Pub Date : 2024-03-29DOI: 10.58346/jowua.2024.i1.002
Dr. Walaa Saber Ismail
In the modern era of digital communication, the analysis of sentiment has emerged as a crucial tool for understanding and inferring public sentiment as communicated through written text. This is particularly relevant in the context of social media platforms such as Twitter, Facebook and Instagram. The present study focuses on the urgent matter of public opinion regarding the practice of animal testing, employing advanced deep-learning methodologies for sentiment analysis. A dataset of 15,360 tweets about animal testing was collected using the Twitter API. The data was prepared for analysis by undergoing careful preprocessing and word embedding it through the utilization of Word2vec. To classify tweets into positive and negative sentiment categories, a Long Short-Term Memory (LSTM) model was employed, given its suitability for processing sequential data. Remarkably, an accuracy rate of 88.7 percent was achieved by the model. It was determined that around 80% of tweets expressed criticism towards animal testing, indicating the presence of a substantial negative sentiment majority. These results show the topic's continuing significance by emphasizing its highly emotional and controversial nature. It is concluded that deep learning, and in particular LSTM models, can be used to effectively analyze large amounts of social media data and yield insightful understandings of public opinion. This study underlines the significance of sentiment analysis for gaining insight into public opinion and for its applications in policymaking and discourse analysis.
{"title":"Emotion Detection in Text: Advances in Sentiment Analysis Using Deep Learning","authors":"Dr. Walaa Saber Ismail","doi":"10.58346/jowua.2024.i1.002","DOIUrl":"https://doi.org/10.58346/jowua.2024.i1.002","url":null,"abstract":"In the modern era of digital communication, the analysis of sentiment has emerged as a crucial tool for understanding and inferring public sentiment as communicated through written text. This is particularly relevant in the context of social media platforms such as Twitter, Facebook and Instagram. The present study focuses on the urgent matter of public opinion regarding the practice of animal testing, employing advanced deep-learning methodologies for sentiment analysis. A dataset of 15,360 tweets about animal testing was collected using the Twitter API. The data was prepared for analysis by undergoing careful preprocessing and word embedding it through the utilization of Word2vec. To classify tweets into positive and negative sentiment categories, a Long Short-Term Memory (LSTM) model was employed, given its suitability for processing sequential data. Remarkably, an accuracy rate of 88.7 percent was achieved by the model. It was determined that around 80% of tweets expressed criticism towards animal testing, indicating the presence of a substantial negative sentiment majority. These results show the topic's continuing significance by emphasizing its highly emotional and controversial nature. It is concluded that deep learning, and in particular LSTM models, can be used to effectively analyze large amounts of social media data and yield insightful understandings of public opinion. This study underlines the significance of sentiment analysis for gaining insight into public opinion and for its applications in policymaking and discourse analysis.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"94 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140365824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.58346/jowua.2024.i1.005
I. G. D. Nugraha, Edwiansyah Zaky Ashadi, Ardiansyah Musa Efendi
LoRa can be used as the communication technology for the intelligent monitoring system. However, LoRa is usually used for outdoor communication. The usage of LoRa as indoor communication has many challenges. One of the challenges is that collision happens when using standard LoRa devices with only one channel. The algorithms based on TDMA (Time-division Multiple Access) and CSMA (Carrier-sense Multiple Access) protocols can be used to address this challenge. These two algorithms can be modified by applying the device that is the center of the network (gateway) as a central control and the data transmitter (sensor node) as a passive device. The test was conducted on the Intelligent Laboratory Monitoring System to evaluate this design on a multi-node LoRa network. RSSI testing proves that the distance and building interference affect the signal strength or RSSI of sensor nodes, so the average RSSI value is -73.75 with an RSSI threshold of value -106. The gateway successfully collected each sensor node data with an average success of about 64.953%. The experiment results show the success rate of the CSMA-based algorithm is 10% versus 100% in TDMA-based algorithm; the delay is 4125 ms for CSMA-based and 428.3 ms for TDMA-based. This result means that the CSMA-based algorithm is more complex, takes more time to process the data than the TDMA-based algorithm, has a low success rate, and is more prone to collisions.
{"title":"Performance Evaluation of Collision Avoidance for Multi-node LoRa Networks based on TDMA and CSMA Algorithm","authors":"I. G. D. Nugraha, Edwiansyah Zaky Ashadi, Ardiansyah Musa Efendi","doi":"10.58346/jowua.2024.i1.005","DOIUrl":"https://doi.org/10.58346/jowua.2024.i1.005","url":null,"abstract":"LoRa can be used as the communication technology for the intelligent monitoring system. However, LoRa is usually used for outdoor communication. The usage of LoRa as indoor communication has many challenges. One of the challenges is that collision happens when using standard LoRa devices with only one channel. The algorithms based on TDMA (Time-division Multiple Access) and CSMA (Carrier-sense Multiple Access) protocols can be used to address this challenge. These two algorithms can be modified by applying the device that is the center of the network (gateway) as a central control and the data transmitter (sensor node) as a passive device. The test was conducted on the Intelligent Laboratory Monitoring System to evaluate this design on a multi-node LoRa network. RSSI testing proves that the distance and building interference affect the signal strength or RSSI of sensor nodes, so the average RSSI value is -73.75 with an RSSI threshold of value -106. The gateway successfully collected each sensor node data with an average success of about 64.953%. The experiment results show the success rate of the CSMA-based algorithm is 10% versus 100% in TDMA-based algorithm; the delay is 4125 ms for CSMA-based and 428.3 ms for TDMA-based. This result means that the CSMA-based algorithm is more complex, takes more time to process the data than the TDMA-based algorithm, has a low success rate, and is more prone to collisions.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"62 46","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140364997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.58346/jowua.2024.i1.011
Vimitha R Vidhya Lakshmi
Opportunistic Mobile Social Networks (OMSN) are prone to data integrity attacks that jeopardize the integrity of the routing data inside the network. Among the several techniques that cope with these attacks in OMSN, tree-based approaches have proven to be the most effective due to its ease of data verification and ensurance in data integrity. This paper evaluates two tree-based data structures, Merkle tree and Verkle tree in terms of their effectiveness in detecting and preventing such attacks. The evaluation considers tree-generation time and proof-checking time, and the results demonstrate that the Verkle tree is a bandwidth-efficient solution and have lower proof-checking time, with a reduction of 98.33% than Merkle tree. This makes Verkle tree a good choice for handling data integrity attacks in OMSN. A Verkle tree-based approach, named VADIA, is proposed to handle data integrity attacks such as packet dropping, packet modification and pollution attack in OMSN. The proposed approach is implemented in the Opportunistic Network Environment (ONE) simulator and is shown to be effective in detecting malicious nodes and paths, reducing false negative rates, and improving accuracy in detecting malicious activities. The results demonstrate a 47%, 84% and 69% improvement in malicious node, malicious path and malicious activity detection over a period of time. Furthermore, the approach achieves an 80% reduction in false negative rates.
{"title":"VADIA-Verkle Tree-based Approach for Dealing Data Integrity Attacks in Opportunistic Mobile Social Networks","authors":"Vimitha R Vidhya Lakshmi","doi":"10.58346/jowua.2024.i1.011","DOIUrl":"https://doi.org/10.58346/jowua.2024.i1.011","url":null,"abstract":"Opportunistic Mobile Social Networks (OMSN) are prone to data integrity attacks that jeopardize the integrity of the routing data inside the network. Among the several techniques that cope with these attacks in OMSN, tree-based approaches have proven to be the most effective due to its ease of data verification and ensurance in data integrity. This paper evaluates two tree-based data structures, Merkle tree and Verkle tree in terms of their effectiveness in detecting and preventing such attacks. The evaluation considers tree-generation time and proof-checking time, and the results demonstrate that the Verkle tree is a bandwidth-efficient solution and have lower proof-checking time, with a reduction of 98.33% than Merkle tree. This makes Verkle tree a good choice for handling data integrity attacks in OMSN. A Verkle tree-based approach, named VADIA, is proposed to handle data integrity attacks such as packet dropping, packet modification and pollution attack in OMSN. The proposed approach is implemented in the Opportunistic Network Environment (ONE) simulator and is shown to be effective in detecting malicious nodes and paths, reducing false negative rates, and improving accuracy in detecting malicious activities. The results demonstrate a 47%, 84% and 69% improvement in malicious node, malicious path and malicious activity detection over a period of time. Furthermore, the approach achieves an 80% reduction in false negative rates.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"40 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140368269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.58346/jowua.2024.i1.017
Dr. Bob Subhan Riza, Dr. Rina Yunita, Dr. Rika Rosnelly
Tuberculosis is an infectious disease and requires serious treatment. Extrapulmonary Tuberculosis is detected using a microscope. Currently it will take a long time because the fluid preparations are viewed in a microscope one by one carefully and in the fluid preparations there are 150 fields of vision. Examination for Extra Pulmonary Tuberculosis by culture takes between 1-2 weeks or even more. Examination by biopsy will take a long time because the fluid preparations are looked at carefully under the microscope one by one. The image of Tuberculosis is expressed if in the image there is a bacillus object in red, and it turns out that apart from the bacillus object there are other objects also in red. So that examinations for tuberculosis can be more efficient, examinations using computer technology are needed. This research aims to compare the Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BiLSTM) classification methods in the detection of extra-pulmonary tuberculosis disease to obtain better accuracy results. This research carried out HSI color space transformation, segmentation using global thresholding, feature extraction using 13 features based on shape and texture using the Correlation Based Feature Selection (CFS) feature selection method. The results show that BiLSTM has the best accuracy with a value of 88.40% at the number of features = 3, namely Short Run High Gray-Level Emphasis, Run Length Nonuniformity, Minor axis length, while LSTM produces an accuracy of 63.19% at the number of features = 5. BiLSTM is capable of detecting opposite features, meaning that BiLSTM can detect opposite features in data sequences and BiLSTM's ability to understand multiple contexts, so it tends to provide more accurate results in some data classification tasks.
{"title":"Comparative Analysis of LSTM and BiLSTM in Image Detection Processing","authors":"Dr. Bob Subhan Riza, Dr. Rina Yunita, Dr. Rika Rosnelly","doi":"10.58346/jowua.2024.i1.017","DOIUrl":"https://doi.org/10.58346/jowua.2024.i1.017","url":null,"abstract":"Tuberculosis is an infectious disease and requires serious treatment. Extrapulmonary Tuberculosis is detected using a microscope. Currently it will take a long time because the fluid preparations are viewed in a microscope one by one carefully and in the fluid preparations there are 150 fields of vision. Examination for Extra Pulmonary Tuberculosis by culture takes between 1-2 weeks or even more. Examination by biopsy will take a long time because the fluid preparations are looked at carefully under the microscope one by one. The image of Tuberculosis is expressed if in the image there is a bacillus object in red, and it turns out that apart from the bacillus object there are other objects also in red. So that examinations for tuberculosis can be more efficient, examinations using computer technology are needed. This research aims to compare the Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BiLSTM) classification methods in the detection of extra-pulmonary tuberculosis disease to obtain better accuracy results. This research carried out HSI color space transformation, segmentation using global thresholding, feature extraction using 13 features based on shape and texture using the Correlation Based Feature Selection (CFS) feature selection method. The results show that BiLSTM has the best accuracy with a value of 88.40% at the number of features = 3, namely Short Run High Gray-Level Emphasis, Run Length Nonuniformity, Minor axis length, while LSTM produces an accuracy of 63.19% at the number of features = 5. BiLSTM is capable of detecting opposite features, meaning that BiLSTM can detect opposite features in data sequences and BiLSTM's ability to understand multiple contexts, so it tends to provide more accurate results in some data classification tasks.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"24 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140368522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.58346/jowua.2024.i1.015
Sofiene Mansouri, Souhaila Boulares, S. Chabchoub
In this work, a machine learning (ML)-based e-diagnostic system is suggested specifically for the detection of gestational diabetes mellitus (GDM). Reviewing recent GDM data and outlining the intimate connection between GDM and prediabetic conditions, as well as the potential for future declines in insulin resistance and the emergence of overt Type 2 diabetes, were our goals. The present study explores the application of the K-nearest neighbors (KNN) algorithm to project diabetes diagnosis on the widely-used Pima Indians Diabetes database. The KNN algorithm, a non-parametric, instance-based learning method, was employed to classify individuals as either diabetic or non-diabetic, our objectives were to evaluate the algorithm’s ability to make accurate predictions and explore factors influencing its performance. The study commenced with data preprocessing, including handling missing values, feature scaling, and data splitting into training and testing sets. The KNN classifier was trained and tested using these best-fit parameters. The results of this study revealed a model with an accuracy of approximately 0.76 in predicting diabetes diagnosis. This study looked at the various machine-learning approaches for diabetes patient classification, including recall, accuracy, precision, and F1-score. The study discusses the significance of hyperparameter tuning, data preprocessing, and imbalanced data handling in achieving optimal KNN model performance. Lastly, this study shows how the KNN algorithm may be used to project diabetes using the Pima Indians Diabetes Database. The findings suggest that KNN can serve as a viable tool in the early detection of diabetes, paving the way for more extensive applications in healthcare and predictive modelling.
在这项研究中，我们提出了一种基于机器学习（ML）的电子诊断系统，专门用于检测妊娠糖尿病（GDM）。我们的目标是回顾最近的 GDM 数据，概述 GDM 与糖尿病前期症状之间的密切联系，以及未来胰岛素抵抗下降和明显 2 型糖尿病出现的可能性。本研究探索了 K 近邻（KNN）算法在广泛使用的皮马印第安人糖尿病数据库中糖尿病诊断预测中的应用。KNN 算法是一种非参数、基于实例的学习方法，用于将个体划分为糖尿病患者或非糖尿病患者，我们的目标是评估该算法做出准确预测的能力，并探索影响其性能的因素。研究从数据预处理开始，包括处理缺失值、特征缩放以及将数据分成训练集和测试集。使用这些最佳拟合参数对 KNN 分类器进行了训练和测试。研究结果表明，该模型预测糖尿病诊断的准确率约为 0.76。本研究探讨了用于糖尿病患者分类的各种机器学习方法，包括召回率、准确率、精确度和 F1 分数。研究讨论了超参数调整、数据预处理和不平衡数据处理在实现最佳 KNN 模型性能方面的重要性。最后，本研究展示了如何利用皮马印第安人糖尿病数据库将 KNN 算法用于预测糖尿病。研究结果表明，KNN 可以作为早期检测糖尿病的可行工具，为更广泛地应用于医疗保健和预测建模铺平道路。
{"title":"Machine Learning for Early Diabetes Detection and Diagnosis","authors":"Sofiene Mansouri, Souhaila Boulares, S. Chabchoub","doi":"10.58346/jowua.2024.i1.015","DOIUrl":"https://doi.org/10.58346/jowua.2024.i1.015","url":null,"abstract":"In this work, a machine learning (ML)-based e-diagnostic system is suggested specifically for the detection of gestational diabetes mellitus (GDM). Reviewing recent GDM data and outlining the intimate connection between GDM and prediabetic conditions, as well as the potential for future declines in insulin resistance and the emergence of overt Type 2 diabetes, were our goals. The present study explores the application of the K-nearest neighbors (KNN) algorithm to project diabetes diagnosis on the widely-used Pima Indians Diabetes database. The KNN algorithm, a non-parametric, instance-based learning method, was employed to classify individuals as either diabetic or non-diabetic, our objectives were to evaluate the algorithm’s ability to make accurate predictions and explore factors influencing its performance. The study commenced with data preprocessing, including handling missing values, feature scaling, and data splitting into training and testing sets. The KNN classifier was trained and tested using these best-fit parameters. The results of this study revealed a model with an accuracy of approximately 0.76 in predicting diabetes diagnosis. This study looked at the various machine-learning approaches for diabetes patient classification, including recall, accuracy, precision, and F1-score. The study discusses the significance of hyperparameter tuning, data preprocessing, and imbalanced data handling in achieving optimal KNN model performance. Lastly, this study shows how the KNN algorithm may be used to project diabetes using the Pima Indians Diabetes Database. The findings suggest that KNN can serve as a viable tool in the early detection of diabetes, paving the way for more extensive applications in healthcare and predictive modelling.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"80 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140368949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.58346/jowua.2024.i1.003
B. Sreevidya, Dr.M. Supriya
Wireless technology has changed the way entities communicate with one another. Wireless networks have created several opportunities in fields such as military, health care, and habitat monitoring, to name a few. However, only a few data-critical applications are built on wireless sensor networks, such as border reconnaissance, detecting infringement, and patient monitoring. These applications require the processing of a large amount of private data. Because most applications are data-sensitive, securing data transmission among wireless sensor networks is crucial. While incorporating data security, the most important requirement of wireless sensor nodes being energy optimized also need to be kept in consideration. There are various forms of assaults that are relevant in Wireless Sensor Networks (WSN). Attacks like Black Hole attacks, sink hole attacks, False data Injection attacks etc. are the most commonly seen attacks on WSNs. The common element in all these attacks is the concept of malicious / compromised node - a node which either drops / modifies the data content while forwarding it. Existing techniques for data security generally use cryptographic algorithms, but the use of cryptographic algorithms is in contrast with the energy optimization requirement of sensor nodes. An energy efficient data security scheme needs to be developed. The proposed system analyses several attacks and proposes a multi-layer data security approach to prevent change of data / dropping of data by the compromised nodes. The proposed system is a routing protocol referred as Trust Based Routing (TBR). A concept of trust value of a node is the core idea of TBR. Forwarding node is selected based on highest trust value and thus avoid malicious / compromised nodes from being involved in the routing process. The trust factor is calculated by considering the number of packets dropped, packets rejected, and the node's remaining energy. The idea of TBR is enhanced by incorporating the concept of past trust and trust of node towards a specific destination. This proposed scheme is referred as Extended Trust Based Routing (ETBR). This scheme is further enhanced by including Direct Trust, Indirect Trust and Energy Trust concepts. This scheme is referred as Consolidated Trust Estimation – Trust Based Routing (CTE-TBR). Network Simulator NS2 is used to simulate the proposed schemes. Various network factors are compared to classic Adhoc On-Demand Vector (AODV) and newly proposed schemes. The result indicates the effectiveness of the proposed data security scheme in terms of energy efficiency and Packet Delivery ratio (PDR).
{"title":"Trust based Routing – A Novel Approach for Data Security in WSN based Data Critical Applications","authors":"B. Sreevidya, Dr.M. Supriya","doi":"10.58346/jowua.2024.i1.003","DOIUrl":"https://doi.org/10.58346/jowua.2024.i1.003","url":null,"abstract":"Wireless technology has changed the way entities communicate with one another. Wireless networks have created several opportunities in fields such as military, health care, and habitat monitoring, to name a few. However, only a few data-critical applications are built on wireless sensor networks, such as border reconnaissance, detecting infringement, and patient monitoring. These applications require the processing of a large amount of private data. Because most applications are data-sensitive, securing data transmission among wireless sensor networks is crucial. While incorporating data security, the most important requirement of wireless sensor nodes being energy optimized also need to be kept in consideration. There are various forms of assaults that are relevant in Wireless Sensor Networks (WSN). Attacks like Black Hole attacks, sink hole attacks, False data Injection attacks etc. are the most commonly seen attacks on WSNs. The common element in all these attacks is the concept of malicious / compromised node - a node which either drops / modifies the data content while forwarding it. Existing techniques for data security generally use cryptographic algorithms, but the use of cryptographic algorithms is in contrast with the energy optimization requirement of sensor nodes. An energy efficient data security scheme needs to be developed. The proposed system analyses several attacks and proposes a multi-layer data security approach to prevent change of data / dropping of data by the compromised nodes. The proposed system is a routing protocol referred as Trust Based Routing (TBR). A concept of trust value of a node is the core idea of TBR. Forwarding node is selected based on highest trust value and thus avoid malicious / compromised nodes from being involved in the routing process. The trust factor is calculated by considering the number of packets dropped, packets rejected, and the node's remaining energy. The idea of TBR is enhanced by incorporating the concept of past trust and trust of node towards a specific destination. This proposed scheme is referred as Extended Trust Based Routing (ETBR). This scheme is further enhanced by including Direct Trust, Indirect Trust and Energy Trust concepts. This scheme is referred as Consolidated Trust Estimation – Trust Based Routing (CTE-TBR). Network Simulator NS2 is used to simulate the proposed schemes. Various network factors are compared to classic Adhoc On-Demand Vector (AODV) and newly proposed schemes. The result indicates the effectiveness of the proposed data security scheme in terms of energy efficiency and Packet Delivery ratio (PDR).","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"58 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140364922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.58346/jowua.2023.i3.012
Olga Fisenko, Larisa Adonina, Heriberto Solis Sosa, Shiguay Guizado Giomar Arturo, Angélica Sánchez Castro, Fernando Willy Morillo Galarza, David Aroni Palomino
The use of flexible antennas has garnered significant interest in light of their wide-ranging applications inside contemporary wireless communication systems. The need for these antennas stems from the necessity for small, conformal, and versatile systems that can effectively function across many frequency ranges. The present study investigates designing and optimizing a universal triband antenna, focusing on meeting the distinct demands of Wireless Local Area Networks (WLAN), Worldwide Interoperability for Microwave Access (WiMAX), and 5G applications. The current methodologies often need help attaining maximum efficiency over a wide range of frequency bands, resulting in concerns such as subpar radiation patterns and restricted bandwidth. To address the obstacles, this research proposes a novel approach known as the Triband Antenna Design using the Artificial Neural Network (3AD-ANN) method. This method utilizes machine learning techniques to devise and enhance the attributes of the antenna effectively. The 3AD-ANN approach presents several notable characteristics, such as heightened adaptability, increased radiation patterns, and a condensed physical structure. The mean values for far-field radiation gain are around -37.4 dB in simulated scenarios and -39.9 dB in actual observations. The average return loss is roughly -23.8 dB in simulations and -25.8 dB in experimental measurements. The numerical findings illustrate the effectiveness of this methodology, exhibiting exceptional return loss and gain sizes over a range of frequencies, including WLAN, WiMAX, and 5G.
{"title":"Advancements in Flexible Antenna Design: Enabling Tri-Band Connectivity for WLAN, WiMAX, and 5G Applications","authors":"Olga Fisenko, Larisa Adonina, Heriberto Solis Sosa, Shiguay Guizado Giomar Arturo, Angélica Sánchez Castro, Fernando Willy Morillo Galarza, David Aroni Palomino","doi":"10.58346/jowua.2023.i3.012","DOIUrl":"https://doi.org/10.58346/jowua.2023.i3.012","url":null,"abstract":"The use of flexible antennas has garnered significant interest in light of their wide-ranging applications inside contemporary wireless communication systems. The need for these antennas stems from the necessity for small, conformal, and versatile systems that can effectively function across many frequency ranges. The present study investigates designing and optimizing a universal triband antenna, focusing on meeting the distinct demands of Wireless Local Area Networks (WLAN), Worldwide Interoperability for Microwave Access (WiMAX), and 5G applications. The current methodologies often need help attaining maximum efficiency over a wide range of frequency bands, resulting in concerns such as subpar radiation patterns and restricted bandwidth. To address the obstacles, this research proposes a novel approach known as the Triband Antenna Design using the Artificial Neural Network (3AD-ANN) method. This method utilizes machine learning techniques to devise and enhance the attributes of the antenna effectively. The 3AD-ANN approach presents several notable characteristics, such as heightened adaptability, increased radiation patterns, and a condensed physical structure. The mean values for far-field radiation gain are around -37.4 dB in simulated scenarios and -39.9 dB in actual observations. The average return loss is roughly -23.8 dB in simulations and -25.8 dB in experimental measurements. The numerical findings illustrate the effectiveness of this methodology, exhibiting exceptional return loss and gain sizes over a range of frequencies, including WLAN, WiMAX, and 5G.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135039018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.58346/jowua.2023.i3.020
Ratih Hurriyati, Ana A., Sulastri Sulastri, Lisnawati Lisnawati, Thosporn Sawangsang
Financial experts may make successful selections thanks to the stock market's research and forecasting capabilities, which is exciting. This study examines the stock market forecast outcomes through a simple feed-forward neural network (FFNN) model. Then, we contrast those outcomes with those produced using more sophisticated Elman, fuzzy logic, and radial basis function networks. Any problem with finite input-output mapping may be solved using the FFNN as long as it has at least one hidden layer and a sufficient number of neurons. An ANN in which RBFs are used as activation functions is called a radial basis function network (RBFN). Utilizing the Levenberg-Marquardt Back Propagation technique, the FFNN and Elman networks are trained in this study. A Fuzzy Inference System (FIS) of Sugeno type is employed to replicate the predictive procedure within the realm of fuzzy logic. We choose the optimal RBF values using several clustering techniques. The approaches were validated using public stock market data on the National Stock Exchange of Indonesia.
{"title":"Stock Market Trend Analysis and Machine Learning-based Predictive Evaluation","authors":"Ratih Hurriyati, Ana A., Sulastri Sulastri, Lisnawati Lisnawati, Thosporn Sawangsang","doi":"10.58346/jowua.2023.i3.020","DOIUrl":"https://doi.org/10.58346/jowua.2023.i3.020","url":null,"abstract":"Financial experts may make successful selections thanks to the stock market's research and forecasting capabilities, which is exciting. This study examines the stock market forecast outcomes through a simple feed-forward neural network (FFNN) model. Then, we contrast those outcomes with those produced using more sophisticated Elman, fuzzy logic, and radial basis function networks. Any problem with finite input-output mapping may be solved using the FFNN as long as it has at least one hidden layer and a sufficient number of neurons. An ANN in which RBFs are used as activation functions is called a radial basis function network (RBFN). Utilizing the Levenberg-Marquardt Back Propagation technique, the FFNN and Elman networks are trained in this study. A Fuzzy Inference System (FIS) of Sugeno type is employed to replicate the predictive procedure within the realm of fuzzy logic. We choose the optimal RBF values using several clustering techniques. The approaches were validated using public stock market data on the National Stock Exchange of Indonesia.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135040236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.58346/jowua.2023.i3.009
Dr. Lixin Wang, Dr. Jianhua Yang, Maochang Qin
Hackers usually send attacking commands through compromised hosts, called stepping-stones, for the purpose of decreasing the chance of being discovered. An effective approach for stepping-stone intrusion detection (SSID) is to estimate the length of a connection chain. This type of detection method is referred to as the network-based SSID (NSSID). All the existing NSSID approaches use the distribution of packet round-trip times (RTTs) to estimate the length of a connection chain. In this paper, we explore a novel approach – Fast Fourier Transformation (FFT) to analyze the distribution of packet RTTs. We first capture network packets from different stepping-stones in a connection chain, identify and match the Send and Echo packets in each stepping-stone. Packet RTTs can be obtained from matched pairs of packets. We then apply the FFT interpolation method to obtain a RTT time function and finally conduct FFT transformation to the RTT function in each stepping-stone host. Finally, we conduct a complete FFT analysis for the distribution of packet RTTs and present the FFT analysis results in this paper.
{"title":"Analyzing Distribution of Packet Round-Trip Times using Fast Fourier Transformation","authors":"Dr. Lixin Wang, Dr. Jianhua Yang, Maochang Qin","doi":"10.58346/jowua.2023.i3.009","DOIUrl":"https://doi.org/10.58346/jowua.2023.i3.009","url":null,"abstract":"Hackers usually send attacking commands through compromised hosts, called stepping-stones, for the purpose of decreasing the chance of being discovered. An effective approach for stepping-stone intrusion detection (SSID) is to estimate the length of a connection chain. This type of detection method is referred to as the network-based SSID (NSSID). All the existing NSSID approaches use the distribution of packet round-trip times (RTTs) to estimate the length of a connection chain. In this paper, we explore a novel approach – Fast Fourier Transformation (FFT) to analyze the distribution of packet RTTs. We first capture network packets from different stepping-stones in a connection chain, identify and match the Send and Echo packets in each stepping-stone. Packet RTTs can be obtained from matched pairs of packets. We then apply the FFT interpolation method to obtain a RTT time function and finally conduct FFT transformation to the RTT function in each stepping-stone host. Finally, we conduct a complete FFT analysis for the distribution of packet RTTs and present the FFT analysis results in this paper.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135038958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.58346/jowua.2023.i3.010
Nirmala M.S.
Deaf and mute people have unique communication and social challenges that make it hard to express their thoughts, needs, and ideas. Understanding people's behavior is more important to protect them and help them integrate into society. This study discusses the critical need for behavioral analysis on deaf and mute people and introduces the Automatic Behavioral Analysis Employing Gesture Detection Framework (ABA-GDF). Gesture detection technology has gained popularity recently. This emphasis may be due to its ability to overcome communication hurdles and illuminate nonverbal communication. Current methods have various challenges, including limited accuracy and adaptability. The ABA-GDF architecture comprises three phases: dataset collection, modeling, and deployment. The data collection technique includes hand signals used by deaf and quiet people. The material is then processed to partition and normalize the hand area for consistent analysis. During Modelling, feature descriptor attributes are developed to extract relevant motion information. A classifier learns and predicts using the feature vectors, enabling the framework to recognize and interpret motions and actions. Large-scale simulations of ABA-GDF showed promising results. The ABA-GDF framework achieved 92% gesture recognition accuracy on the dataset. The system's robustness is demonstrated by its capacity to understand non-verbal messages. The research showed a 15% reduction in false positives compared to earlier methods, demonstrating its real-world usefulness.
{"title":"Behavioural Analysis of Deaf and Mute People Using Gesture Detection","authors":"Nirmala M.S.","doi":"10.58346/jowua.2023.i3.010","DOIUrl":"https://doi.org/10.58346/jowua.2023.i3.010","url":null,"abstract":"Deaf and mute people have unique communication and social challenges that make it hard to express their thoughts, needs, and ideas. Understanding people's behavior is more important to protect them and help them integrate into society. This study discusses the critical need for behavioral analysis on deaf and mute people and introduces the Automatic Behavioral Analysis Employing Gesture Detection Framework (ABA-GDF). Gesture detection technology has gained popularity recently. This emphasis may be due to its ability to overcome communication hurdles and illuminate nonverbal communication. Current methods have various challenges, including limited accuracy and adaptability. The ABA-GDF architecture comprises three phases: dataset collection, modeling, and deployment. The data collection technique includes hand signals used by deaf and quiet people. The material is then processed to partition and normalize the hand area for consistent analysis. During Modelling, feature descriptor attributes are developed to extract relevant motion information. A classifier learns and predicts using the feature vectors, enabling the framework to recognize and interpret motions and actions. Large-scale simulations of ABA-GDF showed promising results. The ABA-GDF framework achieved 92% gesture recognition accuracy on the dataset. The system's robustness is demonstrated by its capacity to understand non-verbal messages. The research showed a 15% reduction in false positives compared to earlier methods, demonstrating its real-world usefulness.","PeriodicalId":38235,"journal":{"name":"Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135038805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：