Pub Date : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672228
M. Negash, Michael Melese Woldeyohannis
Internet-based social media sites such as Twitter represent a growing level of modern experience. These sites claim a large number of users and their influence is increasingly being experienced in clinical practice. Psychiatric disorders currently are affecting many people from different cultures, ages, and geographic locations. Although, the majority of individuals who experience symptom of psychiatric disorder practice the desire to be isolated, which drives them to use online channels to share their feelings. Hence, this sites provide a way to detect undiagnosed psychiatric disorders. In order to address this issue, we propose a model to classify the severity level of psychiatric symptoms (i.e. depression, anxiety, and bipolar) based on a data extracted from Twitter. The model is employed by fusing the linguistic features of Term Frequency Inverse Document Frequency (TFIDF) weighed by N-gram (unigram, bigram, and trigram), and word2vce, with Pattern of Life Feature (PLF) that take polarity, subjectivity, and gender. The experiment, is conducted by incorporating with machine learning classifiers of Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Naïve Bayes (NB). Experimental results show that SVM with features of TFIDF weighed by unigram combined with PLF outperforms with an accuracy score of 97.3%. In future, the proposed model could be employed to include lexicon-based features for classifying various psychiatric symptoms with a combined approach of machine learning and lexicon-based classification.
{"title":"Classifying Severity Level of Psychiatric Symptoms on Twitter Data","authors":"M. Negash, Michael Melese Woldeyohannis","doi":"10.1109/ict4da53266.2021.9672228","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672228","url":null,"abstract":"Internet-based social media sites such as Twitter represent a growing level of modern experience. These sites claim a large number of users and their influence is increasingly being experienced in clinical practice. Psychiatric disorders currently are affecting many people from different cultures, ages, and geographic locations. Although, the majority of individuals who experience symptom of psychiatric disorder practice the desire to be isolated, which drives them to use online channels to share their feelings. Hence, this sites provide a way to detect undiagnosed psychiatric disorders. In order to address this issue, we propose a model to classify the severity level of psychiatric symptoms (i.e. depression, anxiety, and bipolar) based on a data extracted from Twitter. The model is employed by fusing the linguistic features of Term Frequency Inverse Document Frequency (TFIDF) weighed by N-gram (unigram, bigram, and trigram), and word2vce, with Pattern of Life Feature (PLF) that take polarity, subjectivity, and gender. The experiment, is conducted by incorporating with machine learning classifiers of Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Naïve Bayes (NB). Experimental results show that SVM with features of TFIDF weighed by unigram combined with PLF outperforms with an accuracy score of 97.3%. In future, the proposed model could be employed to include lexicon-based features for classifying various psychiatric symptoms with a combined approach of machine learning and lexicon-based classification.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116434028","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672246
T. Abebe, E. Alemneh
Corpus is a milestone to study natural languages and to develop various tools for the processing of human languages. Since, few studies are carried out on the development of Amharic language corpus development, the existing corpora are very small in size and not well accessible for academicians as well as commercial and non-commercial organizations. This paper presents Amharic text corpus developed by applying the processes of annotating each word with its part of speech tag and reducing each orthographic word to its headword using either derivational or inflectional process. We extracted 12,720 sentences from various text documents collected in the domain of proclamations. Ethiopian 1987 E.C constitution and a few policies of Amhara regional state, Ethiopia and federal government of Ethiopia are some of those documents. We found 331,728 tokens from those sentences. 66 tag sets are compiled from base part of speech tag set classes and compound part of speech tag set classes based on different factors and representation of orthographic words. To help the manual annotation of each orthographic word, we developed a semi-automatic Amharic text tagger. The outputs of the research project are pre-processed Amharic text stored in plain text format and tagged Amharic text corpus encoded with extensible markup language format. The tag sets of annotated text corpora are represented in both Ge'ez script and English characters. We plan to increase the number of tag sets and size of text corpus in the near future. Moreover, we are working towards converting the semi-automatic Amharic text tagger to full automation.
{"title":"Amharic Text Corpus based on Parts of Speech tagging and headwords","authors":"T. Abebe, E. Alemneh","doi":"10.1109/ict4da53266.2021.9672246","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672246","url":null,"abstract":"Corpus is a milestone to study natural languages and to develop various tools for the processing of human languages. Since, few studies are carried out on the development of Amharic language corpus development, the existing corpora are very small in size and not well accessible for academicians as well as commercial and non-commercial organizations. This paper presents Amharic text corpus developed by applying the processes of annotating each word with its part of speech tag and reducing each orthographic word to its headword using either derivational or inflectional process. We extracted 12,720 sentences from various text documents collected in the domain of proclamations. Ethiopian 1987 E.C constitution and a few policies of Amhara regional state, Ethiopia and federal government of Ethiopia are some of those documents. We found 331,728 tokens from those sentences. 66 tag sets are compiled from base part of speech tag set classes and compound part of speech tag set classes based on different factors and representation of orthographic words. To help the manual annotation of each orthographic word, we developed a semi-automatic Amharic text tagger. The outputs of the research project are pre-processed Amharic text stored in plain text format and tagged Amharic text corpus encoded with extensible markup language format. The tag sets of annotated text corpora are represented in both Ge'ez script and English characters. We plan to increase the number of tag sets and size of text corpus in the near future. Moreover, we are working towards converting the semi-automatic Amharic text tagger to full automation.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126772450","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672236
Kehali A. Jember, T. Abose, T. Olwal, Murad R. Hassen
Recently, wireless data traffic is growing exponentially due to innovative wireless devices such as smart phones, tablets, and machine-to-machine communications and so on. 3GPP introduces LTE release-8 as first standard and continues further research to introduce LTE-A for network improvement having those innovative devices and services in mind. As far as LTE-A is concerned, Heterogeneous Networks are introduced to improve network performance by deploying small cells over the coverage area of the serving Macro cells. The essential target of deploying such a small cell is to offload the users from the congested Macro cells towards the small cells. Small cell covers only limited areas due to low transmit power. To increase coverage and capacity of small cell, cell range extension was introduced in this research. Cell range extension boosts received signal power of small cell users by adding positive offset bias. Computer simulations are carried out following the developed analytical frameworks. The simulation results validates that deploying small cell over Macro cell improves user and cell throughput.
{"title":"Impact of Enhanced Inter-Cell Interference Coordination on Heterogeneous Network Topology in LTE-A Using Cell Range Extension","authors":"Kehali A. Jember, T. Abose, T. Olwal, Murad R. Hassen","doi":"10.1109/ict4da53266.2021.9672236","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672236","url":null,"abstract":"Recently, wireless data traffic is growing exponentially due to innovative wireless devices such as smart phones, tablets, and machine-to-machine communications and so on. 3GPP introduces LTE release-8 as first standard and continues further research to introduce LTE-A for network improvement having those innovative devices and services in mind. As far as LTE-A is concerned, Heterogeneous Networks are introduced to improve network performance by deploying small cells over the coverage area of the serving Macro cells. The essential target of deploying such a small cell is to offload the users from the congested Macro cells towards the small cells. Small cell covers only limited areas due to low transmit power. To increase coverage and capacity of small cell, cell range extension was introduced in this research. Cell range extension boosts received signal power of small cell users by adding positive offset bias. Computer simulations are carried out following the developed analytical frameworks. The simulation results validates that deploying small cell over Macro cell improves user and cell throughput.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122351075","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672232
Lata Guta Kanessa, S. Tulu
The easily accessibility of different online platform allows every individuals people to express their ideas and share experiences easily without any restriction because of freedom of speech. Since social media don't have general framework to identify hate and neutral speech this results anonymity. However, the propagation of hate speech on social media distresses the society in many aspects, such as affecting the mental health of targeted audiences, affects social interaction and distraction of properties. This research proposed the SVM with TF-IDF, N-gram, and W2vec feature extraction to construct dataset which is binary classifier to detect hate speech for Afaan Oromoo language. To construct dataset for this study first we crawl data from Facebook posts and comments by using Face pager and scrap storm API. After we collect we labeled the collected data to two class hate and neutral class. The general objective of this research is to design a framework which classify hate and neutral speech. Furthermore, when we compare the results of different Machine Learning algorithms. The experiment is evaluated based on accuracy, F-score, recall and precision measurements. The framework based on SVM with n-gram combination with TF-IDF achieve 96% in all metrics.
{"title":"Automatic Hate and Offensive speech detection framework from social media: the case of Afaan Oromoo language","authors":"Lata Guta Kanessa, S. Tulu","doi":"10.1109/ict4da53266.2021.9672232","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672232","url":null,"abstract":"The easily accessibility of different online platform allows every individuals people to express their ideas and share experiences easily without any restriction because of freedom of speech. Since social media don't have general framework to identify hate and neutral speech this results anonymity. However, the propagation of hate speech on social media distresses the society in many aspects, such as affecting the mental health of targeted audiences, affects social interaction and distraction of properties. This research proposed the SVM with TF-IDF, N-gram, and W2vec feature extraction to construct dataset which is binary classifier to detect hate speech for Afaan Oromoo language. To construct dataset for this study first we crawl data from Facebook posts and comments by using Face pager and scrap storm API. After we collect we labeled the collected data to two class hate and neutral class. The general objective of this research is to design a framework which classify hate and neutral speech. Furthermore, when we compare the results of different Machine Learning algorithms. The experiment is evaluated based on accuracy, F-score, recall and precision measurements. The framework based on SVM with n-gram combination with TF-IDF achieve 96% in all metrics.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127930479","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672221
Tadele Shimels, Lemma F. Lessa
Information system security is more critical than ever before because security threats are rapidly growing and the environment requires organizations to continuously adapt to changes. Before putting in place information systems security measures, organizations are required to determine the maturity level of their information security governance. Extant literature reveals that there is no recent study on information systems security maturity level of banks in Ethiopia. This study, thus, seeks to measure the existing maturity level and examine the security gaps in order to propose possible changes in Ethiopian private banking industry's information system security maturity indicators. Four private banks are selected as a representative sample. SSE-CMM (System Security Engineering Capability Maturity Model) is used as the maturity measurement criteria and the measurement was based on ISO/IEC 27001 information security control areas. The data for the study was gathered using a questionnaire. A total of 93 valid questionnaires were gathered from 110 participants in the study. Based on the SSE-CMM maturity model assessment criteria, the private banking industry's current maturity level is level 2 (repeatable but intuitive). Institutions have a pattern that is repeated when completing information security operations, but its existence was not thoroughly proven, and institutional inconsistency still exists. Recommendations are forwarded for management intervention in order to address the identified gaps.
{"title":"Maturity of information systems security in selected private Banks in Ethiopia","authors":"Tadele Shimels, Lemma F. Lessa","doi":"10.1109/ict4da53266.2021.9672221","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672221","url":null,"abstract":"Information system security is more critical than ever before because security threats are rapidly growing and the environment requires organizations to continuously adapt to changes. Before putting in place information systems security measures, organizations are required to determine the maturity level of their information security governance. Extant literature reveals that there is no recent study on information systems security maturity level of banks in Ethiopia. This study, thus, seeks to measure the existing maturity level and examine the security gaps in order to propose possible changes in Ethiopian private banking industry's information system security maturity indicators. Four private banks are selected as a representative sample. SSE-CMM (System Security Engineering Capability Maturity Model) is used as the maturity measurement criteria and the measurement was based on ISO/IEC 27001 information security control areas. The data for the study was gathered using a questionnaire. A total of 93 valid questionnaires were gathered from 110 participants in the study. Based on the SSE-CMM maturity model assessment criteria, the private banking industry's current maturity level is level 2 (repeatable but intuitive). Institutions have a pattern that is repeated when completing information security operations, but its existence was not thoroughly proven, and institutional inconsistency still exists. Recommendations are forwarded for management intervention in order to address the identified gaps.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126199986","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672238
{"title":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA) - Spine art","authors":"","doi":"10.1109/ict4da53266.2021.9672238","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672238","url":null,"abstract":"","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126705688","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9671270
Mesay Gemeda Yigezu, Michael Melese Woldeyohannis, A. Tonja
Unlike technologically favored languages, under-resourced languages highly suffer from the lack of language resources for machine translation. In this paper, we present a new approach to overcome the problem of language resources that share significant amount of linguistic resource in the Ometo language family. The dataset for the experiment are collected from religious domain consisting of four Ometo (Wolaita, Gamo, Gofa, and Dawuro) languages paired with English sentence and automatically extracted from the web. The collected corpus were used for conducting neural machine translation experiments from Ometo to English. Among the experiments, the Wolaita, Dawuro and Gamo paired with English sentence combination for training and Gofa for testing gives highest BLEU score 4.5 than the other combinations while the Wolaita, Gamo, and Gofa with Dawuro testing provide the lowest result. The BLEU score of the machine translation system shows a promising result despite the language differences, the morphological richness, and complexity of the Ometo languages which has high impact on the performance of the Ometo-English machine translation. Further, we are now working towards developing a translation system that significantly reduces the effect of morphological richness and complexity of the Ometo languages through different linguistic processing.
{"title":"Multilingual Neural Machine Translation for Low Resourced Languages: Ometo-English","authors":"Mesay Gemeda Yigezu, Michael Melese Woldeyohannis, A. Tonja","doi":"10.1109/ict4da53266.2021.9671270","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9671270","url":null,"abstract":"Unlike technologically favored languages, under-resourced languages highly suffer from the lack of language resources for machine translation. In this paper, we present a new approach to overcome the problem of language resources that share significant amount of linguistic resource in the Ometo language family. The dataset for the experiment are collected from religious domain consisting of four Ometo (Wolaita, Gamo, Gofa, and Dawuro) languages paired with English sentence and automatically extracted from the web. The collected corpus were used for conducting neural machine translation experiments from Ometo to English. Among the experiments, the Wolaita, Dawuro and Gamo paired with English sentence combination for training and Gofa for testing gives highest BLEU score 4.5 than the other combinations while the Wolaita, Gamo, and Gofa with Dawuro testing provide the lowest result. The BLEU score of the machine translation system shows a promising result despite the language differences, the morphological richness, and complexity of the Ometo languages which has high impact on the performance of the Ometo-English machine translation. Further, we are now working towards developing a translation system that significantly reduces the effect of morphological richness and complexity of the Ometo languages through different linguistic processing.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126570493","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672244
O. Salami, Abdulrazaq Muhammad Bashir, E. A. Adedokun, Yahaya Basira
Authentication of user on a computer or network enable privacy protection and directing information to appropriate audience. Present authentication mechanisms only authenticate user once at the beginning of a communication session. The new wave of attacks that are used to steal information has made one-time authentication of users inadequate because the authenticated session can now be hijacked. Thus, it has become necessary for the communicating parties in a computer transaction session to reconfirm the other party on the other end periodically. Researchers have proposed different solutions to prevent or detect malicious taking over of a computer session. The solutions either work for particular types of attacks or only suitable for specific applications used to develop it. Others would fail in the face of spoofing attacks. This research proposed PERT for mitigating session hijacking and Cross-Site Request Forgery attacks. PERT ensure that a node is communicating only with a known system that it had previously successfully transacted with. The prototype was tested in NS-3 testbed. The tests were carried out to observe the proposed solution's performance against spoofing attacks and identity theft attacks. PERT performed satisfactorily better than two other solutions used to benchmark it as presented in the results section. It recorded 35% longer average execution time than the faster benchmark but 20.06% shorter average execution time than the slower benchmark. It prevented 97% and 95% of requests from an identity thief and a spoofing attacker respectively. The benchmark solutions recorded lower prevention efficiency.
{"title":"Past Event Recall Test for Mitigating Session Hijacking and Cross-Site Request Forgery","authors":"O. Salami, Abdulrazaq Muhammad Bashir, E. A. Adedokun, Yahaya Basira","doi":"10.1109/ict4da53266.2021.9672244","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672244","url":null,"abstract":"Authentication of user on a computer or network enable privacy protection and directing information to appropriate audience. Present authentication mechanisms only authenticate user once at the beginning of a communication session. The new wave of attacks that are used to steal information has made one-time authentication of users inadequate because the authenticated session can now be hijacked. Thus, it has become necessary for the communicating parties in a computer transaction session to reconfirm the other party on the other end periodically. Researchers have proposed different solutions to prevent or detect malicious taking over of a computer session. The solutions either work for particular types of attacks or only suitable for specific applications used to develop it. Others would fail in the face of spoofing attacks. This research proposed PERT for mitigating session hijacking and Cross-Site Request Forgery attacks. PERT ensure that a node is communicating only with a known system that it had previously successfully transacted with. The prototype was tested in NS-3 testbed. The tests were carried out to observe the proposed solution's performance against spoofing attacks and identity theft attacks. PERT performed satisfactorily better than two other solutions used to benchmark it as presented in the results section. It recorded 35% longer average execution time than the faster benchmark but 20.06% shorter average execution time than the slower benchmark. It prevented 97% and 95% of requests from an identity thief and a spoofing attacker respectively. The benchmark solutions recorded lower prevention efficiency.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"496 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116407808","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672224
Florian Schellroth, Jannik Lehner, A. Verl
With the increasing development of GPUs, the inference time of CNNs continues to decrease. This enables new AI applications in manufacturing that have a direct impact on the control of a process. For this, a GPU is integrated into a real-time system so that the CNN can be executed in real-time. However, it is not sufficient to consider the inference process only, but also to minimize the latency of the whole pipeline. For this purpose, execution strategies of the inference pipeline are presented and evaluated in this paper. The presented architectures are compared using criteria for latency, implementation effort, and exchangeability. The latencies are quantified with measurements on a demonstrator. As a result, the most synchronous architecture has the lowest latency but is not suitable for the use in a service-oriented architecture as targeted by the Industry 4.0. For this, another architecture is presented, providing a good balance between latency and service orientation.
{"title":"Latency optimized architectures for a real-time inference pipeline for control tasks","authors":"Florian Schellroth, Jannik Lehner, A. Verl","doi":"10.1109/ict4da53266.2021.9672224","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672224","url":null,"abstract":"With the increasing development of GPUs, the inference time of CNNs continues to decrease. This enables new AI applications in manufacturing that have a direct impact on the control of a process. For this, a GPU is integrated into a real-time system so that the CNN can be executed in real-time. However, it is not sufficient to consider the inference process only, but also to minimize the latency of the whole pipeline. For this purpose, execution strategies of the inference pipeline are presented and evaluated in this paper. The presented architectures are compared using criteria for latency, implementation effort, and exchangeability. The latencies are quantified with measurements on a demonstrator. As a result, the most synchronous architecture has the lowest latency but is not suitable for the use in a service-oriented architecture as targeted by the Industry 4.0. For this, another architecture is presented, providing a good balance between latency and service orientation.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131207854","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 : 2021-11-22DOI: 10.1109/ict4da53266.2021.9672245
Tegegn Kebebaw, E. Alemneh, M. Azage, Eyava Misgan, Dabere Nigatu, Enyew Abate
Globally, high number of mothers and infants die every year during childbirth. To reduce this problem WHO recommends use of partograph to monitor the progression of labor. However, the conventional paper-based partograph is usually improperly used or it is not used at all. Filling paper partograph and drawing graphs based on measured parameters takes time and it is tiresome and complex. Automating partograph enhances partograph utilization and reduces adverse maternal and fetal outcomes. In this paper, we present the development and usability evaluations made to an electronic partograph (e-partograph). The usability evaluation was done to identify usability problems on the e-partograph and take remedies before putting it in operation. Four usability experts have involved in evaluating the application in each of the three devices (smartphones, tablets, & desktops) used for testing the application. Most of the usability problems were detected by experts who had used small sized devices. In order to give more attentions on the most serious problems we had conducted severity analysis. The analysis shows that the majority of the usability problems (82.8%) that were detected by smartphone users are ranked minor problems. Because of the size of the screens, usability discomforts must have been categorized as usability problems.
{"title":"Development and Heuristic-based Usability Evaluation of an e-partograph","authors":"Tegegn Kebebaw, E. Alemneh, M. Azage, Eyava Misgan, Dabere Nigatu, Enyew Abate","doi":"10.1109/ict4da53266.2021.9672245","DOIUrl":"https://doi.org/10.1109/ict4da53266.2021.9672245","url":null,"abstract":"Globally, high number of mothers and infants die every year during childbirth. To reduce this problem WHO recommends use of partograph to monitor the progression of labor. However, the conventional paper-based partograph is usually improperly used or it is not used at all. Filling paper partograph and drawing graphs based on measured parameters takes time and it is tiresome and complex. Automating partograph enhances partograph utilization and reduces adverse maternal and fetal outcomes. In this paper, we present the development and usability evaluations made to an electronic partograph (e-partograph). The usability evaluation was done to identify usability problems on the e-partograph and take remedies before putting it in operation. Four usability experts have involved in evaluating the application in each of the three devices (smartphones, tablets, & desktops) used for testing the application. Most of the usability problems were detected by experts who had used small sized devices. In order to give more attentions on the most serious problems we had conducted severity analysis. The analysis shows that the majority of the usability problems (82.8%) that were detected by smartphone users are ranked minor problems. Because of the size of the screens, usability discomforts must have been categorized as usability problems.","PeriodicalId":371663,"journal":{"name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130336592","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：