Construction and validation of tertiary models for predicting growth of Salmonella Infantis in chicken liver during a processing chain deviation by Thomas P. Oscar

“…Therefore, a three-phase linear, polynomial regression, tertiary model (TMPR) and a multiple layer feedforward neural network with two nodes in the hidden layer, tertiary model (TMNN) for growth of Salmonella Infantis in chicken liver as a function of dose (101–106), time (0–8 h), and temperature (18–30°C) were constructed, validated, and compared using the criteria of the Acceptable Prediction Zones (APZ) method. …”
Get full text

Release Control of Biologically Active Substances from Simulation Model of Silicone Liners by S. V. Gribanova, I. L. Udyanskaya, V. G. Yankova, T. K. Slonskaya, N. B. Epshtein, A. A. Zhukova, O. N. Plakhotnaya, V. N. Kuzina

“…Silicone disks (SDs), impregnated with BAS (0,2 % of the volume) were used as a simulation model of silicone liners. The BAS release from silicone liner models was assessed using highly sensitive chromatographic methods of thin-layer and gas-liquid chromatography.Results and discussion. …”
Get full text

Modeling of digital spatial processing under conditions of troposphere propagation of centimeter radio waves for wireless telecommunication by Ilia W. Peshkov, Dmitry N. Borisov

Get full text

A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models by Hussein Mohammed Ridha, Hashim Hizam, Seyedali Mirjalili, Mohammad Lutfi Othman, Mohammad Effendy Ya’acob, Noor Izzri Bin Abdul Wahab, Masoud Ahmadipour

Get full text

Formation of a dense cloud of points and its processing when creating a digital model of the terrain by Ye. Butenko, O. Kutsenko, О. Tertyshna, Ye. Tkachuk, K. Yaretska

“…The stages of point cloud classification, creation of classification layers, data export to QGIS, Digitals and 3D Survey software tools for further modeling and drawing of models with isolines were studied. …”
Get full text

Predicting mass transfer activation energy and physicochemical properties of dried onion using numerical modeling and artificial intelligence by Fangfang Liu, Hany S. El-Mesery, Ahmed H. ElMesiry, Zicheng Hu, Ali Salem

Get full text

Intensification of Foam Layered Apparatus by Foam Stabilization by Liaposhchenko O., Khukhryanskiy О., Moiseev V., Ochowiak M., Manoilo Е.

“…The series of experimental dependencies for the main parameters of the process are given. The possibility of effective mass-exchange processes in an intensive foam layer on counter-current coarse-grating lattices is confirmed. …”
Get full text

Prediction of Input–Output Characteristic Curves of Hydraulic Cylinders Based on Three-Layer BP Neural Network by Wei Cai, Yirui Zhang, Jianxin Zhang, Shunshun Guo, Rui Guo

“…In the process of model improvement, a nonlinear adaptive decreasing weight mechanism is introduced to improve the optimization accuracy of the algorithm, facilitating the search for optimal solutions. …”
Get full text

ACSAformer: A crime forecasting model based on sparse attention and adaptive graph convolution by Zhenkai Qin, Baozhong Wei, Baozhong Wei, Caifeng Gao, Caifeng Gao, Feng Zhu, Feng Zhu, Weiqi Qin, Weiqi Qin, Qian Zhang

“…The model integrates the Transformer architecture with adaptive graph convolutional layers and a sparse attention mechanism. …”
Get full text

A Multi-Architecture Approach for Offensive Language Identification Combining Classical Natural Language Processing and BERT-Variant Models by Ashok Yadav, Farrukh Aslam Khan, Vrijendra Singh

“…We also propose an architecture that utilizes advanced transformer models such as BERT, ALBERT, and ELECTRA for pre-processing and encoding, with 1D CNN and neural network layers serving as the classification components. …”
Get full text

The geometry of meaning: evaluating sentence embeddings from diverse transformer-based models for natural language inference by Mohammed Alsuhaibani

“…We conduct comprehensive experiments with different pooling techniques and evaluate the embeddings using different norms across multiple layers of each model. Our results demonstrate that the choice of pooling strategy, norm, and model layer significantly impacts the performance of NLI, with the best results achieved using max pooling and the L2 norm across specific model layers. …”
Get full text

Ensemble genetic and CNN model-based image classification by enhancing hyperparameter tuning by Wajahat Hussain, Muhammad Faheem Mushtaq, Mobeen Shahroz, Urooj Akram, Ehab Seif Ghith, Mehdi Tlija, Tai-hoon Kim, Imran Ashraf

Get full text

Recognition of Industrial Spare Parts Using an Optimized Convolutional Neural Network Model by Chandralekha Mohan, Takfarinas Saber, Priyadharshini Jayadurga Nallathambi

“…In this article, a novel Deep Learning-based object recognition model based on a convolutional neural network architecture is proposed and constructed using stacked convolutional layers to extract and learn features of the spare parts efficiently with the goal of improving the effectiveness of the spare part image recognition process. …”
Get full text

Aligning large language models and geometric deep models for protein representation by Dong Shu, Bingbing Duan, Kai Guo, Kaixiong Zhou, Jiliang Tang, Mengnan Du

“…Our work examines alignment factors from both model and protein perspectives, identifying challenges in current alignment methodologies and proposing strategies to improve the alignment process. …”
Get full text

Finite Element Stress Model of Direct Band Gap Ge Implementation Method Compatible with Si Process by Xiaohuan Xue, Jianjun Song, Rongxi Xuan

“…Among the various implementations of Ge band gap-type conversion, the related methods that are compatible with the Si process are most promising. It is such a method to etch around the Ge epitaxial layer on the Si substrate and introduce the biaxial tensile stress by SiGe selective filling. …”
Get full text

RESEARCH ON THE RESIDUAL STRESS OF THE CRYSTAL SURFACE DURING LAPPING PROCESS BASED ON A SINGLE PARTICLE MODEL by WANG XiaoBo, XIE RuiQing

“…In order to understand the formation mechanism of the residual stress of the lapping surface of laser crystal,a single particle model of a YAG crystal workpiece during lapping process was established by the finite element analysis software ANSYS. …”
Get full text

COMPLEX GEOLOGICAL–GEOPHYSICAL 3D MODEL OF THE CRUST IN THE SOUTHEASTERN FENNOSCANDIAN SHIELD: NATURE OF DENSITY LAYERING OF THE CRUST AND THE CRUST–MANTLE BOUNDARY by V. N. Glaznev, M. V. Mints, O. M. Muravina, A. B. Raevsky, L. G. Osipenko

“…Based on results of complex geophysical simulation and geological interpretation of the 3D model, the following conclusions are drawn. (1) The nearly horizontal density layering of the continental crust is superimposed on the previously formed geological structure; rock differentiation by density is decreasing with depth; the density layering is controlled by the recent and near-recent state of the crust, but can be disturbed by the latest deformations. (2) Temperature variations at the Moho are partially determined by local variations of heat generation in the mantle, which, in turn, are related to local features of its origin and transformation. (3) The concept of the lower continental crust being a reflectivity zone and the concept of the lower continental crust being a layer of high density and velocity are not equivalent: the lower crust is the deepest, high-density element of near-horizontal layering, whereas the seismic image of the reflectivity zone is primarily related to transformation of the crust as a result of magmatic under- and intraplating under conditions of extension and mantle-plume activity. (4) At certain combinations of crustal thickness and temperature at the level of Moho discontinuity, the crust in a platform region can be transformed into eclogites. …”
Get full text

A Thermo-Hydro-Mechanical Damage Coupling Model for Stability Analysis During the In Situ Conversion Process by Guoping Li, Juan Jin, Weixi Chen, Minghui Zhao, Jiandong Liu, Bo Fang, Tingfu Ye

“…To capture tensile–compressive asymmetry in geotechnical materials, an equivalent strain based on strain energy density is introduced, which regularizes the tensile component of the elastic strain energy density. Additionally, the model simulates the multi-layer wellbore structure and the dynamic heating and extraction processes, recreating the in situ environment. …”
Get full text

Short-term photovoltaic power forecasting based on a new hybrid deep learning model incorporating transfer learning strategy by Tiandong Ma, Feng Li, Renlong Gao, Siyu Hu, Wenwen Ma

“…First, the processed data are input into the DCNN layer, and the dilation convolution mechanism captures the spatial features of the wide sensory field of the input data. …”
Get full text

A stacked ensemble model for traffic conflict prediction using emerging sensor data by Bowen Cai, Léah Camarcat, Nicolette Formosa, Mohammed Quddus

Get full text