NTU Journal of Engineering and Technology

WIRELESS LAN DESIGN AND FUTURE INTERNET ARCHITECTURE

Ashraf Thaker Mahmood , Osman Nuri UÇAN — Fri, 15 Mar 2024 00:00:00 +0000

In this research thesis, an advance work is being done on the Wireless Local Area Network (WLAN) design and future internet architecture for intrusion detection. There has been a large shift worldwide in using technology in almost every aspect of our lives. This trend has been termed in many industries as the "Internet of Things" (IoT), where the Internet and cloud- based activities are seeing more and more use for control, monitoring and data storage applications. As stated earlier, these assumptions were made because of the extreme difficulty in obtaining any related telemetry from an actual WLAN system or business-critical network. To improve the validity of the simulation, it would be beneficial to obtain even sanitized telemetry from an actual system. Then, the simulation could be refined to better reflect the dynamics of the signals in a real system. If actual WLAN system data is unobtainable, then the test by itself can be modified to reflect more processes seen in these systems. First, a small flow loop with sensing and control elements could be constructed and driven by the servers of the test bed. The primary server in the test bed that acts as the WLAN server could then be programmed to poll the sensors, issue commands and collect data. Time synchronous averaging techniques are used to resample telemetry sources that have different sampling rates. The research provides several case studies to prove the efficacy of the newly developed variable grouping technique for WLAN. Recall that variable grouping methods are needed to extract sets or subsets of variables that give the lowest model prediction errors. The research also presents AAKR and AAMSET model results for several successfully detected intrusion activities from two different data sets. The models utilized four different clusters of telemetry taken from the Linux kernel to determine which class of telemetry was more effective for intrusion detection. The knowledge-based system is certainly the most numerous and widely used type that uses signatures or features of known wireless network attacks for detection purposes. While this type is easy to implement and has a low rate of false/missed alarms, it will always miss the so-called zero-day wireless network attacks. Recall that a zero-day wireless network attack is a new, unknown intrusion. Because the knowledge-based system has never seen a zero-day intrusion event, it will classify this new behavior as normal. In contrast, the behavior-based system can detect known and zero-day wireless network attacks with an accuracy of 97.86% correctly. This type uses data-driven modeling techniques to learn normal system behavior. Once trained, any future monitored telemetry that deviates from this learned behavior will be labeled as an intrusion event.

Preserving Big Data Privacy in Cloud Environments Based on Homomorphic Encryption and Distributed Clustering

Shatha A. Baker — Fri, 15 Mar 2024 00:00:00 +0000

Cloud computing has grown in popularity in recent years because to its efficiency, flexibility, scalability, and the services it provides for data storage and processing. Still, big businesses and organizations have severe concerns about protecting privacy and data security while processing these massive volumes of data.

This paper proposes approach that intends to enhance efficiency in delivering advanced data protection, hence filling security holes, by enhancing data protection from various big data sources. A partial homomorphic encryption system is used to encrypt data created by many sources or users and processed in the cloud without decrypting it, hence protecting data from attackers. Extremely Distributed Clustering (EDC) has also been applied to partition large datasets into many cloud computing node subsets. This method can ensure privacy and protect data while also enhancing the effectiveness and performance of big data analytics. According to the results, the proposed technique was faster and gave improved encryption performance by around 23-28%.

Network Attack Detection for Business Safety

Fadia Abduljabbar Saeed, Ghalia Nassreddine, Joumana Younis — Fri, 15 Mar 2024 00:00:00 +0000

In the technology age, the use of networks has hugely increased. this led to an increment in the number of attackers. A network attack is an try to achieve unauthorized access to personnel of an organization’s network, steal data or perform other malicious activity. Machine Learning is a subset of artificial Intelligence techniques that teaches machines to learn from historical information. In this paper, a machine learning-based approach was developed to detect network attacks. Two Machine learning models were used: Support vector machine and Artificial neural network. In this approach, a feature selection step based on the p-value is executed first to reduce the size of the dataset. After that, training and testing steps were performed. The proposed approach was tested on a real dataset collected from Kaggle. Confusion matrix, recall, precision, and f1 score were used to test the performance of the used ML techniques. The result shows the efficiency of this approach.

ARTIFICIAL INTELLIGENCE BASED HELIPAD DETECTION WITH CONVOLUTIONAL NEURAL NETWORK

Emad Ahmed Mohammed, Ahmed J. Ali, Abdullah Mohammed Abdullah — Fri, 15 Mar 2024 00:00:00 +0000

When a malfunction occurs in the helicopter or the pilot faints during a flight or performing a duty, and in order to ensure the safety of the pilot and the helicopter, a system must be available to detect the helicopter landing pads, so that the helicopter can land at the airport. Closest safe place immediately. This study focuses on helicopter landing pad detection using YOLOv8 and YOLOv5 models. A dataset of 1877 images collected from the Internet was used to evaluate the performance of the models. YOLOv8 showed good performance in helipad detection with 96.7% accuracy and 95.8% recall, resulting in an average accuracy (mAP@0.5) of 98.8%. As for YOLOv5, it reached 95.1% precision, 95.8% recall, and 97.5% mAP@0.5. Both models showed good results, but YOLOv8 outperformed it by a small percent.

Translating Sumerian Symbols into French Letters

Raid Rafi Omar Al-Nima, Lubab H. Albak, Arwa Hamed Al-Hamdany — Fri, 15 Mar 2024 00:00:00 +0000

Sumerian symbols, which look like cuneiform letters, were used in a very old writing style. In this paper, a new method to translate the Sumerian symbols into French letters is introduced. It is based on the Cascade-Forward Neural Network (CFNN). The CFNN is exploited and adapted for the translation issue. It accepts a cuneiform letter image as an input and produces an appropriate output that refers to the translated french letter. Reasonable image augmentations are employed. These augmentations are for the: left direction rotations, right direction rotations and multiple translation directions (to the left, right, bottom and top). Total of 780 images are utilized for rotations and 338 images are collected for translations. This work can successfully attain the performance of 100%.

Influence of Using ACO Algorithm in STATCOM Performance

Maha Al-Flaiyeh — Fri, 15 Mar 2024 00:00:00 +0000

Flexible alternating current transmission systems (FACTS) are technologies that rely on the use of high-power electronic equipment and advanced control methods to increase the ability of electrical transmission lines to transmit the largest amount of electrical power.Static_ synchronous _compensator (STATCOM) is one of FACTS_ family It has a rapid ability to supply or absorb reactive power from the system, traditional controller in STATCOM is (PID) or (PI). The controller is used to control the currents and voltages. In (STATCOM) there are two control loop, the inner loop which is represented by controlling the source current, and the outer loop which is used to control the voltage of the DC-link energy –storage- capacitor (vdc). Many algorithms are used in optimization to predict a specific behavior and to find the best solution for it. Two optimization methods were used Ant Colony Algorithm (ACO) and Genetic Algorithm (GA) to adjust the parameters of the outer PI controller. This unit is responsible for adjusting (vdc). The capacitor voltage is converted by the STATCOM inverter into a three-phase voltage, which is used to supply the load with required reactive power. Through the simulation and control process, the results demonstrated the effectiveness of the compensator in supplying the reactive power to the linear or non-linear loads, The results also showed that using the ACO technique that the integrated time absolute error ( ITAE) was reduced which gives more precise in adjusting the PI control parameters Which is achieved best Vd.c response ,compared with the GA and ziklur-nichlos method , by measuring the response of the lowest settling time (TS) and minimal peak overshoot (P-ov) .