Search

Software-defined networking (SDN) is an innovative paradigm that separates the control and data planes, introducing centralized network control. SDN is increasingly being adopted by Carrier Grade networks, offering enhanced network management capabilities than those of traditional networks. However, because SDN is designed to ensure high-level service availability, it faces additional challenges. One of the most critical challenges is ensuring efficient detection and recovery from link failures in the data plane. Such failures can significantly impact network performance and lead to service outages, making resiliency a key concern for the effective adoption of SDN. Since the recovery process is intrinsically dependent on timely failure detection, this research surveys and analyzes the current literature on both failure detection and recovery approaches in SDN. The survey provides a critical comparison of existing failure detection techniques, highlighting their advantages and disadvantages. Additionally, it examines the current failure recovery methods, categorized as either restoration-based or protection-based, and offers a comprehensive comparison of their strengths and limitations. Lastly, future research challenges and directions are discussed to address the shortcomings of existing failure recovery methods. [ABSTRACT FROM AUTHOR]

Link failure is a critical issue in large networks and must be effectively addressed. In software-defined networks (SDN), link failure recovery schemes can be categorized into proactive and reactive approaches. Reactive schemes have longer recovery times while proactive schemes provide faster recovery but overwhelm the memory of switches by flow entries. As SDN adoption grows, ensuring efficient recovery from link failures in the data plane becomes crucial. In particular, data center networks (DCNs) demand rapid recovery times and efficient resource utilization to meet carrier-grade requirements. This paper proposes an efficient Decentralized Failure Recovery (DFR) model for SDNs, meeting recovery time requirements and optimizing switch memory resource consumption. The DFR model enables switches to autonomously reroute traffic upon link failures without involving the controller, achieving fast recovery times while minimizing memory usage. DFR employs the Fast Failover Group in the OpenFlow standard for local recovery without requiring controller communication and utilizes the k-shortest path algorithm to proactively install backup paths, allowing immediate local recovery without controller intervention and enhancing overall network stability and scalability. DFR employs flow entry aggregation techniques to reduce switch memory usage. Instead of matching flow entries to the destination host's MAC address, DFR matches packets to the destination switch's MAC address. This reduces the switches' Ternary Content-Addressable Memory (TCAM) consumption. Additionally, DFR modifies Address Resolution Protocol (ARP) replies to provide source hosts with the destination switch's MAC address, facilitating flow entry aggregation without affecting normal network operations. The performance of DFR is evaluated through the network emulator Mininet 2.3.1 and Ryu 3.1 as SDN controller. For different number of active flows, number of hosts per edge switch, and different network sizes, the proposed model outperformed various failure recovery models: restoration-based, protection by flow entries, protection by group entries and protection by Vlan-tagging model in terms of recovery time, switch memory consumption and controller overhead which represented the number of flow entry updates to recover from the failure. Experimental results demonstrate that DFR achieves recovery times under 20 milliseconds, satisfying carrier-grade requirements for rapid failure recovery. Additionally, DFR reduces switch memory usage by up to 95% compared to traditional protection methods and minimizes controller load by eliminating the need for controller intervention during failure recovery. The results underscore the efficiency and scalability of the DFR model, making it a practical solution for enhancing network resilience in SDN environments. [ABSTRACT FROM AUTHOR]

Seaweed foreign object detection has become crucial for food consumption and industrial use. This process not only can prevent potential health issues, but also maintain the overall marketability of seaweed production in the food industry. Traditional methods of inspecting seaweed foreign objects heavily rely on human judgment, which deals with large volumes with diverse impurities and can be inconsistent and inefficient. An automation system for real-time seaweed foreign object detection in the inspection process should be adopted. However, automated seaweed foreign object detection has several challenges due to its dependency on visual input inspection, such as an uneven surface and undistinguishable impurities. In fact, limited access to advanced technologies and high-cost equipment would also influence visual input acquisition, thereby hindering the advancement of seaweed foreign object detection in this field. Therefore, we introduce a computer vision model utilizing a deep learning-based algorithm to detect seaweed impurities and classify the samples into 'clean' and 'unclean' categories. In this study, we managed to identify six types of seaweed impurities including sand sticks, shells, discolored seaweed, grass, worm shells, and mixed impurities. We collected 1204 images and our model's performance was thoroughly evaluated based on comparisons with three pre-trained models, i.e., Yolov8, ResNet, and MobileNet. Our experiment shows that Yolov8 outperforms the other two models with an accuracy of 98.86%. This study also included the development of an Android application to validate the deep learning engine to ensure its optimal performance. Based on our experiments, the mobile application managed to classify 50 pieces of seaweed samples within 0.2 s each, showcasing its potential use in large-scale production lines and factories. This research demonstrates the impact of Artificial Intelligence on food safety by offering a scalable and efficient solution that can be deployed in other food production processes facing similar challenges. Our approach paves the way for broader industry adoption and advancements in automated foreign object detection systems by optimizing detection accuracy and speed. [ABSTRACT FROM AUTHOR]

Current credit card authorization was developed on single-threaded model whereby authentication process takes longer time to respond due to sequential process of card's risk management profile and its limitation of handling huge number of simultaneous transactions at single point of time. As a result, the performance of the authorization system was affected during peak hours. This study presented an architectural framework and prototype of credit card authorization system using multi-threading and shared memory pool techniques in order to improve the response time during authorization process. Through multi-threading technique, each worker thread will be assigned with several child threads to perform online fraud validation concurrently, depending on numbers of cryptographic elements presented in transaction message. Meanwhile, the worker threads itself performed card restriction validation based on the information stored in card's shared memory pool. This approach was implemented to reduce the idle time while waiting for slow cryptographic operation in each I/O operations that is performed through external device and to accelerate the authorization process through memory operation instead of accessing similar information from database. The implementation of these techniques, were then measured in terms of response time. The results showed that the performance of multi-threaded authentication engine was almost double of single-threaded authentication engine and the number of credit card authorization that can be processed using shared memory was ten percent higher than the number of credit card authorization that can be processed using database at single point of time. Key words: Credit card, authorization system, multi-threading, shared-memory pool, INTRODUCTION Credit card authorization is a process whereby the card issuer decides whether to approve or decline requests to accept transactions (1) performed by cardholders which is based on a [...]

Human emotion is often a reflection of one's behaviour that leads to awareness of one's mental health. Emotion detection on Twitter users specifically gains attention as it generates information that is useful in the field of psychology and linguistics. However, most existing works related to the subject analysed the emotion of a tweet based on the number of keywords or phrases in it, thus resulting in false annotations and eventually false judgement of the user's emotion. This paper proposes a two-step model with high and reliable accuracy to detect the emotion of Twitter users based on the semantic meaning of the tweets they posted. The first step classified the emotion of each tweet using four different deep learning techniques. The second step detected the emotion of the user based on the proposed statistical post-level features and a boosting technique. Then, Kappa's agreement score method was implemented to validate both models. The first step achieved 0.9482 in accuracy while the second step achieved 0.9683 in accuracy. To further validate such highly accurate result, a case study was conducted, and a web-based system was developed to analyse the emotion of college students during the COVID-19 pandemic. Additionally, our analysis corresponded to most of the current reports on the pandemic which further proved the reliability of the developed model. [ABSTRACT FROM AUTHOR]