Faidance Mashauri^1,2,*, Mokili Mbuluyo^1,3, Nsalambi Nkongolo^2,4

Revue Internationale de Géomatique, Vol.32, pp. 99-122, 2023, DOI:10.32604/rig.2023.044899

Abstract L’analyse et la quantification des caractéristiques hydro-morphométriques sont essentielles pour une meilleure gestion des ressources en eau et une planification plus efficace des projets hydroélectriques dans le bassin de la Tshopo. Malheureusement, peu d’études ont été réalisées pour évaluer ces caractéristiques à l’échelle de ce bassin. Notre approche méthodologique consiste à utiliser les outils d’analyse des logiciels Système d’Information Géographique (SIG) appliqués au Modèle Numérique de Terrain (MNT) dérivé de l’image Advanced Land Observing Satellite (ALOS) World 3D-30m. Cela nous a permis d’extraire automatiquement le réseau hydrographique et de générer les sous-bassins versants de la Tshopo. Les résultats de cette… More >

Derwin Suhartono^1,*, Alif Tri Handoyo¹, Franz Adeta Junior²

CMC-Computers, Materials & Continua, Vol.77, No.3, pp. 3637-3657, 2023, DOI:10.32604/cmc.2023.045301

Abstract Sarcasm detection in text data is an increasingly vital area of research due to the prevalence of sarcastic content in online communication. This study addresses challenges associated with small datasets and class imbalances in sarcasm detection by employing comprehensive data pre-processing and Generative Adversial Network (GAN) based augmentation on diverse datasets, including iSarcasm, SemEval-18, and Ghosh. This research offers a novel pipeline for augmenting sarcasm data with Reverse Generative Adversarial Network (RGAN). The proposed RGAN method works by inverting labels between original and synthetic data during the training process. This inversion of labels provides feedback to the generator for generating… More >

Jongwook Si¹, Sungyoung Kim^2,*

CMC-Computers, Materials & Continua, Vol.77, No.3, pp. 3119-3138, 2023, DOI:10.32604/cmc.2023.043797

Abstract The objective of style transfer is to maintain the content of an image while transferring the style of another image. However, conventional methods face challenges in preserving facial features, especially in Korean portraits where elements like the “Gat” (a traditional Korean hat) are prevalent. This paper proposes a deep learning network designed to perform style transfer that includes the “Gat” while preserving the identity of the face. Unlike traditional style transfer techniques, the proposed method aims to preserve the texture, attire, and the “Gat” in the style image by employing image sharpening and face landmark, with the GAN. The color,… More >

Faidance Mashauri^1,2,*, Mokili Mbuluyo^1,3, Nsalambi Nkongolo^2,4

Revue Internationale de Géomatique, Vol.32, pp. 79-98, 2023, DOI:10.32604/RIG.2023.044124

Abstract Les paramètres hydro-morphométriques les plus caractéristiques qui contrôlent l’écoulement des eaux du bassin versant de la Tshopo n’ont pas encore été déterminés. L’analyse de corrélation, la régression linéaire multiple et la classification ascendante hiérarchique ont été appliquées à l’ensemble des données afin d’identifier les variables les plus caractéristiques qui influencent considérablement la vitesse d’écoulement des eaux et regrouper les sous-bassins versants semblables physiquement. Les résultats obtenus mettent en évidence l’importance de la topographie sur l’écoulement des eaux. Trois variables topographiques, à savoir l’altitude médiane (H50), le dénivelé global (Dg) et le dénivelé spécifique (Ds), ont une influence significative (p-value ≤… More >

Hussein El Hage Hassan^1,*, Laurence Charbel², Ninon Blond³

Revue Internationale de Géomatique, Vol.32, pp. 53-78, 2023, DOI:10.32604/RIG.2023.043180

Abstract Le pourtour occidental du plateau du Jord Tannourine-Aaqoura (Liban) est une région montagnarde méditerranéenne qui réunit les conditions de l’érosion hydrique : pluie abondante, pente raide, couvert végétal naturel ravagé et sol sensible à la dégradation. Cependant les terrasses agricoles aménagées depuis des décennies demeurent une pratique robuste pour limiter le ruissellement et élargir la surface agricole utile. Afin d’évaluer l’érosion aréolaire et le rôle des pratiques antiérosives, la méthodologie adoptée repose sur l’équation universelle de l’USLE révisée (RUSLE). La combinaison de paramètres du modèle, dans un SIG, a permis de définir que l’érosion hydrique peut dépasser les 51 t/ha/an… More >

Jinxi Guo¹, Kai Chen^1,2, Jiehui Liu¹, Yuhao Ma², Jie Wu^2,*, Yaochun Wu², Xiaofeng Xue³, Jianshen Li¹

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.3, pp. 2619-2640, 2024, DOI:10.32604/cmes.2023.031360

Abstract Intelligent diagnosis driven by big data for mechanical fault is an important means to ensure the safe operation of equipment. In these methods, deep learning-based machinery fault diagnosis approaches have received increasing attention and achieved some results. It might lead to insufficient performance for using transfer learning alone and cause misclassification of target samples for domain bias when building deep models to learn domain-invariant features. To address the above problems, a deep discriminative adversarial domain adaptation neural network for the bearing fault diagnosis model is proposed (DDADAN). In this method, the raw vibration data are firstly converted into frequency domain… More >

Muwei Jian^1,2,*, Yue Jin¹, Hui Yu³

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.3, pp. 3051-3063, 2024, DOI:10.32604/cmes.2023.030236

Abstract Universal lesion detection (ULD) methods for computed tomography (CT) images play a vital role in the modern clinical medicine and intelligent automation. It is well known that single 2D CT slices lack spatial-temporal characteristics and contextual information compared to 3D CT blocks. However, 3D CT blocks necessitate significantly higher hardware resources during the learning phase. Therefore, efficiently exploiting temporal correlation and spatial-temporal features of 2D CT slices is crucial for ULD tasks. In this paper, we propose a ULD network with the enhanced temporal correlation for this purpose, named TCE-Net. The designed TCE module is applied to enrich the discriminate… More >

Anwar Ullah¹, Xinguo Yu^1,*, Muhammad Numan²

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 2359-2383, 2023, DOI:10.32604/cmc.2023.041219

Abstract Generating realistic and synthetic video from text is a highly challenging task due to the multitude of issues involved, including digit deformation, noise interference between frames, blurred output, and the need for temporal coherence across frames. In this paper, we propose a novel approach for generating coherent videos of moving digits from textual input using a Deep Deconvolutional Generative Adversarial Network (DD-GAN). The DD-GAN comprises a Deep Deconvolutional Neural Network (DDNN) as a Generator (G) and a modified Deep Convolutional Neural Network (DCNN) as a Discriminator (D) to ensure temporal coherence between adjacent frames. The proposed research involves several steps.… More >

Jebran Khan¹, Kashif Ahmad², Kyung-Ah Sohn^1,3,*

Computer Systems Science and Engineering, Vol.47, No.3, pp. 2869-2894, 2023, DOI:10.32604/csse.2023.040159

Abstract In recent years, the growing popularity of social media platforms has led to several interesting natural language processing (NLP) applications. However, these social media-based NLP applications are subject to different types of adversarial attacks due to the vulnerabilities of machine learning (ML) and NLP techniques. This work presents a new low-level adversarial attack recipe inspired by textual variations in online social media communication. These variations are generated to convey the message using out-of-vocabulary words based on visual and phonetic similarities of characters and words in the shortest possible form. The intuition of the proposed scheme is to generate adversarial examples… More >

Xi Zhao¹, Haizheng Yu^1,*, Hong Bian²

CMC-Computers, Materials & Continua, Vol.77, No.1, pp. 181-198, 2023, DOI:10.32604/cmc.2023.041479

Abstract In recent years, Pix2Pix, a model within the domain of GANs, has found widespread application in the field of image-to-image translation. However, traditional Pix2Pix models suffer from significant drawbacks in image generation, such as the loss of important information features during the encoding and decoding processes, as well as a lack of constraints during the training process. To address these issues and improve the quality of Pix2Pix-generated images, this paper introduces two key enhancements. Firstly, to reduce information loss during encoding and decoding, we utilize the U-Net++ network as the generator for the Pix2Pix model, incorporating denser skip-connection to minimize… More >