{"title":"Speech recognition system based on deep neural network acoustic modeling for low resourced language-Amharic","authors":"Eshete Derb Emiru, Yaxing Li, Shengwu Xiong, Awet Fesseha","doi":"10.1145/3369555.3369564","DOIUrl":"https://doi.org/10.1145/3369555.3369564","url":null,"abstract":"In this paper automatic speech recognition is investigated using deep neural network (DNN) acoustic modeling method for Amharic language at syllabic acoustic units. In grapheme based database; graphemes/characters are basic units of lexicon and language model. A large portion of them represents syllables which are a combination of consonants and vowels (CV). Grapheme to phoneme (G2P) conversion was required to represent all text corpuses into CV phoneme representations via G2P conversion algorithm developed for this purpose. This algorithm used to develop syllable based pronunciation dictionary and language modeling which are vital for speech recognizer. DNN based acoustic model (AM) such as tanh-DNNs, tanh-fast-DNNs, p-norm-DNNs and p-norm-fast-DNNs are also explored with different hidden layers, hidden units and parameter settings. These DNN AMs are trained with morpheme based Amharic read speech in order to develop models. The recognition performance of our methods is evaluated in testing data and the reduced WER is achieved in p-norm-fast(p=2) DNN AMs.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121823622","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}
Gomotsegang Ntehelang, Bassey Isong, Francis Lugayizi, Nosipho Dladlu
{"title":"IoT-based big data analytics issues in healthcare","authors":"Gomotsegang Ntehelang, Bassey Isong, Francis Lugayizi, Nosipho Dladlu","doi":"10.1145/3369555.3369573","DOIUrl":"https://doi.org/10.1145/3369555.3369573","url":null,"abstract":"Internet of Things devices constantly generate big data which when analyzed reveals hidden patterns, information and trends, thus, enabling decision making. Several organization today utilized data analytics to improve organizational performance and deliver high quality of service and experience. Healthcare is not an exception and uses data analytics for some of its capabilities such as detecting diseases and diagnose patients at early stages, identifying high-risk patients and providing them treatment to reduce unnecessary hospitalization or readmission. However, the existing and expected increase of connected devices poses several challenges for data analysis, especially with little work being done to address them. Therefore, this paper brings together some of these challenges that needs to be addressed and some of the proposed solutions. We performed a review of some of the studies in the literature with a view of providing research directions for researchers.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131555725","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}
{"title":"Big data analytics and artificial intelligence in air pollution studies for the prediction of particulate matter concentration","authors":"S. Abdullah, M. Ismail, A. Ahmed, W. Mansor","doi":"10.1145/3369555.3369557","DOIUrl":"https://doi.org/10.1145/3369555.3369557","url":null,"abstract":"Statistical modeling has found not suitable to be used when predicting the particulate matter (PM10) as it is non-linear in nature. The complexity and nonlinearity of PM10 concentration in the atmosphere are known best captured by the nonlinear model which emerges nowadays such as Multi-Layer Perceptron Neural Network (MLP-NN). In order to assess the capability of MLP-NN model in predicting the PM10 concentration, a statistical or traditional model known as Multiple Linear Regression (MLR) was also developed as a reference model. The daily air quality data and meteorological variables from the year 2010-2014 were assembled in developing the models. The MLP-NN model with the combination of logsig and purelin activation function revealed 75.5% of the variance in data with 6.59 μg/m3 (RMSE) and 88.0% of the variance in data with 6.30 μg/m3 (RMSE), during training and testing phase, respectively. The MLP-NN model improves by 61.5% and reducing the 62.2% error as compared to the MLR model. This model is appropriate for operational used by respected authorities in managing air quality in maintaining sustainability and as an early warning during an unhealthy level of air quality.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131077297","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}
{"title":"A systematic literature review of security software defined network: research trends, threat, attack, detect, mitigate, and countermeasure","authors":"M. T. Kurniawan, S. Yazid","doi":"10.1145/3369555.3369567","DOIUrl":"https://doi.org/10.1145/3369555.3369567","url":null,"abstract":"The development of internet technology in the current decade is growing very rapidly. This triggers a variety of innovations in the application layer. However, these developments cannot be followed by network layers that tend to be slow. The concept of Software Defined network is present to solve the problem. Various studies were conducted for SDN technology, one of them is security. The highlight in security is the security architecture. Many security systems that are created do not refer to the security architecture so it is difficult in its development. In addition, the current security architecture does not refer to the guidelines for the creation of security architectures according to [1] there are two parts of security zones and security layers so that only 8% of security architectures meet both sections. In this study, a survey was conducted to find out the development trend in SDN security and security architecture of SDN using systematic literature review (SLR) method, and SLR result stated that research in architecture of network security is still very relevant to be done. By knowing the guidelines for making security architecture, it is hoped that the security architecture that is designed can be the foundation of the development of security framework and security system that will be developed.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128741767","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}
R. W. Purnamaningsih, N. R. Poespawati, T. Abuzairi, E. Dogheche
{"title":"An efficient GaN-based two branches optical power splitter based on self-imaging phenomena","authors":"R. W. Purnamaningsih, N. R. Poespawati, T. Abuzairi, E. Dogheche","doi":"10.1145/3369555.3369569","DOIUrl":"https://doi.org/10.1145/3369555.3369569","url":null,"abstract":"Underwater wireless optical communication (UOWC) has been attracted to many researchers since it has higher data rate transfer compared to underwater acoustic communications. Therefore, optical devices for this application should be developed. In this paper, we proposed a design of an efficient GaN-based 1×2 optical power splitter based on self-imaging phenomena for underwater application. The design has been optimised and analysed using the finite difference beam propagation method (FDBPM) at 450nm of wavelength, in which the deep seawater has a low absorption. The optimisation was conducted by investigating the effect of waveguide parameters on the structure. The best length and width of the structure were found to be 450 μm and 10 μm, respectively. We have confirmed that the optical power was successfully split input light into two output branches with an almost perfect splitting ratio of 50% at each output port. based 1×2 optical power splitter based on self-imaging phenomena for underwater application. The design has been optimised and analysed using the finite difference beam propagation method (FDBPM) at 450nm of wavelength, in which the deep sea water has a low absorption. The optimisation was conducted by investigating the effect of waveguide parameters on the structure. The best length and width of the structure were found to be 450 μm and 10 μm, respectively. We have confirmed that the optical power was successfully split input light into two output branches with an almost perfect splitting ratio of 50% at each output port.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123149508","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. Lagman, J. Q. Calleja, Corazon G. Fernando, Joseph G. Gonzales, J. B. Legaspi, J. H. J. Ortega, Ronel F. Ramos, M. V. Solomo, Regina C. Santos
{"title":"Embedding naïve Bayes algorithm data model in predicting student graduation","authors":"A. Lagman, J. Q. Calleja, Corazon G. Fernando, Joseph G. Gonzales, J. B. Legaspi, J. H. J. Ortega, Ronel F. Ramos, M. V. Solomo, Regina C. Santos","doi":"10.1145/3369555.3369570","DOIUrl":"https://doi.org/10.1145/3369555.3369570","url":null,"abstract":"In the Philippines, according to Philippine Authority of Statistics, there is an imbalance between the student enrollment and student graduation. Almost half of the first-time freshmen full time students who began seeking a bachelor's degree do not graduate on time. The study aims to utilize how Naïve Bayes algorithm - a data classification algorithm that is based on probabilistic analysis - can be used in educational data mining specifically in student graduation. The study is focused on the application of the Naïve Bayes algorithm in predicting student graduation by generating a model that could early predict and identify students who are prone of not having graduation on time, so proper remediation and retention policies can be formulated and implemented by institutions.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134082626","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}
Yuan Feng, Xueli Zhao, Mingxu Han, Tianying Sun, Chen Li
{"title":"The study of identification of fishing vessel behavior based on VMS data","authors":"Yuan Feng, Xueli Zhao, Mingxu Han, Tianying Sun, Chen Li","doi":"10.1145/3369555.3369574","DOIUrl":"https://doi.org/10.1145/3369555.3369574","url":null,"abstract":"Accurate identification of different behaviours of fishing vessels is important for fisheries management and fisheries ecology, which can enhance the management of overfishing and marine resources. In this study we identify fishing vessel fishing behavior through Vessel Monitoring System (VMS) data and BP neural networks. The change trend of the direction angle and speed of the fishing vessel is selected as the input parameters of the model, and the accuracy of identifying the fishing behavior is 79%. The fishery distribution is drawn according to the behavior of the fishing vessel identified by the model, which is similar to the distribution of the actual fishery and the fishing density. This laid the foundation for the deep exploration of the spatio-temporal characteristics of VMS in the future and the high-precision prediction of the distribution of fishing areas in China's offshore fisheries.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124765040","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}
{"title":"An accuracy optimization method for random access inter-satellite measurement system","authors":"Xiaoyi Xu, Chunhui Wang, Zhong-he Jin, Bei Ye","doi":"10.1145/3369555.3369571","DOIUrl":"https://doi.org/10.1145/3369555.3369571","url":null,"abstract":"In this paper, we present a precision optimization method which is for double one-way pseudo-code inter-satellite measurement system based on random access. The objective of this paper is to improve the accuracy of random access to inter-satellite measurement system. We have carried out several sets of theoretical analysis and numerical simulation to verify the validity of the proposed method for the accuracy optimization of inter-satellite measurement system. The studies we have performed showed that the proposed method could eliminate the main satellite error which caused by the dynamic characteristic of satellites and the frequency source drift. The research work has resulted in a solution of inter-satellite ranging scheme based on random access. The results of the paper have made a fundamental contribution to the future of distributed satellite communications.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"09 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127466687","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}
{"title":"An attribute-based mutual authentication scheme with time-bounded keys","authors":"Han-Yu Lin, Pei-yih Ting, Hong-Ru Wu","doi":"10.1145/3369555.3369568","DOIUrl":"https://doi.org/10.1145/3369555.3369568","url":null,"abstract":"Remote user authentication scheme is an important technique for securely accessing the resources of servers. Traditionally, password-based authentication schemes are commonly adopted mechanisms, i.e., a user first chooses a password and then registers to the server for becoming a legitimate member. Nevertheless, such schemes are vulnerable to password guessing attacks and a remote server might have to maintain a password table for verifying users. In recent years, attribute-based cryptosystems have been received much attention. An attribute-based authentication scheme allows a remote system to verify a user's membership according to his/her owned attribute sets without using passwords. In 2015, Yun et al. proposed an improved attribute-based authentication protocol by utilizing Shamir's secret sharing technique. Their protocol is secure against man-in-the-middle, replay and collusion attacks. However, we find out that their scheme only achieves one-way authentication rather than mutual authentication. In this paper, we extend their work to further fulfill the crucial property of mutual authentication. Moreover, we incorporate the concept of time-bounded keys into the extended variant for providing more flexible applications in the real world.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124007345","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}
Michiki Hara, Kizito Nkurikiyeyezu, Yu Nakayama, H. Ishizuka, Yukitoshi Kashimoto, Lopez Guillaume, Y. Tobe
{"title":"Identification of applications running on smartphones using call detail records","authors":"Michiki Hara, Kizito Nkurikiyeyezu, Yu Nakayama, H. Ishizuka, Yukitoshi Kashimoto, Lopez Guillaume, Y. Tobe","doi":"10.1145/3369555.3369576","DOIUrl":"https://doi.org/10.1145/3369555.3369576","url":null,"abstract":"The surge use in network traffic due to increased adoption of 4G LTE-capable portable devices put pressure on network providers to constantly upgrade their network infrastructures. At the same time, unlike traditional Internet access devices (e.g., computer desktops), whose network traffic can be easily tracked via their port numbers, applications of handheld devices typically communicate via HTTP and encrypted HTTPS. Additionally, for scalability purpose, most of their data are sent and received via Content Distribution Networks (CDNs). These communication characteristics obscure any attempt to monitor their network usage. This paper uses cellular network traffic generated by the applications running on a smartphone to predict a 62% prediction accuracy in distinguishing social network services (SNS) from other background applications.","PeriodicalId":377760,"journal":{"name":"Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering","volume":"694 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126401887","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}