dhafer thamer ahmed alhajim

The current research introduces a Squeeze-Excitation Dilated Attention-based Residual U-Net (SEDARU-Net) with a robust intensity normalization technique to address the challenges related to different types and sizes of lung nodules and to achieve an improved lung nodule segmentation

This technique normalizes image intensity by subtracting the grey-value of the most frequent bin from the image. The novel method is tested on the Multimodal Brain Tumor Segmentation (BRATS) 2015 dataset, showing that the use of ConvLSTM blocks improved segmentation quality by 1.6% on the test subset. The addition of skip connections further improved performance by 3.3% and 1.7% relative to the U-net and ConvLSTM-based U-net models, respectively. Moreover, the inclusion of up skip connections could enhance the performance by 5.7%, 3.99% and 2.2% relative to the simple U-net, ConvLSTM-based U-net, and ConvLSTM-based U-net with skip connections, respectively. Finally, the novel preprocessing technique had a positive effect on the proposed network, resulting in a 3.3% increase in the segmentation outcomes.

The modern world is full of data of all kinds; however, the vast amount of video and image data available provides the data set needed for facial recognition. Facial recognition is crucial in safety and surveillance systems that analyze visual data and millions of images. Using facial recognition software, a person's identity can be verified through a variety of media images. For facial recognition, there is a variety of algorithms available. The article presents an approach to a face recognition framework using Haar Cascade, a biometric technology in safety and surveillance systems. It investigates combining standard machine learning techniques for face detection and identification with Raspberry Pi face detection, a cost-effective and easy-to-use embedded system. The system detects faces from indirect and direct images, achieving high speed using the latest Raspberry Pi 4 and Python libraries. The work demonstrates a machine-learning-based design method and a complete embedded system. The face detection accuracy is 92%, and the average time is 0.35 compared to the local binary model (LBP). Many facial recognition algorithms on the web and in literature reviews are vulnerable to image attacks. These methods are very effective in identifying faces in webcams, video streams, images, and videos. This system's use of the Raspberry Pi 4 and advanced Python libraries results in fast and accurate real-time face detection. This paper extends the work first presented at the 12th Iranian/Second International Conference on Machine Vision and Image Processing (MVIP).

https://journals.uob.edu.bh/handle/123456789/5485

This article reviews and discusses feature extraction techniques used for text classification as well as natural language processing in biomedical applications.This researchaims to analyze the similarities of techniques used as technology and algorithms that have become more sophisticated to optimize feature extraction. In feature extraction, a specific of words is taken out from text data. After that, they transform into a feature set to be usable by a classifier. Several algorithms have been identified for classification,including but not limited to SVM, deep neural networks as well as Naïve Bayes algorithms. Next, the natural language is processed and achieves better performance results as indicated by certain metrics like execution time, specificity, accuracy, specificity,and sensitivity.

In today’s world, we are surrounded by data of many types, but the abundance of image and video data available offers the data set needed for face recognition technology to function. Face recognition is a critical component of security and surveillance systems that analyze visual data and millions of pictures. In this article, we investigated the possibility of combining standard face detection and identification techniques such as machine learning and deep learning with Raspberry Pi face detection since the Raspberry Pi makes the system cost-effective, easy to use, and improves performance. Furthermore, some images of a selected individual were shot with a camera and a Python program in order to do face recognition. This paper proposes a facial recognition system that can detect faces from direct and indirect images. We call this system FFDR, which is characterized by high speed and accuracy in the diagnosis of faces because it uses the Raspberry Pi 4 and the latest libraries and advanced environments in the Python language.