Pub Date : 2022-10-12DOI: 10.1109/AICT55583.2022.10013581
R. Alguliyev, L. Sukhostat, Aykhan Mammadov
Various problems inevitably arise in cyber-physical systems, such as equipment failure, performance degradation, etc. Untimely detection of an abnormal state caused by a cyber-attack or a failure to operate devices in a cyber-physical system can lead to severe losses for the entire system. This paper proposes a method based on a deep bidirectional gated recurrent unit and variational autoencoder model to detect anomalies in a cyber-physical system. Experiments on a real dataset have shown the effectiveness of the proposed method in detecting anomalies in a cyber-physical system. Comparison with known methods showed the most accurate results according to the precision, recall, and F-measure metrics and amounted to 99.87%, 77.39%, and 87.20%, respectively.
{"title":"Anomaly Detection in Cyber-Physical Systems based on BiGRU-VAE","authors":"R. Alguliyev, L. Sukhostat, Aykhan Mammadov","doi":"10.1109/AICT55583.2022.10013581","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013581","url":null,"abstract":"Various problems inevitably arise in cyber-physical systems, such as equipment failure, performance degradation, etc. Untimely detection of an abnormal state caused by a cyber-attack or a failure to operate devices in a cyber-physical system can lead to severe losses for the entire system. This paper proposes a method based on a deep bidirectional gated recurrent unit and variational autoencoder model to detect anomalies in a cyber-physical system. Experiments on a real dataset have shown the effectiveness of the proposed method in detecting anomalies in a cyber-physical system. Comparison with known methods showed the most accurate results according to the precision, recall, and F-measure metrics and amounted to 99.87%, 77.39%, and 87.20%, respectively.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115144588","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013532
Grady McPeak
One of the great advantages of machine learning as a whole is its ability to assist a human with digesting extremely large sets of data, and helping them to learn useful information that otherwise would have been significantly more difficult to piece together, and improvements to ML models often can result in improvements in this ability. To that end, this paper presents an evaluation of the relative performances of differing versions of Bidirectional Encoder Representations from Transformers (BERT) on the task of classifying a dataset of titles from posts scraped from two UNIX-related Q&A forum websites into classes based on what command each post is most likely about. The differing versions of BERT were each first fine-tuned on a different dataset from the post titles in order to try to improve the accuracy and precision of the model’s classification abilities through the introduction of relevant yet longer, more detailed, and more information-rich information. Additionally, the performances of these models are compared to that of the Heterogeneous Graph Attention Network (HGAT). The novel contributions of this paper are a real-world-use comparison between HGAT and BERT, the production of a novel dataset, and the presentation of supporting evidence for the value of relevance and length of text in pretraining for short-text classification.
{"title":"Improving BERT Classification Performance on Short Queries About UNIX Commands Using an Additional Round of Fine-Tuning on Related Data","authors":"Grady McPeak","doi":"10.1109/AICT55583.2022.10013532","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013532","url":null,"abstract":"One of the great advantages of machine learning as a whole is its ability to assist a human with digesting extremely large sets of data, and helping them to learn useful information that otherwise would have been significantly more difficult to piece together, and improvements to ML models often can result in improvements in this ability. To that end, this paper presents an evaluation of the relative performances of differing versions of Bidirectional Encoder Representations from Transformers (BERT) on the task of classifying a dataset of titles from posts scraped from two UNIX-related Q&A forum websites into classes based on what command each post is most likely about. The differing versions of BERT were each first fine-tuned on a different dataset from the post titles in order to try to improve the accuracy and precision of the model’s classification abilities through the introduction of relevant yet longer, more detailed, and more information-rich information. Additionally, the performances of these models are compared to that of the Heterogeneous Graph Attention Network (HGAT). The novel contributions of this paper are a real-world-use comparison between HGAT and BERT, the production of a novel dataset, and the presentation of supporting evidence for the value of relevance and length of text in pretraining for short-text classification.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127522217","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013571
Pedro A Segura-Saldaña, Frank Britto-Bisso, D. Pacheco, M. Álvarez-Vargas, A. L. Manrique, Gisella M. Bejarano Nicho
Clinical decision making in the emergency room needs to be fast and accurate, especially for myocardial infarction (MI) cases. The best way to address data-based decisions is through artificial intelligence techniques (AI), which haven’t been systematize for MI detection. Thereby, we performed a systematic review (PROSPERO: CRD42021229084). The literature search from Pubmed, Web of Science, Scopus, IEEE Xplore and Embase resulted in n = 48 included articles. 71% of those articles implemented deep-learning models, while the other 29% developed machine-learning models, from which Convolutional Neural Networks and Support Vector Machines were the most common architectures. Data pre-processing methods, ECG-derived features with their corresponding feature extraction techniques, dimensionality reduction and redundancy evaluation algorithms and classifier are discussed in the present work. Furthermore, public and private datasets are analyzed, and class balance is addressed. To the extent of our knowledge, the present work is one of the most comprehensive reviews that addressed systematically the characteristics of artificial intelligence algorithms for the detection of MI based on ECG information.
急诊室的临床决策需要快速和准确，特别是对于心肌梗死(MI)病例。解决基于数据的决策的最佳方法是通过人工智能技术(AI)，这些技术尚未系统化用于MI检测。因此，我们进行了系统评价(PROSPERO: CRD42021229084)。从Pubmed、Web of Science、Scopus、IEEE Xplore和Embase进行文献检索，得到n = 48篇纳入文章。其中71%的文章实现了深度学习模型，而另外29%的文章开发了机器学习模型，其中卷积神经网络和支持向量机是最常见的架构。本文讨论了数据预处理方法、脑电图衍生特征及其相应的特征提取技术、降维和冗余评估算法以及分类器。此外，还分析了公共和私有数据集，并解决了类平衡问题。就我们所知，目前的工作是最全面的综述之一，系统地解决了基于ECG信息检测心肌梗死的人工智能算法的特点。
{"title":"Automated detection of myocardial infarction using ECG-based artificial intelligence models: a systematic review","authors":"Pedro A Segura-Saldaña, Frank Britto-Bisso, D. Pacheco, M. Álvarez-Vargas, A. L. Manrique, Gisella M. Bejarano Nicho","doi":"10.1109/AICT55583.2022.10013571","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013571","url":null,"abstract":"Clinical decision making in the emergency room needs to be fast and accurate, especially for myocardial infarction (MI) cases. The best way to address data-based decisions is through artificial intelligence techniques (AI), which haven’t been systematize for MI detection. Thereby, we performed a systematic review (PROSPERO: CRD42021229084). The literature search from Pubmed, Web of Science, Scopus, IEEE Xplore and Embase resulted in n = 48 included articles. 71% of those articles implemented deep-learning models, while the other 29% developed machine-learning models, from which Convolutional Neural Networks and Support Vector Machines were the most common architectures. Data pre-processing methods, ECG-derived features with their corresponding feature extraction techniques, dimensionality reduction and redundancy evaluation algorithms and classifier are discussed in the present work. Furthermore, public and private datasets are analyzed, and class balance is addressed. To the extent of our knowledge, the present work is one of the most comprehensive reviews that addressed systematically the characteristics of artificial intelligence algorithms for the detection of MI based on ECG information.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115041856","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013576
L. Lyadova, N. Suvorov, V. Zayakin, E. Zamyatina
The development of complex software systems is impossible without using modern modeling tools. At the design process, various models are developed: when solving each task, the attributes of processes and systems, which are significant for solving this task, are to be presented in the model. Developing analytical systems for data-intensive areas has specifics, which determine new requirements for the system functionality and architecture (interoperability, adaptability, etc.). These requirements can be implemented in the system based on a combination of two approaches: knowledge-driven development and model-driven development. This article presents an approach to creating a knowledge-driven analytical platforms, which integrate language toolkits allowing to create "on the fly" new domain-specific languages (DSLs). DSLs provide "user interfaces" which are customizable to the specifics of the tasks, solved by users with modeling tools, and to the corresponding users' domains. The architecture of the analytical platform, the graph model, and the metalanguage which are the basis of the language toolkits implementation are described in the paper. The multifaceted ontology, which is the core of the analytical platform, is presented too.
{"title":"An Ontological Approach to the Development of Analytical Platform Language Toolkits","authors":"L. Lyadova, N. Suvorov, V. Zayakin, E. Zamyatina","doi":"10.1109/AICT55583.2022.10013576","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013576","url":null,"abstract":"The development of complex software systems is impossible without using modern modeling tools. At the design process, various models are developed: when solving each task, the attributes of processes and systems, which are significant for solving this task, are to be presented in the model. Developing analytical systems for data-intensive areas has specifics, which determine new requirements for the system functionality and architecture (interoperability, adaptability, etc.). These requirements can be implemented in the system based on a combination of two approaches: knowledge-driven development and model-driven development. This article presents an approach to creating a knowledge-driven analytical platforms, which integrate language toolkits allowing to create \"on the fly\" new domain-specific languages (DSLs). DSLs provide \"user interfaces\" which are customizable to the specifics of the tasks, solved by users with modeling tools, and to the corresponding users' domains. The architecture of the analytical platform, the graph model, and the metalanguage which are the basis of the language toolkits implementation are described in the paper. The multifaceted ontology, which is the core of the analytical platform, is presented too.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115093246","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013501
Mohammad Jaber Hossain, Juan Luis Nieves
Medical image analysis using deep learning techniques found good attention to diagnose critical diseases within a shorter time and recommendable performance in the identification of disease conditions. Early detection of this disease has a way of doing the treatment effectively if it is possible to identify it before the symptoms appear. In this study, different methods are being proposed with their performance analysis using deep neural networks to diagnose the different stages of Alzheimer’s disease. The dataset used in this study was collected from the kaggle repository and consists of 3 different classes of Alzheimer’s disease which include Very Mild Demented, Mild Demented and Non Demented. In this study, VGG19 and ResNet50 pre-trained models with fine-tuning were used to classify different stages of the disease, alongside other two deep neural networks used where these VGG19 and ResNet50 pre-trained models were used as a feature extractor. Finally, an AlzheimerNet proposed, which outperformed previously mentioned methods that achieved 96.41% accuracy, 97% precision, 96% recall and F1- score. The current findings of the study indicate deep learning-based method achieved significant improvement in classifying Alzheimer’s disease in its early stage.
{"title":"Performance analysis of transfer learning based deep neural networks in Alzheimer classification","authors":"Mohammad Jaber Hossain, Juan Luis Nieves","doi":"10.1109/AICT55583.2022.10013501","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013501","url":null,"abstract":"Medical image analysis using deep learning techniques found good attention to diagnose critical diseases within a shorter time and recommendable performance in the identification of disease conditions. Early detection of this disease has a way of doing the treatment effectively if it is possible to identify it before the symptoms appear. In this study, different methods are being proposed with their performance analysis using deep neural networks to diagnose the different stages of Alzheimer’s disease. The dataset used in this study was collected from the kaggle repository and consists of 3 different classes of Alzheimer’s disease which include Very Mild Demented, Mild Demented and Non Demented. In this study, VGG19 and ResNet50 pre-trained models with fine-tuning were used to classify different stages of the disease, alongside other two deep neural networks used where these VGG19 and ResNet50 pre-trained models were used as a feature extractor. Finally, an AlzheimerNet proposed, which outperformed previously mentioned methods that achieved 96.41% accuracy, 97% precision, 96% recall and F1- score. The current findings of the study indicate deep learning-based method achieved significant improvement in classifying Alzheimer’s disease in its early stage.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129476231","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013597
Mai Abusair, Rania Dameh, Ruba Egbaria, Salsabeel Alzaqa
In many countries people target different places to open a business and succeed in it. They may choose an unsuccessful business or the location does not need the type of this business. In this paper, we aim to improve the opportunity of choosing a correct business and location. We suggest an approach based on many principles of machine learning. The approach uses a prediction model based on analysing data about zones (areas) and their commercial services. The zones are classified using K-Means clustering method that depends on the number of same businesses and their costs averages in an area. To show the novelty of our work, we developed a system that implements the approach principles for several zones in Nablus city. We evaluate the work by running several test cases to show the system ability in recommending kinds of businesses.
{"title":"A Business Recommender System Based on Zones and Commercial Data","authors":"Mai Abusair, Rania Dameh, Ruba Egbaria, Salsabeel Alzaqa","doi":"10.1109/AICT55583.2022.10013597","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013597","url":null,"abstract":"In many countries people target different places to open a business and succeed in it. They may choose an unsuccessful business or the location does not need the type of this business. In this paper, we aim to improve the opportunity of choosing a correct business and location. We suggest an approach based on many principles of machine learning. The approach uses a prediction model based on analysing data about zones (areas) and their commercial services. The zones are classified using K-Means clustering method that depends on the number of same businesses and their costs averages in an area. To show the novelty of our work, we developed a system that implements the approach principles for several zones in Nablus city. We evaluate the work by running several test cases to show the system ability in recommending kinds of businesses.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122228305","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013650
Reza Biazaran, H. J. Helgert
Soft decision decoders applicable to low density parity check codes such as sum product algorithms provide excellent error performance, however, it comes at the expense of computational complexity. Additionally, many iterations may be required of these decoders to achieve desired error performance. The processing delay associated with too many iterations may be a drawback for cases where low latency is a critical requirement. Conversely, performance of hard decision decoders such as bit flipping decoder and its variants, while improved, generally are not on par with that of soft decision decoders. Such decoders also require many iterations to achieve a given error performance. We have proposed a two-stage hybrid decoder with a simplified sum product algorithm (SPA) in the first stage, and an improved noisy gradient decent bit flipping decoder in the second stage. We have shown that our proposed hybrid decoder outperforms the legacy individual decoders, studied in this paper, from error performance point of view as well as required number of iterations that will reduce the overall network latency.
{"title":"An Improved Hybrid LDPC Decoder over Rayleigh Fading Channel","authors":"Reza Biazaran, H. J. Helgert","doi":"10.1109/AICT55583.2022.10013650","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013650","url":null,"abstract":"Soft decision decoders applicable to low density parity check codes such as sum product algorithms provide excellent error performance, however, it comes at the expense of computational complexity. Additionally, many iterations may be required of these decoders to achieve desired error performance. The processing delay associated with too many iterations may be a drawback for cases where low latency is a critical requirement. Conversely, performance of hard decision decoders such as bit flipping decoder and its variants, while improved, generally are not on par with that of soft decision decoders. Such decoders also require many iterations to achieve a given error performance. We have proposed a two-stage hybrid decoder with a simplified sum product algorithm (SPA) in the first stage, and an improved noisy gradient decent bit flipping decoder in the second stage. We have shown that our proposed hybrid decoder outperforms the legacy individual decoders, studied in this paper, from error performance point of view as well as required number of iterations that will reduce the overall network latency.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133368907","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013562
Lifang Fu, Shuai Liu
There are two types of sentiment analysis about Chinese sentences: explicit sentiment analysis and implicit sentiment analysis. Implicit sentiment, unlike explicit sentiment, lacks a well-defined sentiment vocabulary. Currently, the majority of relevant research has focused on extracting implicit emotion via word analysis, ignoring the role of syntactic structures and relationships between words in the analysis of implicit emotions in Chinese. In this paper, we use a graph convolutional neural network (GCN) to analyze the syntactic structure of implicit sentiment texts, then combine it with a Bidirectional Encoder Representations from Transformers (BERT) to extract contextual information to create the BSGCN, a multi-classification Chinese implicit sentiment analysis model, that can classify implicit sentiment Chinese sentences into five types: happiness, sadness, disgust, surprise, and neutral. In the experiment based on the dataset SMP-ECISA, the accuracy of the Chinese implicit sentiment analysis model proposed in this paper was 82.1%, which is a significant improvement over existing models.
汉语句子的情感分析有两种类型:显性情感分析和隐性情感分析。内隐情感与外显情感不同，缺乏明确的情感词汇。目前，相关研究大多侧重于通过词语分析提取内隐情绪，忽视了句法结构和词间关系在汉语内隐情绪分析中的作用。本文利用图卷积神经网络(GCN)对隐式情感文本的句法结构进行分析，并结合BERT (Bidirectional Encoder Representations from Transformers)提取语境信息，建立了多分类汉语隐式情感分析模型BSGCN，将隐式情感汉语句子分为快乐、悲伤、厌恶、惊讶和中性五种类型。在基于SMP-ECISA数据集的实验中，本文提出的汉语隐式情感分析模型的准确率为82.1%，比现有模型有了显著提高。
{"title":"A Syntax-based BSGCN Model for Chinese Implicit Sentiment Analysis with Multi-classification","authors":"Lifang Fu, Shuai Liu","doi":"10.1109/AICT55583.2022.10013562","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013562","url":null,"abstract":"There are two types of sentiment analysis about Chinese sentences: explicit sentiment analysis and implicit sentiment analysis. Implicit sentiment, unlike explicit sentiment, lacks a well-defined sentiment vocabulary. Currently, the majority of relevant research has focused on extracting implicit emotion via word analysis, ignoring the role of syntactic structures and relationships between words in the analysis of implicit emotions in Chinese. In this paper, we use a graph convolutional neural network (GCN) to analyze the syntactic structure of implicit sentiment texts, then combine it with a Bidirectional Encoder Representations from Transformers (BERT) to extract contextual information to create the BSGCN, a multi-classification Chinese implicit sentiment analysis model, that can classify implicit sentiment Chinese sentences into five types: happiness, sadness, disgust, surprise, and neutral. In the experiment based on the dataset SMP-ECISA, the accuracy of the Chinese implicit sentiment analysis model proposed in this paper was 82.1%, which is a significant improvement over existing models.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131660670","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013534
Syed Hussain Ali Kazmi, Faizan Qamar, Rosilah Hassan, K. Nisar
Global interest in drones is prone to surface challenges related to collision avoidance in dense constellation. Existing collision avoidance mechanism, known as Automatic Dependent Surveillance-Broadcast (ADS-B), contains serious limitations of interference effects due to broadcasting. Therefore, we propose a novel Discrete Sequence Spread Spectrum (DSSS) enabled Minimum Shift Keying (MSK) modulation for Three Dimension (3D) position sharing in collision avoidance mechanism. Our proposed scheme avoids extra processing through physical layer addressing and provides convergence to further reduced broadcast rate. We analyzed the performance of the proposed mechanism in the spectrum completely covered with Gaussian noise. The MATLAB based analysis results indicate the proposed scheme as a potential solution to address the challenges faced in drone to drone communication for collision avoidance in dense swarms of drones or Unmanned Aerial Vehicles (UAV). Moreover, the proposed scheme outperforms the traditional demodulation approach compare to direct correlation without demodulation. Further, we discussed possible future research directions in subject solution.
{"title":"Interference Resistant Position Awareness for Collision Avoidance in Dense Drones Swarming","authors":"Syed Hussain Ali Kazmi, Faizan Qamar, Rosilah Hassan, K. Nisar","doi":"10.1109/AICT55583.2022.10013534","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013534","url":null,"abstract":"Global interest in drones is prone to surface challenges related to collision avoidance in dense constellation. Existing collision avoidance mechanism, known as Automatic Dependent Surveillance-Broadcast (ADS-B), contains serious limitations of interference effects due to broadcasting. Therefore, we propose a novel Discrete Sequence Spread Spectrum (DSSS) enabled Minimum Shift Keying (MSK) modulation for Three Dimension (3D) position sharing in collision avoidance mechanism. Our proposed scheme avoids extra processing through physical layer addressing and provides convergence to further reduced broadcast rate. We analyzed the performance of the proposed mechanism in the spectrum completely covered with Gaussian noise. The MATLAB based analysis results indicate the proposed scheme as a potential solution to address the challenges faced in drone to drone communication for collision avoidance in dense swarms of drones or Unmanned Aerial Vehicles (UAV). Moreover, the proposed scheme outperforms the traditional demodulation approach compare to direct correlation without demodulation. Further, we discussed possible future research directions in subject solution.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115344942","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 : 2022-10-12DOI: 10.1109/AICT55583.2022.10013605
M. Mammadova, A. Ahmadova
This article analyzes the essence and goals of e-health and the problems hindering its development and highlights its structural components. It explores the integration of Industry 4.0 technologies into health and its effects, and reviews the possibilities opened up by Health 4.0. The integration issues of health information systems and generated data on the management levels of healthcare are studied and a conceptual model of a unified digital medical information space in the Republic of Azerbaijan is proposed. The issues of data sharing and interoperability of medical information systems in a unified medical space are investigated.
{"title":"Formation of Unified Digital Health Information Space in Healthcare 4.0 Environment and interoperability issues","authors":"M. Mammadova, A. Ahmadova","doi":"10.1109/AICT55583.2022.10013605","DOIUrl":"https://doi.org/10.1109/AICT55583.2022.10013605","url":null,"abstract":"This article analyzes the essence and goals of e-health and the problems hindering its development and highlights its structural components. It explores the integration of Industry 4.0 technologies into health and its effects, and reviews the possibilities opened up by Health 4.0. The integration issues of health information systems and generated data on the management levels of healthcare are studied and a conceptual model of a unified digital medical information space in the Republic of Azerbaijan is proposed. The issues of data sharing and interoperability of medical information systems in a unified medical space are investigated.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117107055","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：