The sports industry has seen a lucrative rise in stature and has now become an important contributor to the global economy. Huge amounts of finances and money are being invested in the sports industry and with that the amount of data generated by sports has multiplied exponentially. With the rise of data science, and the increase in sports data, sports analytics has become an interesting research direction. In this paper, we developed a mathematical model for rating each player, based on their position statistics and performance. These performance ratings are also beneficial to coaches and managers who look to improve player performances and justify player selections. Extensive experiments on a public hockey dataset of 2014 world cup Hockey shows the effectiveness of the proposed approach. We also applied the proposed model to 2018 world cup hockey dataset to rate each player. In addition, a visualization framework is developed to visualize each player's performance.
{"title":"An efficient rating system for players based on their position statistics","authors":"Maira Sami, Sehrish Taufiq, Karan Agarwal, Rizwan Qureshi","doi":"10.1109/ICOSST53930.2021.9683832","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683832","url":null,"abstract":"The sports industry has seen a lucrative rise in stature and has now become an important contributor to the global economy. Huge amounts of finances and money are being invested in the sports industry and with that the amount of data generated by sports has multiplied exponentially. With the rise of data science, and the increase in sports data, sports analytics has become an interesting research direction. In this paper, we developed a mathematical model for rating each player, based on their position statistics and performance. These performance ratings are also beneficial to coaches and managers who look to improve player performances and justify player selections. Extensive experiments on a public hockey dataset of 2014 world cup Hockey shows the effectiveness of the proposed approach. We also applied the proposed model to 2018 world cup hockey dataset to rate each player. In addition, a visualization framework is developed to visualize each player's performance.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"17 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123597194","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683962
Israr Ahmad, K. Yau
Trust investigation in 5G the next-generation wireless network, is still naive. The article investigates into a trust model based on reinforcement learning (RL) to select a legitimate (or trusted) forwarding entity (or node). RL can be embedded in an entity (that can be legitimate or malicious) to enable to learn a higly dynamic and heterogenous environments. The legitimate entity (e.g., a node) uses RL to select the best possible next hop forwarder (a relay) and to successfully transmit the desired packet towards the destination while the malicious entities exist in the network. The malicious entity can also use RL to launch an attack (i.e., intelligent attack) without being detected. Simulation results show that the legitimate entity can learn fast (i.e., converge fast) at a higher learning rate (i.e., $alpha=0.9$) and perform well in terms of trusted forwarder selection. Nevertheless, the malicious entity can also learn fast and launch successful attacks (i.e., affecting the throughput by dropping the packets) without being detected due to its fugitive nature.
{"title":"A Trust Model for Multi-Hop 5G Networks: A Reinforcement Learning Approach","authors":"Israr Ahmad, K. Yau","doi":"10.1109/ICOSST53930.2021.9683962","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683962","url":null,"abstract":"Trust investigation in 5G the next-generation wireless network, is still naive. The article investigates into a trust model based on reinforcement learning (RL) to select a legitimate (or trusted) forwarding entity (or node). RL can be embedded in an entity (that can be legitimate or malicious) to enable to learn a higly dynamic and heterogenous environments. The legitimate entity (e.g., a node) uses RL to select the best possible next hop forwarder (a relay) and to successfully transmit the desired packet towards the destination while the malicious entities exist in the network. The malicious entity can also use RL to launch an attack (i.e., intelligent attack) without being detected. Simulation results show that the legitimate entity can learn fast (i.e., converge fast) at a higher learning rate (i.e., $alpha=0.9$) and perform well in terms of trusted forwarder selection. Nevertheless, the malicious entity can also learn fast and launch successful attacks (i.e., affecting the throughput by dropping the packets) without being detected due to its fugitive nature.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134353397","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683961
Munib Ahmad, Z. Rana
Software process improvement (SPI) is typically one of the most significant areas considered by Software industry when boosting the whole efficiency of its business processes and practices. Implementing SPI helps achieve objectives such as speed growth, product quality or cost reduction and to identify shortfalls in the software development cycle and fix them in a better way. In the industry, different models for improving software processes are used including CMMI, PSP, SPICE, MSF, RUP, ISO etc. All these models consist of a very comprehensive set of practices and to follow all these practices is quite expensive for the companies. These models have significant advantages, but it is hard for small and medium businesses to use them because of their expense. However, in literature there are some lightweight practices for those software organizations that cannot afford the expensive ones. In this research, we performed a comparative study on customized software engineering process (CSEP) and lightweight practices (LWP) proposed in literature on industrial software projects. The objective is to study which of these practices are effective if performed by an organization. We also measure which of these practices give better defect rate, delivery, schedule deviation, and performance. The comparison on a software project shows that the lightweight practices have improved defect rate, delivery time, and productivity.
{"title":"Comparative Analysis of light weight practices for SPI in small and medium software organizations","authors":"Munib Ahmad, Z. Rana","doi":"10.1109/ICOSST53930.2021.9683961","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683961","url":null,"abstract":"Software process improvement (SPI) is typically one of the most significant areas considered by Software industry when boosting the whole efficiency of its business processes and practices. Implementing SPI helps achieve objectives such as speed growth, product quality or cost reduction and to identify shortfalls in the software development cycle and fix them in a better way. In the industry, different models for improving software processes are used including CMMI, PSP, SPICE, MSF, RUP, ISO etc. All these models consist of a very comprehensive set of practices and to follow all these practices is quite expensive for the companies. These models have significant advantages, but it is hard for small and medium businesses to use them because of their expense. However, in literature there are some lightweight practices for those software organizations that cannot afford the expensive ones. In this research, we performed a comparative study on customized software engineering process (CSEP) and lightweight practices (LWP) proposed in literature on industrial software projects. The objective is to study which of these practices are effective if performed by an organization. We also measure which of these practices give better defect rate, delivery, schedule deviation, and performance. The comparison on a software project shows that the lightweight practices have improved defect rate, delivery time, and productivity.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127811269","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683986
Ishrat Hameed, S. A. A. Naqvi
The number of internet users in Pakistan is sharply on the rise. This acceleration of digital adoption coupled with a general lack of awareness about cybersecurity in the Pakistani population has created fertile ground for cyber criminals and bad actors to exploit the digital medium thus harming both individuals and society in the process. This paper presents an overview of the state of cybercrime in Pakistan. We discuss the various types of cybercrime, the different groups of people falling victim to these crimes, the factors motivating cybercrime, the factors supporting cybercrime, and the measures necessary to reduce cybercrime activity. The insights presented have been drawn through a process of in-depth interviews with cybercrime experts, followed by a broad-based survey of individuals regarding their experiences with cybercrime.
{"title":"An Analysis of the factors affecting Cybercrime against individuals in Pakistan","authors":"Ishrat Hameed, S. A. A. Naqvi","doi":"10.1109/ICOSST53930.2021.9683986","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683986","url":null,"abstract":"The number of internet users in Pakistan is sharply on the rise. This acceleration of digital adoption coupled with a general lack of awareness about cybersecurity in the Pakistani population has created fertile ground for cyber criminals and bad actors to exploit the digital medium thus harming both individuals and society in the process. This paper presents an overview of the state of cybercrime in Pakistan. We discuss the various types of cybercrime, the different groups of people falling victim to these crimes, the factors motivating cybercrime, the factors supporting cybercrime, and the measures necessary to reduce cybercrime activity. The insights presented have been drawn through a process of in-depth interviews with cybercrime experts, followed by a broad-based survey of individuals regarding their experiences with cybercrime.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133721817","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683956
Shehla Inam, Faisal Amin, Muhammad Zia ur Rehman
Surface EMG is being used as a control source for myoelectric control of upper-limb prosthetics. There has been a concern whether there exists any difference in the EMG of males and females and the features that are proposed in research have been used generally for both males and females. This study aimed to evaluate any difference in EMG and compare the performance of different features for both male and female subjects. The EMG of 11 healthy males and females was recorded using BIOPAC by performing 11 basic hand movements with their dominant hand. The classification was performed using Artificial Neural Networks (ANN) and performing ANOVA tests for 13 basic features. Also, the graphical analysis of comparison of mean RMS values across each channel of each movement and the ANOVA tests for RMS values of males and females were performed. From classification results, it was found that there was no significant difference existed ($mathrm{p} > 0.05$) except for WL feature where classification accuracies of male subjects ($96.29pm 3.33$) were significantly higher ($mathrm{p} < 0.05$) than females subjects ($87.91pm 11.73$). The feature Mean Frequency achieved the highest classification accuracy for males and females ($97.63pm 1.76$ and $96.99 pm 1.57$) followed by AR as the second highest ($97.48pm 1.82$ and $96.96 pm 1.65$). Based on RMS of EMG signals, there was no significant difference found between the male and female subjects.
{"title":"Comparative Study of Flexor and Extensor Muscles EMG for Upper Limb Prosthesis","authors":"Shehla Inam, Faisal Amin, Muhammad Zia ur Rehman","doi":"10.1109/ICOSST53930.2021.9683956","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683956","url":null,"abstract":"Surface EMG is being used as a control source for myoelectric control of upper-limb prosthetics. There has been a concern whether there exists any difference in the EMG of males and females and the features that are proposed in research have been used generally for both males and females. This study aimed to evaluate any difference in EMG and compare the performance of different features for both male and female subjects. The EMG of 11 healthy males and females was recorded using BIOPAC by performing 11 basic hand movements with their dominant hand. The classification was performed using Artificial Neural Networks (ANN) and performing ANOVA tests for 13 basic features. Also, the graphical analysis of comparison of mean RMS values across each channel of each movement and the ANOVA tests for RMS values of males and females were performed. From classification results, it was found that there was no significant difference existed ($mathrm{p} > 0.05$) except for WL feature where classification accuracies of male subjects ($96.29pm 3.33$) were significantly higher ($mathrm{p} < 0.05$) than females subjects ($87.91pm 11.73$). The feature Mean Frequency achieved the highest classification accuracy for males and females ($97.63pm 1.76$ and $96.99 pm 1.57$) followed by AR as the second highest ($97.48pm 1.82$ and $96.96 pm 1.65$). Based on RMS of EMG signals, there was no significant difference found between the male and female subjects.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128170122","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683838
Qurat ul Ain, Iqra Duaa, Komal Haroon, Faisal Amin, Muhammad Zia ur Rehman
Brain tumors are one of the most rapidly spreading types of tumors known to humans. The worst and most dangerous type of tumor is a brain tumor. However, if diagnosed early, patients with brain tumors have a higher chance of survival acknowledgments to simple and inexpensive treatments. Expert radiologists, equipment, and biopsies are used in the traditional method of diagnosing a brain tumor. Machine learning has proved to deliver cutting-edge methods for early identification of brain tumors with better accuracies, avoiding costly diagnoses and unnecessary biopsies and assisting radiologists. Using a machine learning approach, this study proposes a technique for brain tumor classification and segmentation as HGG and LGG (High-Grade Glioma & Low-Grade Glioma). One of the most inflexible and innovative challenges confronting artificial intelligence approaches is medical diagnostics utilizing image processing and machine learning. The project involves the preprocessing, edge detection, segmentation, feature extraction, and classification of MRI brain images. The preprocessing is implemented by using median filter and canny edge detection is adapted in edge detection stage to inspect the best performing edge detector in terms of accuracy. Then, the MR image is segmented by K-means clustering technique. However, some of the important features are extracted including GLCM features for texture identification. Finally, in the classification phase, the Support Vector Machine (SVM) and k-nearest neighbors (KNN) classifiers are used. After using these classifiers, we distinguished the tumors as HGG or LGG. To determine whether an MRI image of the brain has a tumor and to classify as HGG or LGG, a machine learning methodology is applied. The aim is to develop a system with better tumor detection from MRI images to be used as a tool in real time by employing machine learning approach. The proposed method is validated using the MATLAB environment on the available BRATS 2019 dataset. Then, to illustrate the performance of SVM and KNN classifiers, a confusion matrix is frequently used. The SVM classifier achieves a maximum accuracy of 92%.
{"title":"MRI Based Glioma Detection and Classification into Low-grade and High-Grade Gliomas","authors":"Qurat ul Ain, Iqra Duaa, Komal Haroon, Faisal Amin, Muhammad Zia ur Rehman","doi":"10.1109/ICOSST53930.2021.9683838","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683838","url":null,"abstract":"Brain tumors are one of the most rapidly spreading types of tumors known to humans. The worst and most dangerous type of tumor is a brain tumor. However, if diagnosed early, patients with brain tumors have a higher chance of survival acknowledgments to simple and inexpensive treatments. Expert radiologists, equipment, and biopsies are used in the traditional method of diagnosing a brain tumor. Machine learning has proved to deliver cutting-edge methods for early identification of brain tumors with better accuracies, avoiding costly diagnoses and unnecessary biopsies and assisting radiologists. Using a machine learning approach, this study proposes a technique for brain tumor classification and segmentation as HGG and LGG (High-Grade Glioma & Low-Grade Glioma). One of the most inflexible and innovative challenges confronting artificial intelligence approaches is medical diagnostics utilizing image processing and machine learning. The project involves the preprocessing, edge detection, segmentation, feature extraction, and classification of MRI brain images. The preprocessing is implemented by using median filter and canny edge detection is adapted in edge detection stage to inspect the best performing edge detector in terms of accuracy. Then, the MR image is segmented by K-means clustering technique. However, some of the important features are extracted including GLCM features for texture identification. Finally, in the classification phase, the Support Vector Machine (SVM) and k-nearest neighbors (KNN) classifiers are used. After using these classifiers, we distinguished the tumors as HGG or LGG. To determine whether an MRI image of the brain has a tumor and to classify as HGG or LGG, a machine learning methodology is applied. The aim is to develop a system with better tumor detection from MRI images to be used as a tool in real time by employing machine learning approach. The proposed method is validated using the MATLAB environment on the available BRATS 2019 dataset. Then, to illustrate the performance of SVM and KNN classifiers, a confusion matrix is frequently used. The SVM classifier achieves a maximum accuracy of 92%.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133673746","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683975
Bilal Ahmad, Faiq Ahmad Khan, Kaleem Nawaz Khan, Muhammad Salman Khan
Heart diseases are serious and must be detected early using an auscultation examination. To explore and diagnose heart problems, several signal processing and machine learning approaches are used. From a Phonocardiogram (PCG) signal, the heart sound (HS) can be categorized into normal and abnormal. This paper presents an improvedcomputer-aidedtechniquefor classification of HS using long short-term memory (LSTM)deployed withdifferent time and frequency domain features, i.e., discrete wavelet transform (DWT) and Mel-frequency cepstral coefficients (MFCCs). The overall score, accuracy, sensitivity, and specificity of the LSTM classifier are calculated for the performance evaluation. With the proposed set of experimentsthe classification algorithm achieved a final score of 90.04% (Accuracy 90%, Sensitivity 92.30%, and Specificity 87.69%).
{"title":"Automatic Classification of Heart Sounds Using Long Short-Term Memory","authors":"Bilal Ahmad, Faiq Ahmad Khan, Kaleem Nawaz Khan, Muhammad Salman Khan","doi":"10.1109/ICOSST53930.2021.9683975","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683975","url":null,"abstract":"Heart diseases are serious and must be detected early using an auscultation examination. To explore and diagnose heart problems, several signal processing and machine learning approaches are used. From a Phonocardiogram (PCG) signal, the heart sound (HS) can be categorized into normal and abnormal. This paper presents an improvedcomputer-aidedtechniquefor classification of HS using long short-term memory (LSTM)deployed withdifferent time and frequency domain features, i.e., discrete wavelet transform (DWT) and Mel-frequency cepstral coefficients (MFCCs). The overall score, accuracy, sensitivity, and specificity of the LSTM classifier are calculated for the performance evaluation. With the proposed set of experimentsthe classification algorithm achieved a final score of 90.04% (Accuracy 90%, Sensitivity 92.30%, and Specificity 87.69%).","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125443228","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683873
Shujah Ur Rehman, Bilal Tahir, M. Mehmood
The plethora of online content has paved the way for the development of sophisticated and advanced Natural Language Processing (NLP) and Information Retrieval (IR) tools. However, such tools are only available for English and other high-resource languages while being unavailable for low-resource languages such as Urdu. In this regard, generally, cross-lingual transfer learning techniques are adopted to utilize tools developed for the English language for low resource languages. In this paper, we evaluate the performance of three word-level transfer learning methods: OrthoMap, VecMap-supervised, and VecMap unsupervised for Urdu text. We further test these transfer learning methods for three tasks: propaganda identification, topic classification, and sentiment analysis. For this purpose, we augment an English-Urdu word dictionary and three datasets of Ur-En Propaganda, Ur-En News Dataset, and Ur-En Sentiment Corpus. Our analysis shows that the transfer learning methods optimize better for the short-text of Ur-En Sentiment Corpus with a precision of 40.1%. While for propaganda detection, the classifier attained an accuracy of 83% after transfer learning which is competitive with the 87% accuracy achieved after training the model on Urdu text data. We believe that this work will be beneficial for NLP, IR, and computational linguistic researchers working on Urdu language content.
{"title":"Investigating Cross-Lingual Transfer Learning Techniques for Urdu Text Using Word Embeddings","authors":"Shujah Ur Rehman, Bilal Tahir, M. Mehmood","doi":"10.1109/ICOSST53930.2021.9683873","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683873","url":null,"abstract":"The plethora of online content has paved the way for the development of sophisticated and advanced Natural Language Processing (NLP) and Information Retrieval (IR) tools. However, such tools are only available for English and other high-resource languages while being unavailable for low-resource languages such as Urdu. In this regard, generally, cross-lingual transfer learning techniques are adopted to utilize tools developed for the English language for low resource languages. In this paper, we evaluate the performance of three word-level transfer learning methods: OrthoMap, VecMap-supervised, and VecMap unsupervised for Urdu text. We further test these transfer learning methods for three tasks: propaganda identification, topic classification, and sentiment analysis. For this purpose, we augment an English-Urdu word dictionary and three datasets of Ur-En Propaganda, Ur-En News Dataset, and Ur-En Sentiment Corpus. Our analysis shows that the transfer learning methods optimize better for the short-text of Ur-En Sentiment Corpus with a precision of 40.1%. While for propaganda detection, the classifier attained an accuracy of 83% after transfer learning which is competitive with the 87% accuracy achieved after training the model on Urdu text data. We believe that this work will be beneficial for NLP, IR, and computational linguistic researchers working on Urdu language content.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124568208","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683948
Sonain Jamil, Muhammad Sohail Abbas, Muhammad Ahsan, Muhammad Tauseef Ejaz
Novel coronavirus (COVID-19) is a hazardous virus. Initially, detected in China and spread worldwide, causing several deaths. Over time, there have been several variants of COVID-19, we have grouped all of them into two major categories. The categories are known to be variants of concern and variants of interest. Talking about the first of these two, it is very dangerous, and we need a system that can not only detect the disease but also classify it without physical interaction with a patient suffering from COVID-19. This paper proposes a Bag-of-Features (BoF) based deep learning framework that can detect as well as classify COVID-19 and all of its variants as well. Initially, the spatial features are extracted with deep convolutional models, while hand-crafted features have been extracted from several hand-crafted descriptors. Both spatial and hand-crafted features are combined to make a feature vector. This feature vector feeds the classifier to classify different variants in respective categories. The experimental results show that the proposed methodology outperforms all the existing methods.
{"title":"A Bag-of-Features (BoF) Based Novel Framework for the Detection of COVID-19","authors":"Sonain Jamil, Muhammad Sohail Abbas, Muhammad Ahsan, Muhammad Tauseef Ejaz","doi":"10.1109/ICOSST53930.2021.9683948","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683948","url":null,"abstract":"Novel coronavirus (COVID-19) is a hazardous virus. Initially, detected in China and spread worldwide, causing several deaths. Over time, there have been several variants of COVID-19, we have grouped all of them into two major categories. The categories are known to be variants of concern and variants of interest. Talking about the first of these two, it is very dangerous, and we need a system that can not only detect the disease but also classify it without physical interaction with a patient suffering from COVID-19. This paper proposes a Bag-of-Features (BoF) based deep learning framework that can detect as well as classify COVID-19 and all of its variants as well. Initially, the spatial features are extracted with deep convolutional models, while hand-crafted features have been extracted from several hand-crafted descriptors. Both spatial and hand-crafted features are combined to make a feature vector. This feature vector feeds the classifier to classify different variants in respective categories. The experimental results show that the proposed methodology outperforms all the existing methods.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123415833","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 : 2021-12-15DOI: 10.1109/ICOSST53930.2021.9683840
Rehab Arif, Maryam Bashir
With the arrival of the World Wide Web, the tremendous increase in textual data has encouraged the development of such platforms where a user can answer a question or ask a question in natural language. Community Question Answering (CQA) based websites play a significant role in the rise of the Social Web. These systems are designed to answer complex user queries effectively. In this study, a system has been proposed to solve the problem of re-ranking relevant answers to community questions by considering the syntactic structures between them using Tree Kernels i.e. Partial Tree Kernels (PTK), SubTree Kernels (STK), and SubSet Tree Kernels (SSTK). For this purpose, various experiments were conducted to achieve maximum accuracy and mean average precision score. The results were compared with an already existing state-of-art system and with a system using standard information retrieval similarity measures including cosine similarity, BM25, Levenshtein distance, and Jaccard coefficient. Results show the superior performance of tree kernels over compared baseline similarity measures.
{"title":"Question Answer Re-Ranking using Syntactic Relationship","authors":"Rehab Arif, Maryam Bashir","doi":"10.1109/ICOSST53930.2021.9683840","DOIUrl":"https://doi.org/10.1109/ICOSST53930.2021.9683840","url":null,"abstract":"With the arrival of the World Wide Web, the tremendous increase in textual data has encouraged the development of such platforms where a user can answer a question or ask a question in natural language. Community Question Answering (CQA) based websites play a significant role in the rise of the Social Web. These systems are designed to answer complex user queries effectively. In this study, a system has been proposed to solve the problem of re-ranking relevant answers to community questions by considering the syntactic structures between them using Tree Kernels i.e. Partial Tree Kernels (PTK), SubTree Kernels (STK), and SubSet Tree Kernels (SSTK). For this purpose, various experiments were conducted to achieve maximum accuracy and mean average precision score. The results were compared with an already existing state-of-art system and with a system using standard information retrieval similarity measures including cosine similarity, BM25, Levenshtein distance, and Jaccard coefficient. Results show the superior performance of tree kernels over compared baseline similarity measures.","PeriodicalId":325357,"journal":{"name":"2021 15th International Conference on Open Source Systems and Technologies (ICOSST)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115374925","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：