Pub Date : 2023-05-04DOI: 10.13052/jmm1550-4646.1945
Haekyung Chung, Jang-Hyok Ko
In this study, we developed an augmented reality-based educational application that can learn the relationship between life and mathematics by implementing objects in everyday life as a three-dimensional figure of an augmented reality environment. AR images can induce interest in math study to elementary school children, and children who have started learning three-dimensional figures can easily imagine the shape of figures in real life and provide development maps so that they can grasp the relationship between each development and three-dimensional figures. In addition, it is possible to efficiently learn mathematics through an augmented reality-based educational content providing apparatus and method. In this study, firstly literature study was conducted to understand overall understanding of education service and completed persona through survey methods such as in-depth interviews. The user’s goal was simple, easy to operate the app.
{"title":"Augmented Reality-based Educational Content Application Development","authors":"Haekyung Chung, Jang-Hyok Ko","doi":"10.13052/jmm1550-4646.1945","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1945","url":null,"abstract":"In this study, we developed an augmented reality-based educational application that can learn the relationship between life and mathematics by implementing objects in everyday life as a three-dimensional figure of an augmented reality environment. AR images can induce interest in math study to elementary school children, and children who have started learning three-dimensional figures can easily imagine the shape of figures in real life and provide development maps so that they can grasp the relationship between each development and three-dimensional figures. In addition, it is possible to efficiently learn mathematics through an augmented reality-based educational content providing apparatus and method. In this study, firstly literature study was conducted to understand overall understanding of education service and completed persona through survey methods such as in-depth interviews. The user’s goal was simple, easy to operate the app.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134574151","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 : 2023-05-04DOI: 10.13052/jmm1550-4646.1944
Jinsook Bong, Uijin Jang
To provide optimized individual-oriented medical service, an open eco system is required so that personal health information could be safely recorded, managed, shared and viewed. However, the current health information is being separately collected, stored, managed by various management institutions, so data linkage is not guaranteed. The data ownership for personal health information belongs to management entities not an individual and also health information is electronically recorded and managed, so it’s vulnerable to forgery and leakage like other electronic data. This paper proposes a personal health information sharing platform applying the Hyperledger fabric. The proposed platform was designed based on blockchain to provide user-oriented health information management and access rights. Therefore, it is possible to create, manage and share reliable medical data.
{"title":"Hyperledger Fabric-based Reliable Personal Health Information Sharing Model","authors":"Jinsook Bong, Uijin Jang","doi":"10.13052/jmm1550-4646.1944","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1944","url":null,"abstract":"To provide optimized individual-oriented medical service, an open eco system is required so that personal health information could be safely recorded, managed, shared and viewed.\u0000However, the current health information is being separately collected, stored, managed by various management institutions, so data linkage is not guaranteed. The data ownership for personal health information belongs to management entities not an individual and also health information is electronically recorded and managed, so it’s vulnerable to forgery and leakage like other electronic data.\u0000This paper proposes a personal health information sharing platform applying the Hyperledger fabric. The proposed platform was designed based on blockchain to provide user-oriented health information management and access rights. Therefore, it is possible to create, manage and share reliable medical data.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131216551","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 : 2023-05-04DOI: 10.13052/jmm1550-4646.1948
Sanjaya Kumar Sarangi, R. Lenka, Ravi Shankar, H. Mehraj, V. G. Krishnan
Fifth generation (5G) wireless networks’ system performance is dependent on having perfect knowledge of the channel state information (CSI). Deep learning (DL) has helped improve both the end-to-end reliability of 5G and beyond fifth generation (B5G) networks and the computational complexity of these networks. This work uses the Bi-linear long short-term memory (Bi-LSTM) scheme to examine the overall performance of the 5G orthogonal frequency division multiplexing (OFDM) technology. The least squares (LS) channel estimation scheme is a famous scheme employed to estimate the fading channel coefficients due to their lower complexity without the prior CSI. However, this scheme has an exceedingly high CSI error. Using pilot symbols (PS) and loss functions, this work has proposed the Bi-LSTM 5G OFDM estimators to improve the channel estimation obtained by the LS approach. All simulation analysis uses convex optimization (CO) software (CVX software) and stochastic gradient descent (SGD). When combined with many PS (72) and a cross-entropy loss function, the proposed Bi-LSTM outperforms the long-short-term memory (LSTM) cross-entropy, LS, and minimum mean square error (MMSE) estimators in low, medium, and high signal-to-noise ratio (SNR) regimes. The computational and training times of Bi-LSTM and LSTM DL estimators are also compared. Because of its DNN design, it can evaluate massive datasets, find hidden statistical patterns and characteristics, establish underlying relationships, and transfer what it has learnt to other contexts. Statistical analysis of the bit error rate (BER) reveals that Bi-LSTM outperforms the MMSE in terms of accurate channel prediction.
{"title":"Examination of the Bi-LSTM Based 5G-OFDM Wireless Network Over Rayleigh Fading Channel Conditions","authors":"Sanjaya Kumar Sarangi, R. Lenka, Ravi Shankar, H. Mehraj, V. G. Krishnan","doi":"10.13052/jmm1550-4646.1948","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1948","url":null,"abstract":"Fifth generation (5G) wireless networks’ system performance is dependent on having perfect knowledge of the channel state information (CSI). Deep learning (DL) has helped improve both the end-to-end reliability of 5G and beyond fifth generation (B5G) networks and the computational complexity of these networks. This work uses the Bi-linear long short-term memory (Bi-LSTM) scheme to examine the overall performance of the 5G orthogonal frequency division multiplexing (OFDM) technology. The least squares (LS) channel estimation scheme is a famous scheme employed to estimate the fading channel coefficients due to their lower complexity without the prior CSI. However, this scheme has an exceedingly high CSI error. Using pilot symbols (PS) and loss functions, this work has proposed the Bi-LSTM 5G OFDM estimators to improve the channel estimation obtained by the LS approach. All simulation analysis uses convex optimization (CO) software (CVX software) and stochastic gradient descent (SGD). When combined with many PS (72) and a cross-entropy loss function, the proposed Bi-LSTM outperforms the long-short-term memory (LSTM) cross-entropy, LS, and minimum mean square error (MMSE) estimators in low, medium, and high signal-to-noise ratio (SNR) regimes. The computational and training times of Bi-LSTM and LSTM DL estimators are also compared. Because of its DNN design, it can evaluate massive datasets, find hidden statistical patterns and characteristics, establish underlying relationships, and transfer what it has learnt to other contexts. Statistical analysis of the bit error rate (BER) reveals that Bi-LSTM outperforms the MMSE in terms of accurate channel prediction.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133268762","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 : 2023-05-04DOI: 10.13052/jmm1550-4646.1946
Thanaphol Kongrit, S. Kiattisin
This paper studies online game engagement in Thailand gaming communities. ‘Planned Behavior’ is the theory used in this study and it explains factors in order to determine the sustainability of the online gaming business. The theoretical research model of the paper focuses on flow experience, human-computer interaction, social interaction, and perceived enjoyment. A quantitative method has been used to measure the implications and data was collected from 800 participants’ online gamer via streaming tournament. The key findings show that the conveyed player attitudes and the flow experience have a positive influence on players’ continued intention to play an online game via Live-streaming. Hence Live-streaming is also an online game community connector and can be used as an indicator on the engagement of a sustainable game industry.
{"title":"Live Streaming Contents Influencing Game Playing Behavior Among Thailand Gamers","authors":"Thanaphol Kongrit, S. Kiattisin","doi":"10.13052/jmm1550-4646.1946","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1946","url":null,"abstract":"This paper studies online game engagement in Thailand gaming communities. ‘Planned Behavior’ is the theory used in this study and it explains factors in order to determine the sustainability of the online gaming business. The theoretical research model of the paper focuses on flow experience, human-computer interaction, social interaction, and perceived enjoyment. A quantitative method has been used to measure the implications and data was collected from 800 participants’ online gamer via streaming tournament. The key findings show that the conveyed player attitudes and the flow experience have a positive influence on players’ continued intention to play an online game via Live-streaming. Hence Live-streaming is also an online game community connector and can be used as an indicator on the engagement of a sustainable game industry.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128180135","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 : 2023-05-04DOI: 10.13052/jmm1550-4646.1941
S. Bhatnagar, M. Dayal, Deepti Singh, Shitiz Upreti, K. Upreti, J. Kumar
Some of the well-known signature techniques like Winternitz and Lamport are not considered to be very appropriate for the usage of hashing or smart contracts in Blockchains security because of their size O(n2), which is prominently too high. Although in Blockchain, the security concern is on the top priority because of its distributed P2P design still, the security enhancement is required to sign and verify the documents forwarded to the peers, especially in Hyperledger Fabric. Here, this paper presents a new signature technique “Block-Hash” to enhance Blockchain security by using it in smart contracts as well as hashing with size 3Xn bits (n=256, generally for SHA-256 Hashing) and which can score 112 bits security. The proposed signature can be used appropriately for signing a smart contract by the endorser or committer node. Also, it can be used with a hash algorithm in forming a Merkle tree. Apart from the description and implementation of Block-Hash Signature, this paper has covered the analysis of its security and correctness measures with a table for result comparison.
{"title":"Block-Hash Signature (BHS) for Transaction Validation in Smart Contracts for Security and Privacy using Blockchain","authors":"S. Bhatnagar, M. Dayal, Deepti Singh, Shitiz Upreti, K. Upreti, J. Kumar","doi":"10.13052/jmm1550-4646.1941","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1941","url":null,"abstract":"Some of the well-known signature techniques like Winternitz and Lamport are not considered to be very appropriate for the usage of hashing or smart contracts in Blockchains security because of their size O(n2), which is prominently too high. Although in Blockchain, the security concern is on the top priority because of its distributed P2P design still, the security enhancement is required to sign and verify the documents forwarded to the peers, especially in Hyperledger Fabric. Here, this paper presents a new signature technique “Block-Hash” to enhance Blockchain security by using it in smart contracts as well as hashing with size 3Xn bits (n=256, generally for SHA-256 Hashing) and which can score 112 bits security. The proposed signature can be used appropriately for signing a smart contract by the endorser or committer node. Also, it can be used with a hash algorithm in forming a Merkle tree. Apart from the description and implementation of Block-Hash Signature, this paper has covered the analysis of its security and correctness measures with a table for result comparison.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134546024","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 : 2023-05-04DOI: 10.13052/jmm1550-4646.1943
T. Kyoseva, V. Poulkov, P. Lindgren
Every telecom constantly faces the dilemma of when to invest in the next generation infrastructure network and how the investment would be monetized. The telco value proposition comprises products, services, processes, technologies, and network infrastructure. This paper explores making the business case out of Open RAN investment for a 5G network, where Open RAN is further researched if telcos perceive it as radical or disruptive innovation. As part of the research, different telecom companies are approached with a set of questions. The results are analysed and mapped in a Business Model Innovation chart. Furthermore, this paper also covers an analysis related to evaluating the sensitivity of how profitable a telco could be depending on Open RAN TCO investment for 5G deployments and the number of customers using value propositions – products, services and processes. Two sensitivity scenarios are simulated so various combinations could be observed before taking any further decision for Open RAN 5G business model implementation.
每家电信公司都面临着何时投资下一代基础设施网络以及如何将投资货币化的困境。电信公司的价值主张包括产品、服务、流程、技术和网络基础设施。本文探讨了5G网络开放RAN投资的商业案例，如果电信公司将其视为激进或颠覆性创新，则对开放RAN进行进一步研究。作为研究的一部分，研究人员向不同的电信公司提出了一系列问题。分析结果并将其映射到商业模式创新图表中。此外，本文还涵盖了与评估电信公司盈利程度的敏感性相关的分析，这取决于5G部署的开放式RAN TCO投资以及使用价值主张(产品、服务和流程)的客户数量。模拟了两种灵敏度场景，以便在对Open RAN 5G商业模式实施做出任何进一步决定之前，可以观察到各种组合。
{"title":"The Disruptive Innovation Potential and Business Case Investment Sensitivity of Open RAN","authors":"T. Kyoseva, V. Poulkov, P. Lindgren","doi":"10.13052/jmm1550-4646.1943","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1943","url":null,"abstract":"Every telecom constantly faces the dilemma of when to invest in the next generation infrastructure network and how the investment would be monetized. The telco value proposition comprises products, services, processes, technologies, and network infrastructure. This paper explores making the business case out of Open RAN investment for a 5G network, where Open RAN is further researched if telcos perceive it as radical or disruptive innovation. As part of the research, different telecom companies are approached with a set of questions. The results are analysed and mapped in a Business Model Innovation chart. Furthermore, this paper also covers an analysis related to evaluating the sensitivity of how profitable a telco could be depending on Open RAN TCO investment for 5G deployments and the number of customers using value propositions – products, services and processes. Two sensitivity scenarios are simulated so various combinations could be observed before taking any further decision for Open RAN 5G business model implementation.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116164513","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 : 2023-05-04DOI: 10.13052/jmm1550-4646.1947
Raslapat Suteeca, Smitti Darakorn Na Ayuthaya, S. Kiattisin
Individuals’ running styles define trail running. Diverse motivational strategies for running emerge because of diverse running behaviors. Customizable design for motivation: when it comes to environmental considerations during a product’s or service’s use stage, the design process has become increasingly focused on behavior. Virtual reality enables the creation and integration of a variety of environments, as well as the redesign, retesting, and enhancement of these environments within a virtual computing structure. These benefits exist because players’ perspectives and behaviors in virtual environments are more comparable to those in their physical environments. The purpose of this study is to create a model for the relationship between persuasive strategy, user personal factors and target behavior that is effective based on the Social Cognitive Model, two hypotheses are tested using structural equation modelling (SEM). According to the findings, persuasive strategies have a significant positive influence on user personal factors. Second, user personal factors were able to influence target behaviors. To increase intrinsic motivation, virtual reality application designers should support persuasive tactics such as goal setting and self-monitoring in a target context. These results may guide designers in selecting effective persuasion strategies for various user groups.
{"title":"A Conceptual Model of Personalized Virtual Reality Trail Running Gamification Design","authors":"Raslapat Suteeca, Smitti Darakorn Na Ayuthaya, S. Kiattisin","doi":"10.13052/jmm1550-4646.1947","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1947","url":null,"abstract":"Individuals’ running styles define trail running. Diverse motivational strategies for running emerge because of diverse running behaviors. Customizable design for motivation: when it comes to environmental considerations during a product’s or service’s use stage, the design process has become increasingly focused on behavior. Virtual reality enables the creation and integration of a variety of environments, as well as the redesign, retesting, and enhancement of these environments within a virtual computing structure. These benefits exist because players’ perspectives and behaviors in virtual environments are more comparable to those in their physical environments. The purpose of this study is to create a model for the relationship between persuasive strategy, user personal factors and target behavior that is effective based on the Social Cognitive Model, two hypotheses are tested using structural equation modelling (SEM). According to the findings, persuasive strategies have a significant positive influence on user personal factors. Second, user personal factors were able to influence target behaviors. To increase intrinsic motivation, virtual reality application designers should support persuasive tactics such as goal setting and self-monitoring in a target context. These results may guide designers in selecting effective persuasion strategies for various user groups.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132529652","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 : 2023-05-04DOI: 10.13052/jmm1550-4646.1942
T. S. Rani, A. Babu, D. Haritha
Research Objectives: Molecular genetic data is managed by the information technology known as bioinformatics. Major concept involved in bioinformatics is a protein sequence. Amino acids bonded with peptide bond constitute the sequence of Protein and it is very essential to lead life. To predict sequence of amino acid, primary sequence obtains amino sequence folding and structures prediction. Research Novelty: In this manuscript, dictionary based regression learning and fuzzy genetic algorithm is proposed for protein prediction from structural analysis (DRL-FGA-PD-SA). In this input data are taken from Kaggle domain dataset. The extraction of protein features from given data is made through Kernel Matrix (KM) which extracts composition of amino acids, composition of dipeptide, composition of pseudo-amino-acid, composition of functional domain and distance-based features. Then fuzzy based genetic algorithm (FGA) update the selected features for classification of protein and the features are clustered. Finally, dictionary based regression learning (DRL) predicts the class of protein with conversion of values either 0’s or 1’s. Research Conclusions: The proposed method is executed on MATLAB. Here evaluation metrics as sensitivity, precision, f-measure, specificity, accuracy and error rate are outlined. Then the performance of the proposed DRL-FGA-PD-SA method provides 22.08%, 24.03%, 34.76% higher accuracy, 23.34%, 26.45%, 34.44% higher precision, compared with the existing systems such assdeep learning methods in protein structure prediction (FFNN-RNN-PD-SA), deep learning technique for protein structure prediction and protein design (DNN-PD-SA) and improved protein structure prediction using potentials from deep learning (DNN-SGDA-PD-SA) respectively.
{"title":"Protein Prediction using Dictionary Based Regression Learning","authors":"T. S. Rani, A. Babu, D. Haritha","doi":"10.13052/jmm1550-4646.1942","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1942","url":null,"abstract":"Research Objectives: Molecular genetic data is managed by the information technology known as bioinformatics. Major concept involved in bioinformatics is a protein sequence. Amino acids bonded with peptide bond constitute the sequence of Protein and it is very essential to lead life. To predict sequence of amino acid, primary sequence obtains amino sequence folding and structures prediction.\u0000Research Novelty: In this manuscript, dictionary based regression learning and fuzzy genetic algorithm is proposed for protein prediction from structural analysis (DRL-FGA-PD-SA). In this input data are taken from Kaggle domain dataset. The extraction of protein features from given data is made through Kernel Matrix (KM) which extracts composition of amino acids, composition of dipeptide, composition of pseudo-amino-acid, composition of functional domain and distance-based features. Then fuzzy based genetic algorithm (FGA) update the selected features for classification of protein and the features are clustered. Finally, dictionary based regression learning (DRL) predicts the class of protein with conversion of values either 0’s or 1’s.\u0000Research Conclusions: The proposed method is executed on MATLAB. Here evaluation metrics as sensitivity, precision, f-measure, specificity, accuracy and error rate are outlined. Then the performance of the proposed DRL-FGA-PD-SA method provides 22.08%, 24.03%, 34.76% higher accuracy, 23.34%, 26.45%, 34.44% higher precision, compared with the existing systems such assdeep learning methods in protein structure prediction (FFNN-RNN-PD-SA), deep learning technique for protein structure prediction and protein design (DNN-PD-SA) and improved protein structure prediction using potentials from deep learning (DNN-SGDA-PD-SA) respectively.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"105 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132901234","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 : 2023-02-15DOI: 10.13052/jmm1550-4646.1935
Raja Varma Pamba, Rahul Bhandari, A. Asha, Rahul Neware, A. Bist
In recent times, the advancement in network devices has focused entirely on the miniaturisation of services that should ensure better connectivity between them via fifth generation (5G) technology. The 5G network communication aims to improve Quality of Service (QoS). However, the allocation of resources is a core problem that increases the complexity of packet scheduling. In this paper, we develop a resource allocation model using a novel deep learning algorithm for optimal resource allocation. The novel deep learning is formulated using the constraints associated with optimal radio resource allocation. The objective function design aims at reducing the system delay. The study predicts the traffic in a complex environment and allocates resources accordingly. The simulation was conducted to test the scheduling efficacy and the results showed an improved rate of allocation than the other methods.
{"title":"Novel Deep Learning Approach to Support Optimal Resource Allocation in 5G Environment","authors":"Raja Varma Pamba, Rahul Bhandari, A. Asha, Rahul Neware, A. Bist","doi":"10.13052/jmm1550-4646.1935","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1935","url":null,"abstract":"In recent times, the advancement in network devices has focused entirely on the miniaturisation of services that should ensure better connectivity between them via fifth generation (5G) technology. The 5G network communication aims to improve Quality of Service (QoS). However, the allocation of resources is a core problem that increases the complexity of packet scheduling. In this paper, we develop a resource allocation model using a novel deep learning algorithm for optimal resource allocation. The novel deep learning is formulated using the constraints associated with optimal radio resource allocation. The objective function design aims at reducing the system delay. The study predicts the traffic in a complex environment and allocates resources accordingly. The simulation was conducted to test the scheduling efficacy and the results showed an improved rate of allocation than the other methods.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125124661","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 : 2023-02-15DOI: 10.13052/jmm1550-4646.1937
Mongkhon Sinsirimongkhon, Sujitra Arwatchananukul, P. Temdee
Machine learning–based methods are widely applied for the prediction of noncommunicable diseases (NCDs), such as hypertension, diabetes, and cardiovascular disease. However, few models have been developed for predicting hypertension with diabetes, even though these diseases generally co-occur and can cause devastating harm to patients. This paper proposes a multi-class classification method that will be able to predict hypertension with diabetes. The proposed method consists of data preprocessing, model construction and validation, and model comparison. For data preprocessing, feature engineering of corresponding data types is conducted. For model construction, several machine learning methods are applied, including Random Forest (RF), Gradient Boosting (GB), Extra Tree (ET), Decision Tree (DCT), and Support Vector Machine (SVM). The dataset used in this study consists of 17,077 records and 28 features, obtained from Phaya Mengrai Hospital, Chiang Rai, Thailand. The predictive performance of each model with and without feature engineering is compared in terms of accuracy and average area under the Receiver Operating Characteristic curve (AUC-ROC). From the comparison results, SVM with feature engineering outperformed other models based on accuracy and average AUC-ROC achieving a value of 88.39% and 93.32%, respectively. For all ensemble learning–based methods, RF performed the best in terms of both accuracy and average AUC-ROC for both with and without feature engineering. Overall, all the models performed better when feature engineering was applied.
{"title":"Multi-Class Classification Method with Feature Engineering for Predicting Hypertension with Diabetes","authors":"Mongkhon Sinsirimongkhon, Sujitra Arwatchananukul, P. Temdee","doi":"10.13052/jmm1550-4646.1937","DOIUrl":"https://doi.org/10.13052/jmm1550-4646.1937","url":null,"abstract":"Machine learning–based methods are widely applied for the prediction of noncommunicable diseases (NCDs), such as hypertension, diabetes, and cardiovascular disease. However, few models have been developed for predicting hypertension with diabetes, even though these diseases generally co-occur and can cause devastating harm to patients. This paper proposes a multi-class classification method that will be able to predict hypertension with diabetes. The proposed method consists of data preprocessing, model construction and validation, and model comparison. For data preprocessing, feature engineering of corresponding data types is conducted. For model construction, several machine learning methods are applied, including Random Forest (RF), Gradient Boosting (GB), Extra Tree (ET), Decision Tree (DCT), and Support Vector Machine (SVM). The dataset used in this study consists of 17,077 records and 28 features, obtained from Phaya Mengrai Hospital, Chiang Rai, Thailand. The predictive performance of each model with and without feature engineering is compared in terms of accuracy and average area under the Receiver Operating Characteristic curve (AUC-ROC). From the comparison results, SVM with feature engineering outperformed other models based on accuracy and average AUC-ROC achieving a value of 88.39% and 93.32%, respectively. For all ensemble learning–based methods, RF performed the best in terms of both accuracy and average AUC-ROC for both with and without feature engineering. Overall, all the models performed better when feature engineering was applied.","PeriodicalId":425561,"journal":{"name":"J. Mobile Multimedia","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133736965","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：