NTU Journal of Engineering and Technology

In the human body, the skin serves as the primary layer of defense for essential organs. However, as a result of ozone layer degradation, exposure to UV radiation, fungal and viral infections. Skin cancer is becoming more common .This studyproposes a novel deep learning-based framework for the multi-classification of eight different types of skin cancer. The suggested framework is divided into several steps. The initial phase is the data augmentation of images. In the second step, deep models are fine-tuned. The model is opted, for Inception-v3, and updated their layers. In the third step, The suggested model has been applied to train both fine-tuned on augmented datasets.After optimization, the pre-trained model performs well for classifying skin tumors, with Inception-v3 having accuracy and an F-score of 81% and 81%, respectively.

Recently, periocular region has been employed in recognitions and it can be so effective especially in wearing a face mask as happened during the Coronavirus pandemic. In this study, anew method is proposed for recognizing persons based on their perioculars. It is named the Dual Deep Periocular Parts (DDPP). In this method, two deep learning networks are employed, where each network is determined for acertain periocular side (right or left). They are termed the Deep Network for the Right Periocular (DNRP) and Deep Network for the Left Periocular (DNLP). Both the DNRP and DNLP are fused together to construct the proposed DDPP approach. Also in this paper, a database called the Northern Technical University Periocular Database (NTUPD) is collected from scratch. Persons recognition based on the proposed periocular approach shows further performance enhancementsas we obtained results of accuracy that reached 98.7% and Equal Error Rate (EER) 1.3%

Understanding and utilizing informal words not recognized in standard dictionaries poses challenges for users. These words are specific to certain communities, hindering comprehension for those outside. Natural language processing tasks, like translation and summarization, struggle with informal vocabulary and local dialects. Although existing models can translate informal words, comprehensive solutions are elusive due to regional and contextual variations. Developing natural language processing models that consider informal words and local dialects is crucial for future research. This paper presents an updated dataset of informal English words tailored to current usage. Multiple models from the Transformer core library on the Hugging Face platform were trained and evaluated, with the facebook/bart-base model demonstrating high accuracy (training data loss: 0.05299). Continued research and innovation in this field are imperative for effective cross-cultural and intercommunity communication.

Fog computing hasemerged as a promising paradigm for bringing capabilities of cloud computing closer to the edge computing. It tries to overcome the limits of traditional cloud designs by putting storage,computing, and resources of networking closer to the data source. This results in accelerated processing, decreased latency, and enhanced system performance. Fog computing designs use a hierarchical approach, where the fog nodes act as an intermediary layer for local data processing and the cloud infrastructure acts as the top layer to support the fog nodes while the devices and sensors generate the data at the bottom layer.The paper discusses the uses of fog computing, and security issues,and suggests countermeasures including encryption, intrusion detection, and access control to reduce risks. It is anticipated that as fog computing develops further, it will spur creativity and efficiency in the linked world because to its adaptability and versatility. Inorder to properly utilize the promise of fog computing and handle security concerns, the paperunderlines the significance of ongoing research and development.

Denial of service and Distributed denial of service (Dos/DDos) attacks continue to be one of the most significant dangers in cybersecurity. Many efforts are being put into developing defenses against these types of attacks. The tools used by attackers to perform these types of attacks increase day-to-day. Thus, a countermeasure is necessary. For this reason, this thesis utilized one of the most recent datasets (CSE-CICIDS2018 and CIC-DDoS2019) containing most Dos/DDoS attacks. This study proposed a framework based on Machine Learning for detecting denial-of-service (DoS) and distributed denial-of-service (DDoS) attacks. The framework comprises three main modules: feature selection method using Random Forest—Recursive Feature Elimination (RF-RFE), handling the Imbalanced class distributions using Synthetic Minority Oversampling Technique (SMOTE), and classification. This study used five classifiers to make comparisons that include Random Forest (RF), Naive Bayes (NB), Logistic Regression (LR), and Linear and Quadratic Discriminant Analysis (LDA, QDA)”. Framework empirical findings reveal that the RF-RFE_SMOTE_RF outperformed all other models by obtaining an accuracy of 100% for CSE-CIC-IDS2018 and 0.99% for CIC-DDoS2019.

The importance of power system operation is becoming increasingly significant due to the escalating demand observed in many nations. The exponential growth in load demand exerts substantial stress on electrical power systems, since they run in close proximity to their critical thresholds due to limitations imposed by environmental and economic factors. The basic goal of operating electricalpower networks is to efficiently supply energy to users at optimal frequency and voltage levels, with a focus on cost minimization.The main objective of this study is to examine the augmentation of voltage stability margin by deploying Flexible AC Transmission Systems (FACTS) at their ideal positions. In order to determine the most efficient size of a Static Synchronous Compensator (STATCOM), it is necessary to explore the relationship between the loading factor and the capacity of the STATCOM. The casestudy utilized the Iraqi National Super Grid System (INSGS), which consisted of a 24-bus configuration.The effectiveness of the CPF technique has been assessed in the framework of the Iraqi Super Grid test System. The appropriate place for attaching STATCOM to enhance voltage stability in the Iraqi network system was identified to be Bus (20).

This paper presents the design and implementation of a solar panel data monitoring system using a SCADA (Supervisory Control and Data Acquisition) system. The system is built via the Siemens S7-1200 Programmable Logic Controller (PLC) and programmed using TIA (Totally Integrated Automation) Portal V17 software. The system includes various sensors and instrumentation for monitoring solar panel performance, such as temperature sensors, current and voltage sensors, and irradiance sensors. The PLC collects data from these sensors and transmits it to the SCADA software, which displays real-time data on the graphical user interface (GUI). The system also includes features such as alarms and notifications for abnormal conditions, data logging for historical analysis, and remote access for monitoring and control from a central location. The system's reliability and efficiency are enhanced through the use of the S7-1200 PLC and TIA Portal V17 software, which provide advanced programming and automation capabilities. Therefore, this solar panel data monitoring system provides a comprehensive solution for monitoring and optimizing the performance of solar panel systems, helping to increase efficiency, reduce downtime, and improve overall system performance.