Enterprise Tax Assessment and Risk Avoidance Based on Deep Learning by Yali Lan

“…The approach simplifies business complexity and allows for more precise tax planning.…”
Get full text

A Novel Tree Model-based DNN to Achieve a~High-Resolution DOA Estimation via Massive MIMO Receive Array by Y. Li, F. Shu, Y. Song, J. Wang

“…To satisfy the high-resolution requirements of direction-of-arrival (DOA) estimation, conventional deep neural network (DNN)-based methods using grid idea need to significantly increase the number of output classifications and also produce a huge high model complexity. To address this problem, a multi-level tree-based DNN model (TDNN) is proposed as an alternative , where each level takes small-scale multi-layer neural networks (MLNNs) as nodes to divide the target angular interval into multiple sub-intervals, and each output class is associated to a MLNN at the next level. …”
Get full text

APPLICATION OF THE EVOLUTIONARY PARADIGM TO DESIGNING ARCHITEСTURE OF A NEURAL NETWORK FOR RECOGNIZING THE DISTORTED TEXT by Y. A. Bury, D. I. Samal

“…Nevertheless, the traditional heuristic approaches to design of multi-layer neural networks are based on the recombination of already existing neural network architectures.This approach allows us to solve a wide range of problems, but implies compliance with specific conditions for the quality work of algorithms.The natural analogues of such intelligent systems in living nature, however, are universal enough to adapt to virtually any habitat.Despite their extreme complexity and limited ability to study their structures, it is known that these structures were formed as a result of the evolutionary process. …”
Get full text

Preventing inter-ethnic conflict: Evidence from the Gereb traditional institutions in Northeast Ethiopia by Awet Halefom Kahsay

“…Additionally, examining the role of traditional institutions in conflict prevention introduces a third layer of complexity to the discussion as they are typically approached within the context of conflict resolution. …”
Get full text

Hydrogen Absorption and Self-Corrosion of Mg Anode: Influence of Aqueous Electrolyte Species by Andrei Nazarov, Tatiana Yurasova, Andrey Marshakov

“…The NDE conditions showed delayed reduction activity at the surface, attributed to a hydride phase within the corrosion product layer. Hydride ions were quantified through their anodic oxidation in an alkaline electrolyte, measured by the electric charge passed. …”
Get full text

The Role of Long Non-Coding RNAs in Human Endoderm Differentiation by Annanda Lyra Ribeiro, Bruno Dallagiovanna

“…The human genome sequencing revealed a vast complexity of transcripts, with over 80% of the genome being transcribed into non-coding RNAs. …”
Get full text

A Gain-Computation Enhancements Resource Allocation for Heterogeneous Service Flows in IEEE 802.16 m Mobile Networks by Wafa Ben Hassen, Meriem Afif

“…In a single service access, we propose a dynamic resource allocation algorithm at the physical layer aiming to maximize the cell data rate while ensuring fairness among users. …”
Get full text

Effect of tool angle in nanocutting of single crystal GaN using diamond cutter by Yongqiang WANG, Hao XIA, Zhihang HU, Shuaiyang ZHANG, Shaohui YIN

“…The simulations employed highly validates interatomic potentials capable of capturing the complex bonding and deformation behavior of GaN. The model incorporates realistic crystal orientations and environmental conditions. …”
Get full text

U-Net-based VGG19 model for improved facial expression recognition by Xiaohu ZHAO, Jingyi ZHANG, Mingzhi JIAO, Lixun XIE, Lanfei WANG, Weiqing SUN, Di ZHANG

“…Furthermore, modifications are made to the fully connected layers by substituting the first two layers with convolutional layers while retaining the fully connected final layer. …”
Get full text

Wearable Sensor-Based Human Activity Recognition: Performance and Interpretability of Dynamic Neural Networks by Dalius Navakauskas, Martynas Dumpis

“…LSTM achieved the highest classification accuracy (98.76%), followed by GRU (97.33%) and FIRNN (95.74%), with FIRNN offering the lowest computational complexity. To improve model transparency, Layer-wise Relevance Propagation (LRP) was applied to both input and hidden layers. …”
Get full text

Succulent Plant Image Classification Based on Lightweight GoogLeNet with CBAM Attention Mechanism by Xingyu Tong, Zhihong Liang, Fangrong Liu

“…Meanwhile, batch normalization (BN) operations are added after each convolutional layer to accelerate network convergence and improve model stability. …”
Get full text

Methods of Cell Propulsion through the Local Stroma in Breast Cancer by Kerry J. Davies

“…Normal epithelial cells depend on the formation of intercellular adhesion contacts to form a continuous sheet of stratifying cell layers that are attached to one and other horizontally and vertically. …”
Get full text

Study on the propagation law of hydraulic fractures in heterogeneous permeability reservoirs. by Linhao Zou, Yinao Su, Xingsheng Xu, Wei Li, Huan Zhao, Mingxiu Zhang, Shengjie Jiao

“…The development of unconventional oil and gas resources is increasingly shifting toward heterogeneous reservoirs with complex permeability distributions, making the effective control of hydraulic fracture propagation patterns critical for optimizing production. …”
Get full text

Texts All the Way Down: The Intertextual Networks Project by Ash Clark, Sarah Connell

“…Owing to its size, this project can offer a model for large-scale bibliographic data wrangling among a complex set of primary sources. This paper shares insights and challenges from this project, discussing strategies for modeling, enabling discovery, and revealing complex layers of textual data and textuality among not only a primary corpus but also a related collection of texts.…”
Get full text

The life cycle of the Book of the Dead as a Digital Humanities resource by Ulrike Henny, Jonathan Blumtritt, Marcel Schaeben, Patrick Sahle

“…In a nutshell, they are: (a) the importance of wary technological choices in an initial phase cannot be underestimated, (b) the application and presentation layers of a digital resource, if present, are an essential part of it, (c) a certain degree of commitment from the research community and funding bodies alike is indispensable for maintaining a web-based complex Digital Humanities resource.…”
Get full text

A convolutional deep reinforcement learning architecture for an emerging stock market analysis by Anita Hadizadeh, Mohammad Jafar Tarokh, Majid Mirzaee Ghazani

“… In the complex and dynamic stock market landscape, investors seek to optimize returns while minimizing risks associated with price volatility. …”
Get full text

Boron as a passivating dopant of oxygen-vacancy-induced hole traps at GaN/SiO2 interface by Yuansheng Zhao, Atsushi Oshiyama, Kenji Shiraishi

“…Recent experiments followed by our first-principles calculations have shown that heavily Mg-doped GaN epitaxial layers suppress hole traps due to oxygen vacancy V _O in the GaO _x interfacial layer at the GaN/SiO _2 interfaces, but leave a serious issue of controlling hole-concentration profiles. …”
Get full text

Underground Manchester as urban palimpsest in Jeanette Winterson’s Frankissstein: A Love Story (2019) by Claire Wrobel

“…Building on Jens Martin Gurr’s suggestion that the notion of the urban palimpsest may be extended to post-industrial cities, the first section seeks to analyse how Winterson represent urban complexity – i.e. the coexistence of layers of urban memory – by mobilizing textual strategies centred on the figure of Victor Stein. …”
Get full text

Application of Traffic Cone Target Detection Algorithm Based on Improved YOLOv5 by Mingwu Wang, Dan Qu, Zedong Wu, Ao Li, Nan Wang, Xinming Zhang

“…The system used the lightweight shuffle Net network as a backbone for feature extraction, replaced convolutional layers with focus modules to reduce computational complexity, and reduced the use of the C3 layer to increase network speed, thereby meeting the speed and accuracy requirements of traffic cone placement and retraction operations while maintaining acceptable model inference accuracy. …”
Get full text

Elastic Information Management for Air Pollution Monitoring in Large-Scale M2M Sensor Networks by Yajie Ma, Yike Guo, Dilshan Silva, Orestis Tsinalis, Chao Wu

“…The continual increases in size, data generating rates, and connectivity of sensor networks present significant scale and complexity challenges. Traditional schemes of information management are no longer applicable in such a scenario. …”
Get full text