Innovative EMD-Based Technique for Preventing Coffee Grinder Damage from Stones with FPGA Implementation by Chiang Liang Kok, Yuwei Dai, Yit Yan Koh, Maoyang Xiang, Tee Hui Teo

Get full text

Deep learning method for cucumber disease detection in complex environments for new agricultural productivity by Jun Liu, Xuewei Wang, Qian Chen, Peng Yan, Xin Liu

“…The model effectively handles symptom variability and complex detection scenarios, outperforming mainstream detection algorithms in accuracy, speed, and compactness, making it ideal for embedded agricultural applications.…”
Get full text

First passage processes in Queuing system MX/Gr/1 with service delay discipline by Lev Abolnikov, Jewgeni H. Dshalalow, Alexander M. Dukhovny

Get full text

CHERI-Crypt: Transparent Memory Encryption on Capability Architectures by Jennifer Jackson, Minmin Jiang, David Oswald

Get full text

dCTIDH: Fast & Deterministic CTIDH by Fabio Campos, Andreas Hellenbrand, Michael Meyer, Krijn Reijnders

Get full text

VeloFHE: GPU Acceleration for FHEW and TFHE Bootstrapping by Shiyu Shen, Hao Yang, Zhe Liu, Ying Liu, Xianhui Lu, Wangchen Dai, Lu Zhou, Yunlei Zhao, Ray C. C. Cheung

Get full text

Multi-Domain Features and Multi-Task Learning for Steady-State Visual Evoked Potential-Based Brain–Computer Interfaces by Yeou-Jiunn Chen, Shih-Chung Chen, Chung-Min Wu

“…Convolutional neural networks are separately used for time and frequency domain signals to extract the embedding features effectively. An element-wise addition operation and batch normalization are applied to fuse the time- and frequency-domain features. …”
Get full text

Sentiment Analysis on the PT Pertamina Corruption Case using IndoBERT and RCNN Methods by Wildan Jaya Kusoema, Ichsan Ibrahim

“…The dataset consists of 10,078 YouTube comments collected via the YouTube Data API, which were then preprocessed, automatically labeled using an Indonesian-language RoBERTa model, and balanced through class distribution techniques including undersampling and contextual embedding-based augmentation with IndoBERT. The model architecture integrates IndoBERT as a feature extractor and RCNN as the classifier, and was tested using various combinations of learning rates and batch sizes. …”
Get full text

Automatic Identification of Amharic Text Idiomatic Expressions Using a Deep Learning Approach by Habtamu Hunegnaw Limenih, Abebe Belay Adege, Abrham Yaregal Alene, Habtamu Tariku Demasu, Habtamu Molla Belachew

“…Among those experiments, the highest accuracy of 98.95% was attained using an 80:20 train-test split ratio, Adamax optimizer, 64 batch sizes, and a 0.001 learning rate by using Bi-LSTM with an attention layer and FastText word embedding model.…”
Get full text

Programmable Control of Droplets on Phase-Change Lubricant-Infused Surfaces Under Low Voltage by Lingjie Sun, Chunlei Gao, Wei Li

“…This study presents a bioinspired phase-change transparent flexible heater (PTFH) for programmable droplet manipulation under ultralow voltage. By embedding a self-junctioned copper nanowire network into paraffin-infused, porous PVDF-HFP gel matrices, the PTFH achieves rapid, non-contact, and reversible control of microdroplet mobility. …”
Get full text

Identification and authentication of additively manufactured components using their microstructural fingerprint by Kanhaiya Gupta, Konstantin Poka, Alexander Ulbricht, Anja Waske

“…This method is demonstrated on a batch of 24 parts manufactured with identical process parameters, proving capable of achieving unambiguous identification and authentication. …”
Get full text

Iron biochar synergy in aquatic systems through surface functionalities electron transfer and reactive species dynamics by Md Abdullah Al Masud, Hasara Samaraweera, Md. Mahmudul Hassan Mondol, Ardie Septian, Rakesh Kumar, Leigh G. Terry

“…Abstract The removal of organic pollutants from water by advanced oxidation has been successfully achieved using iron–biochar (Fe–BC)-based material. By embedding iron particles on the biochar, the resulting Fe–BC composite possesses enhanced surface functionalities that promote electron transfer and generate reactive oxygen species (ROS). …”
Get full text

A Deep Reinforcement Learning-Based Decision-Making Approach for Routing Problems by Dapeng Yan, Qingshu Guan, Bei Ou, Bowen Yan, Zheng Zhu, Hui Cao

“…The encoder incorporates a batch normalization fronting mechanism and a gate-like threshold block to enhance the quality of node embeddings and improve convergence speed. …”
Get full text

Tailoring the Luminescence Properties of Strontium Aluminate Phosphors for Unique Smartphone Detectable Optical Tags by Virginija Vitola, Milena Dile, Katrina Krizmane, Ernests Einbergs, Tinko Eftimov, Kristian Nikolov, Samia Fouzar

“…In this work, a precursor-driven tailoring of strontium aluminate phosphors doped with Eu²⁺ and Dy³⁺ to generate unique, batch-specific luminescent signatures suitable for smartphone-detectable anti-counterfeiting tags was developed. …”
Get full text

A Three-Stage Fusion Neural Network for Predicting the Risk of Root Fracture—A Pilot Study by Yung-Ming Kuo, Liang-Yin Kuo, Hsun-Yu Huang, Tsen-Yu Sung, Chun-Hung Yang, Wan-Ting Chang, Chien-Shun Lo

“…TSFNN combines numerical and categorical NN with batch normalization and embedding layer techniques and can produce the accuracy of 82.1% and a 19.1% improvement in F1-score. …”
Get full text

Immobilization and Monitoring of <i>Clostridium carboxidivorans</i> and <i>Clostridium kluyveri</i> in Synthetic Biofilms by Josha Herzog, Anna C. Jäkel, Friedrich C. Simmel, Dirk Weuster-Botz

“…The pH drop throughout the batch experiment likely contributed to incomplete substrate consumption, particularly for <i>C. kluyveri</i>, which thrives within a narrow pH range. …”
Get full text

Discretization-independent surrogate modeling of physical fields around variable geometries using coordinate-based networks by James Duvall, Karthik Duraisamy

“…DVH models have more trainable weights than a similar DV-MLP model, but an efficient batch-by-case training method allows DVH to be trained in a similar amount of time as DV-MLP. …”
Get full text

Selection of the kinematic scheme and determination of the main characteristics of the generator-drive unit from the axis of the wheelset of a three-element freight bogie by V. G. Kargin, S. N. Naumenko, V. V. Burov, I. N. Chuvashov, S. L. Samoshkin

“…Experimental samples of GPU with a two-stage drive passed preliminary and acceptance tests, according to the results of which it is recommended to make an installation batch. At present, two 60-foot fitting platforms equipped with an autonomous power supply system are being manufactured for the purpose of carrying out running tests.…”
Get full text

Skin-lesion segmentation using boundary-aware segmentation network and classification based on a mixture of convolutional and transformer neural networks by Javaria Amin, Marium Azhar, Habiba Arshad, Amad Zafar, Seong-Han Kim

“…This was designed on a selected number of layers and hyperparameters having two convolutions, two transformers, 64 projection dimensions, tokenizer, position embedding, sequence pooling, MLP, 64 batch size, two heads, 0.1 stochastic depth, 0.001 learning rate, 0.0001 weight decay, and 100 epochs.ResultsThe CCTM model was evaluated on six skin-lesion datasets, namely MED-NODE, PH2, ISIC-2019, ISIC-2020, HAM10000, and DermNet datasets, achieving over 98% accuracy.ConclusionThe proposed model holds significant potential in the clinical domain. …”
Get full text

BiLSTM-Based Parallel CNN Models With Attention and Ensemble Mechanism for Twitter Sentiment Analysis by Anas W. Abulfaraj

“…Our model uses Google&#x2019;s pre-trained Word2Vec embeddings to represent text as dense vectors. Three parallel CNN layers extract complex low-level features from embeddings after the embedding layer. …”
Get full text