PLANT DISEASE DETECTION USING DEEP LEARNING by Amrita, Sanjay Kumar Nayak, Rajiv Kumar, Sakshi Tomar

“…Based on the testing results, the VGG16 model beats other architectures in terms of training accuracy of 97.73% with validation accuracy of 88.82%.…”
Get full text

Scalable machine learning framework for predicting critical links in urban networks by Nourhan Bachir, Chamseddine Zaki, Hassan Harb, Roland Billen

“…Existing methods, such as simulation-based approaches, are computationally expensive and often impractical for large-scale networks. …”
Get full text

Generative Adversarial Networks In Object Detection: A Systematic Literature Review by Anis Farihan Mat Raffei, Sinung Suakanto, Faqih Hamami, Mohd Arfian Ismail, Ferda Ernawan

“…Despite this progress, persistent challenges including computational cost and training stability remain. By critically analyzing these advancements and limitations, this paper provides crucial insights into the current state and potential future developments of GAN-based object detection systems.…”
Get full text

Detecting muscle fatigue during lower limb isometric contractions tasks: a machine learning approach by Jiaqi Sun, Cheng Zhang, Guangda Liu, Wenjie Cui, Yubing Sun, Chunyan Zhang

“…Time-domain, frequency-domain, time-frequency domain, and nonlinear features associated with muscle fatigue during isometric contraction were analyzed through EMG signals. …”
Get full text

Deep Learning in Spinal Endoscopy: U-Net Models for Neural Tissue Detection by Hyung Rae Lee, Wounsuk Rhee, Sam Yeol Chang, Bong-Soon Chang, Hyoungmin Kim

“…Qualitative evaluations indicated the effective identification of neural tissue features. Our U-Net-based model robustly performed neural tissue segmentation, indicating its potential to support spine surgeons, especially those with less experience, and improve surgical outcomes in endoscopic procedures. …”
Get full text

Robust Road Surface Classification Using Time Series Augmented Intelligent Tire Sensor Data and 1-D CNN by Seokchan Kim, Yeong-Jae Kim, Dongwook Lee, Hanmin Lee

“…Moreover, a time series data augmentation method is applied to ensure that the learning network has the robustness to perform well under different tires and driving conditions than that in the training dataset. A road surface classification algorithm is trained using a dataset of accelerations measured on dry asphalt, wet asphalt, and basalt tile roads, and the performance of the trained algorithm is validated through test scenarios considering different tire conditions and vehicle types. …”
Get full text

ByteBait USB: a robust simulation toolkit for badUSB phishing campaign by Wenhao Li, Selvakumar Manickam, Yung-Wey Chong, Yongqing He, Ho Yean Li, Binyong Li

“…While enterprises have adopted phishing awareness training, there remains a significant gap in simulated BadUSB phishing campaigns. …”
Get full text

Reservoir water level prediction using combined CEEMDAN-FE and RUN-SVM-RBFNN machine learning algorithms by Lan-ting Zhou, Guan-lin Long, Can-can Hu, Kai Zhang

“…This study proposed a method for reservoir water level prediction based on CEEMDAN-FE and RUN-SVM-RBFNN algorithms. …”
Get full text

A mechanics-informed machine learning framework for traumatic brain injury prediction in police and forensic investigations by Yuyang Wei, Jeremy Oldroyd, Phoebe Haste, Jayaratnam Jayamohan, Michael Jones, Nicholas Casey, Jose-Maria Peña, Sonya Baylis, Stan Gilmour, Antoine Jérusalem

“…To this end, we propose here a numerical framework-based solution coupling biomechanical simulations of a variety of injurious impacts to machine learning training of police reports provided by the UK’s Thames Valley Police and the National Crime Agency’s National Injury Database. …”
Get full text

Participatory Mapping of Community Use Zone in Dena District Adjacent to Dena Preserved Area by Sayedeh Alemohammad, Ahmad Reza Yavari, Bahram Malek mohammadi, Esmaeil Salehi, Mohammad javad Amiri

“…The area-oriented approach is based on the science-based top-down land use planning experience and mapping with geographic tools has led to conflicts with Conservation which because of the ignorance of local communities. …”
Get full text

NetStart 2.0: prediction of eukaryotic translation initiation sites using a protein language model by Line Sandvad Nielsen, Anders Gorm Pedersen, Ole Winther, Henrik Nielsen

“…NetStart 2.0 was trained as a single model across multiple species, and despite the broad phylogenetic diversity represented in the training data, it consistently relied on features marking the transition from non-coding to coding regions. …”
Get full text

Explainable machine learning for predicting ICU mortality in myocardial infarction patients using pseudo-dynamic data by Munib Mesinovic, Peter Watkinson, Tingting Zhu

“…In this study, we use two retrospective cohorts extracted from two US-based ICU databases, eICU and MIMIC-IV, to develop an explainable pseudo-dynamic machine learning framework for mortality prediction in the ICU. …”
Get full text

Didactic potential of digital technologies in linguistic education of university students by Olga M. Osiyanova, Yulia S. Kondrashina

“…Subtitling helps understand the grammatical and pragmatic features of the language and develop auditive skills. …”
Get full text

A Deep Reinforcement Learning Framework for Adaptive Resiliency Enhancement in Smart Power Grids by Boyu Wang, Aliasghar Baziar, Mohammad Reza Askari

“…To overcome these limitations, we propose a deep reinforcement learning framework based on the Deep Deterministic Policy Gradient (DDPG) algorithm, optimized using the Root Mean Square Propagation (RMSprop) method for stable and efficient training. …”
Get full text

Development and validation of machine learning models for predicting extubation failure in patients undergoing cardiac surgery: a retrospective study by Xiaofeng Jiang, Wenyong Peng, Jianbo Xu, Yanhong Zhu

“…The most crucial predictor of extubation failure is the mean value of the anion gap in the 24 h before extubation. The other main features include ventilator parameters and blood gas indicators. …”
Get full text

Formation of the 32nd Guards Rifle Division and Its Participation in the Fighting in the Tuapse Direction in August 1942 by Sergey Kindyakov

“…Identification of the features of the formation of the 32nd Guards Rifle Division and the combat work of its units, taking into account the current operational situation and the specifics of the geographical conditions in the occupied area of defense. …”
Get full text

Protection of accounting information in the conditions of cyber security by S.F., І.M., O.O.

“…Groups of risks are given, based on the selection of risks for all components of the accounting process, which are inherent in electronic accounting information systems (risks associated with the collection and input of data into an automated system, risks associated with information processing and its storage on electronic media, risks associated with stage of generalization and transfer of information) and analyzed their features in order to find ways of minimization. …”
Get full text

Artificial Neural Networks Model for Photosynthetic Rate Prediction of Leaf Vegetable Crops under Normal and Nutrient-Stressed in Greenhouse by Yohanes Bayu Suharto, Herry Suhardiyanto, Anas Dinurroman Susila, Supriyanto

“…This paper introduces an ANN model featuring nine input variables, ten hidden layers, and a single output. …”
Get full text

Enhancing nursing education through e-portfolios: evaluating the impact on learning effectiveness, self-efficacy, and job satisfaction of NPGY trainees by Fang-Chun Wei, Li-Ju Kao, Chia-Ting Chang, Jui-Yuan Chung

“…Continuous usage and enhancement of e-portfolios are recommended to meet user needs and provide a supportive learning environment, especially during critical stages of training. Future research should explore strategies to optimize e-portfolio features to further improve professional development and satisfaction.…”
Get full text

Soft Skills Representation in English and Russian Songs by M. V. Petrova, S. V. Pristupa, G. A. Rozhkov, A. P. Tumanova

“…Vysotsky was considered primarily from the standpoint of linguistic material, the research methodology was based on the principles of linguistic text analysis, such as methods of component, cognitive and discourse analysis. …”
Get full text