2020 6th International Conference on Wireless and Telematics (ICWT), 2020
Nowadays, speaker verification and speech recognition to control the smart home system has gained... more Nowadays, speaker verification and speech recognition to control the smart home system has gained popularity. This paper presents the design and implementation of the voice-based smart home security system using Google Voice Kit, Raspberry Pi 3, relay, and magnetic lock. There are two methods implemented in this research, i.e., Cloud Speech and Assistant methods. Three experiments were conducted, including response time to the voice command, multiuser experiment, and multi-environment experiment. Results showed that the Cloud Speech method performs better than the Assistant method in processing time and accuracy. The Cloud Speech method requires less than 1.67 ms to lock and unlock the magnetic lock. The accuracy of the multiuser experiment using the Cloud Speech method is 90% on average. Finally, on the various environmental condition, the Cloud Speech method has an accuracy of 95%, 90%, and 95% for the ambient room, cocktail noise, and loud musical noise, respectively.
Supplemental material, REVISED_NECS_Supplementary_Table_ROW_percentages for Perception of Harms a... more Supplemental material, REVISED_NECS_Supplementary_Table_ROW_percentages for Perception of Harms and Benefits of Electronic Cigarettes Among Adult Malaysian Men: A Comparison by Electronic Cigarette Use and Smoking Status by Caryn Mei Hsien Chan, Jamalludin Ab Rahman, Tee Guat Hiong, Wee Lei Hum, Ho Bee Kiau, Noor Zurani Md Haris Robson, Shamsul Draman, Jane Ling Miaw Yn, Lim Kuang Hock, Muhammad Fadhli Yusoff, Mira Kartiwi, Norny Syafinaz Ab Rahman and Mohamad Haniki Nik Mohamed in Asia Pacific Journal of Public Health
Supplemental material, Appendix_2 for The Prevalence of E-Cigarette Use Among Adults in Malaysia:... more Supplemental material, Appendix_2 for The Prevalence of E-Cigarette Use Among Adults in Malaysia: Findings From the 2016 National E-Cigarette Survey by Jamalludin Ab Rahman, Muhammad Fadhli Mohd Yusoff, Mohamad Haniki Nik Mohamed, Balkish Mahadir Naidu, Lim Kuang Hock, Dip Public Health, Tee Guat Hiong, Maria Safura Mohamad, Mira Kartiwi, Samsul Draman, Norny Syafinaz Ab Rahman and Tahir Aris in Asia Pacific Journal of Public Health
Introduction: We conducted a nationally representative study to identify characteristics of curre... more Introduction: We conducted a nationally representative study to identify characteristics of current (e-cigarette users, conventional cigarette smokers, and dual users), former and never smokers linked to perceptions of harm and benefit associated with e-cigarette use. Methods: A crosssectional questionnaire survey of 1,987 adults (≥18 years) males was conducted via face-to-face interviews. Survey questions included sociodemographic and smoking-related variables, and questions relating to perceptions of harm and benefit associated with e-cigarette use. Logistic regression was used to identify sociodemographic characteristic linked to the perception of harm and benefit associated with e-cigarettes between types of EC users and smokers, with never smokers as the reference group. Results: Overall, older respondents aged ≥65 years (OR=1.736, CI 0.821-2.260), civil servants (OR=1.721, CI 1.085-2.729), non-governmental organisations (OR=1.570, CI 1.066-2.311) and the selfemployed (OR=1.469...
Introduction: The increasing popularity of electronic cigarettes (ECV) in Malaysia, has made it i... more Introduction: The increasing popularity of electronic cigarettes (ECV) in Malaysia, has made it important to find out its pattern of use. The objective of this study was to determine the pattern of ECV use among urban and rural ECV users in Malaysia. Methods: A household population survey was designed to represent Malaysian adults >18 years old by urbanity at national level. A multistage stratified cluster random sampling with probabilities proportional to size (PPS), stratified by state and by urban/rural areas was done. Respondents were from six zones (North, Central, South, East, Sabah and Sarawak) who answered the NECS Questionnaire Survey Form on demographics and characteristics of ECV use. Results: A total of 4,288 individuals (72% urban) were recruited. Majority were 25-44 years old (44%), Malay (73%), Muslim (79%), married (68%) and educated to secondary education (69%). Majority (86.5%) of current ECV users started ECV use at age) =19 years old. The main reason to use EC...
Introduction: E-cigarette and vape (ECV) use has become a worldwide phenomenon since 2010. This s... more Introduction: E-cigarette and vape (ECV) use has become a worldwide phenomenon since 2010. This study aims to determine the prevalence of ever user, current user and factors associated with ECV use among Malaysian adults. This will provide evidence for policy makers to formulate appropriate measures towards regulation of ECV in Malaysia and can become a reference for other similar countries. Method: Complex sampling design was used to represent 19 million of Malaysian adult household. Samples were stratified by states and urbanity. Sampling units were districts, enumeration blocks and living quarters. All adults from the selected houses were invited to participate in this survey. Analysis was done using sampling weight and complex sampling analysis. Results: A total of 4,288 individual responded in this survey. Majority of the respondents were at 25-44 years of age group (44%), completed at least secondary level of education (69%), of Malay ethnicity (73%), Muslim (79%) and married ...
2019 IEEE International Conference on Smart Instrumentation, Measurement and Application (ICSIMA), 2019
Gender identification via speech processing is one of the hot research topics among the security ... more Gender identification via speech processing is one of the hot research topics among the security research community. Many cyber systems are being developed to recognize human speech type. These systems mainly comprise of a feature segment process which extracts and selects the features of human speeches. Feature extraction and feature selection are the most noteworthy phase of speech recognition involving numerous strategies. The purpose of this paper is to investigate the potential effectiveness of spectral analysis and higher-order statistics performed over the speech segments of different genders. Spectral analysis is done via spectral descriptors consisting of varied parameters which are widely used in machine learning applications. The varied gender speeches are distinguished by means of parameters, i.e., higher order statistics, like spectral centroid, spectral entropy, spectral kurtosis, spectral slope and spectral flatness. The results obtained show successful discrimination of male and female speeches based on the peakiness of speech, voiced and unvoiced and higher and lower formants.
In the speech signal, emotion is considered one of the most critical elements. For the recognitio... more In the speech signal, emotion is considered one of the most critical elements. For the recognition of emotions, the field of speech emotion recognition came into ex-istence. Speech Emotion Recognition (SER) is becoming an area of research in-terest in the last few years. A typical SER system focuses on extracting features such as pitch frequency, formant features, energy-related features, and spectral features from speech, tailing it with a classification quest to foresee different clas-ses of emotion. The critical issue to be addressed for a successful SER system is the emotional feature extraction, which can be solved by using different feature extraction techniques. In this paper, along with Teager Energy Operator (TEO) and Mel Frequency Cepstral Coefficients (MFCC) a trailblazing feature extrac-tion method, a fusion of MFCC and TEO as Teager-MFCC (T-MFCC) is used for the recognition of energy-based emotions. We have used three corpora of emotions in German, English, and Hindi to develop the multilingual SER system. The classification of these energy-based emotions is done by Deep Neural Net-work (DNN). It is found that TEO achieves a better recognition rate compared to MFCC and T-MFCC
Affective computing is a developing interdisciplinary examination field uniting specialists and e... more Affective computing is a developing interdisciplinary examination field uniting specialists and experts from different fields, from artificial intelligence, natural language processing to intellectual and sociologies. The thought behind affective computing is to give computers the aptitude of insight that will, in general, comprehend human feelings. Notwithstanding these victories, the field needs hypothetical firm establishments and efficient rules in numerous regions, especially in feeling demonstrating and developing computational models of feeling. This exploration manages affective computing to improve the exhibition of Human-Machine Interaction. This work's focal point is to distinguish the emotional state of a human utilizing deep learning procedure, i.e., Convolutional Neural Networks (CNN) containing parameters like three convolution layers, pooling layers, learning rates, two fully connected layers, batch normalizations, and dropout ratios. The Warsaw Set of Emotional ...
Introduction: The main objective of this paper is to understand the decision to use electronic ci... more Introduction: The main objective of this paper is to understand the decision to use electronic cigarette and vape (ECV) and vape among Malaysian adults by assessing the perceptions and demographic variables in relations to the current status (i.e., current, former, and never use). The predictive model was developed using Induction Decision Tree (ID3) algorithm, a popular data mining technique an exploratory tool for knowledge discovery. Methods: The dataset was extracted from the National Electronic Cigarette Survey (NECS) 2016.A total of 4,288 responses were collected. The collected data was used to build and verified the model. Eight demographics variables (i.e., age, gender, race, religion, residence (urban/rural), marital, occupation and education) and twenty variables on perception of ECV were included as predictor variables. Results: By using the ID3 algorithm, it is possible to consider the relationship among variables and to identify the most informative variables for predic...
Multichannel audio or surround sound compression is rather more challenging to compress compare t... more Multichannel audio or surround sound compression is rather more challenging to compress compare to mono and stereo audio. Nowadays, many methods and algorithms have been proposed to improve the compression performance on multichannel audio. This book focuses on performance evaluation of various algorithms on multichannel audio compression. First, we identified and investigated current state-of-the-art audio compression algorithms, both lossless and lossy compression, which can handle mono, stereo, 5.1, and 7.1 multichannel audio. Out of various algorithms available, AC3, AAC, and Ogg have been selected as lossy compression algorithms, while FLAC and MPEG-4 ALS have been chosen as lossless compression algorithms. Two performance measure were used in the experiments, i.e. compression ratio and encoding time. The results showed that among three lossy audio compression algorithms, AC3 has the fastest encoding time while Ogg Vorbis has the highest compression ratio. Furthermore, between ...
Introduction: E-cigarette use among adults are steadily increasing over the past few years. It is... more Introduction: E-cigarette use among adults are steadily increasing over the past few years. It is highlighted by the significant increases in online search queries and sharing of information through social media, such as Twitter. However, little attention has been given on understanding the reasons that led to e-cigarette use among Malaysian. In particular, study that leverage the opportunity to extract critical information from textual data in social media by using text mining technique. It is the aim of this paper to share the potential use of such technique by providing overview of processes and examples of the insights derived from the analysis. Methods: In this study, the textual analytics was used to identify topics and extract meanings from social media posts, in this case Twitter. The messages posted by Malaysian users from 2012 to early 2017 containing any of the selected keywords or phrase (i.e., #vape, #ecig, #vaping, #ejuice, #vapemalaysia) were collected using its searc...
2018 IEEE 5th International Conference on Smart Instrumentation, Measurement and Application (ICSIMA), 2018
Nowadays, electricity is the most important or basic needs of human life. In this paper, the deve... more Nowadays, electricity is the most important or basic needs of human life. In this paper, the development of power factor meter using Arduino will be discussed. To measure power, several parameters were extracted, including voltage and current from the alternating current (AC) source. Voltage and current sensors outputs were interfaced to Arduino, in which the real power and apparent power were calculated to determine the power factor. Experimental results on the current measurement calibration showed the accuracy of our proposed power factor meter. Moreover, the measured data points were logged in an SD card, at the same time it was sent to Matlab with graphical user interface (GUI) for ease of further monitoring. Finally, IoT framework analysis for smart meter was further discussed in this paper.
2021 IEEE 7th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA), 2021
In recent years, artificial intelligence has been utilized in many applications. One of the promi... more In recent years, artificial intelligence has been utilized in many applications. One of the prominent applications is detecting emotion from an image, which can help an intelligent automatic response system respond appropriately based on the user’s emotion. This paper presented the development of emotion recognition using Convolutional Neural Networks (CNN) on image input. First, the extended Cohn-Kanade image emotion database was selected with five defined emotions: happy, sad, anger, fear, surprise, and neutral. Second, face detection and facial landmarks extraction was applied to the input image. Then, the AlexNet model is used as the selected deep learning architecture for transfer learning. Results showed that around 98.2% recognition accuracy could be achieved. Furthermore, precision, recall, and F1-score were evaluated, and it showed the effectiveness of our proposed algorithm.
The Covid-19 pandemic hits the world economy. On July 2020, some countries have plunged into rece... more The Covid-19 pandemic hits the world economy. On July 2020, some countries have plunged into recession. The prescription from the perspective of Islamic economics and finance need to be formulated. The application conventional methodology like survey or any types of regression will not able to examine the dynamic changes on the economy during the occurrence of pandemic and will fail to draw the very long term situation. In this regard, Islamic economics needs to move forward to utilize the advancement of technology. The use of Agent-based Computational Model (ABM) is one of alternative methodology to develop research in the area of Islamic economics and finance. ABM is a computational study which builds the economy as a complex world, thus, the prescription for economic crisis based on Islamic views can be formulated. This research has two objectives, i.e., (a) to review on how ABM has developed research in the area of Islamic economics and finance, (b) to provide an example on how...
Electronic cigarettes (e-cigarettes) are a new method for the consumption of nicotine. A nationwi... more Electronic cigarettes (e-cigarettes) are a new method for the consumption of nicotine. A nationwide survey among 4288 Malaysian adults was conducted in 2016 to measure the prevalence and to describe the population characteristics of e-cigarette users. A complex sampling design was used, and data were collected using a face-to-face questionnaire. The overall prevalence of current, ever, former, and dual users of e-cigarettes in Malaysia were 3.2% (95% confidence interval [CI] = 2.5-4.1), 11.9% (95% CI = 10.5-13.5), 8.6% (95% CI = 7.5-9.8), and 2.3% (95% CI = 1.8-3.1), respectively. The prevalence of all type of e-cigarette use was higher in urban than in rural areas. Current e-cigarette users were likely to be younger, males, and with higher education level. Among current e-cigarette users, 74% (95% CI = 64-82) also smoked conventional cigarettes (dual user). E-cigarette use is prevalent in Malaysia. It is common among younger adults, males, and cigarette smokers.
2020 6th International Conference on Wireless and Telematics (ICWT), 2020
Nowadays, speaker verification and speech recognition to control the smart home system has gained... more Nowadays, speaker verification and speech recognition to control the smart home system has gained popularity. This paper presents the design and implementation of the voice-based smart home security system using Google Voice Kit, Raspberry Pi 3, relay, and magnetic lock. There are two methods implemented in this research, i.e., Cloud Speech and Assistant methods. Three experiments were conducted, including response time to the voice command, multiuser experiment, and multi-environment experiment. Results showed that the Cloud Speech method performs better than the Assistant method in processing time and accuracy. The Cloud Speech method requires less than 1.67 ms to lock and unlock the magnetic lock. The accuracy of the multiuser experiment using the Cloud Speech method is 90% on average. Finally, on the various environmental condition, the Cloud Speech method has an accuracy of 95%, 90%, and 95% for the ambient room, cocktail noise, and loud musical noise, respectively.
Supplemental material, REVISED_NECS_Supplementary_Table_ROW_percentages for Perception of Harms a... more Supplemental material, REVISED_NECS_Supplementary_Table_ROW_percentages for Perception of Harms and Benefits of Electronic Cigarettes Among Adult Malaysian Men: A Comparison by Electronic Cigarette Use and Smoking Status by Caryn Mei Hsien Chan, Jamalludin Ab Rahman, Tee Guat Hiong, Wee Lei Hum, Ho Bee Kiau, Noor Zurani Md Haris Robson, Shamsul Draman, Jane Ling Miaw Yn, Lim Kuang Hock, Muhammad Fadhli Yusoff, Mira Kartiwi, Norny Syafinaz Ab Rahman and Mohamad Haniki Nik Mohamed in Asia Pacific Journal of Public Health
Supplemental material, Appendix_2 for The Prevalence of E-Cigarette Use Among Adults in Malaysia:... more Supplemental material, Appendix_2 for The Prevalence of E-Cigarette Use Among Adults in Malaysia: Findings From the 2016 National E-Cigarette Survey by Jamalludin Ab Rahman, Muhammad Fadhli Mohd Yusoff, Mohamad Haniki Nik Mohamed, Balkish Mahadir Naidu, Lim Kuang Hock, Dip Public Health, Tee Guat Hiong, Maria Safura Mohamad, Mira Kartiwi, Samsul Draman, Norny Syafinaz Ab Rahman and Tahir Aris in Asia Pacific Journal of Public Health
Introduction: We conducted a nationally representative study to identify characteristics of curre... more Introduction: We conducted a nationally representative study to identify characteristics of current (e-cigarette users, conventional cigarette smokers, and dual users), former and never smokers linked to perceptions of harm and benefit associated with e-cigarette use. Methods: A crosssectional questionnaire survey of 1,987 adults (≥18 years) males was conducted via face-to-face interviews. Survey questions included sociodemographic and smoking-related variables, and questions relating to perceptions of harm and benefit associated with e-cigarette use. Logistic regression was used to identify sociodemographic characteristic linked to the perception of harm and benefit associated with e-cigarettes between types of EC users and smokers, with never smokers as the reference group. Results: Overall, older respondents aged ≥65 years (OR=1.736, CI 0.821-2.260), civil servants (OR=1.721, CI 1.085-2.729), non-governmental organisations (OR=1.570, CI 1.066-2.311) and the selfemployed (OR=1.469...
Introduction: The increasing popularity of electronic cigarettes (ECV) in Malaysia, has made it i... more Introduction: The increasing popularity of electronic cigarettes (ECV) in Malaysia, has made it important to find out its pattern of use. The objective of this study was to determine the pattern of ECV use among urban and rural ECV users in Malaysia. Methods: A household population survey was designed to represent Malaysian adults >18 years old by urbanity at national level. A multistage stratified cluster random sampling with probabilities proportional to size (PPS), stratified by state and by urban/rural areas was done. Respondents were from six zones (North, Central, South, East, Sabah and Sarawak) who answered the NECS Questionnaire Survey Form on demographics and characteristics of ECV use. Results: A total of 4,288 individuals (72% urban) were recruited. Majority were 25-44 years old (44%), Malay (73%), Muslim (79%), married (68%) and educated to secondary education (69%). Majority (86.5%) of current ECV users started ECV use at age) =19 years old. The main reason to use EC...
Introduction: E-cigarette and vape (ECV) use has become a worldwide phenomenon since 2010. This s... more Introduction: E-cigarette and vape (ECV) use has become a worldwide phenomenon since 2010. This study aims to determine the prevalence of ever user, current user and factors associated with ECV use among Malaysian adults. This will provide evidence for policy makers to formulate appropriate measures towards regulation of ECV in Malaysia and can become a reference for other similar countries. Method: Complex sampling design was used to represent 19 million of Malaysian adult household. Samples were stratified by states and urbanity. Sampling units were districts, enumeration blocks and living quarters. All adults from the selected houses were invited to participate in this survey. Analysis was done using sampling weight and complex sampling analysis. Results: A total of 4,288 individual responded in this survey. Majority of the respondents were at 25-44 years of age group (44%), completed at least secondary level of education (69%), of Malay ethnicity (73%), Muslim (79%) and married ...
2019 IEEE International Conference on Smart Instrumentation, Measurement and Application (ICSIMA), 2019
Gender identification via speech processing is one of the hot research topics among the security ... more Gender identification via speech processing is one of the hot research topics among the security research community. Many cyber systems are being developed to recognize human speech type. These systems mainly comprise of a feature segment process which extracts and selects the features of human speeches. Feature extraction and feature selection are the most noteworthy phase of speech recognition involving numerous strategies. The purpose of this paper is to investigate the potential effectiveness of spectral analysis and higher-order statistics performed over the speech segments of different genders. Spectral analysis is done via spectral descriptors consisting of varied parameters which are widely used in machine learning applications. The varied gender speeches are distinguished by means of parameters, i.e., higher order statistics, like spectral centroid, spectral entropy, spectral kurtosis, spectral slope and spectral flatness. The results obtained show successful discrimination of male and female speeches based on the peakiness of speech, voiced and unvoiced and higher and lower formants.
In the speech signal, emotion is considered one of the most critical elements. For the recognitio... more In the speech signal, emotion is considered one of the most critical elements. For the recognition of emotions, the field of speech emotion recognition came into ex-istence. Speech Emotion Recognition (SER) is becoming an area of research in-terest in the last few years. A typical SER system focuses on extracting features such as pitch frequency, formant features, energy-related features, and spectral features from speech, tailing it with a classification quest to foresee different clas-ses of emotion. The critical issue to be addressed for a successful SER system is the emotional feature extraction, which can be solved by using different feature extraction techniques. In this paper, along with Teager Energy Operator (TEO) and Mel Frequency Cepstral Coefficients (MFCC) a trailblazing feature extrac-tion method, a fusion of MFCC and TEO as Teager-MFCC (T-MFCC) is used for the recognition of energy-based emotions. We have used three corpora of emotions in German, English, and Hindi to develop the multilingual SER system. The classification of these energy-based emotions is done by Deep Neural Net-work (DNN). It is found that TEO achieves a better recognition rate compared to MFCC and T-MFCC
Affective computing is a developing interdisciplinary examination field uniting specialists and e... more Affective computing is a developing interdisciplinary examination field uniting specialists and experts from different fields, from artificial intelligence, natural language processing to intellectual and sociologies. The thought behind affective computing is to give computers the aptitude of insight that will, in general, comprehend human feelings. Notwithstanding these victories, the field needs hypothetical firm establishments and efficient rules in numerous regions, especially in feeling demonstrating and developing computational models of feeling. This exploration manages affective computing to improve the exhibition of Human-Machine Interaction. This work's focal point is to distinguish the emotional state of a human utilizing deep learning procedure, i.e., Convolutional Neural Networks (CNN) containing parameters like three convolution layers, pooling layers, learning rates, two fully connected layers, batch normalizations, and dropout ratios. The Warsaw Set of Emotional ...
Introduction: The main objective of this paper is to understand the decision to use electronic ci... more Introduction: The main objective of this paper is to understand the decision to use electronic cigarette and vape (ECV) and vape among Malaysian adults by assessing the perceptions and demographic variables in relations to the current status (i.e., current, former, and never use). The predictive model was developed using Induction Decision Tree (ID3) algorithm, a popular data mining technique an exploratory tool for knowledge discovery. Methods: The dataset was extracted from the National Electronic Cigarette Survey (NECS) 2016.A total of 4,288 responses were collected. The collected data was used to build and verified the model. Eight demographics variables (i.e., age, gender, race, religion, residence (urban/rural), marital, occupation and education) and twenty variables on perception of ECV were included as predictor variables. Results: By using the ID3 algorithm, it is possible to consider the relationship among variables and to identify the most informative variables for predic...
Multichannel audio or surround sound compression is rather more challenging to compress compare t... more Multichannel audio or surround sound compression is rather more challenging to compress compare to mono and stereo audio. Nowadays, many methods and algorithms have been proposed to improve the compression performance on multichannel audio. This book focuses on performance evaluation of various algorithms on multichannel audio compression. First, we identified and investigated current state-of-the-art audio compression algorithms, both lossless and lossy compression, which can handle mono, stereo, 5.1, and 7.1 multichannel audio. Out of various algorithms available, AC3, AAC, and Ogg have been selected as lossy compression algorithms, while FLAC and MPEG-4 ALS have been chosen as lossless compression algorithms. Two performance measure were used in the experiments, i.e. compression ratio and encoding time. The results showed that among three lossy audio compression algorithms, AC3 has the fastest encoding time while Ogg Vorbis has the highest compression ratio. Furthermore, between ...
Introduction: E-cigarette use among adults are steadily increasing over the past few years. It is... more Introduction: E-cigarette use among adults are steadily increasing over the past few years. It is highlighted by the significant increases in online search queries and sharing of information through social media, such as Twitter. However, little attention has been given on understanding the reasons that led to e-cigarette use among Malaysian. In particular, study that leverage the opportunity to extract critical information from textual data in social media by using text mining technique. It is the aim of this paper to share the potential use of such technique by providing overview of processes and examples of the insights derived from the analysis. Methods: In this study, the textual analytics was used to identify topics and extract meanings from social media posts, in this case Twitter. The messages posted by Malaysian users from 2012 to early 2017 containing any of the selected keywords or phrase (i.e., #vape, #ecig, #vaping, #ejuice, #vapemalaysia) were collected using its searc...
2018 IEEE 5th International Conference on Smart Instrumentation, Measurement and Application (ICSIMA), 2018
Nowadays, electricity is the most important or basic needs of human life. In this paper, the deve... more Nowadays, electricity is the most important or basic needs of human life. In this paper, the development of power factor meter using Arduino will be discussed. To measure power, several parameters were extracted, including voltage and current from the alternating current (AC) source. Voltage and current sensors outputs were interfaced to Arduino, in which the real power and apparent power were calculated to determine the power factor. Experimental results on the current measurement calibration showed the accuracy of our proposed power factor meter. Moreover, the measured data points were logged in an SD card, at the same time it was sent to Matlab with graphical user interface (GUI) for ease of further monitoring. Finally, IoT framework analysis for smart meter was further discussed in this paper.
2021 IEEE 7th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA), 2021
In recent years, artificial intelligence has been utilized in many applications. One of the promi... more In recent years, artificial intelligence has been utilized in many applications. One of the prominent applications is detecting emotion from an image, which can help an intelligent automatic response system respond appropriately based on the user’s emotion. This paper presented the development of emotion recognition using Convolutional Neural Networks (CNN) on image input. First, the extended Cohn-Kanade image emotion database was selected with five defined emotions: happy, sad, anger, fear, surprise, and neutral. Second, face detection and facial landmarks extraction was applied to the input image. Then, the AlexNet model is used as the selected deep learning architecture for transfer learning. Results showed that around 98.2% recognition accuracy could be achieved. Furthermore, precision, recall, and F1-score were evaluated, and it showed the effectiveness of our proposed algorithm.
The Covid-19 pandemic hits the world economy. On July 2020, some countries have plunged into rece... more The Covid-19 pandemic hits the world economy. On July 2020, some countries have plunged into recession. The prescription from the perspective of Islamic economics and finance need to be formulated. The application conventional methodology like survey or any types of regression will not able to examine the dynamic changes on the economy during the occurrence of pandemic and will fail to draw the very long term situation. In this regard, Islamic economics needs to move forward to utilize the advancement of technology. The use of Agent-based Computational Model (ABM) is one of alternative methodology to develop research in the area of Islamic economics and finance. ABM is a computational study which builds the economy as a complex world, thus, the prescription for economic crisis based on Islamic views can be formulated. This research has two objectives, i.e., (a) to review on how ABM has developed research in the area of Islamic economics and finance, (b) to provide an example on how...
Electronic cigarettes (e-cigarettes) are a new method for the consumption of nicotine. A nationwi... more Electronic cigarettes (e-cigarettes) are a new method for the consumption of nicotine. A nationwide survey among 4288 Malaysian adults was conducted in 2016 to measure the prevalence and to describe the population characteristics of e-cigarette users. A complex sampling design was used, and data were collected using a face-to-face questionnaire. The overall prevalence of current, ever, former, and dual users of e-cigarettes in Malaysia were 3.2% (95% confidence interval [CI] = 2.5-4.1), 11.9% (95% CI = 10.5-13.5), 8.6% (95% CI = 7.5-9.8), and 2.3% (95% CI = 1.8-3.1), respectively. The prevalence of all type of e-cigarette use was higher in urban than in rural areas. Current e-cigarette users were likely to be younger, males, and with higher education level. Among current e-cigarette users, 74% (95% CI = 64-82) also smoked conventional cigarettes (dual user). E-cigarette use is prevalent in Malaysia. It is common among younger adults, males, and cigarette smokers.
Uploads
Papers by Mira Kartiwi