HPRT-DETR: A High-Precision Real-Time Object Detection Algorithm for Intelligent Driving Vehicles by Xiaona Song, Bin Fan, Haichao Liu, Lijun Wang, Jinxing Niu

“…We designed a Basic-iRMB-CGA (BIC) Block for a backbone network that efficiently extracts features and reduces the model’s parameters. …”
Get full text

Human Scene Understanding Mechanism-Based Image Captioning for Blind Assistance by Jong-Hoon Kim, Sung-Wook Park, Jun-Ho Huh, Se-Hoon Jung, Chun-Bo Sim

“…Second, the image features are encoded through the encoding block of ViT and input into the long short-term memory (LSTM) network to generate annotations for the image. …”
Get full text

CL-fusionBEV: 3D object detection method with camera-LiDAR fusion in Bird’s Eye View by Peicheng Shi, Zhiqiang Liu, Xinlong Dong, Aixi Yang

“…Subsequently, to achieve modal fusion within the BEV framework, we employ voxelization to convert the LiDAR point cloud into BEV space, thereby generating LiDAR BEV spatial features. Moreover, to integrate the BEV spatial features from both camera and LiDAR, we have developed a multi-modal cross-attention mechanism and an implicit multi-modal fusion network, designed to enhance the synergy and application of dual-modal data. …”
Get full text

DEVELOPMENT OF THE METHODS FOR RESOURCE REALLOCATION IN CLOUD COMPUTING SYSTEMS by Viacheslav Davydov, Daryna Hrebeniuk

“…The following tasks were solved in the article: development of an complex approach to manage resource reallocation in cloud systems, including decomposition of the cloud computing system into zones (based on the defining features of the resources provided in each zone), initial resource allocation (based on the hierarchy analysis method) and resources reallocation within cloud computing system (based on the developed method); development of a method for computing resources reallocation in cloud computing systems; evaluation of the effectiveness of the developed method. …”
Get full text

Research on 5G base station energy saving system based on DCNN-LSTM load prediction algorithm by Jianbin WANG, Shuchun WANG, Shangjin LIAO, Shuyuan SHI

“…With the rapid construction of the 5G wireless communication network, the energy consumption pressure of operators, and even the overall communication industry, is simultaneously highlighted.Achieving sustainable development of the industry through energy conservation and consumption reduction has become a new research direction for the current 5G network development.Taking the PRB rate as the load evaluation index, LSTM model was improved by using DCNN to extract the depth feature of the cell’s indicators.A set of DCNN-LSTM deep learning model that could predict the future value of PRB rate was proposed.On the basis of the improved algorithm, the network topology of the current 5G access network was optimized.An additional network element and its working system were designed.An intelligent energy-saving system, which ensured the network experience, of 5G base stations was realized.…”
Get full text

A Multimodel Decision Fusion Method Based on DCNN-IDST for Fault Diagnosis of Rolling Bearing by Weixiao Xu, Luyang Jing, Jiwen Tan, Lianchen Dou

“…The features extracted by DCNN adaptively are input into multiple network models for decision fusion. …”
Get full text

MaizeCODE reveals bi-directionally expressed enhancers that harbor molecular signatures of maize domestication by Jonathan Cahn, Michael Regulski, Jason Lynn, Evan Ernst, Cristiane de Santis Alves, Srividya Ramakrishnan, Kapeel Chougule, Sharon Wei, Zhenyuan Lu, Xiaosa Xu, Umamaheswari Ramu, Jorg Drenkow, Cassidy Danyko, Melissa Kramer, Arun Seetharam, Matthew B. Hufford, W. Richard McCombie, Doreen Ware, David Jackson, Michael C. Schatz, Thomas R. Gingeras, Robert A. Martienssen

Get full text

BED-YOLO: An Enhanced YOLOv10n-Based Tomato Leaf Disease Detection Algorithm by Qing Wang, Ning Yan, Yasen Qin, Xuedong Zhang, Xu Li

“…Second, we incorporated a Bidirectional Feature Pyramid Network (BiFPN) on top of the FPN + PAN structure to optimize feature fusion and improve the extraction of small disease regions, thereby enhancing the detection accuracy for small lesion targets. …”
Get full text

An improved beluga whale optimizer-Derived Adaptive multi-channel DeepLabv3+ for semantic segmentation of aerial images. by Anilkumar P, Venugopal P

“…General neural networks are used to improve categorization accuracy, but they also caused significant losses to target scale and spatial features, and the traditional common features fusion techniques can only resolve some of the issues. …”
Get full text

Deep Learning-Based Detection and Digital Twin Implementation of Beak Deformities in Caged Layer Chickens by Hengtai Li, Hongfei Chen, Jinlin Liu, Qiuhong Zhang, Tao Liu, Xinyu Zhang, Yuhua Li, Yan Qian, Xiuguo Zou

“…To address the interference caused by chicken cages, an Efficient Multi-Scale Attention (EMA) mechanism was integrated into the Spatial Pyramid Pooling-Fast (SPPF) module within the backbone network, significantly improving the model’s ability to capture fine-grained beak features. …”
Get full text

Development and validation of a deep learning-enhanced prediction model for the likelihood of pulmonary embolism by Yu Tian, Yu Tian, Jingjie Liu, Shan Wu, Yucong Zheng, Rongye Han, Qianhui Bao, Lei Li, Lei Li, Tao Yang

“…This study aims to develop a deep learning-based, precise, and efficient PE risk prediction model (PE-Mind) to overcome the limitations of current clinical tools and provide a more targeted risk evaluation solution.MethodsWe analyzed clinical data from patients by first simplifying and organizing the collected features. …”
Get full text

Enhancing LoRaWAN Localization in Industrial Environments: Merging Path-Loss Modeling, Extended Kalman Filtering and Map-Matching by Azin Moradbeikie, Ahmad Keshavarz, Sergio Ivan Lopes

“…Localization based on the signal features of the implemented network (such as RSSI) is becoming an appropriate substitute to solve its problems, such as low power consumption and cost. …”
Get full text

Rehabilitation and Motion Symmetry Analysis With a TACX Smart Cycling Trainer Using Computational Intelligence by Hana Charvatova, Daniel Martynek, Alexandra Molcanova, Ales Prochazka

“…The classification of spectral features evaluated separately for the left and right legs pointed the classification accuracy of 94.5% for accelerometric data and 99.1% for gyrometric data estimated by the use of the two layer neural network and the symmetry coefficient of 1.05 for the slope of 8%. …”
Get full text

A Review of Smart Contracts Applications in Various Industries: A Procurement Perspective by Yongshun Xu, Heap-Yih Chong, Ming Chi

“…Thus, this paper aims to address the gap with a mixed method of bibliometric analysis and systematic literature review. Based on the evaluation of 174 filtered publications, the review has analyzed the current development status of this research area with its distributions in years and journals, cooperation networks between authors, institutions, and countries, keywords cooccurrence network, and classifications of the application of smart contracts. …”
Get full text

Diaproteo: A supervised learning framework for early detection of diabetes mellitus based on proteomic profiles by Hamza Shahab Awan, Fahad Alturise, Tamim Alkhalifah, Yaser Daanial Khan

“…This study proposes novel approaches and evaluates prediction models with classic machine learning algorithms and cutting-edge deep learning architecture. …”
Get full text

Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative Study by Md. Wira Putra Dananjaya, Putu Gita Pujayanti

“…The models were evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R2) metrics. …”
Get full text

Improving prediction of solar radiation using Cheetah Optimizer and Random Forest. by Ibrahim Al-Shourbaji, Pramod H Kachare, Abdoh Jabbari, Raimund Kirner, Digambar Puri, Mostafa Mehanawi, Abdalla Alameen

“…The CO component plays a pivotal role in selecting the most informative features for hourly SR forecasting, subsequently serving as inputs to the RF model. …”
Get full text

Flexible Bioelectrodes-Integrated Miniaturized System for Unconstrained ECG Monitoring by Yaoliang Zhan, Xue Wang, Jin Yang

“…Furthermore, an exercise intensity classification model was developed based on ECG characteristics and a fully connected neural network (FCNN) algorithm, with an evaluation accuracy of 98%. …”
Get full text

Review of malware detection and classification visualization techniques by Jinwei WANG, Zhengjia CHEN, Xue XIE, Xiangyang LUO, Bin MA

“…With the rapid advancement of technology, network security faces a significant challenge due to the proliferation of malicious software and its variants.These malicious software use various technical tactics to deceive or bypass traditional detection methods, rendering conventional non-visual detection techniques inadequate.In recent years, data visualization has gained considerable attention in the academic community as a powerful approach for detecting and classifying malicious software.By visually representing the key features of malicious software, these methods greatly enhance the accuracy of malware detection and classification, opening up extensive research opportunities in the field of cyber security.An overview of traditional non-visual detection techniques and visualization-based methods were provided in the realm of malicious software detection.Traditional non-visual approaches for malicious software detection, including static analysis, dynamic analysis, and hybrid techniques, were introduced.Subsequently, a comprehensive survey and evaluation of prominent contemporary visualization-based methods for detecting malicious software were undertaken.This primarily encompasses encompassed the integration of visualization with machine learning and visualization combined with deep learning, each of which exhibits distinct advantages and characteristics within the domain of malware detection and classification.Consequently, the holistic consideration of several factors, such as dataset size, computational resources, time constraints, model accuracy, and implementation complexity, is necessary for the selection of detection and classification methods.In conclusion, the challenges currently faced by detection technologies are summarized, and a forward-looking perspective on future research directions in the field is provided.…”
Get full text

Microfluidic mixing probe: generating multiple concentration-varying flow dipoles by Dima Samer Ali, Ayoub Glia, Pavithra Sukumar, Muhammedin Deliorman, Mohammad A. Qasaimeh

“…Abstract This study advances microfluidic probe (MFP) technology through the development of a 3D-printed Microfluidic Mixing Probe (MMP), which integrates a built-in pre-mixer network of channels and features a lined array of paired injection and aspiration apertures. …”
Get full text