با عرض سلام مقاله سروي(مروري) ما تحت عنوان Evaluation Metrics in Learning Systems تقريبا تا ٢ هفته ديگه سابميت ميشه از دوستان اگر كسي خواست نفرات ٢ تا ٤ اش خالين.
هزينه نفر ٢ ١٠٠٠ دلار
نفر ٣ ٧٠٠ دلار
نفر ٤ هم ٥٠٠ دلار
در اين سروي بالاي ٤٠٠ متريك و بالاي ٨٠٠ مقاله رو بررسي كرديم كه جامع ترين بررسي مي باشد.
@Raminmousa@Machine_learn@Paper4money

با عرض سلام براي يكي از مقالاتمون نياز به اسپانسر داريم كه در حوزه ي طبقه بندي تصاوير پزشكي هستش و هزينه سرور ٤٠٠$ مي باشد. براي اين منظور جايگاه دوم رو به شخص پرداخت كننده واگذار مي كنيم. جهت اطلاعات بيشتر با بنده
در ارتباط باشين.

@Raminmousa

با عرض سلام براي يكي از مقالاتمون نياز به اسپانسر داريم كه در حوزه ي طبقه بندي تصاوير پزشكي هستش و هزينه سرور ٤٠٠$ مي باشد. براي اين منظور جايگاه دوم رو به شخص پرداخت كننده واگذار مي كنيم. جهت اطلاعات بيشتر با بنده
در ارتباط باشين.

@Raminmousa

با عرض سلام این ۵ مقاله ی ما در مرحله ریوایزد می باشند دوستانی که نیاز به سایتیشن دارند میتونیم به مقالاتشون سایت بدیم.
Paper 1:

An Intelligent Hybrid Industrial IoT-based Fault Detection Framework in Digital Twins
Systems

Neural Computing and Applications (Publisher : springer )
Impact factor
4.5 (2023)
5 year impact factor
4.7 (2023)
------------
paper 2
An Artificial Visual System with Fully Cell-modeled Retinal Direction-selective Ganglion
Cell Pathway for Motion Direction Detection in Grayscale Images

Neural Computing and Applications (Publisher : springer )
Impact factor
4.5 (2023)
5 year impact factor
4.7 (2023)
--------------------
paper 3
An Advanced Hybrid Deep Learning Model for Accurate Energy Load Prediction in Smart Building

Energy Exploration & Exploitation (Publisher : Sage )
Impact Factor: 1.9
5-Year Impact Factor: 2.2
-------
paper 4
An Advanced Hybrid Deep Learning Model for Accurate Energy Load Prediction in Smart Building

Energy Exploration & Exploitation (Publisher : Sage )
Impact Factor: 1.9
5-Year Impact Factor: 2.2
---------
paper 5

vSegNet - a variant SegNet for improving segmentation accuracy in medical images with class imbalance and limited data

Medinformatics
Impact Factor: 0.3
@Raminmousa@paper4money@Machine_learn

سلام اين مقالمون براي نيچر نوشته شده از دوستان كسي نياز داشت نفرات ١ تا ٤ اش خالي هستش . Brain Tumor Detection Through Diverse CNN Architectures in IoT healthcare industries: Fast R-CNN, UNet, Transfer Learning-Based CNN, and Fully Connected CNN Abstract…

سلام اين مقالمون براي نيچر نوشته شده از دوستان كسي نياز داشت نفرات ١ تا ٤ اش خالي هستش .

Brain Tumor Detection Through Diverse CNN Architectures in IoT healthcare industries: Fast R-CNN, UNet, Transfer Learning-Based CNN, and Fully Connected CNN

Abstract
Artificial intelligence-powered deep learning methods have significantly advanced the diagnosis of brain tumors in Internet of Thing (IoT)-healthcare systems, achieving high accuracy by processing extensive datasets. Brain health is crucial for human life, and accurate diagnosis is vital for effective treatment. Magnetic Resonance Imaging (MRI) provides critical data for diagnosing brain health issues, offering a substantial source of big data for artificial intelligence applications in image classification. In this study, we aimed to classify brain tumors, specifically glioma, meningioma, and pituitary tumors, from MRI images using Region-based Convolutional Neural Network (R-CNN) and UNet architectures. Additionally, we employed Convolutional Neural Networks (CNN) and CNN-based models such as Inception-V3, EfficientNetB4, and VGG19, leveraging transfer learning methods for classification tasks. The models were evaluated using F-score, recall, precision, and accuracy metrics. Our findings revealed that the Fast R-CNN model achieved the highest accuracy at 99%, with an F-score of 98.5%, an Area Under the Curve (AUC) value of 99.5%, a recall of 99.4%, and a precision of 98.5%. The integration of R-CNN, UNet, and transfer learning models plays a pivotal role in the early diagnosis and prompt treatment of brain tumors in IoT-healthcare systems, significantly improving patient outcomes.

Keywords: Region-based Convolutional Neural Network, UNet, Brain tumor, Transfer learning, Medical imaging

Scientific Reports, Nature Springer

@Raminmousa@paper4money@Machine_learn

سلام
این مقالمون در مرحله ی ریوایزد از دوستان اگر کسی خواست می تونیم به مقالاتشون سایت برنیم.

Title
Comparative Study of Long Short-Term Memory (LSTM), Bidirectional LSTM, and Traditional Machine Learning Approaches for Energy Consumption Prediction
——————————————————————--
Short title
Machine Learning, XGBoost, Tree-based Algorithm, Solar Energy Production, LSTM, Artificial Intelligence, Machine Learning, time-series,Bi-LSTM
——————————————————————
Abstract
Responsible, efficient, and environmentally conscious energy consumption practices are increasingly essential for ensuring the reliability of the modern electricity grid. This study focuses on leveraging time series analysis to enhance the accuracy of forecasting. Time series forecasting is a critical task in various application domains, as real-world time series data often exhibit non-linear patterns with complexities that conventional forecasting techniques struggle to capture. To address this, our approach proposes the utilization of long short-term memory (LSTM) and Bi-LSTM models for precise time series forecasting. To ensure a fair evaluation, the performance of our proposed approach is compared with traditional neural networks, time-series forecasting methods, and conventional decline curves. Additionally, individual models based on LSTM and Bi-LSTM, along with other machine learning methods, are implemented for a comprehensive assessment. The experimental results in this study consistently demonstrate that our proposed model outperforms all benchmarking methods in terms of mean absolute error (MAE) across most datasets. To address the imbalance between activations by both groups of consumers and prosumers, our prediction results show that the proposed method exhibits higher prediction performance compared to several traditional forecasting methods, such as the autoregressive integrated moving average model (ARIMA) and Seasonal autoregressive integrated moving average model (SARIMA). Specifically, the root mean square error (RMSE) of Bi-LSTM is 5.35%, 46.08%, and 50.6% lower than LSTM, ARIMA, and SARIMA, respectively, on the May test data.
——————————————————————--
journal
Energy Exploration & Exploitation (SAGE)

@Raminmousa
@Machine_learn
@paper4money

با عرض سلام این مقاله رو می خواییم برای Nature بفرستیم جایگاه های ۱ تا ۴ اش خالیه از دوستان کسی نیاز داشت در خدمتیم Title: Detection of brain tumors from images using the UNet architecture, with a comparative analysis of transfer learning methods and CNNs.…