Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
2 results
Search Results
Item Restricted Efficient Deep Learning for Plant Disease Classification in Resource Constrained Environment(The University of Georgia, 2024) Alqahtani, Ola; Ramaswamy, LakshmishDeep Neural Networks (DNNs) have been widely used in today’s applications. In many applications such as video analytics, face recognition, computer vision, and classification problems like plant disease classification, etc. DNN models are constrained by efficiency constraints (e.g., latency). Many deep learning applications require low inference latency, which must fall within the parameters set by a service level objective. The prediction of the inference time of DNN models raises another problem which are the limited resources of Internet of Things devices. These devices need an effective way to run DNN models on them. One of the most widely discussed technological developments since the Internet of Things is edge machine learning (Edge ML), and with good reason. Edge Machine Learning is a fast-growing well-known technological improvement since the existence of the Internet of Things (IoT). Edge ML allows smart devices to use machine learning and deep learning techniques to analyze data using servers locally or at the device level, which reduces the need for cloud networks. This is caused by a variety of issues, including poor internet access, expensive cloud resources, low-resource edge devices, and a high failure rate of Internet of Things (IoT) devices, either because of battery or connection issues. Finding a way to effectively run the DNN models locally on IoT devices is crucial.34 0Item Restricted QUALITY OF SERVICE AWARE DYNAMIC WAVELENGTH AND BANDWIDTH ALLOCATION ALGORITHM FOR 5G FRONTHAUL NETWORKS(Universiti Teknologi Malaysia, 2024-01-01) Alsheibi, Abdullah Zaini Zaini; Muhammad Bin Muhammad Al Farabi, IqbalThe Quality of Service (QoS) requirements for 5G are very strict in terms of latency of Fifth Generation (5G) traffic. 5G fronthaul networks between the baseband unit and remote radio heads are planned to use Next Generation – Passive Optical Networks 2 (NG-PON2) to carry their traffic. However, these Time Wavelength Division Multiplexing (TWDM) PON based networks also provide service to other traffic such as residential and corporate users. Therefore, it is crucial to provide QoS guarantees to 5G traffic. The main issue includes allocating transmission over multiple wavelengths while maintaining QoS. Although using all the available wavelengths all the time may seem to be the simple solution, each active wavelength increases the cost of operation. To solve these issues, this work proposes a technique using fuzzy logic to dynamically allocate wavelength and bandwidth for 5G fronthaul networks. Two types of traffic, i.e., 5G traffic and normal traffic are considered while the problem of Dynamic Wavelength and Bandwidth Allocation (DWBA) is formulated as a queueing theory problem using penalties and a cost function. Penalties are assigned for waiting packets as well as each active wavelength. Then, modelling the number of active wavelengths, the number of packets in the system, the total cost, and the traffic intensity as input fuzzy variables while modelling the change in the number of active wavelengths as the fuzzy output variable. The Mamdani implication is used for the fuzzy inference engine and the height method is used for defuzzification of the output variable. Simulations in MATLAB show that the proposed technique can maintain the latency of 5G traffic lower than the defined threshold while also significantly reducing the number of active wavelengths. A comparison with the existing state-of-the-art techniques shows that the proposed technique results in an improvement of at least 46% and 29% in terms of the average number of active wavelengths and the average latency for 5G traffic, respectively.24 0