Winter discharge fluctuations due to ice formation in a Swiss alpine catchment by Nina C. Nagel, Michael Margreth, Florian Lustenberger, David F. Vetsch

“…This study observed the discharges using wildlife cameras and employed temperature measurements at potential sites in the Dischmà stream to better understand the controls of ice formation and its impact on winter discharge fluctuations. A new algorithm was developed for detection of icing events in the stream and quantification of water retention volumes based on discharge and temperature data whereas the observations were used as ground truth for verification and calibration of the algorithm. …”
Get full text

A Machine Vision Perspective on Droplet‐Based Microfluidics by Ji‐Xiang Wang, Hongmei Wang, Huang Lai, Frank X. Liu, Binbin Cui, Wei Yu, Yufeng Mao, Mo Yang, Shuhuai Yao

Get full text

TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network Security by Ryozo Masukawa, Sanggeon Yun, Sungheon Jeong, Nathaniel D. Bastian, Mohsen Imani

“…TriageHD constructs dynamic scene graphs from time-based network flow data, integrating feature representations extracted via a self-attention-based payload encoder. …”
Get full text

Implementation of a wireless sensor network for irrigation management in drip irrigation systems by Mehmet Kamil Meriç

Get full text

BSO-CNN: A BSO Pressure Optimized CNN Model for Water Distribution Networks by Waghmare Shwetambari Pandurang, Renu Praveen Pathak, Imtiyaz Ahmad Wani

Get full text

HMS-PAU-IN: A heterogeneous multi-scale spatiotemporal interaction network model for population analysis units by Xiaorui Yang, Rui Li, Jing Xia, Junhao Wang, Hongyan Li, Nixiao Zou

“…To validate the model, we developed a population prediction model that integrates the multi-scale features of PAUs and introduced Leiden-IES-PMS, a community detection method based on the Leiden algorithm, which integrates internal and external environmental semantics and adopts a proximity merging strategy. …”
Get full text

Advancing Neurodegenerative Disease Management: Technical, Ethical, and Regulatory Insights from the NeuroPredict Platform by Marilena Ianculescu, Lidia Băjenaru, Ana-Mihaela Vasilevschi, Maria Gheorghe-Moisii, Cristina-Gabriela Gheorghe

“…Through the integration of wearable physiological sensors, motion sensors, and neurological assessment tools, the NeuroPredict platform harnesses AI and smart sensor technologies to enhance the management of specific neurodegenerative diseases. Machine learning algorithms process these data flows to find patterns that point out disease evolution. …”
Get full text

Accurate estimation of permeability reduction resulted from low salinity water flooding in clay-rich sandstones by Xiaojuan Zhang, Muntadher Abed Hussein, Tarak Vora, Anupam Yadav, Asha Rajiv, Aman Shankhyan, Sachin Jaidka, Mehul Manu, Farzona Alimova, Issa Mohammed Kadhim, Zainab Jamal Hamoodah, Fadhil Faez, Ahmad Khalid

“…The results show that random forest and ensemble learning algorithms delivered the highest predictive accuracy, evidenced by the most substantial coefficient of determination (R2) and minimal error metrics. …”
Get full text

Passive forensic based on spatio-temporal localization of video object removal tampering by Linqiang CHEN, Quanxin YANG, Lifeng YUAN, Ye YAO, Zhen ZHANG, Guohua WU

“…To address the problem of identification of authenticity and integrity of video content and the location of video tampering area,a deep learning detection algorithm based on video noise flow was proposed.Firstly,based on SRM (spatial rich model) and C3D (3D convolution) neural network,a feature extractor,a frame discriminator and a RPN (region proposal network) based spatial locator were constructed.Secondly,the feature extractor was combined with the frame discriminator and the spatial locator respectively,and then two neural networks were built.Finally,two kinds of deep learning models were trained by the enhanced data,which were used to locate the tampered area in temporal domain and spatial domain respectively.The test results show that the accuracy of temporal-domain location is increased to 98.5%,and the average intersection over union of spatial localization and tamper area labeling is 49%,which can effectively locate the tamper area in temporal domain and spatial domain.…”
Get full text

Adaptive quadrilateral distance relaying scheme for fault impedance compensation by Patel Ujjaval J., Chothani Nilesh G., Bhatt Praghnesh J.

“…This paper presents a novel standalone adaptive distance protection algorithm for detection, classification and location of fault in presence of variable fault resistance. …”
Get full text

Using modern clustering techniques for parametric fault diagnostics of turbofan engines by I. J. Buraimah

“…In this paper flight parameters such as Exhaust Gas Temperature (EGT), Engine Fan Speeds (N1 and N2), Fuel Flow (FF), Oil Temperature (OT), Oil Pressure (OP), Vibration and others where used to determine engine fault. …”
Get full text

Research on Visual SLAM Navigation Techniques for Dynamic Environments by Tongjun Wang, Peijun Zhao

“…Aiming at the inconsistency between the direction of dynamic objects and static background optical flow, this method adopts a high-real-time dynamic region mask detection algorithm to eliminate the feature points in the dynamic region mask, remove the camera motion optical flow according to the original feature information, and then cluster the optical flow amplitude of dynamic objects so as to realize the dynamic region mask detection and eliminate the dynamic signpost points combined with the polar geometric constraints. …”
Get full text

Study on Calculation of Cross-section Area of River Based on Analysis Method of Mid-point Distance Section by DANG Xicheng, LUO Yi, WANG Haiyan, LI Rong

“…The cross-section area is one of the key factors in flow measurement by velocity area method,and its calculation accuracy is directly related to the accuracy of flow measurement.Due to the complexity and diversity of the river section,the existing software algorithm cannot accurately judge the real position of the river flow through the large section data,resulting in the extraction error of the range of the cross section and the vertical depth.Therefore,with computer programming technology,this paper puts forward the analysis method of river mid-point distance section for identifying the position of river flow and judging the type of section,such as single section and compound section,extracting the water's edge and vertical line,and calculating the area.The application shows that the software can accurately analyze the river flow position under different hydraulic conditions by this method,and calculate the river cross-section area,achieving the purpose of algorithm design.This method can be widely used in automatic hydrological detection equipment or hydrological analysis software to improve the analysis ability of the equipment or software for cross-section flow area of river.…”
Get full text

Stroke Lesion Prediction by Bille-Viper-Segmentation with Tandem-MU-net Model by Beevi Fathima, N Santhi Dr, N Ramasamy Dr

“…Furthermore, the Focus View Algorithm is suggested, which incorporates features from infarcted regions to improve early detection of emerging lesions. …”
Get full text

Fast loop-free path migration strategy in software defined network by Binghao YAN, Qinrang LIU, Jianliang SHEN, Xiantuo TANG, Dong LIANG

“…Aiming at the problems of slow and faulty path migration caused by distributed deployment and asynchronous operation of data plane forwarding devices in software defined network, a fast loop-free path migration strategy was proposed.First, a fast loop detection algorithm based on node ranking was proposed.By comparing the position differences of adjacent nodes on the old and new paths of the flow, whether there was a forwarding loop in the path migration process and the location detection where the loop occurs could be quickly determined.Then, a greedy update mechanism based on node relaxation dependency was proposed.The fast loop detection algorithm was used to uncover the relaxation dependency between the common switches on the old and new paths, and the number of switches updated in each round of the migration process was ensured to be maximized.Simulation results show that the proposed strategy can effectively avoid migration loops and obtain the optimal update time overhead under different network states compared with existing migration schemes.…”
Get full text

DTFA-Net: Dynamic and Texture Features Fusion Attention Network for Face Antispoofing by Xin Cheng, Hongfei Wang, Jingmei Zhou, Hui Chang, Xiangmo Zhao, Yilin Jia

“…We proposed a dynamic information fusion structure of an interchannel attention block to fuse the magnitude and direction of optical flow to extract facial motion features. In addition, for the face detection failure of HOG algorithm under complex illumination, we proposed an improved Gamma image preprocessing algorithm, which effectively improved the face detection ability. …”
Get full text

A Novel Multisensor Traffic State Assessment System Based on Incomplete Data by Yiliang Zeng, Jinhui Lan, Bin Ran, Yaoliang Jiang

“…The system comprises probe vehicle detection sensors, fixed detection sensors, and traffic state assessment algorithm. …”
Get full text

Retracted: Study on Modeling Method of Forest Tree Image Recognition Based on CCD and Theodolite by Yeqiong Shi, Sainan Wang, Shuna Zhou, M. M. Kamruzzaman

“…The image processing algorithm is designed for the image processing module, and the flow chart of the image processing algorithm is given. …”
Get full text

BUSClean: Open-source software for breast ultrasound image pre-processing and knowledge extraction for medical AI. by Arianna Bunnell, Kailee Hung, John A Shepherd, Peter Sadowski

“…Experiments on an internal testing dataset of 430 clinical BUS images achieve >95% sensitivity and >98% specificity in detecting every type of text annotation, >98% sensitivity and specificity in detecting scans with blood flow highlighting, alternative scan modes, or invalid scans. …”
Get full text

Multi-Vehicle Object Recognition Method Based on YOLOv7-W by Xin Liu, Jingbin Zhao, Zhi Zhang, Rongxing Wu, Xun Li

“…This algorithm effectively addresses three key challenges: high vehicle miss detection rates, inadequate perception of small-angle targets, and insufficient feature extraction capabilities. …”
Get full text