The aim of this study is to build an artificial intelligence chatbot application to support public health services. The chatbot acts as an information service that can replace the role of humans. The analysis of functional needs was obtained from information submitted by one of the heads of public health centers in Indonesia. This study uses the Scrum method with pregame stages to produce a plan consisting of functional and non-functional requirements analysis and conceptual design of the chatbot, which will be developed using Unified Modeling Language (UML) diagrams. The process of finding answers uses the matching graph master technique, which is a backtrack matching that utilizes a depth-first search strategy. There are 6 topics of chatbot services, including service schedules, health information, registration, diseases, drugs, and early care services for chatbot users. Tests conducted on these 6 topics showed an average correct answer ratio of 93.1% out of a total of 251 questions. The result of the usability measurement on the chatbot application that has been built obtained a system usability scale value of 80.1, indicating that the developed chatbots are acceptable for use.
{"title":"Artificial Intelligence-Based Chatbot to Support Public Health Services in Indonesia","authors":"Rudi Setiawan, Rossi Iskandar, Nadilla Madjid, Ridwan Kusumawardani","doi":"10.3991/ijim.v17i19.36263","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.36263","url":null,"abstract":"The aim of this study is to build an artificial intelligence chatbot application to support public health services. The chatbot acts as an information service that can replace the role of humans. The analysis of functional needs was obtained from information submitted by one of the heads of public health centers in Indonesia. This study uses the Scrum method with pregame stages to produce a plan consisting of functional and non-functional requirements analysis and conceptual design of the chatbot, which will be developed using Unified Modeling Language (UML) diagrams. The process of finding answers uses the matching graph master technique, which is a backtrack matching that utilizes a depth-first search strategy. There are 6 topics of chatbot services, including service schedules, health information, registration, diseases, drugs, and early care services for chatbot users. Tests conducted on these 6 topics showed an average correct answer ratio of 93.1% out of a total of 251 questions. The result of the usability measurement on the chatbot application that has been built obtained a system usability scale value of 80.1, indicating that the developed chatbots are acceptable for use.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136353054","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 : 2023-10-10DOI: 10.3991/ijim.v17i19.42575
None Ilham, None Muhammad Niswar, None Ady Wahyudi Paundu
The rapid growth of Android applications has led to more cybercrime cases, specifically Reverse Engineering attacks, on Android apps. One of the most common cases of reverse engineering is application repackaging, where the application is downloaded via the Play Store or the official website and then repackaged with various additions or changes. One of the ways to avoid Application Repackaging attacks is to check the signature of an application. However, hackers can manipulate the application by adding a hook, i.e., replacing the original function for getting signatures with a new modified function in the application. In this research, the development of a verification method for Android applications is carried out by utilizing Dex CRC and the Blake2 algorithm, which will be written in C using the Java Native Interface (JNI). The results of this study indicate that the verification method using Dex CRC and the Blake2 algorithm can effectively protect Android applications from Application Repackaging attacks without burdening application performance.
{"title":"Signature Verification Based on Dex CRC and Blake2 Algorithm to Prevent Reverse Engineering Attack in Android Application","authors":"None Ilham, None Muhammad Niswar, None Ady Wahyudi Paundu","doi":"10.3991/ijim.v17i19.42575","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.42575","url":null,"abstract":"The rapid growth of Android applications has led to more cybercrime cases, specifically Reverse Engineering attacks, on Android apps. One of the most common cases of reverse engineering is application repackaging, where the application is downloaded via the Play Store or the official website and then repackaged with various additions or changes. One of the ways to avoid Application Repackaging attacks is to check the signature of an application. However, hackers can manipulate the application by adding a hook, i.e., replacing the original function for getting signatures with a new modified function in the application. In this research, the development of a verification method for Android applications is carried out by utilizing Dex CRC and the Blake2 algorithm, which will be written in C using the Java Native Interface (JNI). The results of this study indicate that the verification method using Dex CRC and the Blake2 algorithm can effectively protect Android applications from Application Repackaging attacks without burdening application performance.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136295587","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}
Smart home manufacturers widely produce Wireless Lamp Socket and Power Plug devices, which offer various features ranging from basic on/off control to more complex functionalities such as monitoring energy consumption, power losses, and harmonics. However, these devices tend to be expensive, as indicated by market surveys. To address this issue, the current study aimed to develop low-cost wireless control nodes for smart homes that operate using relays. The two nodes consisted of lamp socket and power plug built with lowcost electronic components, including a Wi-Fi built-in Microcontroller ESP8266 (Wemos D1 mini model) as the backbone to create ESP-Mesh wireless network and to provide control ports for high/low logic, a relay module, an AC-to-DC converter module, and terminals (E27 screw for lamp socket node and C-type plug for the power plug node). This paper primarily focuses on the hardware aspects. In order to evaluate the effectiveness of the nodes, the following tests are conducted: (1) product demonstration to assess the product functions, (2) power measurement in idle and active conditions, (3) ESP-Mesh connection testing, and (4) RSSI measurement. Functional testing is done using a smartphone with the UPISmartHome version 2.0 Android application, which successfully controlled the nodes wirelessly. In idle conditions, power plug and lamp socket nodes consume 426.36 mWatt and 418.275 mWatt of power, respectively. Further, in active conditions, power plug and lamp socket nodes consume 435.704 mWatt and 440.583 mWatt of power, respectively. RSSI testing results show that both nodes can be controlled within an optimal range of 60 meters (with reference to RSSI below –85 dBm) without the Internet, utilizing the ESP-Mesh feature of ESP8266. This range is deemed reasonable for smart homes of 21, 36, or 45 square meters. Both nodes could be controlled under the ESP-Mesh network that gets build. We also present the comparison with other products of competitors in this paper.
{"title":"Low-cost Wireless Lamp Socket and Power Plug for Smart Homes and Its Comparison with Available Commercial Competitors","authors":"Syifaul Fuada, None Hendriyana, None Subashri Duttagupta, None Nuur Wachid Abdul Majid","doi":"10.3991/ijim.v17i19.41145","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.41145","url":null,"abstract":"Smart home manufacturers widely produce Wireless Lamp Socket and Power Plug devices, which offer various features ranging from basic on/off control to more complex functionalities such as monitoring energy consumption, power losses, and harmonics. However, these devices tend to be expensive, as indicated by market surveys. To address this issue, the current study aimed to develop low-cost wireless control nodes for smart homes that operate using relays. The two nodes consisted of lamp socket and power plug built with lowcost electronic components, including a Wi-Fi built-in Microcontroller ESP8266 (Wemos D1 mini model) as the backbone to create ESP-Mesh wireless network and to provide control ports for high/low logic, a relay module, an AC-to-DC converter module, and terminals (E27 screw for lamp socket node and C-type plug for the power plug node). This paper primarily focuses on the hardware aspects. In order to evaluate the effectiveness of the nodes, the following tests are conducted: (1) product demonstration to assess the product functions, (2) power measurement in idle and active conditions, (3) ESP-Mesh connection testing, and (4) RSSI measurement. Functional testing is done using a smartphone with the UPISmartHome version 2.0 Android application, which successfully controlled the nodes wirelessly. In idle conditions, power plug and lamp socket nodes consume 426.36 mWatt and 418.275 mWatt of power, respectively. Further, in active conditions, power plug and lamp socket nodes consume 435.704 mWatt and 440.583 mWatt of power, respectively. RSSI testing results show that both nodes can be controlled within an optimal range of 60 meters (with reference to RSSI below –85 dBm) without the Internet, utilizing the ESP-Mesh feature of ESP8266. This range is deemed reasonable for smart homes of 21, 36, or 45 square meters. Both nodes could be controlled under the ESP-Mesh network that gets build. We also present the comparison with other products of competitors in this paper.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136294662","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}
A Mobile Ad-hoc Network (MANET) is a self-organizing collection of mobile devices communicating in a distributed fashion across numerous hops. MANETs are an appealing technology for many applications, including rescue operations, environmental monitoring, tactical operations, and so on, because they let people communicate without the usage of permanent infrastructure. This flexibility, however, creates additional security vulnerabilities. Because of its benefits and expanding demand, MANETs have attracted a lot of interest from the scientific community. They do, however, seem to be more vulnerable to numerous attacks that wreak havoc on their performance than any network. Traditional cryptography techniques cannot entirely defend MANETs in terms of fresh attacks and vulnerabilities due to the distributed architecture of MANETs; however, these issues can be overcome by using machine learning approaches-based intrusion detection systems (IDS). IDS, typically screening system processes and identifying intrusions, are commonly employed to supplement existing security methods because preventative techniques are never enough. Because MANETs are continually evolving, their highly limited nodes, and the lack of central observation stations, intrusion detection is a complex and tough process. Conventional IDSs are difficult to apply to them. Existing methodologies must be updated for MANETs or new approaches must be created. This paper aims to present a novel concept founded on deep belief networks (DBN) and long shortterm memory (LSTM) for MANET attack detection. The experimental analysis was performed on the probe, root to local, user to root, and denial of service (DoS) attacks. In the first phase of this paper, particle swarm optimization was used for feature selection, and subsequently, the DBN and LSTM were used for the classification of attacks in the MANET. The experimental results gave an accuracy reaching 99.46%, a sensitivity of 99.52%, and a recall of 99.52% for DBN and LSTM accuracy reaching 99.75%, a sensitivity of 99.79%, and a recall of 99.79%.
{"title":"An Effective Intrusion Detection in Mobile Ad-hoc Network Using Deep Belief Networks and Long Short-Term Memory","authors":"Abdulfatai Shola Hanafi, Yakub Kayode Saheed, Micheal Olaolu Arowolo","doi":"10.3991/ijim.v17i19.27663","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.27663","url":null,"abstract":"A Mobile Ad-hoc Network (MANET) is a self-organizing collection of mobile devices communicating in a distributed fashion across numerous hops. MANETs are an appealing technology for many applications, including rescue operations, environmental monitoring, tactical operations, and so on, because they let people communicate without the usage of permanent infrastructure. This flexibility, however, creates additional security vulnerabilities. Because of its benefits and expanding demand, MANETs have attracted a lot of interest from the scientific community. They do, however, seem to be more vulnerable to numerous attacks that wreak havoc on their performance than any network. Traditional cryptography techniques cannot entirely defend MANETs in terms of fresh attacks and vulnerabilities due to the distributed architecture of MANETs; however, these issues can be overcome by using machine learning approaches-based intrusion detection systems (IDS). IDS, typically screening system processes and identifying intrusions, are commonly employed to supplement existing security methods because preventative techniques are never enough. Because MANETs are continually evolving, their highly limited nodes, and the lack of central observation stations, intrusion detection is a complex and tough process. Conventional IDSs are difficult to apply to them. Existing methodologies must be updated for MANETs or new approaches must be created. This paper aims to present a novel concept founded on deep belief networks (DBN) and long shortterm memory (LSTM) for MANET attack detection. The experimental analysis was performed on the probe, root to local, user to root, and denial of service (DoS) attacks. In the first phase of this paper, particle swarm optimization was used for feature selection, and subsequently, the DBN and LSTM were used for the classification of attacks in the MANET. The experimental results gave an accuracy reaching 99.46%, a sensitivity of 99.52%, and a recall of 99.52% for DBN and LSTM accuracy reaching 99.75%, a sensitivity of 99.79%, and a recall of 99.79%.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136353516","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 : 2023-10-10DOI: 10.3991/ijim.v17i19.42389
Muhammad Hakiki, Herman Dwi Surjono, None Wagiran, Radinal Fadli, Ridho Dedy Arief Budiman, Witri Ramadhani, Zulqoidi R. Habibie, Sani Suhardiman, Yayuk Hidayah
Web-based Mobile Learning can enhance the learning experience in various educational contexts. However, in operating system courses, practical challenges arise when implementing a web-based mobile learning platform, which impacts the effectiveness and accessibility of learning materials for students. To overcome these challenges, this research and development (R&D) aims to improve the practicality of web-based mobile learning in operating system courses. The research adopts a systematic 4D (Define, Design, Develop, Disseminate) model to identify and explore strategies to optimize the practicality of the platform. Data collected from lecturers and students showed a high average value of practicality, 88.33% and 88.35%, respectively. This research contributes to improving the practical aspects of web-based mobile learning, thereby enhancing students’ learning experience and outcomes in the context of operating system courses.
{"title":"Enhancing Practicality of Web-Based Mobile Learning in Operating System Course: A Developmental Study","authors":"Muhammad Hakiki, Herman Dwi Surjono, None Wagiran, Radinal Fadli, Ridho Dedy Arief Budiman, Witri Ramadhani, Zulqoidi R. Habibie, Sani Suhardiman, Yayuk Hidayah","doi":"10.3991/ijim.v17i19.42389","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.42389","url":null,"abstract":"Web-based Mobile Learning can enhance the learning experience in various educational contexts. However, in operating system courses, practical challenges arise when implementing a web-based mobile learning platform, which impacts the effectiveness and accessibility of learning materials for students. To overcome these challenges, this research and development (R&D) aims to improve the practicality of web-based mobile learning in operating system courses. The research adopts a systematic 4D (Define, Design, Develop, Disseminate) model to identify and explore strategies to optimize the practicality of the platform. Data collected from lecturers and students showed a high average value of practicality, 88.33% and 88.35%, respectively. This research contributes to improving the practical aspects of web-based mobile learning, thereby enhancing students’ learning experience and outcomes in the context of operating system courses.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136255218","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}
In the area of Phayao Province that used to be part of the ancient Lanna Kingdom, there are unique works of art that can be found until today, which are sandstone carvings caused by religious beliefs resulting in works such as Buddha statues. These are art related to religion. Nowadays, these works of art have started to fade away and receive less and less attention from people. The creation of art objects in this research therefore uses the interpretation of the creative objects in line with people’s lifestyles by selecting the lotus, which is a plant related to rivers, and is important in religion. In the lotus, which is interconnected and aligned with Buddhism, and in harmony with a way of life that aligns with the river, creative works are found in various forms, connecting people in Buddhism, including sandstone carving. In this creation, digital technology tools and methods are used to collect data to create a 3D work piece. Photogrammetry is used to record detailed proportions and information and customization of 3D work pieces. In these steps, mobile phone-type tools are used to collect image data to create the 3D work or an application is used to customize 3D work pieces from a tablet device to create prototypes of sandstone sculptures from the artisans that remain today. This can be seen in creating, maintaining, and recording digital data, creation, and the integration of knowledge. This demonstrates that today’s tools and portable devices can help create more creative pieces of work and preserve art and culture.
{"title":"Development and Creation of Ancient Sandstone Carvings Using 3D Software Tools and Mobile/Tablet Devices","authors":"Jirawat Sookkaew, Wisoot Kaenmueang, Nakarin Chaikaew","doi":"10.3991/ijim.v17i19.39007","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.39007","url":null,"abstract":"In the area of Phayao Province that used to be part of the ancient Lanna Kingdom, there are unique works of art that can be found until today, which are sandstone carvings caused by religious beliefs resulting in works such as Buddha statues. These are art related to religion. Nowadays, these works of art have started to fade away and receive less and less attention from people. The creation of art objects in this research therefore uses the interpretation of the creative objects in line with people’s lifestyles by selecting the lotus, which is a plant related to rivers, and is important in religion. In the lotus, which is interconnected and aligned with Buddhism, and in harmony with a way of life that aligns with the river, creative works are found in various forms, connecting people in Buddhism, including sandstone carving. In this creation, digital technology tools and methods are used to collect data to create a 3D work piece. Photogrammetry is used to record detailed proportions and information and customization of 3D work pieces. In these steps, mobile phone-type tools are used to collect image data to create the 3D work or an application is used to customize 3D work pieces from a tablet device to create prototypes of sandstone sculptures from the artisans that remain today. This can be seen in creating, maintaining, and recording digital data, creation, and the integration of knowledge. This demonstrates that today’s tools and portable devices can help create more creative pieces of work and preserve art and culture.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136352903","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}
We propose a microservices-based framework for scalable data analysis in agriculture with IoT integration, leveraging the flexibility and modularity of microservices architecture to build a highly adaptable, maintainable, and efficient data analysis system. This framework allows for faster data processing and carry a diversity of agricultural data analysis tasks while maintaining scalability and fault tolerance. Despite the potential benefits, several challenges and obstacles need to be addressed, such as data integration and standardization, the development of agricultural-specific analytical microservices, and ensuring data security and privacy. Practical application and real-world validation are required to assess the impact of the proposed framework on the agricultural sector and inform future research directions.
{"title":"A Microservices-based Framework for Scalable Data Analysis in Agriculture with IoT Integration","authors":"Othmane Aitlmoudden, Mohamed Housni, Nisrine Safeh, Abdelwahed Namir","doi":"10.3991/ijim.v17i19.40457","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.40457","url":null,"abstract":"We propose a microservices-based framework for scalable data analysis in agriculture with IoT integration, leveraging the flexibility and modularity of microservices architecture to build a highly adaptable, maintainable, and efficient data analysis system. This framework allows for faster data processing and carry a diversity of agricultural data analysis tasks while maintaining scalability and fault tolerance. Despite the potential benefits, several challenges and obstacles need to be addressed, such as data integration and standardization, the development of agricultural-specific analytical microservices, and ensuring data security and privacy. Practical application and real-world validation are required to assess the impact of the proposed framework on the agricultural sector and inform future research directions.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136353354","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}
This study focuses on the challenge of developing abstract models to differentiate various cloud resources. It explores the advancements in cloud products that offer specialized services to meet specific external needs. The study proposes a new approach to request processing in clusters, improving downtime, load distribution, and overall performance. A comparison of three clustering approaches is conducted: local single cluster, local multiple clusters, and multiple cloud clusters. Performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness are evaluated through experiments with 50 requests. All three approaches achieve a 100% success rate, but processing times vary. The local single cluster has the longest duration, while the local multiple clusters and multiple cloud clusters perform better and offer faster processing, scalability, fault tolerance, and availability. From a cost perspective, the local single cluster and local multiple clusters incur capital and operational expenses, while the multiple cloud clusters follow a pay-as-you-go model. Overall, the local multiple clusters and multiple cloud clusters outperform the local single cluster in terms of performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness. These findings provide valuable insights for selecting appropriate clustering strategies in cloud environments.
{"title":"Optimizing Clustering Approaches in Cloud Environments","authors":"Abdel-Rahman Al-Ghuwairi, Dimah Al-Fraihat, Yousef Sharrab, Yazeed Kreishan, Ayoub Alsarhan, Hasan Idhaim, Ayman Qahmash","doi":"10.3991/ijim.v17i19.42029","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.42029","url":null,"abstract":"This study focuses on the challenge of developing abstract models to differentiate various cloud resources. It explores the advancements in cloud products that offer specialized services to meet specific external needs. The study proposes a new approach to request processing in clusters, improving downtime, load distribution, and overall performance. A comparison of three clustering approaches is conducted: local single cluster, local multiple clusters, and multiple cloud clusters. Performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness are evaluated through experiments with 50 requests. All three approaches achieve a 100% success rate, but processing times vary. The local single cluster has the longest duration, while the local multiple clusters and multiple cloud clusters perform better and offer faster processing, scalability, fault tolerance, and availability. From a cost perspective, the local single cluster and local multiple clusters incur capital and operational expenses, while the multiple cloud clusters follow a pay-as-you-go model. Overall, the local multiple clusters and multiple cloud clusters outperform the local single cluster in terms of performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness. These findings provide valuable insights for selecting appropriate clustering strategies in cloud environments.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136352754","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 : 2023-10-10DOI: 10.3991/ijim.v17i19.41379
Ashraf Hamdan Aljammal, Ahmad Qawasmeh, Ala Mughaid, Salah Taamneh, Fadi I. Wedyan, Mamoon Obiedat
Botnets are today recognized as one of the most advanced vulnerability threats. Botnets control a huge percentage of network traffic and PCs. They have the ability to remotely control PCs (zombie machines) by their creator (BotMaster) via Command and Control (C&C) framework. They are the keys to a variety of Internet attacks such as spams, DDOS, and spreading malwares. This study proposes a number of machine learning techniques for detecting botnet assaults via IoT networks to help researchers in choosing the suitable ML algorithm for their applications. Using the BoT-IoT dataset, six different machine learning methods were evaluated: REPTree, RandomTree, RandomForest, J48, metaBagging, and Naive Bayes. Several measures, including accuracy, TPR, FPR, and many more, have been used to evaluate the algorithms’ performance. The six algorithms were evaluated using three different testing situations. Scenario-1 tested the algorithms utilizing all of the parameters presented in the BoT-IoT dataset, scenario-2 used the IG feature reduction approach, and scenario-3 used extracted features from the attacker’s received packets. The results revealed that the assessed algorithms performed well in all three cases with slight differences.
{"title":"Performance Evaluation of Machine Learning Approaches in Detecting IoT-Botnet Attacks","authors":"Ashraf Hamdan Aljammal, Ahmad Qawasmeh, Ala Mughaid, Salah Taamneh, Fadi I. Wedyan, Mamoon Obiedat","doi":"10.3991/ijim.v17i19.41379","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.41379","url":null,"abstract":"Botnets are today recognized as one of the most advanced vulnerability threats. Botnets control a huge percentage of network traffic and PCs. They have the ability to remotely control PCs (zombie machines) by their creator (BotMaster) via Command and Control (C&C) framework. They are the keys to a variety of Internet attacks such as spams, DDOS, and spreading malwares. This study proposes a number of machine learning techniques for detecting botnet assaults via IoT networks to help researchers in choosing the suitable ML algorithm for their applications. Using the BoT-IoT dataset, six different machine learning methods were evaluated: REPTree, RandomTree, RandomForest, J48, metaBagging, and Naive Bayes. Several measures, including accuracy, TPR, FPR, and many more, have been used to evaluate the algorithms’ performance. The six algorithms were evaluated using three different testing situations. Scenario-1 tested the algorithms utilizing all of the parameters presented in the BoT-IoT dataset, scenario-2 used the IG feature reduction approach, and scenario-3 used extracted features from the attacker’s received packets. The results revealed that the assessed algorithms performed well in all three cases with slight differences.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136353049","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 : 2023-10-10DOI: 10.3991/ijim.v17i19.42153
Jawad Ul Hassan, None Malik Muhammad Saad Missen, None Amnah Firdous, None Arfa Maham, None Amna Ikram
Mobile devices have evolved from communication tools to versatile platforms for various purposes, including learning. Usability is crucial for practical mobile learning applications, ensuring ease of use and expected performance. However, existing research on mobile educational apps has primarily focused on typical learners, neglecting the specific requirements of slow learners who face cognitive limitations. In this work, we fill this research gap by proposing an adaptable learning-oriented usability model (ALUM) for mobile learning apps specifically tailored to support slow learners. The research conducts a detailed usability analysis and systematic review to identify the problems users face and investigate how slow learners respond to learning apps in terms of efficiency, effectiveness, satisfaction, and learning outcomes. Twenty-four participants classified as slow learners evaluated the usability of 25 HTML-based learning apps. The evaluation revealed critical deficiencies in existing learning apps concerning the needs of slow learners, particularly in user-friendliness and learnability, leading to their dissatisfaction. We propose a model that leverages a hybrid recommendation system to address these challenges. The model incorporates a navigational graph, ontology, and item matrix to provide personalized topic recommendations, tailoring the content and delivery of educational materials based on individual needs and preferences. By enhancing the learning experience for slow learners, the proposed model aims to improve their learning outcomes. This research bridges the gap between academic research and practical applications in interactive mobile technologies. The adaptable learning-oriented usability model presented in this paper offers a framework for supporting slow learners, emphasizing its essential components and their interactions to enhance the learning outcomes for this user group.
{"title":"An Adaptive M-Learning Usability Model for Facilitating M-Learning for Slow Learners","authors":"Jawad Ul Hassan, None Malik Muhammad Saad Missen, None Amnah Firdous, None Arfa Maham, None Amna Ikram","doi":"10.3991/ijim.v17i19.42153","DOIUrl":"https://doi.org/10.3991/ijim.v17i19.42153","url":null,"abstract":"Mobile devices have evolved from communication tools to versatile platforms for various purposes, including learning. Usability is crucial for practical mobile learning applications, ensuring ease of use and expected performance. However, existing research on mobile educational apps has primarily focused on typical learners, neglecting the specific requirements of slow learners who face cognitive limitations. In this work, we fill this research gap by proposing an adaptable learning-oriented usability model (ALUM) for mobile learning apps specifically tailored to support slow learners. The research conducts a detailed usability analysis and systematic review to identify the problems users face and investigate how slow learners respond to learning apps in terms of efficiency, effectiveness, satisfaction, and learning outcomes. Twenty-four participants classified as slow learners evaluated the usability of 25 HTML-based learning apps. The evaluation revealed critical deficiencies in existing learning apps concerning the needs of slow learners, particularly in user-friendliness and learnability, leading to their dissatisfaction. We propose a model that leverages a hybrid recommendation system to address these challenges. The model incorporates a navigational graph, ontology, and item matrix to provide personalized topic recommendations, tailoring the content and delivery of educational materials based on individual needs and preferences. By enhancing the learning experience for slow learners, the proposed model aims to improve their learning outcomes. This research bridges the gap between academic research and practical applications in interactive mobile technologies. The adaptable learning-oriented usability model presented in this paper offers a framework for supporting slow learners, emphasizing its essential components and their interactions to enhance the learning outcomes for this user group.","PeriodicalId":53486,"journal":{"name":"International Journal of Interactive Mobile Technologies","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136353060","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：