Showing items 1 - 7 of 7

Your selections:

Pre-trained language models with limited data for intent classification

- Kasthuriarachchy, Buddhika, Chetty, Madhu, Karmakar, Gour, Walls, Darren

  • Authors: Kasthuriarachchy, Buddhika , Chetty, Madhu , Karmakar, Gour , Walls, Darren
  • Date: 2020
  • Type: Text , Conference proceedings , Conference paper
  • Relation: 2020 International Joint Conference on Neural Networks, IJCNN 2020
  • Full Text: false
  • Reviewed:
  • Description: Intent analysis is capturing the attention of both the industry and academia due to its commercial and noncommercial significance. The rapid growth of unstructured data of micro-blogging platforms, such as Twitter and Facebook, are amongst the important sources for intent analysis. However, the social media data are often noisy and diverse, thus making the task very challenging. Further, the intent analysis frequently suffers from lack of sufficient data because the labeled datasets are often manually annotated. Recently, BERT (Bidirectional Encoder Representation from Transformers), a state-of-the-art language representation model, has attracted attention for accurate language modelling. In this paper, we investigate the application of BERT for its suitability for intent analysis. We study the fine-tuning of the BERT model through inductive transfer learning and investigate methods to overcome the challenges due to limited data availability by proposing a novel semantic data augmentation approach. This technique generates synthetic sentences while preserving the label-compatibility using the semantic meaning of the sentences, to improve the intent classification accuracy. Thus, based on the considerations for finetuning and data augmentation, a systematic and novel step-bystep methodology is presented for applying the linguistic model BERT for intent classification with limited data available. Our results show that the pre-trained language can be effectively used with noisy social media data to achieve state-of-the-art accuracy in intent analysis under low labeled-data regime. Moreover, our results also confirm that the proposed text augmentation technique is effective in eliminating noisy synthetic sentences, thereby achieving further performance improvements. © 2020 IEEE.

Deep learning for combo object detection

- Zhao, Jing, Ardekani, Iman Tabatabaei, Pang, Shaoning

  • Authors: Zhao, Jing , Ardekani, Iman Tabatabaei , Pang, Shaoning
  • Date: 2019
  • Type: Text , Book chapter
  • Relation: Chapter 11 p. 125-137
  • Full Text: false
  • Reviewed:
  • Description: Convolutional neural networks (CNNs) have become the most vigorous technique for a variety of different tasks in computer vision, due to their proficiency in automatically learning high-level visual representations for images. In this paper, we investigate the effect of deep neural networks on the accuracy in combo object detection setting. The insufficiency of labeled data, coupled with the uncertainty of spacial distribution and dynamic changes in luminance, creates situations where combo object detection is far more challenging. Using transfer learning, we present a system for combo object detection based on a deep CNN called ComboNN. The proposed ComboNN is pre-trained on a huge auxiliary dataset ImageNet and fine-tuned on our small dataset. The use of data augmentation and regularization technique significantly reduces overfitting and improves the robustness of the ComboNN. Experimental results demonstrate that our system is capable of making reliable prediction on combo object detection in the real-world images, and achieves much better accuracy than the state-of-the-art CNNs.

Handwriting dynamics assessment using deep neural network for early identification of Parkinson's disease

- Kamran, Iqra, Naz, Saeeda, Razzak, Imran, Imran, Muhammad

  • Authors: Kamran, Iqra , Naz, Saeeda , Razzak, Imran , Imran, Muhammad
  • Date: 2021
  • Type: Text , Journal article
  • Relation: Future Generation Computer Systems Vol. 117, no. (2021), p. 234-244
  • Full Text: false
  • Reviewed:
  • Description: The etiology of Parkinson's disease (PD) remains unclear. Symptoms usually appear after approximately 70% of dopamine-producing cells have stopped working normally. PD cannot be cured, but its symptoms can be managed to delay its progression. Evidence suggests that early diagnosis is important in establishing an effective pathway for management of symptoms. However, PD diagnosis is challenging, particularly in the early stages of the disease. In this paper, we present a method for early diagnosis of PD using patients’ handwriting samples. To improve performance, we combined multiple PD handwriting datasets and used deep transfer learning-based algorithms to overcome the challenge of high variability in the handwritten material. Our approach achieved excellent PD identification performance with 99.22% accuracy on illuminated task of combined HandPD, NewHandPD and Parkinson's Drawing datasets, demonstrating the superiority of our approach over current state-of-the-art methods. © 2020 Elsevier B.V.

Automatic driver distraction detection using deep convolutional neural networks

- Hossain, Md Uzzol, Rahman, Md Ataur, Islam, Md Manowarul, Akhter, Arnisha, Uddin, Md Ashraf, Paul, Bikash

  • Authors: Hossain, Md Uzzol , Rahman, Md Ataur , Islam, Md Manowarul , Akhter, Arnisha , Uddin, Md Ashraf , Paul, Bikash
  • Date: 2022
  • Type: Text , Journal article
  • Relation: Intelligent Systems with Applications Vol. 14, no. (2022), p.
  • Full Text:
  • Reviewed:
  • Description: Recently, the number of road accidents has been increased worldwide due to the distraction of the drivers. This rapid road crush often leads to injuries, loss of properties, even deaths of the people. Therefore, it is essential to monitor and analyze the driver's behavior during the driving time to detect the distraction and mitigate the number of road accident. To detect various kinds of behavior like- using cell phone, talking to others, eating, sleeping or lack of concentration during driving; machine learning/deep learning can play significant role. However, this process may need high computational capacity to train the model by huge number of training dataset. In this paper, we made an effort to develop CNN based method to detect distracted driver and identify the cause of distractions like talking, sleeping or eating by means of face and hand localization. Four architectures namely CNN, VGG-16, ResNet50 and MobileNetV2 have been adopted for transfer learning. To verify the effectiveness, the proposed model is trained with thousands of images from a publicly available dataset containing ten different postures or conditions of a distracted driver and analyzed the results using various performance metrics. The performance results showed that the pre-trained MobileNetV2 model has the best classification efficiency. © 2022 The Author(s)

Few-shot image classification : current status and research trends

- Liu, Ying, Zhang, Hengchang, Zhang, Weidong, Lu, Guojun, Tian, Qi, Ling, Nam

  • Authors: Liu, Ying , Zhang, Hengchang , Zhang, Weidong , Lu, Guojun , Tian, Qi , Ling, Nam
  • Date: 2022
  • Type: Text , Journal article , Review
  • Relation: Electronics (Switzerland) Vol. 11, no. 11 (2022), p.
  • Full Text:
  • Reviewed:
  • Description: Conventional image classification methods usually require a large number of training samples for the training model. However, in practical scenarios, the amount of available sample data is often insufficient, which easily leads to overfitting in network construction. Few-shot learning provides an effective solution to this problem and has been a hot research topic. This paper provides an intensive survey on the state-of-the-art techniques in image classification based on few-shot learning. According to the different deep learning mechanisms, the existing algorithms are di-vided into four categories: transfer learning based, meta-learning based, data augmentation based, and multimodal based methods. Transfer learning based methods transfer useful prior knowledge from the source domain to the target domain. Meta-learning based methods employ past prior knowledge to guide the learning of new tasks. Data augmentation based methods expand the amount of sample data with auxiliary information. Multimodal based methods use the information of the auxiliary modal to facilitate the implementation of image classification tasks. This paper also summarizes the few-shot image datasets available in the literature, and experimental results tested by some representative algorithms are provided to compare their performance and analyze their pros and cons. In addition, the application of existing research outcomes on few-shot image classification in different practical fields are discussed. Finally, a few future research directions are iden-tified. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Single-session anodal tDCS with small-size stimulating electrodes over frontoparietal superficial sites does not affect motor sequence learning

- Hashemirad, Fahimeh, Fitzgerald, Paul, Zoghi, Maryam, Jaberzadeh, Shapour

  • Authors: Hashemirad, Fahimeh , Fitzgerald, Paul , Zoghi, Maryam , Jaberzadeh, Shapour
  • Date: 2017
  • Type: Text , Journal article
  • Relation: Frontiers in Human Neuroscience Vol. 11, no. (2017), p. 153-153
  • Full Text:
  • Reviewed:
  • Description: Due to the potential of anodal transcranial direct current stimulation (a-tDCS) for enhancement of fine sequenced movements and increasing interest in achieving high level of fine movements in the trained and untrained hands especially at initial stage of learning, we designed this study to investigate whether the application of single-session a-tDCS with small-size stimulating electrodes over FPN sites, such as dorsolateral prefrontal cortex (DLPFC), primary motor cortex (M1) or posterior parietal cortex (PPC) could enhance sequence learning with the trained hand and these effects are transferred into the untrained hand or not. A total of 51 right-handed healthy participants were randomly assigned to one of the four stimulation groups: a-tDCS of left M1, DLPFC, PPC, or sham. Stimulation was applied for 20 min during a sequential visual isometric pinch task (SVIPT). Eight blocks of training using SVIPT were completed with the right hand during stimulation. Two blocks of sequence training with each hand were performed by participants as assessment blocks at three time points: baseline, 15 min and one day following the intervention. Behavioral outcomes including movement time, error rate and skill were assessed in all assessment blocks across three time points. We also measured corticospinal excitability, short-interval intracortical inhibition, and intracortical facilitation using single- and paired-pulse transcranial magnetic stimulation. The results indicated that the behavioral outcomes were significantly improved with the right trained hand, but this learning effect was not modulated by a-tDCS with small-size stimulating electrodes over the FPN. Transfer of learning into the untrained hand was observed in all four groups for movement time but not for the error rate or skill. Our results suggest that sequential learning in SVIPT and its transfer into the untrained hand were not sensitive to a single-session a-tDCS with small-size stimulating electrodes over left M1, DLPFC or PPC in young healthy participants.

A nethack learning environment language wrapper for autonomous agents

- Goodger, Nikolaj, Vamplew, Peter, Foale, Cameron, Dazeley, Richard

  • Authors: Goodger, Nikolaj , Vamplew, Peter , Foale, Cameron , Dazeley, Richard
  • Date: 2023
  • Type: Text , Journal article
  • Relation: Journal of Open Research Software Vol. 11, no. (2023), p.
  • Full Text:
  • Reviewed:
  • Description: This paper describes a language wrapper for the NetHack Learning Environment (NLE) [1]. The wrapper replaces the non-language observations and actions with comparable language versions. The NLE offers a grand challenge for AI research while MiniHack [2] extends this potential to more specific and configurable tasks. By providing a language interface, we can enable further research on language agents and directly connect language models to a versatile environment. © 2023 The Author(s). This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. See http://creativecommons.org/licenses/by/4.0/.
  • 1