2692-4048ISSN (Online)
2770-0070ISSN (Print)
In the modern-day diagnostics, ultrasound play an important role in different applications such as vascular, gynecological, cardiac, and obstetrical for diagnosis the various diseases. The main benefit of the ultrasound is that it is non-invasive method and inexpensive. However, in the real-scenario, ultrasound images contain speckle noise which negatively impact the image quality in terms of edges, texture information, and boundaries. In order to eliminate noise, various filters are deployed by researchers in the literature. The limitations of their method are that a fixed level of noise is removed using conventional filters in which parameter values of the filters are fixed. However, in the real-time situation, the noise is random and adaptive filters are required which eliminate any level of noise. To achieve this goal, this paper proposes an adaptive filtering model for eliminate speckle noise based on yellow saddle goatfish optimization (YSGO) algorithm. The YSGO algorithm is based on the hunting behaviour of the fishes. In the proposed model, bilateral filter and speckle-reducing anisotropic diffusion filtering methods and enhancement power law method are taken under consideration. Further, the parameter values of the filtering method and enhancement methods are determined using the nature-inspired YSGO algorithm. The YSGO algorithm minimize the noise and enhances the image brightness and edge information based on the objective function. In our model, mean square error (MSE) and entropy is taken as the objective function. Further, the proposed model is applied on the standard ultrasound images. The visual analysis of the images is done based on the subjective analysis whereas various performance metrics are measured for measure the image quality in the objective analysis. The results reveals that the proposed model outperforms over the existing models in terms of PSNR.
Read MoreDoi: https://doi.org/10.54216/FPA.120201
Vol. 12 Issue. 2 PP. 08-18, (2023)
Because network of sensors gives a more accurate representation of remotely sensed environments, a network of wirelessly connected sensors is essential. Data packets must be routed to the base station hop by hop, which causes conventional network data collecting to use a lot of power. Unmanned aerial vehicles (UAV) were employed for hovering over the detected environment and gather data to solve this issue. The paper also aims to provide an automatic alignment for UAV antennas for tracking by utilising computer vision technologies. A directional antenna with high gain is used by a ground station that can operate by a pan-tilt to point towards the low-gain omnidirectional antenna carried by the UAV. To center the UAV's antenna's image in the frame, the antenna is equipped with a camera, and a computer detects the video and controls the pan-tilt. The antennas are aligned if there are no more than a few pixels between the UAV image center and the image center. The proposed imaging system exhibits fast data collection, thus attaining a high packet delivery rate and the minimum use of energy. With the suggested antenna auto-alignment approach, the antennas can be accurately aligned with an angle error of under one. UAVs must take the smoothest and shortest pathways possible to accommodate their motion and time constraints. As a result, the Traveling Sales Problem (TSP) is utilized to determine the shortest route, and Bezier curves are then employed to turn paths into a flyable path.
Read MoreDoi: https://doi.org/10.54216/FPA.120202
Vol. 12 Issue. 2 PP. 19-27, (2023)
The Internet of Things (IoTs) has accelerated with the introduction of powerful biomedical sensors, telemedicine services and population ageing are concerns that can be solved by smart healthcare systems. However, the security of medical signal data that collected from sensors of IoTs technology, while it is being transmitted over public channels has grown to be a serious problem that has limited the adoption of intelligent healthcare systems. This suggests using the technology of blockchain to create a safe and reliable heart sound signal (PCG) that can communicate with wireless body area networks. The security plan offers a totally dependable and safe environment for every data flowing from the back end to front-end. Also in this paper, to classify heart sound signals, we suggested a one-dimensional convolutional neural network (1D-CNN) model. The denoising autoencoder extracted the heart sounds' deep features as an input feature of 1D-CNN. To extract the detailed characteristics from the PCG signals, a Data Denoising Auto Encoder (DDAE) was used instead of the standard MFCC, the suggested model shows significant improvement. The system's benefits include a less difficult encryption algorithm and a more capable and effective blockchain-based data transfer and storage system.
Read MoreDoi: https://doi.org/10.54216/FPA.120203
Vol. 12 Issue. 2 PP. 28-41, (2023)
Certificate management is a tedious task for any university or any other organization. These schemes impose problems in Public Key Infrastructure (PKI). Checking the validity and preserving the security of these documents is of utmost importance. In this work, we have devised a blockchain-based solution for preventing malfunctioning in certificate validation which is an important step for any university. Each certificate is uploaded in its hash format and is stored using blockchain. The hashes are stored in unique transactions in nodes, which are deployed on a private network. Using the SHA-256 hashing algorithm, the certificates are uploaded into the system and can be viewed by anyone with the right credentials. Due to the usage of blockchain technology, the certificates are stored in a decentralized manner, which ensures there is no central point of failure. Any changes in the uploaded document need to be validated by other nodes. This paper also improvises that when certificate uploading is required new nodes are added, instead of modifying the past blocks. This work provides a very user-friendly app where any user with the right credentials can upload documents. In this work, digitized documents are stored using Inter Planetary File System (IPFS) which is distributed method of storage. Our theoretical analysis proves that it is a user-friendly application with the security of blockchain technology in partnership with IPFS. Only the issuer can upload documents and others can only view them. Using our proposed solution, problem of malicious certificates can be tackled with E-certification. The proposed method solves all the issues of storing, validating, and sharing documents. Chaotic Map technique is used in hash generation which is quite simple to implement. The proposed approach Chaotic Key based Certificate validation (CK-Cert) provides a hassle-free solution for certificate managements since it better manages the block size as compared to previously proposed techniques (PBCert and CertChain) as discussed with the help of graphs.
Read MoreDoi: https://doi.org/10.54216/FPA.120204
Vol. 12 Issue. 2 PP. 42-53, (2023)
The Internet of Vehicles (IoV) is a distributed system that enables data connectivity between vehicles and vehicular ad hoc networks, ensuring efficient and secure information exchange with infrastructures. Challenges in IoV include security clustering related to packet loss during data exchange, real-time analysis of public communication, and the need for autonomous-vehicle technology development using machine learning (ML). ML-assisted IoV has made significant progress in communication with public networks and interaction with the immediate surroundings. This study presents an experimental foundation for the advancement of the IoV system. While support vector machine (SVM) offers a robust and accurate approach for clustering velocity and solving classification challenges related to security, it is primarily a binary classifier and faces limitations in handling multi-class classification. To address this, an artificial neural network (ANN) is proposed for effective packet loss management in the autonomous system, improving the physical layer's secure network and offering better packet loss experience using the Global Positioning System. The fusion-based diversified model not only enables IoV systems to compete with rivals but also provides key advantages to ensure consistent profitability in cloud-enabled IoV. This paradigm integrates cloud computing (CC) with in-vehicle networks and the Internet of Things, offering safety and infotainment applications for road users. Data collection and experiments are conducted using Network Simulator 2 to automate AI configuration in the IoV fusion system.
Read MoreDoi: https://doi.org/10.54216/FPA.120205
Vol. 12 Issue. 2 PP. 54-69, (2023)
Gestational diabetes (GD) is a growing global concern, underscoring the need for early detection and effective management to prevent adverse health consequences. This paper presents an innovative and reliable architecture to predict gestational diabetes in pregnant women. While reducing the frequency of doctor visits by sending the necessary data via Internet of Things (IoT) technology and receiving the prediction results via a mobile application in real time. The proposed architecture is a fusion of fog computing hardware with ensemble machine learning to enable low-latency, energy-efficient solutions for data processing, and cloud computing. The GD_Fog architecture leverages fused fog computing and load balancing techniques to reduce latency, power consumption, Network bandwidth consumption, and response time, and cloud computing is used based on the concept of use on demand for more reliability while harnessing the power of group learning to improve prediction accuracy. In addition, GD_Fog can be configured for different operating modes to ensure optimal quality of service and prediction accuracy in various fog calculation scenarios, which meet different user requirements. Through extensive testing using real-world data from pregnant women, the framework shows promising results, outperforming the latest methods in accuracy and efficiency. Where the percentage of improvement in prediction accuracy was approximately 6.5% when using ensemble learning, and the improvement in energy use, amounted to approximately 87.01% when using fused fog computing instead of cloud computing. These results confirm the potential of the proposed structure as an invaluable tool for the early detection and effective management of gestational diabetes.
Read MoreDoi: https://doi.org/10.54216/FPA.120206
Vol. 12 Issue. 2 PP. 70-87, (2023)
In this modern world, artificial intelligence has revolutionized human life in multiple ways. Like other fields, education industry is also transforming with the influence of AI with its smart learning platform and automation of tasks. The introduction of fusion of machine learning tools (FMLT) in the field of education helps to predict learning outcomes and identify challenges in learning. The objective of this paper is to study the fusion of application of machine learning tools in education. This paper highlights the role of data driven FMLT in teaching and learning and also analyzes students and teachers’ experiences as well as challenges faced during the implementation of FMLT system. This article discusses various machine learning tools that can be fused into academics. The experiment is conducted on students at graduate level and the results reveal an increase of 88% in terms of learning efficiency for the proposed FMLT system compared to traditional methods, which reflects high positive impact of the contributions of FMLT in academics. Results of the findings also reveal that FMLT applications facilitate thinking, creativity, class engagement and quality teaching inside and outside classrooms. The feedback findings express mixed attitudes concerning the use of machine learning tools in classrooms.
Read MoreDoi: https://doi.org/10.54216/FPA.120207
Vol. 12 Issue. 2 PP. 88-97, (2023)
The current era of socio-economic development is featured by rapidly increasing fusion of technology and rapid data fusion digitalization of human activities. While most of these advancements are promising to bring various positive aspects, such as reductions in cost and time, there are potential pitfalls that should be considered. In this paper, we aim to measure potential challenges that data fusion data fusion digitalization could bring in the microfinance context. First, we provide the set of stylized facts and trends in data fusion digitalization using three measures: mobile cell users, internet provision, and mobile-money-service provision. The trends in data fusion digitalization are provided across groups of countries by different income levels. Secondly, using pair-wise correlations we analyze how the set of five microfinance financial and five social indicators are correlated with the digital ranking of countries. Our results demonstrate that while there are increasing patterns in data fusion digitalization in most of the developing countries, negative correlations are observed. We explain the negative implications of data fusion digitalization due to increasing moral hazard and asymmetric information. Our findings call for further research on the long-term implications of digitalization in other areas of social sciences so that to better cope with potential challenges.
Read MoreDoi: https://doi.org/10.54216/FPA.120208
Vol. 12 Issue. 2 PP. 98-108, (2023)
There has been a growing need for fusion based research studies on the relations between university teaching and research. The higher educational universities of the current generation believe in and focus on the teaching-research nexus in academics. To improve teaching methodology there is more emphasis given to the fusion teaching by enabling the information fusing concept through pedagogy. Many discussions have been carried out to evaluate the contribution of teaching–research nexus from the student's point of view. The current study highlights teaching through research where the learners are taught with a special focus on research activities at the same time. The objective of this work is to promote fusion of research related activities into the teaching and learning process to achieve positive impact on enhancing students’ interest towards learning. In view of this and to support this, various opportunities were provided for students and teachers to conduct research and a strategic approach was implemented to achieve this objective. We explore a) student involvement in different scholarly activities b) analyse research skill acquisition of the experimental group c) collect feedback to find students satisfaction level on FTBR approach.The findings demonstrate (mean score 3.09) the positive contribution of the fusion research-teaching towards achieving academic excellence.The strategies discussed in the methodology and results of the study may be used to broaden the fusion teaching-research at the graduate and undergraduate levels.
Read MoreDoi: https://doi.org/10.54216/FPA.120209
Vol. 12 Issue. 2 PP. 109-119, (2023)
Complex networks are a diverse set of networks found in various fields, such as social, technological, and biological networks. One important task in complex network analysis is link prediction, which involves detecting missing links or predicting future link formation. Many methods based on network structure analysis have been developed for link prediction, including network representation learning (NRL) models that represent nodes in a low-dimensional space. Fusion-based attributed NRL methods are particularly effective, as they capture both content and structure information. However, NRL models for link prediction are binary classification models, which face challenges in identifying negative links and prioritizing predicted links. To address these challenges, we propose a novel approach that treats link prediction as a novelty detection problem. Our approach uses the Local Outlier Factor (LOF) algorithm to quantify the novelty of non-existent links based on the representations of existing links. Our experimental results show that our proposed approach outperforms existing methods, particularly when used with fusion-based attributed NRL models
Read MoreDoi: https://doi.org/10.54216/FPA.120210
Vol. 12 Issue. 2 PP. 120-131, (2023)
The studies’ primary aim is to help the research scholars as a source who would like to research in the thyroid disease detection region. UC Irvin knowledge discovery provides databases files for the machine learning archives' thyroid dataset. Here, a random vector network model (RVNM) is proposed to perform classification tasks. The proposed model integrates the prior dataset information regarding the samples to train the more effective classifier. This cascaded random vector network model helps in thyroid disease prediction. The evaluation process is performed to predict and determine the respective performance concerning accuracy. The intuition is provided in this research, like forecasting the thyroid disease; it also calls attention to the process of using a Randomized Vector Network Model (RVNM) as a medium for classification. The simulation is done in the MATLAB 2020a environment and establishes a better trade-off than various existing approaches. The model gives a prediction accuracy of 96.1% accuracy compared to other models and shows a better trade than others.
Read MoreDoi: https://doi.org/10.54216/FPA.120211
Vol. 12 Issue. 2 PP. 132-144, (2023)
Analysis of microarray data is extremely complex and considered as a hot topic in recent research. Acute Myeloid Leukemia (AML) prediction based on machine learning shows huge impact on prediction which automatically diagnoses the disease severity and any malfunctions. It is important to design the relevant classifier that processes the large data volume with large data size. Deep learning is an updated machine learning approach for mitigating these issues. It is easy to handle the huge volume of data because of the large number of hidden layers. The proposed classification methodology is used for understanding the training of the proposed Dense Polynomial Dimensionality based Predictor Model (). The hidden neuron numbers are large in a sufficient way where the proposed is elaborated to predict AML. AML and ALL samples are classified using five layers in the deep network model. The data is partitioned as 20% data and 80% data testing and training in the network. Compared with other classifiers, the satisfying outcome from the proposed is higher and fulfilling. The validation is done in three datasets: Kaggle, Gene expression and Bio GPS and it gives 96% accuracy, 94% precision, 96% recall, 96% F1-score, and 98% AUROC while executing with Kaggle; then, 95.50% accuracy, 94% precision, 95% recall, 96% F1-score, and 96% AUROC is achieved while executing with Gene expression and finally 98% accuracy, 94.5% precision, 98.5% recall, 96% F1-score, and 94% AUROC is achieved while executing with Bio GPS. Based on this analysis, it is proven that the model works well with the proposed and establishes a better trade-off.
Read MoreDoi: https://doi.org/10.54216/FPA.120212
Vol. 12 Issue. 2 PP. 145-158, (2023)
Phishing links are spread via text messages, social media platforms, and email by phishing attackers. Social engineering skills are used to visit phishing websites to trick the users and enter critical information related to personal data. The confidential data is stolen to defraud legitimate financial institutions or general websites for illegally attaining the benefits. Many machine learning-based solutions are in the enhancements and the technology of machine learning applications to detect the suggested phishing. The rules are used for a solution which depends on the extracted features, and few features require to lies on the services of third-party that, creating time-consuming and instability in the service of prediction. A deep learning-based framework is suggested to detect website of phishing. A framework is established to determine if there is a risk of phishing in real-time during the web page is visited by the user to give a message of warming by the browser plug-in. The prediction service in real-time merges the various techniques for enhancing the accuracy to lower the fake alarm rates and the time of computation which has the filtering whitelist, interception of the blacklist, and prediction of deep learning (DL). Various models of deep learning are compared using the different datasets in the module of machine learning prediction. The greatest accuracy is obtained as 99.18% by the adaptive Recurrent Neural Networks (a−RNN) model from the results of experiments to demonstrate the suggested feasibility solution.
Read MoreDoi: https://doi.org/10.54216/FPA.120213
Vol. 12 Issue. 2 PP. 159-171, (2023)
This scientific paper presents a novel approach of real-time signal analysis in electrocardiogram (ECG) monitoring systems, focusing on the integration of device design,algorithm implementation for accurate measurement and interpretation of heart activity. The proposed system leverages a low-cost framework, employing a microcontroller and Arduino programming language for raw ECG data acquisition, while utilizing the AD8232 sensor and ESP8266 Node MCU for continuous patient monitoring. The acquired data is processed, stored, and analyzed using the Pan-Tompkins algorithm, which effectively filters and analyzes heart signals, including noise reduction and QRS complex detection. Two case studies involving a healthy individual and a patient with Myocarditis were conducted to demonstrate the effectiveness of the system. The integration of device design and algorithm development in ECG analysis is emphasized, highlighting the affordability, wearability, and potential for continuous monitoring and early detection of heart conditions. By successfully mitigating noise-related challenges, the implementation of the Pan algorithm enables accurate signal analysis. This interdisciplinary research contributes to the advancement of ECG interpretation and underscores the significance of clinical fusion between designed systems and applied algorithms on real cases. The performance of two Pan-Tompkins based QRS complex detection algorithms was systematically analyzed, offering valuable insights for their reasonable utilization.
Read MoreDoi: https://doi.org/10.54216/FPA.120214
Vol. 12 Issue. 2 PP. 172-184, (2023)
In the realm of media studies, understanding student evolution is a crucial aspect for educators and researchers. However, traditional research methods often struggle to capture the dynamic nature of media consumption and the intricate interactions between individuals and media content. To address this challenge, this paper focuses on leveraging social media data fusion and machine learning techniques to enhance the comprehension of student evolution. By integrating data from diverse social media sources and employing the CATBoost algorithm with the Greedy Target-based Statistics (Greedy TBS) technique, we aim to predict student outcomes based on a comprehensive set of attributes. The results showcase the superior performance of CATBoost in accurately capturing the complexities of student evolution, surpassing other machine learning algorithms. The findings hold immense significance for educators, empowering them with valuable insights into students' behaviors, preferences, and performance.
Read MoreDoi: https://doi.org/10.54216/FPA.120215
Vol. 12 Issue. 2 PP. 185-192, (2023)
The article presents the design and control of the adaptive neuro fuzzy Inference system (ANFIS) for the wind-driven permanent magnet synchronous generator (PMSG) in the grid connected system. The rectifier and inverter are connected with the PMSG output and the grid for maintaining the voltage at the grid under variable wind operations. Such interconnections have many challenges, like high harmonics at the output and an improper voltage profile. The harmonics are measured in terms of total harmonic distortion (THD). Performance parameters like peak overshoot and settling time of DC link voltage and rotor speed have been measured. The control of the rectifier and inverter has been assessed with the ANFIS and PID controllers. A closed strategic mechanism has been developed for the ANFIS and PID controllers for improving the performance parameters and harmonics.. Finally, it is observed that the peak overshoot (%) and settling time (sec) of the DC link voltage with ANFIS are 5.2% and 2.9 sec, which are found to be less in comparison to the PID controller with the values of 6.1% and 3.8 sec and other existing methods. Similarly, the settling time (sec) of rotor speed with ANFIS is 1.1 sec, which is less than the settling time (2.6 sec) of the PID controller. Another advantage of ANFIS is the reduction of THD (%) of 5.1% with respect to THD (%) of PID controllers of 6.2% and other existing methods. The reduced THD shows the improved version of the voltage profile.
Read MoreDoi: https://doi.org/10.54216/FPA.120216
Vol. 12 Issue. 2 PP. 193-205, (2023)
Iraqi higher education institutions use the virtual classroom platform to replace face-to-face teaching and online learning, and to overcome the challenges of traditional teaching. Therefore, this research aim was to use multimedia applications by using JavaScript programming to design a virtual classroom simulation model to improve the teaching and learning process in higher education. In same the context, virtual classrooms have emerged as an immersive alternative to face-to-face, hands-on classrooms. In addition, the possibility of using virtual classrooms opens new perspectives for Iraqi universities. The method of this work was based on the interaction design (Design, Development, Testing, Analysis, and Evaluation). Thus, was selected Tikrit university as a case study for different levels of students at university colleges, to conduct a thorough evaluation of the virtual classroom platform based on the Multimedia Criteria in Conole’s Dimensions (12 criteria), which is considered as a general criteria evaluation for the proposed virtual classroom platform by experts’ review from different Iraqi universities. In addition to the students’ experience (first to the fourth year of the bachelor's degree) with the proposed virtual classroom platform from different colleges at Tikrit University. It can be a virtual platform for all Iraqi universities in the future. Finally, the results show that many students (200) are satisfied with the features of learning in the proposed model, with high performance and effectiveness in the learning process. Moreover, the results showed also that there is a strong need for the virtual classroom to process the difficult practical aspects of the learning process.
Read MoreDoi: https://doi.org/10.54216/FPA.120217
Vol. 12 Issue. 2 PP. 206-216, (2023)