Pub Date : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982413
Raja Majid Ali Ujjan, Zeeshan Pervez, K. Dahal
Due to the rapid increment of the cyber attacks, intrusion detection system (IDS) is shifting towards collaborative approaches. There is a huge demand for securing larger networking environments for providing a safeguard against threats. In order to optimize the feasible detection performance, Collaborative Intrusion Detection Networks (CIDN) approaches have been adopted in practical scenarios, which enables a group of IDS nodes to mutually share and exchange mandatory information with each other, for example, IDS-signatures, attacks alarms. However, CIDN networks are distributed in nature, such networks still face plenty of implementation problems, especially, insider intruder can easily dominate any of security node and leave the entire security system vulnerable. To achieve the trust-based communication between each of IDS node, the recent advancement in blockchain applications is considered as a good fit to create trust-based communication in CIDN networks. This work converges CIDN network and blockchain in SDN context. Firstly, we investigated existing related work and highlighted challenges and research gap towards blockchain in CIDN networks. Secondly, we utilised three collaborated Snort IDS to receive the latest signature update from Ryu and then to securely share such signatures updates to all other Snort nodes within test-bed. Our work is motivated to detect seven types of common attacks with collaborated signature-based IDS, which feasibly processes more packets to achieve satisfactory detection results. Overall the evaluation results show that with the adoption of blockchain protocols, the proposed CIDN network achieves 96% of TP rate detection rate for TCP, UDP and ICMP packets.
{"title":"Snort Based Collaborative Intrusion Detection System Using Blockchain in SDN","authors":"Raja Majid Ali Ujjan, Zeeshan Pervez, K. Dahal","doi":"10.1109/SKIMA47702.2019.8982413","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982413","url":null,"abstract":"Due to the rapid increment of the cyber attacks, intrusion detection system (IDS) is shifting towards collaborative approaches. There is a huge demand for securing larger networking environments for providing a safeguard against threats. In order to optimize the feasible detection performance, Collaborative Intrusion Detection Networks (CIDN) approaches have been adopted in practical scenarios, which enables a group of IDS nodes to mutually share and exchange mandatory information with each other, for example, IDS-signatures, attacks alarms. However, CIDN networks are distributed in nature, such networks still face plenty of implementation problems, especially, insider intruder can easily dominate any of security node and leave the entire security system vulnerable. To achieve the trust-based communication between each of IDS node, the recent advancement in blockchain applications is considered as a good fit to create trust-based communication in CIDN networks. This work converges CIDN network and blockchain in SDN context. Firstly, we investigated existing related work and highlighted challenges and research gap towards blockchain in CIDN networks. Secondly, we utilised three collaborated Snort IDS to receive the latest signature update from Ryu and then to securely share such signatures updates to all other Snort nodes within test-bed. Our work is motivated to detect seven types of common attacks with collaborated signature-based IDS, which feasibly processes more packets to achieve satisfactory detection results. Overall the evaluation results show that with the adoption of blockchain protocols, the proposed CIDN network achieves 96% of TP rate detection rate for TCP, UDP and ICMP packets.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126197602","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982422
Thepparit Sinthamrongruk, K. Dahal, Xinheng Wang, M. Iqbal
Routing workforce planning problem is a difficult problem, requiring a combination of the vehicle routing problem and the staff scheduling problem. This problem associates with a lot of constraints, even when having only a single criterion and homogeneous staff skill. This paper introduces three-step scheduling-a generic scheduling procedure for solving the workforce planning problems which incorporates between an optimisation tool, fuzzy inference system and geographic information system technology. The scheduling problem is hierarchically divided into sub-problems and then solved with the proposed scheduling framework. A simulated case study of the electricity meter installation service problems is employed to verify the proposed framework. In this study, we are focusing on the route scheduling which is the first step of the three-step scheduling. The total of travel distance is defined as an objective function. Particular case requirements such as lunch and parking time are also included in the model for optimisation. Our empirical study reveals that the proposed route scheduling is capable of exploring the optimal solutions for the case study with the shortest service path, compared to the original procedure.
{"title":"A three-step scheduling based on geographic information system for workforce-planning problem","authors":"Thepparit Sinthamrongruk, K. Dahal, Xinheng Wang, M. Iqbal","doi":"10.1109/SKIMA47702.2019.8982422","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982422","url":null,"abstract":"Routing workforce planning problem is a difficult problem, requiring a combination of the vehicle routing problem and the staff scheduling problem. This problem associates with a lot of constraints, even when having only a single criterion and homogeneous staff skill. This paper introduces three-step scheduling-a generic scheduling procedure for solving the workforce planning problems which incorporates between an optimisation tool, fuzzy inference system and geographic information system technology. The scheduling problem is hierarchically divided into sub-problems and then solved with the proposed scheduling framework. A simulated case study of the electricity meter installation service problems is employed to verify the proposed framework. In this study, we are focusing on the route scheduling which is the first step of the three-step scheduling. The total of travel distance is defined as an objective function. Particular case requirements such as lunch and parking time are also included in the model for optimisation. Our empirical study reveals that the proposed route scheduling is capable of exploring the optimal solutions for the case study with the shortest service path, compared to the original procedure.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129069042","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982493
M. Roy, Piyali Maur, C. Chowdhury, N. Aslam
Wireless Body Area Networks (WBANs) are evolving as a popular choice for a wide range of monitoring applications that prerequisite reliable network layer operations. However, the resource (such as energy, storage, computational capacity etc.) constrained nodes impose inherent challenges to the design approach. In addition, the communications may take place over multiple mediums based on the type of the communicating nodes and thus the channel conditions have significant impact on the performance as well. Moreover, the link quality may suffer due to relative node movements as a result of posture change. Hence, choosing optimal transmission power that provides a trade-off between reliable data communication and energy draining is another aspect of designing solution. Hence, in this paper a lightweight routing approach is proposed that ensures reliable data delivery to the sink with minimal overhead so that the protocol could be readily implemented in resource constrained networks like WBAN. Transmission power for each data communication is chosen adaptively based on the energy resource and the channel conditions. The protocol has been simulated in Castalia simulator and compared with the state of the art WBAN routing protocol.
{"title":"Power Aware Reliable Lightweight (PARL) Routing Protocol for Wireless Body Area Networks","authors":"M. Roy, Piyali Maur, C. Chowdhury, N. Aslam","doi":"10.1109/SKIMA47702.2019.8982493","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982493","url":null,"abstract":"Wireless Body Area Networks (WBANs) are evolving as a popular choice for a wide range of monitoring applications that prerequisite reliable network layer operations. However, the resource (such as energy, storage, computational capacity etc.) constrained nodes impose inherent challenges to the design approach. In addition, the communications may take place over multiple mediums based on the type of the communicating nodes and thus the channel conditions have significant impact on the performance as well. Moreover, the link quality may suffer due to relative node movements as a result of posture change. Hence, choosing optimal transmission power that provides a trade-off between reliable data communication and energy draining is another aspect of designing solution. Hence, in this paper a lightweight routing approach is proposed that ensures reliable data delivery to the sink with minimal overhead so that the protocol could be readily implemented in resource constrained networks like WBAN. Transmission power for each data communication is chosen adaptively based on the energy resource and the channel conditions. The protocol has been simulated in Castalia simulator and compared with the state of the art WBAN routing protocol.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"354 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122800336","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982391
Md. Yasir Arafat, S. Hoque, Shuxiang Xu, D. Farid
Multi-class imbalanced data classification in supervised learning is one of the most challenging research issues in machine learning for data mining applications. Although several data sampling methods have been introduced by computational intelligence researchers in the past decades for handling imbalanced data, still learning from imbalanced data is a challenging task and played as a significant focused research interest as well. Traditional machine learning algorithms usually biased to the majority class instances whereas ignored the minority class instances. As a result, ignoring minority class instances may affect the prediction accuracy of classifiers. Generally, under-sampling and over-sampling methods are commonly used in single model classifiers or ensemble learning for dealing with imbalanced data. In this paper, we have introduced an under-sampling method with support vectors for classifying imbalanced data. The proposed approach selects the most informative majority class instances based on the support vectors that help to engender decision boundary. We have tested the performance of the proposed method with single classifiers (C4.5 Decision Tree classifier and naïve Bayes classifier) and ensemble classifiers (Random Forest and AdaBoost) on 13 benchmark imbalanced datasets. It is explicitly shown by the experimental result that the proposed method produces high accuracy when classifying both the minority and majority class instances compared to other existing methods.
{"title":"An Under-Sampling Method with Support Vectors in Multi-class Imbalanced Data Classification","authors":"Md. Yasir Arafat, S. Hoque, Shuxiang Xu, D. Farid","doi":"10.1109/SKIMA47702.2019.8982391","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982391","url":null,"abstract":"Multi-class imbalanced data classification in supervised learning is one of the most challenging research issues in machine learning for data mining applications. Although several data sampling methods have been introduced by computational intelligence researchers in the past decades for handling imbalanced data, still learning from imbalanced data is a challenging task and played as a significant focused research interest as well. Traditional machine learning algorithms usually biased to the majority class instances whereas ignored the minority class instances. As a result, ignoring minority class instances may affect the prediction accuracy of classifiers. Generally, under-sampling and over-sampling methods are commonly used in single model classifiers or ensemble learning for dealing with imbalanced data. In this paper, we have introduced an under-sampling method with support vectors for classifying imbalanced data. The proposed approach selects the most informative majority class instances based on the support vectors that help to engender decision boundary. We have tested the performance of the proposed method with single classifiers (C4.5 Decision Tree classifier and naïve Bayes classifier) and ensemble classifiers (Random Forest and AdaBoost) on 13 benchmark imbalanced datasets. It is explicitly shown by the experimental result that the proposed method produces high accuracy when classifying both the minority and majority class instances compared to other existing methods.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"458 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114016369","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982507
Siraprapa Wattanakul, Napaporn Reeveerakul, S. Henry, Y. Ouzrout
The transit time of transportation and port clearance is considered as the second most salient risk in the global supply chain. This further affects the accurate estimation of shipment lead time due to the high variability. This research proposes a literature review to explore the behaviour of uncertainty influencing the global logistics chain. The classification of logistics roles (Shipper, Shipping line, Port: Fundamental and Port: Intermodal) presents how the uncertainty currently influences the decisions of each logistics role in strategical, tactical and operational problems. It is found that uncertainty occurred during the logistics operation influencing to all logistics roles and it is transferrable to the adjacent logistics role. The Unitary Traceability Object such as smart container has an opportunity to monitor the logistics operation and extract the behaviour of uncertainty during the operation in the field. This information further supports the planning decisions to respond/treat the uncertainty.
{"title":"Uncertainty handling in containerized logistics: Unitary Traceability Object approach","authors":"Siraprapa Wattanakul, Napaporn Reeveerakul, S. Henry, Y. Ouzrout","doi":"10.1109/SKIMA47702.2019.8982507","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982507","url":null,"abstract":"The transit time of transportation and port clearance is considered as the second most salient risk in the global supply chain. This further affects the accurate estimation of shipment lead time due to the high variability. This research proposes a literature review to explore the behaviour of uncertainty influencing the global logistics chain. The classification of logistics roles (Shipper, Shipping line, Port: Fundamental and Port: Intermodal) presents how the uncertainty currently influences the decisions of each logistics role in strategical, tactical and operational problems. It is found that uncertainty occurred during the logistics operation influencing to all logistics roles and it is transferrable to the adjacent logistics role. The Unitary Traceability Object such as smart container has an opportunity to monitor the logistics operation and extract the behaviour of uncertainty during the operation in the field. This information further supports the planning decisions to respond/treat the uncertainty.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132749871","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982462
Nureddin Moustafa, A. Iglesias, A. Gálvez
Swarm intelligence is a subfield of artificial intelligence based on the collective behavior of decentralized, self-organized systems comprised of very simple individual interacting locally with one another and with their environment. Such interactions lead to the emergence of intelligent behavior, unknown to the individual agents. One of the most remarkable applications of swarm intelligence is swarm robotics, Swarm robotics is one of the most exciting developments in artificial intelligence during the last few years is swarm robotics, where expensive and sophisticated robots can be replaced by a swarm of simple inexpensive micro-robots. In this context, this paper introduces Proteus-I, a flexible and adaptable low-cost general-purpose micro-robot prototype especially designed for swarm robotics. The robot has been designed to support the most popular swarm intelligence algorithms by either hardware or software. The paper describes the main components of the micro-robot along with some of the most important features to support swarm intelligence algorithms for swarm robotics.
{"title":"Proteus-I: A Flexible and Adaptable Low-Cost General-Purpose Micro-Robot Prototype for Swarm Robotics","authors":"Nureddin Moustafa, A. Iglesias, A. Gálvez","doi":"10.1109/SKIMA47702.2019.8982462","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982462","url":null,"abstract":"Swarm intelligence is a subfield of artificial intelligence based on the collective behavior of decentralized, self-organized systems comprised of very simple individual interacting locally with one another and with their environment. Such interactions lead to the emergence of intelligent behavior, unknown to the individual agents. One of the most remarkable applications of swarm intelligence is swarm robotics, Swarm robotics is one of the most exciting developments in artificial intelligence during the last few years is swarm robotics, where expensive and sophisticated robots can be replaced by a swarm of simple inexpensive micro-robots. In this context, this paper introduces Proteus-I, a flexible and adaptable low-cost general-purpose micro-robot prototype especially designed for swarm robotics. The robot has been designed to support the most popular swarm intelligence algorithms by either hardware or software. The paper describes the main components of the micro-robot along with some of the most important features to support swarm intelligence algorithms for swarm robotics.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116490778","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982421
Jensen Selwyn Joymangul, A. Sekhari, N. Moalla, O. Grasset
Obstructive Sleep Apnea (OSA) is a sleep pathology that leads to different illness. The goal therapy for OSA is a Continuous Positive Airway Pressure (CPAP). However, CPAP therapy is one of the therapies which has the lowest adherence level. This paper presents a data-driven framework to improve the experience of the patients during the initiation phase of CPAP therapy. Since this phase is a key factor for adherence level over time. Our approach uses data analytics techniques to provide personalised services for each patient through a different process of knowledge discovery. We have integrated a validation process for each outcome of the framework, Therefore, there is also continuous improvement of the data models.
{"title":"Data-oriented approach to improve adherence to CPAP therapy during the initiation phase","authors":"Jensen Selwyn Joymangul, A. Sekhari, N. Moalla, O. Grasset","doi":"10.1109/SKIMA47702.2019.8982421","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982421","url":null,"abstract":"Obstructive Sleep Apnea (OSA) is a sleep pathology that leads to different illness. The goal therapy for OSA is a Continuous Positive Airway Pressure (CPAP). However, CPAP therapy is one of the therapies which has the lowest adherence level. This paper presents a data-driven framework to improve the experience of the patients during the initiation phase of CPAP therapy. Since this phase is a key factor for adherence level over time. Our approach uses data analytics techniques to provide personalised services for each patient through a different process of knowledge discovery. We have integrated a validation process for each outcome of the framework, Therefore, there is also continuous improvement of the data models.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"270 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123019978","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982425
A. Malyshev, X. Tai
We propose a variant of convex reformulation of the standard variational model with non-convex data terms. The proposed convex relaxation of multilabel problems is a continuous formulation of Ishikawa’s method for extension of the graph min-cut to the multilabel problems. Our convex continuous reformulation is based upon functional lifting to a higher-dimensional space using superlevel functions. We solve the resulting convex variational problem by the augmented Lagrangian method. The most time consuming part of this method is the numerical solution of a boundary value problem for the Poisson equation in three-dimensional space, which is implemented by means of a fast Poisson solver. We illustrate the developed theory with several numerical examples for the standard correspondence problem for a rectified stereo image pair.
{"title":"Variational Model for Depth Estimation from Images","authors":"A. Malyshev, X. Tai","doi":"10.1109/SKIMA47702.2019.8982425","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982425","url":null,"abstract":"We propose a variant of convex reformulation of the standard variational model with non-convex data terms. The proposed convex relaxation of multilabel problems is a continuous formulation of Ishikawa’s method for extension of the graph min-cut to the multilabel problems. Our convex continuous reformulation is based upon functional lifting to a higher-dimensional space using superlevel functions. We solve the resulting convex variational problem by the augmented Lagrangian method. The most time consuming part of this method is the numerical solution of a boundary value problem for the Poisson equation in three-dimensional space, which is implemented by means of a fast Poisson solver. We illustrate the developed theory with several numerical examples for the standard correspondence problem for a rectified stereo image pair.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126849775","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982520
Abdelhak Belhi, Houssem Gasmi, A. Al-Ali, A. Bouras, S. Foufou, Xi Yu, Haiqing Zhang
Cultural heritage takes an important part of the history of humankind as it is one of the most powerful tools for the transfer and preservation of moral identity. As a result, these cultural assets are considered highly valuable and sometimes priceless. Digital technologies provided multiple tools that address challenges related to the promotion and information access in the cultural context. However, the large data collections of cultural information have more potential to add value and address current challenges in this context with the recent progress in artificial intelligence (AI) with deep learning and data mining tools. Through the present paper, we investigate several approaches that are used or can potentially be used to promote, curate, preserve and value cultural heritage through new and evolutionary techniques based on deep learning tools. The deep learning approaches entirely developed by our team are intended to classify and annotate cultural data, complete missing data, or map existing data schemes and information to standardized schemes with language processing tools.
{"title":"Deep Learning and Cultural Heritage: The CEPROQHA Project Case Study","authors":"Abdelhak Belhi, Houssem Gasmi, A. Al-Ali, A. Bouras, S. Foufou, Xi Yu, Haiqing Zhang","doi":"10.1109/SKIMA47702.2019.8982520","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982520","url":null,"abstract":"Cultural heritage takes an important part of the history of humankind as it is one of the most powerful tools for the transfer and preservation of moral identity. As a result, these cultural assets are considered highly valuable and sometimes priceless. Digital technologies provided multiple tools that address challenges related to the promotion and information access in the cultural context. However, the large data collections of cultural information have more potential to add value and address current challenges in this context with the recent progress in artificial intelligence (AI) with deep learning and data mining tools. Through the present paper, we investigate several approaches that are used or can potentially be used to promote, curate, preserve and value cultural heritage through new and evolutionary techniques based on deep learning tools. The deep learning approaches entirely developed by our team are intended to classify and annotate cultural data, complete missing data, or map existing data schemes and information to standardized schemes with language processing tools.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126817978","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 : 2019-07-18DOI: 10.1109/SKIMA47702.2019.8982449
Marzia Hoque Tania, Khin T. Lwin, A. Shabut, Kamal Abu-Hassan, M. S. Kaiser, M. A. Hossain
The colourimetric analysis has been used in diversified fields for years. This paper provides a unique overview of colourimetric tests from the perspective of computer vision by describing different aspects of a colourimetric test in the context of image processing, followed by an investigation into the development of a colorimetric assay type detection system using advanced machine learning algorithms. To the best of our knowledge, this is the first attempt to define colourimetric assay types from the eyes of a machine and perform any colorimetric test using deep learning. This investigation utilizes the state-of-the-art pre-trained models of Convolutional Neural Network (CNN) to perform the assay type detection of an enzyme-linked immunosorbent assay (ELISA) and lateral flow assay (LFA). The ELISA dataset contains images of both positive and negative samples, prepared for the plasmonic ELISA based TB-antigen specific antibody detection. The LFA dataset contains images of the universal pH indicator paper of eight pH levels. It is noted that the pre-trained models offered 100% accurate visual recognition for the assay type detection. Such detection can assist novice users to initiate a colorimetric test using his/her personal digital devices. The assay type detection can also aid in calibrating an image-based colorimetric classification.
{"title":"Assay Type Detection Using Advanced Machine Learning Algorithms","authors":"Marzia Hoque Tania, Khin T. Lwin, A. Shabut, Kamal Abu-Hassan, M. S. Kaiser, M. A. Hossain","doi":"10.1109/SKIMA47702.2019.8982449","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982449","url":null,"abstract":"The colourimetric analysis has been used in diversified fields for years. This paper provides a unique overview of colourimetric tests from the perspective of computer vision by describing different aspects of a colourimetric test in the context of image processing, followed by an investigation into the development of a colorimetric assay type detection system using advanced machine learning algorithms. To the best of our knowledge, this is the first attempt to define colourimetric assay types from the eyes of a machine and perform any colorimetric test using deep learning. This investigation utilizes the state-of-the-art pre-trained models of Convolutional Neural Network (CNN) to perform the assay type detection of an enzyme-linked immunosorbent assay (ELISA) and lateral flow assay (LFA). The ELISA dataset contains images of both positive and negative samples, prepared for the plasmonic ELISA based TB-antigen specific antibody detection. The LFA dataset contains images of the universal pH indicator paper of eight pH levels. It is noted that the pre-trained models offered 100% accurate visual recognition for the assay type detection. Such detection can assist novice users to initiate a colorimetric test using his/her personal digital devices. The assay type detection can also aid in calibrating an image-based colorimetric classification.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115860592","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：