix update mechanism and learnable graph to further improve the accuracy of autism diagnosis and recognition results. Based on the Autism Brain Imaging Data Exchange I dataset(ABIDE I), we reached a prediction accuracy of 74% between ASD and TD subjects. Besides, to study the biomarkers that can help doctors analyze diseases and interpretability, we used the features by extracting the top five maximum and minimum ROI weights. This work provides a meaningful way for brain disorder identification.

Keywords: autism spectrum disorder, brain map, supervised machine learning, graph network, multimodal data, model interpretability

Procedia PDF Downloads 71

Authors: L. Madouni, M. Ould Ouali, N. E. Hannachi

Abstract:

Two constitutive models for concrete are available in ABAQUS/Explicit, the Brittle Cracking Model and the Concrete Damaged Plasticity Model, and their suitability and limitations are well known. The aim of the present paper is to implement a damage-friction concrete constitutive model and to evaluate the performance of this model by comparing the predicted response with experimental data. The constitutive formulation of this material model is reviewed. In order to have consistent results, the parameter identification and calibration for the model have been performed. Several numerical simulations are presented in this paper, whose results allow for validating the capability of the proposed model for reproducing the typical nonlinear performances of concrete structures under different monotonic and cyclic load conditions. The results of the evaluation will be used for recommendations concerning the application and further improvements of the investigated model.

Keywords: Abaqus, concrete, constitutive model, numerical simulation

Procedia PDF Downloads 365

Authors: Ammarah Irum, Muhammad Ali Tahir

Abstract:

Document-level sentiment analysis in Urdu is a challenging Natural Language Processing (NLP) task due to the difficulty of working with lengthy texts in a language with constrained resources. Deep learning models, which are complex neural network architectures, are well-suited to text-based applications in addition to data formats like audio, image, and video. To investigate the potential of deep learning for Urdu sentiment analysis, we implemented five different deep learning models, including Bidirectional Long Short Term Memory (BiLSTM), Convolutional Neural Network (CNN), Convolutional Neural Network with Bidirectional Long Short Term Memory (CNN-BiLSTM), and Bidirectional Encoder Representation from Transformer (BERT). In this study, we developed a hybrid deep learning model called BiLSTM-Single Layer Multi Filter Convolutional Neural Network (BiLSTM-SLMFCNN) by fusing BiLSTM and CNN architecture. The proposed and baseline techniques are applied on Urdu Customer Support data set and IMDB Urdu movie review data set by using pre-trained Urdu word embedding that are suitable for sentiment analysis at the document level. Results of these techniques are evaluated and our proposed model outperforms all other deep learning techniques for Urdu sentiment analysis. BiLSTM-SLMFCNN outperformed the baseline deep learning models and achieved 83%, 79%, 83% and 94% accuracy on small, medium and large sized IMDB Urdu movie review data set and Urdu Customer Support data set respectively.

Keywords: urdu sentiment analysis, deep learning, natural language processing, opinion mining, low-resource language

Procedia PDF Downloads 73

Authors: Arslan Murtaza

Abstract:

Model Driven Architecture (MDA) is technique presented by OMG (Object Management Group) for software development in which different models are proposed and converted them into code. The main plan is to identify task by using PIM (Platform Independent Model) and transform it into PSM (Platform Specific Model) and then converted into code. In this review paper describes some challenges and issues that are faced in MDA, type and transformation of models (e.g. CIM, PIM and PSM), and evaluation of MDA-based methodologies.

Keywords: OMG, model driven rrchitecture (MDA), computation independent model (CIM), platform independent model (PIM), platform specific model(PSM), MDA-based methodologies

Procedia PDF Downloads 459

Authors: Maria Krambia-Kapardis, Andreas Kapardis

Abstract:

The relevant literature has been inundated with arguments for ethics, moral values, honesty, resilience, trust in leadership as well as responsible leadership. In many countries around the globe, and as shown by some recent reports, many political leaders are not role models and do not show best practices by being ethical, responsible, compassionate, and resilient. Journalists, whistleblowers, WikiLeaks, Al Jazeera, and the International Consortium of Investigative Journalists (ICIJ) have been brought out from the shadow of political leaders who lack the virtues/attributes outlined above by the UN Global Compact. A number of political leaders who lack ethical and responsible leadership skills will continue to find loopholes to enrich themselves and their close friends and relatives. Some researchers use the Millon Inventory of Diagnostic; however, this test, while it provides helpful and useful insights into the personality of a person who leads or inspire his/her people but does not show if that person is ethical, motivating, and empowers his people with trust and honesty. Thus, it is recommended that political leaders ought to undergo training that encompasses Aristotelian Ethics by embedding the appropriate values and behaviours in their strategies, policies, and decisions, enhancing the change factors that will help in the implementation of a more sustainable development model. Finally, there is a need to develop a pedagogy and a curriculum which enables the development of responsible political leaders.

Keywords: political leaders, corruption, anti-corruption, political corruption

Procedia PDF Downloads 75

Authors: Mohamed Rabhi, Kouider Halim Benrahou

Abstract:

The rheological properties of the carbonyl-methylcellulose (CMC), of different concentrations (25000, 50000, 60000, 80000 and 100000 ppm) and different temperatures were studied. We found that the rheological behavior of all CMC solutions presents a pseudo-plastic behavior, it follows the model of Ostwald-de Waele. The objective of this work is the modeling of flow by the CMC Cross model. The Cross model gives us the variation of the viscosity according to the shear rate. This model allowed us to adjust more clearly the rheological characteristics of CMC solutions. A comparison between the Cross model and the model of Ostwald was made. Cross the model fitting parameters were determined by a numerical simulation to make an approach between the experimental curve and those given by the two models. Our study has shown that the model of Cross, describes well the flow of "CMC" for low concentrations.

Keywords: CMC, rheological modeling, Ostwald model, cross model, viscosity

Procedia PDF Downloads 406

Authors: Viet-Hung Truong, Seung-Eock Kim

Abstract:

Rain–wind induced vibration of inclined cable is a special aerodynamic phenomenon because it is easily influenced by many factors, especially the distribution of rivulet and wind velocity. This paper proposes a new 3D model of inclined cable, based on single degree-of-freedom model. Aerodynamic forces are firstly established and verified with the existing results from a 2D model. The 3D model of inclined cable is developed. The 3D model is then applied to assess the effects of wind velocity distribution and the continuity of rivulets on the cable. Finally, an inclined cable model with small sag is investigated.

Keywords: 3D model, rain - wind induced vibration, rivulet, analytical model

Procedia PDF Downloads 490

Authors: Shaker Alsharif, Xavier Banquy

Abstract:

Controlled drug delivery technology represents one of the most rapidly advancing areas of science in which chemists and chemical engineers are contributing to human health care. Such delivery systems provide numerous advantages compared to conventional dosage forms including improved efficacy, and improved patient compliance and convenience. Such systems often use synthetic polymers as carriers for the drugs. As a result, treatments that would not otherwise be possible are now in conventional use. The role of bilayered vesicles as efficient carriers for drugs, vaccines, diagnostic agents and other bioactive agents have led to a rapid advancement in the liposomal drug delivery system. Moreover, the site avoidance and site-specific drug targeting therapy could be achieved by formulating a liposomal product, so as to reduce the cytotoxicity of many potent therapeutic agents. Our project focuses on developing and building hydrogel with nanoinclusion of liposomes loaded with active compounds such as proteins and growth factors able to release them in a controlled fashion. In order to achieve that, we synthesize several liposomes of two different phospholipids concentrations encapsulating model drug. Then, formulating hydrogel with specific mechanical properties embedding the liposomes to manage the release of active compound.

Keywords: controlled release, hydrogel, liposomes, active compounds

Procedia PDF Downloads 449

Authors: Go Bong Choi, Shin Je Lee, Sung Jin Yoo, Gibaek Lee, Jong Min Lee

Abstract:

In South Korea, it is difficult to obtain data for statistical pipe assessment. In this paper, to address these issues, we find that various statistical model presented before is how data mixed with noise and are whether apply in South Korea. Three major type of model is studied and if data is presented in the paper, we add noise to data, which affects how model response changes. Moreover, we generate data from model in paper and analyse effect of noise. From this we can find robustness and applicability in Korea of each model.

Keywords: proportional hazard model, survival model, water main deterioration, ecological sciences

Procedia PDF Downloads 744

Authors: Rahimah Saimin

Abstract:

Previous research has shown that young children can learn from educational television programmes, videos or other technological media. However, the blending of any of these with traditional printed-based text appears to be omitted. Repeated viewing is an important factor in children's ability to comprehend the content or plot. The present study combined videos with traditional printed-based text and required repeated viewing and is original and distinctive. The first study was a pilot study to explore whether the intervention is implementable in ordinary classrooms. The second study explored whether the curricular embedding is important or whether the video with curricular embedding is effective. The third study explored the effect of “dosage”, i.e. whether a longer/ more intense intervention has a proportionately greater effect on outcomes. Both measured outcomes (comprehension, word sounds, and early word recognition) and unmeasured outcomes (engagement to reading traditional printed-based texts or/and multimodal texts) were obtained from this study. Observation indicated degree of engagement in reading. The theoretical framework was multimodality theory combined with Piaget’s and Vygotsky’s learning theories. An experimental design was used with 4-5-year-old children in nursery schools and primary schools. Six links to video clips exploring non-fiction science content were provided to teachers. The first session is whole-class and subsequent sessions small-group. The teacher then engaged the children in dialogue using supplementary materials. About half of each class was selected randomly for pre-post assessments. Two assessments were used the British Picture Vocabulary Scale (BPVSIII) and the York Assessment of Reading for Comprehension (YARC): Early Reading. Different programme fidelity means were deployed- observations, teacher self-reports attendance logs and post-delivery interviews. Data collection is in progress and results will be available shortly. If this multiphase study show effectiveness in one or other application, then teachers will have other tools which they can use to enhance vocabulary, letter knowledge and word reading. This would be a valuable addition to their repertoire.

Keywords: language skills, literacy skills, multimodality, video

Procedia PDF Downloads 339

Authors: Majid Habib Khan, Jinwei Zhao, Xinhong Hei, Liu Jiedong, Rana Shahzad Noor, Muhammad Imran

Abstract:

Deep learning is increasingly employed in image classification, yet the scarcity and high cost of labeled data for training remain a challenge. Limited samples often lead to overfitting due to biased sample distribution. This paper introduces a dynamic distribution calibration method for few-shot learning. Initially, base and new class samples undergo normalization to mitigate disparate feature magnitudes. A pre-trained model then extracts feature vectors from both classes. The method dynamically selects distribution characteristics from base classes (both adjacent and remote) in the embedding space, using a threshold value approach for new class samples. Given the propensity of similar classes to share feature distributions like mean and variance, this research assumes a Gaussian distribution for feature vectors. Subsequently, distributional features of new class samples are calibrated using a corrected hyperparameter, derived from the distribution features of both adjacent and distant base classes. This calibration augments the new class sample set. The technique demonstrates significant improvements, with up to 4% accuracy gains in few-shot classification challenges, as evidenced by tests on miniImagenet and CUB datasets.

Keywords: deep learning, computer vision, image classification, few-shot learning, threshold

Procedia PDF Downloads 67

Authors: Shian Wan, Yi-Chang Wang, Yu-Chien Lin

Abstract:

This research discussed the various theories of service design, the importance of service design methodology, and the development of transformative service design framework. In this study, transformative service design is applied while building a new brand community service for women, children and infants retailing business. The goal is to enhance the brand recognition and customer loyalty, effectively increase the brand community engagement by embedding the brand community in social network and ultimately, strengthen the impact and the value of the company brand.

Keywords: service design, transformative service design, brand community, innovation

Procedia PDF Downloads 499

Authors: Leila Baghaarabani, Parvin Razzaghi, Mennatolla Magdy Mostafa, Ahmad Albaqsami, Al Warith Al Rushaidi, Masoud Al Rawahi

Abstract:

Predicting the interaction between drugs and their molecular targets is pivotal for advancing drug development processes. Due to the time and cost limitations, computational approaches have emerged as an effective approach to drug-target interaction (DTI) prediction. Most of the introduced computational based approaches utilize the drug molecule and protein sequence as input. This study does not only utilize these inputs, it also introduces a protein representation developed using a masked protein language model. In this representation, for every individual amino acid residue within the protein sequence, there exists a corresponding probability distribution that indicates the likelihood of each amino acid being present at that particular position. Then, the similarity between each pair of amino-acids is computed to create similarity matrix. To encode the knowledge of the similarity matrix, Bi-Level Routing Attention (BiFormer) is utilized, which combines aspects of transformer-based models with protein sequence analysis and represents a significant advancement in the field of drug-protein interaction prediction. BiFormer has the ability to pinpoint the most effective regions of the protein sequence that are responsible for facilitating interactions between the protein and drugs, thereby enhancing the understanding of these critical interactions. Thus, it appears promising in its ability to capture the local structural relationship of the proteins by enhancing the understanding of how it contributes to drug protein interactions, thereby facilitating more accurate predictions. To evaluate the proposed method, it was tested on two widely recognized datasets: Davis and KIBA. A comprehensive series of experiments was conducted to illustrate its effectiveness in comparison to cuttingedge techniques.

Keywords: BiFormer, transformer, protein language processing, self-attention mechanism, binding affinity, drug target interaction, similarity matrix, protein masked representation, protein language model

Procedia PDF Downloads 15