Maize seed variety identification model using image processing and deep learning
- Authors: Gebeyehu, Seffi , Shibeshi, Zelalem S
- Date: 2024
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429191 , vital:72566 , DOI: 10.11591/ijeecs.v33.i2.pp990-9985
- Description: Maize is Ethiopia’s dominant cereal crop regarding area coverage and production level. There are different varieties of maize in Ethiopia. Maize varieties are classified based on morphological features such as shape and size. Due to the nature of maize seed and its rotation variant, studies are still needed to identify Ethiopian maize seed varieties. With expert eyes, identification of maize seed varieties is difficult due to their similar morphological features and visual similarities. We proposed a hybrid feature-based maize variety identification model to solve this problem. For training and testing the model, images of each maize variety were collected from the adet agriculture and research center (AARC), Ethiopia. A multi-class support vector machine (MCSVM) classifier was employed on a hybrid of handcrafted (ie, gabor and histogram of oriented gradients) and convolutional neural network (CNN)-based feature selection techniques and achieved an overall classification accuracy of 99%.
- Full Text:
- Date Issued: 2024
Information extraction model from Ge’ez texts
- Authors: Gebeyehu, Seffi , Wolde, Worke , Shibeshi, Zelalem S
- Date: 2023
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429176 , vital:72565 , 10.11591/ijeecs.v30.i2.pp787-795
- Description: Nowadays, voluminous and unstructured textual data is found on the Internet that could provide varied valuable information for different institutions such as health care, business-related, training, religion, culture, and history, among others. A such alarming growth of unstructured data fosters the need for various methods and techniques to extract valuable information from unstructured data. However, exploring helpful information to satisfy the needs of the stakeholders becomes a problem due to information overload via the internet. This paper, therefore, presents an effective model for extracting named entities from Ge'ez text using deep learning algorithms. A data set with a total of 5,270 sentences were used for training and testing purposes. Two experimental setups, i.e., long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM) were used to make an empirical evaluation with training and a testing split ratio of 80% to 20%, respectively. Experimental results showed that the proposed model could be a practical solution for building information extraction (IE) systems using Bi-LSTM, reaching a training, validation, and testing accuracy as high as 98.59%, 97.96%, and 96.21%, respectively. The performance evaluation results reflect a promising performance of the model compared with resource-rich languages such as English.
- Full Text:
- Date Issued: 2023
Comparison of Task Scheduling Algorithms for Traffic Surveillance Application Using Fog Computing
- Authors: Sinqadu, Mluleki , Shibeshi, Zelalem S , Khalid, Khuram
- Date: 2022
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429150 , vital:72563 , https://doi.org/10.1007/978-3-030-89776-5_3
- Description: One of the issues that service consumers face when using cloud-based solutions is the delay in processing large and real-time data. Fog computing has been introduced as a solution to this issue since it allows the data to be processed at the edge of a network while enabling different tasks to be scheduled for processing in fog devices at the edge network. These devices still require cloud resources to give them the capacity of processing real-time applications. However, scheduling these tasks must be made in such a way that they do not consume all the available resources on a fog device. When a task consumes all available resources, it can lead to network breakdown or high latency which is not acceptable for real-time applications. Therefore, to address this problem, this chapter proposes a task scheduling technique for traffic surveillance vehicular network application through smart cameras. We used the iFogSim simulator, where the scenario of vehicle tracking is considered. Simulations are conducted to find an efficient scheduling algorithm among a pool of available ones that can optimize the energy consumption and average delay of our proposed real-time application model. The results show that the First Come First Serve (FCFS) scheduling algorithm outperforms the Short Job First (SJF), Generalized Priority (GP) and Round Robin (RR) counterparts in terms of average latency, energy usage, execution time and network usage.
- Full Text:
- Date Issued: 2022
An Application to Support end-users of wi-fi Hotspots in the Township of Makhanda
- Authors: Buwa, Lubabalo , Shibeshi, Zelalem S , Terzoli, Alfredo
- Date: 2021
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429077 , vital:72558 , https://ieeexplore.ieee.org/abstract/document/9514200
- Description: Having access to the Internet is a powerful resource that can change one's life, but connectivity inequality continues to be a significant issue, especially for disadvantaged communities. The usage of Wi-Fi hotspots is becoming very useful for accommodating many people living in underprivileged areas to connect to the Internet. Primarily, these hotspots get deployed in public places like hotels, restaurants, etc. This paper discusses how such a system can be made to work as a solution for disadvantaged communities considering the user base in such communities and adhering to government regulations. The research is developed in collaboration with Khula Tech Solutions ISP that provides wireless Internet services in Makhanda (formally known as Grahamstown). Khula Tech Solutions is starting an initiative of installing Wi-Fi hotspots around the township of Makhanda and needs an application that will support users of the Wi-Fi hotspots. The research's result is a proof-of-concept mobile application developed through iterative and incremental software development techniques and mobile application technologies. With this research, the hope is that it is the beginning of further work for the users to become connected citizens.
- Full Text:
- Date Issued: 2021
Implementing a Content-Based Routing Framework for Application Integration on to Teleweaver Application Server
- Authors: Ngwenya, Sikhumbuzo , Shibeshi, Zelalem S , Terzoli, Alfredo
- Date: 2021
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/430580 , vital:72701 , https://ieeexplore.ieee.org/abstract/document/9576969
- Description: This paper presents an architectural overview of content-based dynam-ic routing for integrating applications on to an application server named TeleWeaver, a middleware platform developed within Siyakhula Living Lab (SLL). SLL is an ICT4D project in the Eastern Cape Province of South Africa. TeleWeaver was created as a mediation layer between software systems developed for use by beneficiaries of the Siyakhula Living Lab. The main challenge with these disparate systems was that they had unnecessary, redundant components; TeleWeaver acts as a common platform that suits the development of many services such as eGovernment, eHealth, and eJudiciary.
- Full Text:
- Date Issued: 2021
Towards the Development of a Photovoltaic Array Fault Detection and Diagnosis (PVAFDD) System
- Authors: Ncube, Prince D N , Meyer, Edson L , Shibeshi, Zelalem S
- Date: 2021
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429105 , vital:72560 , https://ieeexplore.ieee.org/abstract/document/9698581
- Description: The perpetual increment in energy demand continues to put pressure on the South African Economy. Independent Power Producers (IPPs) have been contracted to relieve the strain by supplementing energy production using solar photovoltaic (PV) technologies. These IPPs are paid per megawatt they produce and face stiff penalties should they fail to deliver on contractual obligations. Naturally solar PV plants are susceptible to numerous PV faults that could lead to a negative return on investment. It therefore makes economic sense to adopt mechanisms that can be able to detect, localize and diagnose PV faults when they occur within a solar PV system. There exists an extensive literature on how to detect and diagnose PV faults, however, localizing PV faults is still in its infancy. This paper proposes to cater to the needs of the IPPs by developing an intelligent PV Array Fault Detection and Diagnostics (PVAFDD) system capable of localizing PV faults which can be embedded into the Supervisory Control and Data Acquisition (SCADA) system used to manage and control such PV systems. The PVAFDD system is based on a machine learning (ML) model implemented using logistic regression algorithm. The ML model is trained using meteorological data ranging over a period of eight years in Alice, Eastern Cape. Using simulations driven by real-life data scenarios, we have been able to train, validate and test the PVAFDD system. When the PVAFDD system detects a fault, a cascade of real-time PVA tests is undertaken to localize the PV fault. The system then carries out PVA fault diagnostics and gives recommendations on the PV fault classification. Corrective measures can therefore be implemented on the affected PVA swiftly reducing the downtime of the PV plant, ergo proving to be a cost-effective measure that offers a competitive edge to IPPs using the PVAFDD system.
- Full Text:
- Date Issued: 2021
An RTSP proxy for implementing the IPTV media function using a streaming server
- Authors: Shibeshi, Zelalem S , Terzoli, Alfredo , Bradshaw, Karen L
- Date: 2012
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429136 , vital:72562 , https://www.informatica.si/index.php/informatica/article/view/383
- Description: Multimedia content delivery in IMS, including IPTV, is handled by a separate unit, the Media Function (MF), made up of media control and media delivery units, which in the case of IPTV are the Media Control Function (MCF) and Media Delivery Function (MDF), respectively. According to the different specifications of an IMS based IPTV architecture, the User Equipment (UE) is expected to use the RTSP protocol as a media control protocol to interact with the MCF, and obtains delivery of media from the MDF using the RTP protocol. This also means that the streaming session needs to be initiated from the media controller on behalf of the user but the delivery of media is sent to the UE from the media deliverer (media server). Due both to the lack of free and open source Media Servers and the availability of free and open source Streaming Servers, the ideal choice for the delivery of multimedia services, including IPTV, by the research community is Streaming Servers. Nevertheless, because of denial of service attacks and other issues, most streaming servers do not allow a different location for the session setup request and the delivery of media in the streaming session. In other words, most streaming servers are not designed to be controlled by some other entity other than the RTSP client that consumes the media. This makes it difficult to have a separate media control unit for IPTV service in IMS if one wanted to use a streaming server as an MDF unit. So, while waiting for streaming servers to work in this manner, it is better to find a work around in order to use streaming servers to develop and test IPTV services in IMS environments. For this purpose we propose another component (an RTSP proxy and relay unit) as part of the IPTV MF and to mediate between the MCF and MDF. This unit correctly relays media control commands from the MCF to the MDF and RTP packets from the MDF to the UE. It also helps in the implementation of other streaming functionalities that are required for IPTV service delivery, but which are not implemented in the current open source streaming servers. Additional services can also be easily implemented with the help of this unit. This will facilitate the development of an IPTV service using readily available open source streaming servers and help researchers to evaluate their proposals on new services they would like to develop. In this paper we show how this RTSP proxy unit can be integrated into the Media Function of the IPTV architecture to ease the media delivery process of an IMS based IPTV service.
- Full Text:
- Date Issued: 2012
Research Testbed Networks: Practical Tools for Service Delivery?
- Authors: Wertlen, Ronald R , Siebörger, Ingrid , Tsietsi, Mosiuoa , Shibeshi, Zelalem S , Terzoli, Alfredo
- Date: 2012
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429204 , vital:72567 , https://doi.org/10.1002/j.1681-4835.2012.tb00351.x
- Description: The Telkom Centre of Excellence (CoE) at Rhodes University, housed in the Computer Science department was opened in 1997. The CoE's focus on Distributed multimedia service platforms soon showed that the technology being researched could be applied in the disadvantaged peri‐urban communities. The CoE has thus concentrated its research on building a testbed network that delivers real services to real users. In 2007, the testbed was extended to include a marginalised rural area in the Siyakhula Living Lab. The greatest factor in the sustainability of the CoE testbed network has been maintaining usefulness to all the stakeholders over the last 12 years. Industrial funding, University outreach goals and research goals could all be harmonised, while sustaining the delivery of high quality informatics services in the community. This paper presents a brief case study of the communications network testbed and how it was applied to the Development Informatics space. It analyses the roles played by stakeholders in either assisting and sustaining or obstructing the service delivery. It makes key recommendations on best practices for research networks that can also bring informatics to disadvantaged communities. It shows how testbeds for the research of new technologies can be designed so as to allow Development Informatics work to take place on such networks.
- Full Text:
- Date Issued: 2012
Delivering a personalised video service using IPTV
- Authors: Shibeshi, Zelalem S , Ndakunda, Shanga , Terzoli, Alfredo , Bradshaw, Karen L
- Date: 2011
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429163 , vital:72564 , https://ieeexplore.ieee.org/abstract/document/5746086
- Description: Video oriented services are taking the lead in terms of revenue in the current Internet environment. In order to tap this revenue, Telcos are resorting to serious measures such as moving to Next Generation Network (NGN) where they can provide QoS for services that demand this feature, such as, IPTV. IPTV is more than just what its name implies and includes various types of additional services to make the TV a better entertainment and communication environment. Various innovative IPTV services have been proposed and developed by researchers and practitioners, including personalized advertisement, personalized EPG (Electronic Program Guide), and personalized VoD (Video on Demand). In this paper we introduce a new IPTV service called, the personalized dynamic video delivery service, which sends new video alerts (like breaking news alert) to subscribed users and notifies them when the video is available. If desired, users can watch the video automatically by switching from what they are currently watching without requiring explicitly a new video setup. Users can configure their profile and also set a policy on the way they wish to be notified and the types of video they wish to be alerted to. The paper describes the issues surrounding the delivery of this service and presents the architecture and the various open source technologies that are used to develop the service.
- Full Text:
- Date Issued: 2011
Using an RTSP Proxy to implement the IPTV Media Function via a streaming server
- Authors: Shibeshi, Zelalem S , Terzoli, Alfredo , Bradshaw, Karen L
- Date: 2010
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429120 , vital:72561 , https://ieeexplore.ieee.org/abstract/document/5676629
- Description: Multimedia in IMS, including IPTV, is handled by a separate unit, the Media Function (MF), which is made up of Media Control and Media Delivery Functions (MCF and MDF). According to the different specifications of an IMS based IPTV architecture, the User Equipment (UE) is expected to use the RTSP protocol as a media control protocol to interact with the MCF, and gets delivery of media from the MDF using the RTP protocol. This generally means that the streaming session is initiated from the media controller on behalf of the user but the delivery of media is sent to the UE from the media deliverer (media server). Due to lack of free and open source Media Servers and on the contrary, the availability of free and open source Streaming Servers, the ideal choice for the delivery of media in multimedia services, including IPTV, by the research community are Streaming Servers. Nevertheless, because of denial of service attack and other issues, most streaming servers do not allow different locations for the session setup request and the delivery of media of the streaming session. This makes it difficult to have a separate media control unit for IPTV service in IMS, if one wants to use a streaming server as an MDF unit. For this purpose we propose another component (an RTSP proxy and relay unit) to be part of the IPTV Media Function (MF). The unit will be used to mediate between the MFC and MDF and will properly relay media control (RTSP) commands from the UE and MFC to the MDF and RTP packets from the MDF to the UE. This, we believe, will facilitate the development of an IPTV service using readily available open source streaming servers. In this paper we show how this RTSP proxy and relay unit can be integrated into the Media Function of the IPTV architecture to ease the media delivery process of IMS based IPTV service.
- Full Text:
- Date Issued: 2010
An Asterisk-based framework for E-learning using open protocols and open source software
- Authors: Tsietsi, Mosiuoa , Shibeshi, Zelalem S , Terzoli, Alfredo , Wells, George C
- Date: 2009
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/429091 , vital:72559 , https://ieeexplore.ieee.org/abstract/document/5338904
- Description: This paper describes the conceptual design of an e-learning system that is based on open protocols and open source software. This is an initial step towards providing a framework within which remote lectures at our university can be conducted with other institutions in the Southern African region. The motivation for this effort is born out of a desire to avoid expensive and inflexible commercial tools that have been used in the past, often with undesirable side effects. Our design promises to deliver most of the features that can be expected of a modern e-learning system such as a Web interface, space for lecture material, real-time audio and video support, instant messaging and the ability to convey presence. We identified two modes of operation, one as a Web-based video archive and the other as a live virtual classroom. It is hoped that this dual-mode setup will support different modes of learning for students and suit different bandwidth resources among institutions.
- Full Text:
- Date Issued: 2009