Enabling Deep Learning and Swarm Optimization Algorithm for Channel Estimation for Low Power RIS Assisted Wireless Communications

International Journal of Interactive Mobile Technologies (iJIM), Год журнала: 2023, Номер 17(12), С. 171 - 194

Опубликована: Июнь 20, 2023

In this study, convolutional neural networks (CNN) and particle swarm optimization are used to offer a channel estimate technique for low power reconfigurable intelligent surface (RIS) assisted wireless communications (PSO). The suggested approach makes use of the RIS channels' sparsity lower CNN model's training complexity uses PSO optimize hyperparameters. proposed system has been trained using 70% dataset, 25% data was testing remaining 5% cross-validation. comparison previous methods, simulation results demonstrate that method delivers correct with much less computing cost. also exceeds current techniques in terms bit error rate (BER) mean squared (MSE) performance. research found 96.47% 90.96% accuracy algorithm respectively. Moverover, network dataset mentioned methodology section realizations, achieved value 0.012 algorithm. Also, study reported outperformed other state-of-the-art techniques. estimation, 0.0075.

Язык: Английский

---

A Training Program According to Interactive Teaching Strategies and its Impact on Achievement and Creative Problem Solving for Fourth-Grade Preparatory Students in Chemistry

International Journal of Emerging Technologies in Learning (iJET), Год журнала: 2023, Номер 18(04), С. 50 - 65

Опубликована: Фев. 23, 2023

The aim of the research is to know effect a training program based on interactive teaching strategies achievement and creative problem solving among fourth-grade students in chemistry directorate education Rusafa first, sample was divided into two groups, one experimental numbering (29) other control group (30) students. underwent first semester year (2021-2022) studied according usual method. Two tools were built, being an academic test consisting (40) multiple-choice items, second problem-solving skills subject (10) essay questions. results, using t-test for independent samples, showed that there statistically significant difference at level (0.05) favor average scores who applied which strategies.

Язык: Английский

---

A Partial Face Encryption in Real World Experiences Based on Features Extraction from Edge Detection

International Journal of Interactive Mobile Technologies (iJIM), Год журнала: 2023, Номер 17(07), С. 69 - 81

Опубликована: Апрель 5, 2023

User confidentiality protection is concerning a topic in control and monitoring spaces. In image, user's faces security with compound information, abused situations, participation on global transmission media real-world experiences are extremely significant. For minifying the counting needs for vast size of image info time needful to be address computationally. consequently, partial encryption user-face picked. This study focuses large technique that designed encrypt face slightly. Primarily, dlib utilizing detection. Susan one top edge detectors valuable localization characteristics marked edges, used extract features vectors from user faces. Moreover, relevance suggested generating key led crucial role improvement by producing them as difficult intruders. According PSNR values, recommended algorithms provided an adequate outcome encryption, they had lower encrypting duration larger impact.

Язык: Английский

---

Face detection by using Haar Cascade Classifier

Wasit Journal of Computer and Mathematics Science, Год журнала: 2023, Номер 2(1), С. 1 - 5

Опубликована: Март 30, 2023

the Haar Cascade Classifier is a popular technique for object detection that uses machine-learning approach to identify objects in images and videos. In context of face detection, algorithm series classifiers are trained on thousands positive negative regions image may contain face. The multi-stage process involves collecting training data, extracting features, classifiers, building cascade classifier, detecting faces test image, post-processing results remove false positives negatives. has been shown be highly accurate efficient videos, but it some limitations, including difficulty under challenging lighting conditions or when partially occluded. Overall, remains powerful widely-used tool important carefully evaluate its performance specific each application consider using more advanced techniques necessary.

Язык: Английский

---

Proposed Hybrid Secured Method to Protect Against DDOS in n Vehicular Adhoc Network (VANET)

International Journal of Interactive Mobile Technologies (iJIM), Год журнала: 2023, Номер 17(11), С. 141 - 154

Опубликована: Июнь 7, 2023

Security and safety are critical concerns in Vehicular Adhoc Networks. vulnerable to Distributed Denial of Service (DDoS) attacks, which occur when multiple vehicles carry out various tasks. This cause disrupts the normal functioning legitimate routes. In this work, Hybrid PSO-BAT Optimization Algorithm (HBPSO) based on modified chaos -cellular neural network (Chaos - CNN) approaches has been proposed overcome DDoS attacks. The suggest consists three-part hybrid optimization search algorithm enhance route from source destination, theory module is used detect abnormal nodes, then Modified Chaotic CNN (MCCN) employed prevent a malicious node sending data destination by determining that consumer more resource, packets lose or victim could reset path between attacker itself. CICIDS dataset test evaluate performance approach criteria accuracy, packet loss, jitter. Chaos approached results outperform similar models related work protects VANETs with high accuracy 0.8736, specificity 0.9959, TPR 0.9561, FPR 0.78, Detection rate 0.9561.

Язык: Английский

---