A comparison between hybrid models for classifying Bangla isolated basic characters

Sharif, S. M. A.; Mahboob, Mahdin

doi:10.1109/icaee.2017.8255355

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, we resized all training and testing images to dimensions of 160 × 160 × 3 for the main branch and 20 × 20 for auxiliary branches. We applied various augmentation techniques to prevent overfitting [70,75] Save current weights of M as best weights: best_weights = M.get_weights() 19: Set weights of M to best weights: M.set_weights(best_weights) All models were trained for 50 epochs with a fixed batch size of 64. Our experiments were conducted on a machine equipped with an AMD Ryzen 3200G central processing unit (CPU) clocked at 3.6 GHz, 16 GB of random-access memory, and a Nvidia GeForce GTX 1060 (6 GB) graphical processing unit (GPU).…”

Section: Training Detailsmentioning

confidence: 99%

Securing Edge Devices: Malware Classification with Dual-Attention Deep Network

Alandjani

2024

Applied Sciences

View full text Add to dashboard Cite

Detecting malware is a crucial defense mechanism against potential cyber-attacks. However, current methods illustrate significant limitations in achieving high performance while maintaining faster inference on edge devices. This study proposes a novel deep network with dual-attention feature refinement on a two-branch deep network to learn real-time malware detection on edge platforms. The proposed method introduces lightweight spatial-asymmetric attention for refining the extracted features of its backbone and multi-head attention to correlate learned features from the network branches. The experimental results show that the proposed method can significantly outperform existing methods in quantitative evaluation. In addition, this study also illustrates the practicability of a lightweight deep network on edge devices by optimizing and deploying the model directly on the actual edge hardware. The proposed optimization strategy achieves a frame rate of over 545 per second on low-power edge devices.

show abstract

Section: Training Detailsmentioning

confidence: 99%

Securing Edge Devices: Malware Classification with Dual-Attention Deep Network

Alandjani

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…As depicted in the figure, the model not only rightly identifies the subject to be a boy, it also accurately describes what the subject is wearing ( a bow tie ). While there has been a lot of recent interest in using machine learning on Bangla isolated characters [5], [6], [7], [8], there has been no significant work on generating Bangla image captions. Taking into account the present state and the challenges, this paper reports the development of "Chittron", an automatic image annotating system in Bangla.…”

Section: Introductionmentioning

confidence: 99%

Chittron: An Automatic Bangla Image Captioning System

Rahman

Mohammed

Mansoor

et al. 2019

Procedia Computer Science

View full text Add to dashboard Cite

Automatic image caption generation aims to produce an accurate description of an image in natural language automatically. However, Bangla, the fifth most widely spoken language in the world, is lagging considerably in the research and development of such domain. Besides, while there are many established data sets to related to image annotation in English, no such resource exists for Bangla yet. Hence, this paper outlines the development of "Chittron", an automatic image captioning system in Bangla. Moreover, to address the data set availability issue, a collection of 16, 000 Bangladeshi contextual images has been accumulated and manually annotated in Bangla. This data set is then used to train a model which integrates a pre-trained VGG16 image embedding model with stacked LSTM layers. The model is trained to predict the caption when the input is an image, one word at a time. The results show that the model has successfully been able to learn a working language model and to generate captions of images quite accurately in many cases. The results are evaluated mainly qualitatively. However, BLEU scores are also reported. It is expected that a better result can be obtained with a bigger and more varied data set.

show abstract