Human resource management model based on multi-objective differential evolution and multi-skill scheduling by Yanxia Dong, Tiantian Lu

“…This study proposes an innovative human resource management model that integrates multi-objective differential evolution algorithm and learning curve model, and adopts a multidimensional chromosome encoding scheme for multi skill scheduling. The experimental results show that compared to the single skill model, this model can effectively shorten project duration, reduce human resource costs, and improve skill scores. …”
Get full text

Prediction of the Remaining Useful Life of Lithium–Ion Batteries Based on Mode Decomposition and ED-LSTM by Bingzeng Song, Guangzhao Yue, Dong Guo, Hanming Wu, Yonghai Sun, Yuhua Li, Bin Zhou

“…The LSTM neural network was used, the encoder–decoder (ED) structure was introduced, the multi-head attention (MHA) mechanism was used to construct a network model, and the particle swarm optimization (PSO) algorithm was used to optimize the model parameters. …”
Get full text

An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection by Faleh Alshameri, Ran Xia

Get full text

Evaluation of Machine Learning and Ensemble Learning Models for Classification Using Delivery Data by İrem Karakaya

“…Data preprocessing steps include handling missing values, encoding categorical variables, calculating geospatial distances, and normalizing data. …”
Get full text

Research on Flexible Job Shop Scheduling Method for Agricultural Equipment Considering Multi-Resource Constraints by Zhangliang Wei, Zipeng Yu, Renzhong Niu, Qilong Zhao, Zhigang Li

“…The experimental results demonstrate that MODGWO achieves better performance in identifying high-quality solutions compared to other competitive algorithms, especially for medium- and large-scale cases. …”
Get full text

Practical implementation of a type-2 fuzzy logic controller for steering a service robot by Suci Dwijayanti, Bhakti Y. Suprapto, Ichlasul A. Rizky

Get full text

CFRNet: Cross-Attention-Based Fusion and Refinement Network for Enhanced RGB-T Salient Object Detection by Biao Deng, Di Liu, Yang Cao, Hong Liu, Zhiguo Yan, Hu Chen

“…We developed an illumination prior-based coefficient predictor (MICP) to determine optimal interaction weights. We then designed a saliency-guided encoder (SG Encoder) to extract multi-scale thermal features incorporating saliency information. …”
Get full text

A text-speech multimodal Chinese named entity recognition model for crop diseases and pests by Ruilin Liu, Xuchao Guo, HongMei Zhu, Lu Wang

“…In the experiment studies, we compare with classical text-only models, lexicon-enhanced models, and multimodal models, our model achieves the optimal precision, recall, and F1 score of 91.32%, 93.05%, and 92.18%, respectively. …”
Get full text

Fault diagnosis of planetary gearboxes based on bispectral composite spectral features of torsional vibration modulation signals by ZHANG Yibao, HU Lei, XU Yuandong, SONG Xinkai

“…A new method for planetary gearbox fault diagnosis based on modulation signal bispectrum (MSB) analysis of torsional vibration signals was proposed.MethodsFirstly, the instantaneous speed signal was solved by the Hilbert transform method for the encoder signal. Secondly, the instantaneous speed signal was analyzed by MSB and the optimal carrier band was searched. …”
Get full text

GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration by Ting Liu, Yuan Liu

“…Additionally, two self-supervised tasks are designed for improved model accuracy and robustness. (3) Results: The fine-tuned model had comparatively optimal performance metrics with significant reductions in Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Error (RMSE). (4) Conclusions: Ultimately, the integration of this model into travel time prediction, based on two large-scale real-world trajectory datasets, demonstrates enhanced performance and computational efficiency.…”
Get full text

Convolutional neural network (CNN) configuration using a learning automaton model for neonatal brain image segmentation. by Iran Sarafraz, Hamed Agahi, Azar Mahmoodzadeh

“…Hence, it is necessary to determine the optimal structure and parameters for these models to achieve the desired results. …”
Get full text

Offline reinforcement learning combining generalized advantage estimation and modality decomposition interaction by Kaixin Jin, Lifang Wang, Xiwen Wang, Wei Guo, Qiang Han, Xiaoqing Yu

“…The decoder utilizes advantage values to optimize action prediction. We compared CGM with state-of-the-art baseline methods on the D4RL dataset. …”
Get full text

SGANet: A Siamese Geometry-Aware Network for Remote Sensing Change Detection by Jiangwei Chen, Sijun Dong, Xiaoliang Meng

“…Extensive experiments on the LEVIR-CD, WHU-CD, SYSU-CD, and S2Looking-CD datasets demonstrated that SGANet achieved substantial enhancements in F1-Score and intersection over union compared to benchmark methods that are in vogue. By integrating geometry priors and effective multimodal fusion mechanisms, SGANet promoted the development of geometry-aware change detection, further enhancing optimal performance.…”
Get full text

Deep Learning Ensemble Approach for Predicting Expected and Confidence Levels of Signal Phase and Timing Information at Actuated Traffic Signals by Seifeldeen Eteifa, Amr Shafik, Hoda Eldardiry, Hesham A. Rakha

“…For task two, the transformer encoder models provided an average mean absolute error (MAE) of 1.49 s, compared to 1.63 s for other models. …”
Get full text

Efficient attention vision transformers for monocular depth estimation on resource-limited hardware by Claudio Schiavella, Lorenzo Cirillo, Lorenzo Papa, Paolo Russo, Irene Amerini

“…More specifically, optimization has been applied not only to the entire network but also independently to the encoder and decoder to assess the model’s sensitivity to these modifications. …”
Get full text

Sentiment Analysis of X Users Toward Electric Motorcycles Using SVM and BERT Algorithms by Calvin Adiwinata, Afiyati Afiyati

“…This study presents a comparative analysis of Support Vector Machine (SVM) and Bidirectional Encoder Representations from Transformers (BERT) for sentiment analysis on electric motorcycles in Indonesia using data from the social media platform X, formerly known as Twitter. …”
Get full text

An Improved Low-Bit-Rate Image Compression Framework Based on Semantic-Aware Model and Neighborhood Attention by Chengbin Zeng, Liang Zhang

“…To address these limitations, we propose a robust image compression framework based on a semantic-aware model and a hyper-prior encoder with neighborhood attention. First, we utilize the encoder of the semantic-aware model to transform the input image into a latent space Z. …”
Get full text

A Novel Filtering Observer: A Cost-Effective Estimation Solution for Industrial PMSM Drives Using in-Motion Control Systems by Cagatay Dursun, Selin Ozcira Ozkilic

“…Based on the results from experiments, the FOBS was compared against traditional approaches and the performance of the motion control system was examined. …”
Get full text

H.264 rate-distortion model based joint source channel coding scheme over wireless channels by GAO Xue-juan, ZHUO Li, SHEN Lan-sun

“…A new rate-distortion model of H.264 encoder was firstly set up according to the rate distortion（R-D） charac-teristics of H.264.Then,the end-to-end video transmission distortion was analyzed and based on the R-D model of the H.264 encoder and the error combat characteristics of the Turbo code,an adaptive joint source channel coding（JSCC） over wireless channel was proposed,which could optimize the rate allocation of the available network bandwidth be-tween source coding and channel coding adaptively according to the actual condition of current wireless channel,so as to improve the robustness of the video transmission.The experiment results indicate that,compared with fix choice of channel coding rate,the proposed JSCC scheme is can greatly improve the transmission robustness and achieve better reconstructed video quality at the receiver.…”
Get full text

Aspect-Based Sentiment Analysis with LDA and IndoBERT Algorithm on Mental Health App: Riliv by Firda Ayu Dwi Aryanti, Ardytha Luthfiarta, Dennis Adiwinata Irwan Soeroso

“…The main results obtained were 1) Identified the sentiment that positive is highest in 2020, neutral is highest in 2020, and negative is highest in 2018. 2) Identified 4 main aspects of the Riliv application: Access Support, Counseling Services, Meditation Features, and User Interface with LDA. 3) The majority distribution was negative on User Interface, neutral on Counseling Services, and positive on Meditation Features. 4) The effectiveness of IndoBERT compared to the non-transformer baseline algorithm. 5) The most optimal results were obtained with 70% training, 10% validation, and 20% testing, resulting in 95% accuracy.…”
Get full text