Diabetic retinopathy is an eye disease in diabetic patients due to damage to the small blood vessels in the retina due to high and low blood sugar levels. Accurate detection and classification of Diabetic Retinopathy is an important task in computer-aided diagnosis, especially when planning for diabetic retinopathy surgery. Therefore, this study aims to design an automated model based on deep learning, which helps ophthalmologists detect and classify diabetic retinopathy severity through fundus images. In this work, a deep convolutional neural network (CNN) with transfer learning and fine tunes has been proposed by using pre-trained networks known as Residual Network-50 (ResNet-50). The overall framework of the proposed

Channel estimation (CE) is essential for wireless links but becomes progressively onerous as Fifth Generation (5G) Multi-Input Multi-Output (MIMO) systems and extensive fading expand the search space and increase latency. This study redefines CE support as the process of learning to deduce channel type and signal-tonoise ratio (SNR) directly from per-tone Orthogonal Frequency-Division Multiplexing (OFDM) observations,with blind channel state information (CSI). We trained a dual deep model that combined Convolutional Neural Networks (CNNs) with Bidirectional Recurrent Neural Networks (BRNNs). We used a lookup table (LUT) label for channel type (class indices instead of per-tap values) and ordinal supervision for SNR (0–20 dB,5-dB steps). T

Abstract This research investigates how activated carbon (AC) was synthesized from potato peel waste (PPW). Different ACs were synthesized under the atmosphere's conditions during carbonation via two activation methods: first, chemical activation, and second, carbon dioxide-physical activation. The influence of the drying period on the preparation of the precursor and the methods of activation were investigated. The specific surface area and pore volume of the activated carbon were estimated using the Brunauer–Emmett–Teller method. The AC produced using physical activation had a surface area as high as 1210 m2/g with a pore volume of 0.37 cm3/g, whereas the chemical activation had a surface area of 1210 m2/g with a pore volume of 0.34 c

Steel–concrete–steel (SCS) structural systems have economic and structural advantages over traditional reinforced concrete; thus, they have been widely used. The performance of concrete made from recycled rubber aggregate from scrap tires has been evaluated since the early 1990s. The use of rubberized concrete in structural construction remains necessary because of its high impact resistance, increases ductility, and produces a lightweight concrete; therefore, it adds such important properties to SCS members. In this research, the use of different concrete core materials in SCS was examined. Twelve SCS specimens were subjected to push-out monotonic loading for inspecting their mechanical performance. One specimen was constructed from co

There is an interesting potential for the use of GFRP-pultruded profiles in hybrid GFRP-concrete structural elements, either for new constructions or for the rehabilitation of existing structures. This paper provides experimental and numerical investigations on the flexural performance of reinforced concrete (RC) specimens composite with encased pultruded GFRP I-sections. Five simply supported composite beams were tested in this experimental program to investigate the static flexural behavior of encased GFRP beams with high-strength concrete. Besides, the effect of using shear studs to improve the composite interaction between the GFRP beam and concrete as well as the effect of web stiffeners of GFRP were explored. Encasing the GFRP

Identifying breast cancer utilizing artificial intelligence technologies is valuable and has a great influence on the early detection of diseases. It also can save humanity by giving them a better chance to be treated in the earlier stages of cancer. During the last decade, deep neural networks (DNN) and machine learning (ML) systems have been widely used by almost every segment in medical centers due to their accurate identification and recognition of diseases, especially when trained using many datasets/samples. in this paper, a proposed two hidden layers DNN with a reduction in the number of additions and multiplications in each neuron. The number of bits and binary points of inputs and weights can be changed using the mask configuration

This paper offers a systemic review of the deep learning methods to detect violence on campus, which is a critical issue in intelligent surveillance to improve the student safety and prompt cut off of violent accidents. The review reviews studies published 2018-2025, concentrating on model structure to detect fights, bullying, vandalism, and aggressive behavior on problematic campuses due to occlusion and light variations and complicated human interactions. The research design includes a comparative study of different deep learning networks, such as CNNs, RNNs, 3D CNNs, attention-based networks, transformers, graph neural networks, neuro-fuzzy, and multimodal systems and federated learning methods. The paper also assesses benchmark

The 3D electro-Fenton technique is, due to its high efficiency, one of the technologies suggested to eliminate organic pollutants in wastewater. The type of particle electrode used in the 3D electro-Fenton process is one of the most crucial variables because of its effect on the formation of reactive species and the source of iron ions. The electrolytic cell in the current study consisted of graphite as an anode, carbon fiber (CF) modified with graphene as a cathode, and iron foam particles as a third electrode. A response surface methodology (RSM) approach was used to optimize the 3D electro-Fenton process. The RSM results revealed that the quadratic model has a high R2 of 99.05 %. At 4 g L-1 iron foam particles, time of 5 h, and