94 research outputs found
Data Diversity in Convolutional Neural Network Based Ensemble Model for Diabetic Retinopathy
No full textThe medical and healthcare domains require automatic diagnosis systems (ADS) for the identification of health problems with technological advancements. Biomedical imaging is one of the techniques used in computer-aided diagnosis systems. Ophthalmologists examine fundus images (FI) to detect and classify stages of diabetic retinopathy (DR). DR is a chronic disease that appears in patients with long-term diabetes. Unattained patients can lead to severe conditions of DR, such as retinal eye detachments. Therefore, early detection and classification of DR are crucial to ward off advanced stages of DR and preserve the vision. Data diversity in an ensemble model refers to the use of multiple models trained on different subsets of data to improve the ensemble’s overall performance. In the context of an ensemble model based on a convolutional neural network (CNN) for diabetic retinopathy, this could involve training multiple CNNs on various subsets of retinal images, including images from different patients or those captured using distinct imaging techniques. By combining the predictions of these multiple models, the ensemble model can potentially make more accurate predictions than a single prediction. In this paper, an ensemble model (EM) of three CNN models is proposed for limited and imbalanced DR data using data diversity. Detecting the Class 1 stage of DR is important to control this fatal disease in time. CNN-based EM is incorporated to classify the five classes of DR while giving attention to the early stage, i.e., Class 1. Furthermore, data diversity is created by applying various augmentation and generation techniques with affine transformation. Compared to the single model and other existing work, the proposed EM has achieved better multi-class classification accuracy, precision, sensitivity, and specificity of 91.06%, 91.00%, 95.01%, and 98.38%, respectively
Digital processing of stress in Standard Arabic
No full textAbstractGiven that accurate stress assignment rules can help enhance speech technology applications, the present paper provides a digital processing of stress in Standard Arabic. The findings indicate that stress in this language is manifested by a variety of correlates, namely duration, intensity and fundamental frequency. Nevertheless, only duration and intensity have proved to be the most reliable phonetic stress correlates. The digital processing also shows that there is an important interaction between syllable structure and stress assignment
SWAP: Smart WAter Protocol for the Irrigation of Urban Gardens in Smart Cities
No full text[EN] The implementation of Smart City projects has experimented a surge in the recent years with examples such as Smart Santander or Barcelona Smart City. Among the different domains that comprise the Smart City, water management has a great importance, more so in areas with water scarcity. Furthermore, water from different sources such as treated sewage water or collected rainwater can be utilized to address water needs where the use of potable water is not necessary. Therefore, the implementation of smart systems for the irrigation of urban gardens and other urban vegetated areas is of great importance to manage both water needs and the available resources. In this paper, a communication protocol for smart irrigation systems designed within the context of the Smart City is presented. The protocol enables the communication among devices with both LoRa and WiFi wireless technologies. Tests were performed with low-cost devices in an urban area. The results demonstrate the good performance of the proposal, obtaining the minimum packet loss by adding a 500 ms delay at the CH node when transmitting messages from WiFi to LoRa and vice versa.This work was supported by the Researchers Supporting Project, King Saud University, Riyadh, Saudi Arabia, under Grant RSP-2021/295.Aldegheishem, A.; Alrajeh, N.; García-García, L.; Lloret, J. (2022). SWAP: Smart WAter Protocol for the Irrigation of Urban Gardens in Smart Cities. IEEE Access. 10:39239-39247. https://doi.org/10.1109/ACCESS.2022.3165579S39239392471
A QoS-Based routing algorithm over software defined networks
No full text[EN] Video streaming requires reliable transmission and a steady network to satisfy the video users and applications QoS needs. The network service must provide and meet a certain level of performance to accommodating these QoS, specially in Smart City environments, but current Internet best-effort service does not guarantee QoS. Software-defined networking (SDN) is an approach intended to separate the network control and data (forwarding) planes to get better management and optimization, which clearly enhance the planning and development of smart urban communities. In this paper, we propose a dynamic QoS algorithm over SDN to select the optimum path that meets video QoS in order to optimize the quality of experience (QoE). We differentiate the traffic based on video resolution QoE parameters to Standard Definition (SD) and High Definition (HD). The results demonstrate that the proposed method obtained better viewing quality for an smart community environment and increases the overall network throughput.Researchers Supporting Project number (RSP-2021/295) , King Saud University, Riyadh, Saudi Arabia.Elbasheer, MO.; Aldegheishem, A.; Lloret, J.; Alrajeh, N. (2021). A QoS-Based routing algorithm over software defined networks. Journal of Network and Computer Applications. 194:1-14. https://doi.org/10.1016/j.jnca.2021.103215S11419
Develop an Optical Sensor to Detect Pollution Incidents in Sewerage
No full text[EN] Cities are big consumers of energy and big producers of pollution. In the past years, the concept of smart cities has been applied to reduce the release of pollutants and to reduce energy consumption. In this article, we present a wireless sensor network (WSN) based on solid sensor nodes to detect illicit discharges in sewerage. The solid sensor is an optical sensor that uses infrared light to determine the pollutant concentration in water. At 0 degrees, a photoreceptor receives infrared LED (IR LED) light and allows the current passage. This provokes a reduction of the internal resistance of the photoreceptor that can be measured. First, we tested different intensities of powered LEDs and resistances in the voltage divider. Once the best combinations had been selected, we calibrated our sensor. Our result suggested that the relative error of our prototype is 3.4% in the range of 200-5000 mg/L.This work was supported in part by the Researchers Supporting Project, King Saud University, Riyadh, Saudi Arabia, under Grant RSP-2021/295; in part by the Ministerio de Educacion, Cultura y Deporte through the "Ayudas para contratacion predoctoral de Formacion de Profesorado Universi-tario (FPU) (Convocatoria 2016)" under Grant FPU16/05540; in part by the "Ministerio de Ciencia e Innovacion (MCIN)" under Project PID2020-114467RR-C33; in part by the "Ministerio de Agricultura, Pesca y Alimentacion" through the Project GO TECNOGAR; and in part by the ThinkInAzul Program by MCIN through the European Union NextGenerationEU under Grant PRTR-C17.I1 and the Generalitat Valenciana under Grant THINKINAZUL/2021/002.Rocher, J.; Aldegheishem, A.; Alrajeh, N.; Lloret, J. (2022). Develop an Optical Sensor to Detect Pollution Incidents in Sewerage. IEEE Sensors Journal. 22(24):24449-24457. https://doi.org/10.1109/JSEN.2022.3219931S2444924457222
Wireless sensor networks: current status and future trends
No full textHuman sensing is one way of collecting information, acquiring knowledge and making reliable decisions. Wireless Sensor Networks (WSNs) imitate this human intelligence capability, but on a wider distributed scale, with faster, cheaper and more effective ways that can be used for different applications. Recognizing this fact, we decided to introduce this book on WSNs that documents the current state of these networks, and their future trends.
As the subject is relatively recent and enjoying fast development, we thought that the book should be written by researchers and experts in the field. We called on those experts to contribute to the book by writing chapters in their area of the expertise. Our role was to organize the flow of knowledge through the various sections of the book; and to ensure consistency on the one hand, and clarity on the other. The book would be useful as a reference item to all students, graduates, academics, and researchers of computer science and engineers, whether working in professional organizations, or research institutions.
The book covers the various issues associated with WSNs, including: their structure, activities, and applications. It consists of five main sections divided into 17 chapters. Consequently, this book could be subdivided into five distinct sections
Intrusion Detection Systems Based on Artificial Intelligence Techniques in Wireless Sensor Networks
No full textIntrusion detection system (IDS) is regarded as the second line of defense against network anomalies and threats. IDS plays an important role in network security. There are many techniques which are used to design IDSs for specific scenario and applications. Artificial intelligence techniques are widely used for threats detection. This paper presents a critical study on genetic algorithm, artificial immune, and artificial neural network (ANN) based IDSs techniques used in wireless sensor network (WSN)
Robust Coding and Modulation for Body-Area Networks
No full textPublication in the conference proceedings of EUSIPCO, Marrakech, Morocco, 201
HIPAA BASED HEALTHCARE INFORMATION SECURITY QUALITATIVE ASSESSMENT, APPLICATION OF INFORMATION SECURITY FOR SAUDI HOSPITALS
No full textThe present paper deals with HIPAA (Health and Insurance Portability and Accountability Act) based Qualitative Assessment of the measures undertaken to ensure Information Security in e-Health Systems. It presents and discusses in particular an “on the ground” experiment targeting the assessment of Healthcare Information System (HIS) Security in 2 majors Saudi University Hospitals (KSUH): KKUH- King Khalid University Hospital including KAUH King Abdulaziz university hospital and KFMC- King Fahd Medical City. The paper describes the proposed HIPAA based Qualitative assessment and its related checklists. It presents the findings related to this approach application led into two Saudi Hospitals, as well as the recommendations emitted to fill the identified gap
- …
