Pub Date : 2020-10-24DOI: 10.1109/NILES50944.2020.9257975
Abeer Youssef, M. Elattar, S. El-Beltagy
Named Entity Recognition (NER) is an important task in many natural language processing applications. There are several studies that have focused on NER for the English language. However, there are some limitations when applying the current methodologies directly on the Arabic language text. Recent studies have shown the effectiveness of pooled contextual embedding representations and significant improvements in English NER tasks. This work investigates the performance of pooled contextual embeddings and bidirectional encoder representations from Transformers (BERT) model when used for NER on the Arabic language while addressing Arabic specific issues. The proposed method is an end-to-end deep learning model that utilizes a combination of pre-trained word embeddings, pooled contextual embeddings, and BERT model. Embeddings are then fed into bidirectional long-short term memory networks with a conditional random field. Different types of classical and contextual embeddings were experimented to pool for the best model. The proposed method achieves an F1 score of 77.62% on the AQMAR dataset, outperforming all previously published results of deep learning, and non-deep learning models on the same dataset. The presented results also surpass those of the wining system for the same task on the same data in the Topcoder website competition.
{"title":"A Multi-Embeddings Approach Coupled with Deep Learning for Arabic Named Entity Recognition","authors":"Abeer Youssef, M. Elattar, S. El-Beltagy","doi":"10.1109/NILES50944.2020.9257975","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257975","url":null,"abstract":"Named Entity Recognition (NER) is an important task in many natural language processing applications. There are several studies that have focused on NER for the English language. However, there are some limitations when applying the current methodologies directly on the Arabic language text. Recent studies have shown the effectiveness of pooled contextual embedding representations and significant improvements in English NER tasks. This work investigates the performance of pooled contextual embeddings and bidirectional encoder representations from Transformers (BERT) model when used for NER on the Arabic language while addressing Arabic specific issues. The proposed method is an end-to-end deep learning model that utilizes a combination of pre-trained word embeddings, pooled contextual embeddings, and BERT model. Embeddings are then fed into bidirectional long-short term memory networks with a conditional random field. Different types of classical and contextual embeddings were experimented to pool for the best model. The proposed method achieves an F1 score of 77.62% on the AQMAR dataset, outperforming all previously published results of deep learning, and non-deep learning models on the same dataset. The presented results also surpass those of the wining system for the same task on the same data in the Topcoder website competition.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126722217","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257903
Asmaa Elhadidy, Mohamed Afifi, Mohammed Hassoubah, Yara Ali, M. Elhelw
One of the key challenges in applying deep learning to solve real-life problems is the lack of large annotated datasets. Furthermore, for a deep learning model to perform well on the test set, all samples in the training and test sets should be independent and identically distributed (i.i.d.), which means that test samples should be similar to the samples that were used to train the model. In many cases, however, the underlying training and test set distributions are different. In such cases, it is common to adapt the test samples by transforming them to their equivalent counterparts in the domain of the training data before being processed by the deep learning model. In this paper, we perform domain adaptation of low-resolution 8, 16 and 32 channels LiDAR 3D point clouds projected on 2D spherical images in order to improve the quality of semantic segmentation tasks. To achieve this, the low-resolution 3D point clouds are transformed using an end-to-end supervised learning approach to spherical images that are very similar to those obtained by projecting high-resolution 64 channels LiDAR point clouds, without changing the underlying structure of the scene. The proposed framework is evaluated by training a semantic segmentation model on 64 channels LiDAR clouds from the Semantic KITTI dataset [1] and using this model to segment 8, 16 and 32 channel point clouds after adapting them using our framework. The results obtained from carried out experiments demonstrate the effectiveness of our framework where segmentation results surpassed those obtained with nearest neighbor interpolation methods.
{"title":"Improved Semantic Segmentation of Low-Resolution 3D Point Clouds Using Supervised Domain Adaptation","authors":"Asmaa Elhadidy, Mohamed Afifi, Mohammed Hassoubah, Yara Ali, M. Elhelw","doi":"10.1109/NILES50944.2020.9257903","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257903","url":null,"abstract":"One of the key challenges in applying deep learning to solve real-life problems is the lack of large annotated datasets. Furthermore, for a deep learning model to perform well on the test set, all samples in the training and test sets should be independent and identically distributed (i.i.d.), which means that test samples should be similar to the samples that were used to train the model. In many cases, however, the underlying training and test set distributions are different. In such cases, it is common to adapt the test samples by transforming them to their equivalent counterparts in the domain of the training data before being processed by the deep learning model. In this paper, we perform domain adaptation of low-resolution 8, 16 and 32 channels LiDAR 3D point clouds projected on 2D spherical images in order to improve the quality of semantic segmentation tasks. To achieve this, the low-resolution 3D point clouds are transformed using an end-to-end supervised learning approach to spherical images that are very similar to those obtained by projecting high-resolution 64 channels LiDAR point clouds, without changing the underlying structure of the scene. The proposed framework is evaluated by training a semantic segmentation model on 64 channels LiDAR clouds from the Semantic KITTI dataset [1] and using this model to segment 8, 16 and 32 channel point clouds after adapting them using our framework. The results obtained from carried out experiments demonstrate the effectiveness of our framework where segmentation results surpassed those obtained with nearest neighbor interpolation methods.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125970120","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257929
Ahmed A. Eid, Zahraa S. Ismail, S. Abdellatif
Perovskite solar cells (PSCs) showed a booming trend due to its tunability as well as simplicity in fabrication. Researchers invested in exploring an appropriate equivalent circuit capable of describing the J-V curves of the PSCs as well as illustrating the physical phenomena associated with optical absorption and carrier transportation. In the same context, we propose a modified SCAPS model to demonstrate the optoelectronic behavior of PSCs through estimating the parasitic elements in the form of resistive and capacitive components. A previously reported PSC was selected as a reference where our enhanced model recorded only 4% mismatching. J-V, E-K and C-V curves have been simulated and analyzed where the appearance of the capacitive impact due to E-K charge accumulation has been addressed.
{"title":"Optimizing SCAPS model for perovskite solar cell equivalent circuit with utilizing Matlab-based parasitic resistance estimator algorithm","authors":"Ahmed A. Eid, Zahraa S. Ismail, S. Abdellatif","doi":"10.1109/NILES50944.2020.9257929","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257929","url":null,"abstract":"Perovskite solar cells (PSCs) showed a booming trend due to its tunability as well as simplicity in fabrication. Researchers invested in exploring an appropriate equivalent circuit capable of describing the J-V curves of the PSCs as well as illustrating the physical phenomena associated with optical absorption and carrier transportation. In the same context, we propose a modified SCAPS model to demonstrate the optoelectronic behavior of PSCs through estimating the parasitic elements in the form of resistive and capacitive components. A previously reported PSC was selected as a reference where our enhanced model recorded only 4% mismatching. J-V, E-K and C-V curves have been simulated and analyzed where the appearance of the capacitive impact due to E-K charge accumulation has been addressed.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133992115","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257962
Hadeel Afifi, M. Elmahdy, M. E. Saban, Mervat Abu-Elkheir
Time-series forecasting, the process of predicting values in the future given the present and previous history, is a challenging problem to tackle. Deterministic forecasting methods were thoroughly investigated but had limitations regarding reliability. Recent research efforts are exploring the advantages that come with probabilistic forecasting. The need to have large datasets for time-series to build more generalized models and thus being less dependent on data augmentation is also driving efforts to collect comprehensive data. This paper proposes a machine learning model to estimate prediction intervals on a large oil production dataset. Prediction intervals are estimated at different percentiles. Prediction Interval Coverage Probability (PICP) and Prediction Interval Normalized Average Width (PINAW) metrics are used for performance evaluation. The best results are obtained by removing trend and using differencing.
{"title":"Probabilistic Time Series Forecasting for Unconventional Oil and Gas Producing Wells","authors":"Hadeel Afifi, M. Elmahdy, M. E. Saban, Mervat Abu-Elkheir","doi":"10.1109/NILES50944.2020.9257962","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257962","url":null,"abstract":"Time-series forecasting, the process of predicting values in the future given the present and previous history, is a challenging problem to tackle. Deterministic forecasting methods were thoroughly investigated but had limitations regarding reliability. Recent research efforts are exploring the advantages that come with probabilistic forecasting. The need to have large datasets for time-series to build more generalized models and thus being less dependent on data augmentation is also driving efforts to collect comprehensive data. This paper proposes a machine learning model to estimate prediction intervals on a large oil production dataset. Prediction intervals are estimated at different percentiles. Prediction Interval Coverage Probability (PICP) and Prediction Interval Normalized Average Width (PINAW) metrics are used for performance evaluation. The best results are obtained by removing trend and using differencing.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127802083","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257933
S. Sharroush
CMOS circuits that contain multiple branches in the pull-down network (PDN) suffer from the trade-off between the leakage-power reduction and the improvement of the propagation delay. As a solution, multiple threshold voltages can be used in order to reduce the subthreshold leakage in some paths while maintaining the speed requirement in others. In this paper, a novel multiple threshold-voltage CMOS (MTCMOS) subthreshold-leakage reduction algorithm is presented that optimizes the design of CMOS circuits with several branches in the PDN. Specifically, the threshold voltages of certain devices in the PDN are increased in order to reduce the subthreshold leakage while keeping the current-driving capabilities of these devices within certain limits in order not to degrade the performance. Simulation results using the 45 nm CMOS technology confirms this reduction with no speed penalty.
{"title":"An MTCMOS Subthreshold-Leakage Reduction Algorithm","authors":"S. Sharroush","doi":"10.1109/NILES50944.2020.9257933","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257933","url":null,"abstract":"CMOS circuits that contain multiple branches in the pull-down network (PDN) suffer from the trade-off between the leakage-power reduction and the improvement of the propagation delay. As a solution, multiple threshold voltages can be used in order to reduce the subthreshold leakage in some paths while maintaining the speed requirement in others. In this paper, a novel multiple threshold-voltage CMOS (MTCMOS) subthreshold-leakage reduction algorithm is presented that optimizes the design of CMOS circuits with several branches in the PDN. Specifically, the threshold voltages of certain devices in the PDN are increased in order to reduce the subthreshold leakage while keeping the current-driving capabilities of these devices within certain limits in order not to degrade the performance. Simulation results using the 45 nm CMOS technology confirms this reduction with no speed penalty.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129248380","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257945
N. Elshaboury, M. Marzouk
The majority of water pipelines suffer severe deterioration and degradation challenges. Therefore, this research aims at developing machine learning models that forecast the structural condition of water pipelines. The models are implemented using several techniques, including multiple linear regression, feed-forward neural network, general regression neural network, and support vector regression models. The performance of the aforementioned models is evaluated by measuring the coefficient of determination and root mean squared error using cross-validation. The results show that the general regression neural network model outperforms the other models with respect to the applied metrics. The models are developed using data collected from a water distribution network in Shaker Al-Bahery, Qalyubia Governorate, Egypt. The developed model is expected to assist the water municipality in allocating budget efficiently as well as scheduling of the needed intervention strategies.
{"title":"Comparing Machine Learning Models For Predicting Water Pipelines Condition","authors":"N. Elshaboury, M. Marzouk","doi":"10.1109/NILES50944.2020.9257945","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257945","url":null,"abstract":"The majority of water pipelines suffer severe deterioration and degradation challenges. Therefore, this research aims at developing machine learning models that forecast the structural condition of water pipelines. The models are implemented using several techniques, including multiple linear regression, feed-forward neural network, general regression neural network, and support vector regression models. The performance of the aforementioned models is evaluated by measuring the coefficient of determination and root mean squared error using cross-validation. The results show that the general regression neural network model outperforms the other models with respect to the applied metrics. The models are developed using data collected from a water distribution network in Shaker Al-Bahery, Qalyubia Governorate, Egypt. The developed model is expected to assist the water municipality in allocating budget efficiently as well as scheduling of the needed intervention strategies.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115255548","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257968
A. Tarek, H. Elsayed, M. Rashad, Manar Hassan, Passant El-Kafrawy
Dynamic programming is a mathematical optimization first invented in 1950s and lived till our times to make optimizations and reduce complexity in several different fields like bioinformatics, Electric vehicles, energy consumption, medical field and much more as a proof of being a powerful technique. In this paper, the various fields and aspects in which Dynamic programming has a significant contribution are surveyed.
{"title":"Dynamic Programming Applications: A Suvrvey","authors":"A. Tarek, H. Elsayed, M. Rashad, Manar Hassan, Passant El-Kafrawy","doi":"10.1109/NILES50944.2020.9257968","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257968","url":null,"abstract":"Dynamic programming is a mathematical optimization first invented in 1950s and lived till our times to make optimizations and reduce complexity in several different fields like bioinformatics, Electric vehicles, energy consumption, medical field and much more as a proof of being a powerful technique. In this paper, the various fields and aspects in which Dynamic programming has a significant contribution are surveyed.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114607344","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257927
Hussein Sarwat, M. Awad, S. Maged, Hassan Sarwat
The scarcity of adequate rehabilitation and treatment centers for post-stroke patients, a relatively common disease among the Egyptian populace, and the lack of awareness and trained physiotherapists, causes many patients to forgo treatment until they are transported to the hospital. Even then, the high cost of treatment will impede most rehabilitation attempts to those who survive. Thankfully, rehabilitation robotics can be used to replace the need for trained physiotherapists. This paper uses the Myo armband as a rehabilitation assessment device, tracking the progress of Post-Stroke patients and comparing them with healthy subjects. By taking a total of 60 samples from 3 healthy subjects and using self-organizing maps, a clustering system that can differentiate between regular and irregular motions using kinematic data with less than 10% error was produced.
{"title":"Self-Organizing Maps to Assess Rehabilitation Progress of Post-Stroke Patients","authors":"Hussein Sarwat, M. Awad, S. Maged, Hassan Sarwat","doi":"10.1109/NILES50944.2020.9257927","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257927","url":null,"abstract":"The scarcity of adequate rehabilitation and treatment centers for post-stroke patients, a relatively common disease among the Egyptian populace, and the lack of awareness and trained physiotherapists, causes many patients to forgo treatment until they are transported to the hospital. Even then, the high cost of treatment will impede most rehabilitation attempts to those who survive. Thankfully, rehabilitation robotics can be used to replace the need for trained physiotherapists. This paper uses the Myo armband as a rehabilitation assessment device, tracking the progress of Post-Stroke patients and comparing them with healthy subjects. By taking a total of 60 samples from 3 healthy subjects and using self-organizing maps, a clustering system that can differentiate between regular and irregular motions using kinematic data with less than 10% error was produced.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114684169","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257944
Md Ashif Uddin, M. Maswood, Uzzwal Kumar Dey, Abdullah G. Alharbi, Moriom Akter
Sensing is not only essential but also unavoidable in the medical fields to analyze different types of biological samples for diagnostic purposes. Although, the conventional laboratory based sensing method provides high accuracy, sometimes, it is not suitable in terms of cost, sensing time, and amount of samples needed for sensing. In this work, we design a novel optical micro ring resonator biosensor utilizing the properties of lithium niobate (LiNbO3) on insulator (LNOI) to detect the concentration of glucose in blood and urine. Optical micro ring resonator attracts researchers in the biomedical field for their compactness, tenability, and low cost. Moreover, LNOI offers some special properties like favorable optical, mechanical, pieozoelectrical, photoelastic, photorefractive, and photovoltaic properties. First, various samples of devices were designed in COMSOL to perform the modal analysis. Then, these devices were implemented in Opti-FDTD to evaluate the performance of the sensor. By varying different parameters like rib height and width, we optimized the structure of the device where rib height, rib width, top layer width of LiNbO3, ring radius, and the distance between ring and waveguide are 0.56 µm, 0.5 µm, 0.16 µm, 15 µm, and approximately 70 to 80 nm, respectively. This optimized structure shows high quality (Q) factor, sharp resonance wavelength, and more distance between two resonance wavelengths of two different concentration of glucose. For sensing purpose, Gaussian modulated continuous wave of 1545 nm wavelength was used as input and best results in output were obtained at 1250 to 1280 nm wavelength.
{"title":"A Novel Optical Micro Ring Resonator Biosensor Design using Lithium Niobate on Insulator (LNOI) to Detect The Concentration of Glucose","authors":"Md Ashif Uddin, M. Maswood, Uzzwal Kumar Dey, Abdullah G. Alharbi, Moriom Akter","doi":"10.1109/NILES50944.2020.9257944","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257944","url":null,"abstract":"Sensing is not only essential but also unavoidable in the medical fields to analyze different types of biological samples for diagnostic purposes. Although, the conventional laboratory based sensing method provides high accuracy, sometimes, it is not suitable in terms of cost, sensing time, and amount of samples needed for sensing. In this work, we design a novel optical micro ring resonator biosensor utilizing the properties of lithium niobate (LiNbO3) on insulator (LNOI) to detect the concentration of glucose in blood and urine. Optical micro ring resonator attracts researchers in the biomedical field for their compactness, tenability, and low cost. Moreover, LNOI offers some special properties like favorable optical, mechanical, pieozoelectrical, photoelastic, photorefractive, and photovoltaic properties. First, various samples of devices were designed in COMSOL to perform the modal analysis. Then, these devices were implemented in Opti-FDTD to evaluate the performance of the sensor. By varying different parameters like rib height and width, we optimized the structure of the device where rib height, rib width, top layer width of LiNbO3, ring radius, and the distance between ring and waveguide are 0.56 µm, 0.5 µm, 0.16 µm, 15 µm, and approximately 70 to 80 nm, respectively. This optimized structure shows high quality (Q) factor, sharp resonance wavelength, and more distance between two resonance wavelengths of two different concentration of glucose. For sensing purpose, Gaussian modulated continuous wave of 1545 nm wavelength was used as input and best results in output were obtained at 1250 to 1280 nm wavelength.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125265924","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257958
Salma A. Essam El-Din, Mohamed A. Abd El-Ghany
Losing the ability to speak exerts psychological and social impacts on the affected people due to the lack of proper communication. Thus, Sign Language (SL) is considered a boon to people with hearing and speech impairment. SL has developed as a handy mean of communication that form the core of local deaf cultures. It is a visual–spatial language based on positional and visual components, such as the shape of fingers and hands, their location and orientation as well as arm and body movements. The problem is that SL is not understood by everyone, forming a communication gap between the mute and the able people. Multiple and systematic scholarly interventions that vary according to context have been implemented to overcome disability-related difficulties. Sign language recognition (SLR) systems based on sensory gloves are significant innovations that aim to procure data on the shape or movement of the human hand to bridge this communication gap, as the proposed system. The proposed model is a glove equipped with five flex sensors, interfacing with a control unit fixed on the arm, translating American Sign Language (ASL) and Arabic Sign Language (ArSL) to both text and speech, displayed on a simple Graphical User Interface (GUI). The proposed system aims to provide an affordable and user friendly SL translator system, working on the basis of Machine Learning (ML). However, it adapts to each person’s hand instead of using a generic data set. The system achieved 95% recognition rate with static gestures and up to 88% with dynamic gestures.
{"title":"Sign Language Interpreter System: An alternative system for machine learning","authors":"Salma A. Essam El-Din, Mohamed A. Abd El-Ghany","doi":"10.1109/NILES50944.2020.9257958","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257958","url":null,"abstract":"Losing the ability to speak exerts psychological and social impacts on the affected people due to the lack of proper communication. Thus, Sign Language (SL) is considered a boon to people with hearing and speech impairment. SL has developed as a handy mean of communication that form the core of local deaf cultures. It is a visual–spatial language based on positional and visual components, such as the shape of fingers and hands, their location and orientation as well as arm and body movements. The problem is that SL is not understood by everyone, forming a communication gap between the mute and the able people. Multiple and systematic scholarly interventions that vary according to context have been implemented to overcome disability-related difficulties. Sign language recognition (SLR) systems based on sensory gloves are significant innovations that aim to procure data on the shape or movement of the human hand to bridge this communication gap, as the proposed system. The proposed model is a glove equipped with five flex sensors, interfacing with a control unit fixed on the arm, translating American Sign Language (ASL) and Arabic Sign Language (ArSL) to both text and speech, displayed on a simple Graphical User Interface (GUI). The proposed system aims to provide an affordable and user friendly SL translator system, working on the basis of Machine Learning (ML). However, it adapts to each person’s hand instead of using a generic data set. The system achieved 95% recognition rate with static gestures and up to 88% with dynamic gestures.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123752912","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：