Utilização de redes neurais artificiais na classificação de níveis de degradação em pastagens Use of artificial neural networks in the classification of degradation levels of pastu... by César S. Chagas, Carlos A. O. Vieira, Elpídio I. Fernandes Filho, Waldir de C. Júnior

“…The neural networks simulator used was the "Neural Java Network Simulator", with a feed forward model and the learning algorithm of back propagation. The obtained results show that the classification using neural networks, while presenting a slightly superior result, had a statistically similar performance compared to the maximum likelihood, getting a Kappa index of 0.80, against 0.79, respectively. …”
Get full text

Revealing long-term dynamics and spatiotemporal drivers of anthropogenic nutrients inputs in China: The effects of dietary and socioeconomic factors by Jia Liu, Wei Gao, Fen Guo, Yuan Zhang, Yanpeng Cai

“…Urbanization and GDP were dominant drivers in developed areas (Type I), while population was key in less–developed regions (Type II). …”
Get full text

SCL-YOLOv11: A Lightweight Object Detection Network for Low-Illumination Environments by Shulong Zhuo, Hao Bai, Lifeng Jiang, Xiaojian Zhou, Xu Duan, Yiqun Ma, Zihan Zhou

“…Experimental results on the ExDark dataset demonstrate that the proposed algorithm achieves 67.6% mAP@0.5 and 42.4% mAP@0.5:0.95, while reducing parameter count by 38.5% and computational cost by 25.4%. …”
Get full text

Human-Aware Robot Collaborative Task Planning Using Artificial Potential Field and DQN Reinforcement Learning by Jayesh Prakash, Sam Altnji, Karthick Thiyagarajan, Jogesh S. Nanda, Abhijit Biswas, Abhra Roy Chowdhury

“…A Deep Q Network (DQN) reinforcement learning model is used to train the robot to perform the goal reaching task while avoiding obstacles to ensure safety. The DQN algorithm makes use of the end-effector position and the relative positions with the goal and obstacles to train a policy that guides the robot arm safely. …”
Get full text

Optimization of microwave-assisted polyphenol extraction and antioxidant activity from papaya peel using response surface methodology and artificial neural network by Md. Waziur Rahman Chy, Tanvir Ahmed, Junaid Iftekhar, Md. Zohurul Islam, Md. Rahmatuzzaman Rana

“…These models were combined with the desirability function (DF) and/or genetic algorithm (GA) optimization approaches. Maximizing TPC and DPPH activity while maintaining MWP, I-time, EtOH%, and S/S within their respective ranges using hybrid optimization approaches (RSM-DF: TPC = 1058 mgGAE/100 g, and DPPH = 83 %, RSM-GA: TPC = 1064 mgGAE/100 g and DPPH = 79 %, and ANN-GA: TPC = 1086 mgGAE/100 g, and DPPH = 83 %,) yielded consistent optimal results. …”
Get full text

MRI-based 2.5D deep learning radiomics nomogram for the differentiation of benign versus malignant vertebral compression fractures by Wenhua Liang, Hong Yu, Lisha Duan, Xiaona Li, Ming Wang, Bing Wang, Jianling Cui

“…Radiomics (Rad) features were extracted using traditional Rad techniques, while 2.5-dimensional (2.5D) deep learning (DL) features were obtained using the ResNet50 model. …”
Get full text

APG mergence and topological potential optimization based heuristic user association strategy by Zhirui HU, Meihua BI, Fangmin XU, Meilin HE, Changliang ZHENG

“…Therefore, it is reasonable to model the problem of improving network scalable degree as minimizing network coupling degree,and it is feasible to improve network scalable degree by reducing network coupling degree.2)The upper limit of computational complexity of the proposed algorithm is <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mi mathvariant="script">O</mi><mo stretchy="false">(</mo><mi>K</mi><mi>N</mi><msub> <mi>log</mi> <mn>2</mn> </msub> <mi>N</mi><mo>+</mo><msup> <mi>k</mi> <mn>2</mn> </msup> <mo>+</mo><mi>N</mi><mi>N</mi><msub> <mover accent="true"> <mi>N</mi> <mo>¯</mo> </mover> <mtext>p</mtext> </msub> <mo stretchy="false">)</mo></math></inline-formula>,while that of directly solving the optimization problem is<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"><mi mathvariant="script">O</mi><mo stretchy="false">(</mo><msup> <mi>N</mi> <mrow> <msub> <mover accent="true"> <mi>N</mi> <mo>¯</mo> </mover> <mtext>u</mtext> </msub> <mi>K</mi></mrow> </msup> <mo stretchy="false">)</mo></math></inline-formula>.3)For theoretical analysis of the network scalable degree,take Fig.3 as an example.If AP2 changes,12 APs in Fig. 3(a)are affected and the network scalable degree is η₂=0.51,while 4 APs in Fig.3(c)are affected and the network scalable degree is η₂=0.79.4)Fig.5 shows the simulation results of network scalable degree.Compared with the traditional strategy,the network scalable degree is improved by 9.59% with 4.43% user rate loss.Compared with the strategy in[10],the network scalable degree is improved by 22.15% with 4.99% user rate loss. 5) The algorithm parameters, the threshold β₀of overlap rate and the upper limit number N₀of AP associated, effect the performance.As shown in Fig.6,with β₀or N₀decreases,η increases and the total user rate decreases. …”
Get full text

Pengembangan Deep Learning untuk Sistem Deteksi Dini Komplikasi Kaki Diabetik Menggunakan Citra Termogram by Medycha Emhandyksa, Indah Soesanti, Rina Susilowati

“…In addition to the deep convolutional neural network architecture model 4, the research contribution obtained from this research is the use of filter size variations of 3x3, 2x2, and 1x1 with a fixed number of convolutional layers and a reduction in the number of hidden layers in the algorithm structure can reduce the number of model parameters while maintaining high detection capability. …”
Get full text

Investigating the Triple Code Model in numerical cognition using stereotactic electroencephalography. by Alexander P Rockhill, Hao Tan, Christian G Lopez Ramos, Caleb Nerison, Beck Shafie, Maryam N Shahin, Adeline Fecker, Mostafa Ismail, Daniel R Cleary, Kelly L Collins, Ahmed M Raslan

“…Time-frequency spectrograms were dimensionally reduced with principal component analysis and passed into a linear support vector machine classification algorithm to identify regions associated with number perception compared to inter-trial periods. …”
Get full text

Implant displacement to the maxillary sinus– a retrospective multicenter cohort study and a management protocol by Daniel Muchnik, Gavriel Chaushu, Eli Rosenfeld, Shaked Adut, Aiman Elmograbi, Meir Debecco, Amir Laviv, Daya Masri

“…Abstract Purpose This study aims to investigate the potential complication of implant displacement into the maxillary sinus, exploring its etiology and various management strategies, while proposing a systematic approach for clinicians to effectively address this evolving complication. …”
Get full text

Lab Retriever: a software tool for calculating likelihood ratios incorporating a probability of drop-out for forensic DNA profiles by Keith Inman, Norah Rudin, Ken Cheng, Chris Robinson, Adam Kirschner, Luke Inman-Semerau, Kirk E. Lohmueller

“…We redesigned parts of the original Balding algorithm to improve computational speed. In addition to incorporating a probability of allelic drop-out and other critical parameters, Lab Retriever computes likelihood ratios for hypotheses that can include up to four unknown contributors to a mixed sample. …”
Get full text

A Comparative Evaluation of Machine Learning Methods for Predicting Student Outcomes in Coding Courses by Zakaria Soufiane Hafdi, Said El Kafhali

“…Utilizing a range of machine learning (ML) algorithms, our research applies multi-classification, data augmentation, and binary classification techniques to evaluate student outcomes effectively. …”
Get full text

Feedforward–Feedback Fuzzy-PID Water Level Control using PLC and Node-RED IoT by Adhitya Sumardi Sunarya, Fitria Suryatini, Nuryanti Nuryanti, Abdur Rohman Harist M, Gailan Anaisabury

“…This research proposes a combined feedforward–feedback control system using a Fuzzy-PID algorithm implemented on an Omron CP1H PLC, integrated with an IoT-based Node-RED monitoring interface. …”
Get full text

A Digital Twin Framework With Meta- and Transfer Learning for Scalable Multi-Machine Modeling and Optimization in Semiconductor Manufacturing by Chin-Yi Lin, Tzu-Liang Tseng, Tsung-Han Tsai

“…This study introduces MOODFG-MLTL, an innovative algorithm that integrates Meta-Learning and Transfer Learning within a Multi-Objective Optimization using Deep-Feature Gaussian Processes (MOODFG) architecture. …”
Get full text

Horizontal Control System for Maglev Ruler Based on Improved Active Disturbance Rejection Controller by Gengyun Tian, Chunlin Tian, Jiyuan Sun, Shusen Diao

“…In the simulation, the positioning accuracy can reach ±5 μm, while, in the experiment, the control accuracy can achieve ±2 μm. …”
Get full text

Frontier machine learning techniques for melanoma skin cancer identification and categorization: An in-Depth review by Viomesh Singh, Kavita A. Sultanpure, Harshwardhan Patil

“…In contrast to the conventional biopsy method, which is both laborious and costly, machine learning algorithms offer a viable alternative for early detection, reducing the burden on specialists while concurrently augmenting the diagnostic accuracy of skin lesions. …”
Get full text

Graph Evolution Rules Meet Communities: Assessing Global and Local Patterns in the Evolution of Dynamic Networks by Alessia Galdeman, Matteo Zignani, Sabrina Gaito

“…From a mesoscopic standpoint, the evolution patterns characterizing communities emphasize a non-homogeneous nature, with each community, or groups of them, displaying specific evolution patterns, while other networks’ communities follow more uniform evolution patterns. …”
Get full text

MULTI-TEMPORAL ANALYSIS OF LAND USE CHANGE IN THE MAGDALENA TEQUISISTLAN MICRO-BASIN, OAXACA, MEXICO by Juan Ángel García-Aguilar, Rufino Sandoval García, José Raymundo Enríquez-del Valle, Gerardo Rodríguez-Ortiz, José Cristóbal Leyva López, Judith Martínez de la Cruz

“…Supervised classification was performed with Quantum Gis® 3.6.0 "Maidenhead" software and the K-Means algorithm was used for atmospheric correction, while concordance and precision were calculated with the Kappa index. …”
Get full text

Optimizing energy cost in the residential sector through home energy management systems in a smart grid environment by Nabeeha Qayyum, Umar Jamil, Anzar Mahmood

“…This research aims to optimize power usage by reducing peak loads and electricity costs through the integration of RESs, such as solar or photovoltaic (PV) systems, while considering grid limitations, PV capacity, appliance ON/OFF schedules, and time-of-use tariffs. …”
Get full text

A Multi-Phase DRL-Driven SDN Migration Framework Addressing Budget, Legacy Service Compatibility, and Dynamic Traffic by Kai Yuan Tan, Saw Chin Tan, Teong Chee Chuah

“…This approach can potentially lower migration costs by up to 64% while achieving network optimization objectives. …”
Get full text