Suchergebnisse - special issues on timely advances of deep learning with applications AND data-driven modeling~

Deep learning approaches and data augmentation for melanoma detection von Alzamel, Mai, Iliopoulos, Costas, Lim, Zara

“… Machine learning (ML) and deep learning (DL) techniques have shown a promising results in prediction and classification tasks …”
Volltext

Exploring distribution-based approaches for out-of-distribution detection in deep learning models von Carvalho, Thiago, Vellasco, Marley, Amaral, José Franco

“… Detecting unknown samples is a crucial task for deep learning applications, especially when considering open-set problems such as autonomous driving or disease classification …”
Volltext

Assessment and deployment of a LSTM-based virtual sensor in an industrial process control loop von González-Herbón, Raúl, González-Mateos, Guzmán, Rodríguez-Ossorio, José R., Prada, Miguel A., Morán, Antonio, Alonso, Serafín, Fuertes, Juan J., Domínguez, Manuel

“… Data-driven techniques are well-suited for this aim, given their capacity to model potentially complex industrial processes …”
Volltext

CM-MLP: hybrid convmixer-deep MLP architecture for enhanced identification of corn and apple leaf diseases von Li, Li-Hua, Tanone, Radius

“… We propose a novel hybrid ConvMixer and Deep MLP architecture called CM-MLP that combines the strengths of ConvMixer with various Deep Multi-layer Perceptron (MLP …”
Volltext

Researching the detection of continuous gravitational waves based on signal processing and ensemble learning von Pintelas, Emmanuel, Livieris, Ioannis E., Pintelas, Panagiotis

“… The detection of Gravitational Waves has introduced a new era for physics, astronomy, and astrophysics, unveiling new universe mysteries. Unfortunately, …”
Volltext

DACL+: domain-adapted contrastive learning for enhanced low-resource language representations in document clustering tasks von Zaikis, Dimitrios, Vlahavas, Ioannis

“… To this end, we introduce a domain-adapted contrastive learning approach for low-resource Greek document clustering …”
Volltext

Zero-day Android botnet detection using neural networks von Seraj, Saeed, Pimenidis, Elias, Trovati, Marcello, Polatidis, Nikolaos

“… Android devices have evolved to offer a diverse array of services, spanning applications related to banking, business, health, and entertainment …”
Volltext

Feature analysis and ensemble-based fault detection techniques for nonlinear systems von Bolboacă, Roland, Haller, Piroska, Genge, Bela

“… Machine learning approaches play a crucial role in nonlinear system modeling across diverse domains, finding applications in system monitoring, anomaly/fault detection, control, and various other areas …”
Volltext

Conditioned fully convolutional denoising autoencoder for multi-target NILM von García, Diego, Pérez, Daniel, Papapetrou, Panagiotis, Díaz, Ignacio, Cuadrado, Abel A., Enguita, José M., Domínguez, Manuel

“… Advances in data-driven models provide techniques like Non-Intrusive Load Monitoring (NILM), which estimates the energy demand of appliances from total consumption …”
Volltext

A fuzzy zeroing neural network and its application on dynamic Hill cipher von Jin, Jie, Lei, Xiaoyang, Chen, Chaoyang, Lu, Ming, Wu, Lianghong, Li, Zhijing

“… Cryptography is the core of information security, and the Hill cipher is one of the most important methods for cryptography. For the purpose of the improvement …”
Volltext

Memetic algorithm-based optimization of hybrid forecasting systems for multivariate time series von Padilha, Guilherme Afonso Galindo, Jung, Jason J., de Mattos Neto, Paulo S. G.

“… ), a hybrid system that combines linear statistical and deep learning (DL) models employing a novel memetic algorithm (MA …”
Volltext

A deep residual sequence autoencoder for future state estimation and aiding prognostics and diagnostics in machines: a case study of mechanical rolling elements von Ramadhan, Bwambale Rashid, Cahit, Perkgoz

“… However, the existing impediments known in RNNs that cause nonconvergence during training have created setbacks in their application in fields with data characterized by long dependent series …”
Volltext

A parameter-free nearest neighbor algorithm with reduced prediction time and improved performance through injected randomness von Singh, Manpreet, Chhabra, Jitender Kumar

“… K-nearest neighbor is considered in top machine learning algorithms because of its effectiveness in pattern classification and simple implementation …”
Volltext

A novel human action recognition using Grad-CAM visualization with gated recurrent units von Jayamohan, M., Yuvaraj, S.

“… Human action recognition is a vital aspect of computer vision, with applications ranging from security systems to interactive technology …”
Volltext

An explainable approach for prediction of remaining useful life in turbofan condition monitoring von Mansourvar, Zahra, Jahangoshai Rezaee, Mustafa, Eshkevari, Milad

“… In the second phase, among various machine learning and deep learning approaches, bidirectional long short-term memory (BiLSTM …”
Volltext

Residual connections improve click-through rate and conversion rate prediction performance von Biçici, Ergun

“… As the learning models become more complex with increasing depth, it has become increasingly challenging to predict CTR and CVR accurately …”
Volltext

Dual Bi-LSTM-GRU based stance detection in tweets ordered classes von Poonam, Km, Ramakrishnudu, Tene

“… There has been a tremendous increase in social media text-based opinions and reviews as a result of the quick development of social media. It emphasizes those …”
Volltext

Efficient deterministic renewable energy forecasting guided by multiple-location weather data von Symeonidis, Charalampos, Nikolaidis, Nikos

“… Electricity generated from renewable energy sources has been established as an efficient remedy for both energy shortages and the environmental pollution …”
Volltext

DAMNet: lightweight dual attention mixed network for efficient image deraining von Thatikonda, Ragini, Cheruku, Ramalingaswamy, Kodali, Prakash

“… A long-standing problem in computer vision (CV) is image deraining. Current deraining networks frequently fail to achieve a good balance between low system …”
Volltext

Novel wavelet-LSTM approach for time series prediction von Tamilselvi, C., Paul, Ranjit Kumar, Yeasin, Md, Paul, A. K.

“… ), followed by long short-term memory (LSTM) modeling on each denoised series. The hyperband search algorithm was employed to identify the optimal hyperparameter combination for each LSTM model, aiding in further fine-tuning the model …”
Volltext