Pub Date : 1900-01-01DOI: 10.1109/ICREST.2019.8644357
Md. Shahriare Satu, Farha Farida Sathi, Md. Sadrul Arifen, Md. Hanif Ali, M. Moni
Autism Spectrum Disorder (ASD) is a neurobehavioral disorder that begins at childhood and exists this whole life. The objective of this work is that to explore significant features of normal and autism of divisional regions in Bangladesh. We collected individual samples of various children from their parents between 16 to 30 months of different residents using Autism Barta apps by web and fieldwork at Savar, Bangladesh. Then, we preprocessed our data and categorized frequent features based on their individual regions. Different tree based techniques such as J48, Logistic Model Tree, Random Forest, Reduced Error Pruned Tree, and Decision Stump were analyzed to find out the best classifier of them. From these classifiers, J48 showed the best outcomes than other classifiers. We extracted 9 rules and associated conditions from J48 decision tree and gathered frequent instances from our data for extracted rules. Finally, 8 within 23 features were required to classify normal and autism of individual regions in Bangladesh. Besides, 4 rules (10 Conditions) for normal and 5 (12 Conditions) rules for autism out of 9 (16 Conditions) rules were extracted from decision tree. This outcomes assist us to find out significant features of autism in Bangladesh. We expect that our work will be helpful things to improve their condition that leads them to a normal life.
{"title":"Early Detection of Autism by Extracting Features: A Case Study in Bangladesh","authors":"Md. Shahriare Satu, Farha Farida Sathi, Md. Sadrul Arifen, Md. Hanif Ali, M. Moni","doi":"10.1109/ICREST.2019.8644357","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644357","url":null,"abstract":"Autism Spectrum Disorder (ASD) is a neurobehavioral disorder that begins at childhood and exists this whole life. The objective of this work is that to explore significant features of normal and autism of divisional regions in Bangladesh. We collected individual samples of various children from their parents between 16 to 30 months of different residents using Autism Barta apps by web and fieldwork at Savar, Bangladesh. Then, we preprocessed our data and categorized frequent features based on their individual regions. Different tree based techniques such as J48, Logistic Model Tree, Random Forest, Reduced Error Pruned Tree, and Decision Stump were analyzed to find out the best classifier of them. From these classifiers, J48 showed the best outcomes than other classifiers. We extracted 9 rules and associated conditions from J48 decision tree and gathered frequent instances from our data for extracted rules. Finally, 8 within 23 features were required to classify normal and autism of individual regions in Bangladesh. Besides, 4 rules (10 Conditions) for normal and 5 (12 Conditions) rules for autism out of 9 (16 Conditions) rules were extracted from decision tree. This outcomes assist us to find out significant features of autism in Bangladesh. We expect that our work will be helpful things to improve their condition that leads them to a normal life.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125536195","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}
We are living in the fourth industrial revolution. Our life is becoming more comfortable and smarter with the help of rapid upgrade of technology. Internet of things (IoT) is playing a massive role in this. One of the major sides of IoT is a smart home. As we are in the era of never-ending growth of the internet and its application, smart home system or home automation system is highly increasing to provide comfort in life and improving the quality of life. In this paper, we present an IoT based low-cost smart home automation system. This system is based on a web portal which controlled by an ESP32 Wi-Fi module. Also, a custom-made private home web server is developed for maintaining the current states of home appliances.
{"title":"Domicile - An IoT Based Smart Home Automation System","authors":"Md. Sadad Mahamud, Md. Saniat Rahman Zishan, Syed Ishmam Ahmad, Ahmed Rezaur Rahman, Md.Mehedi Hasan, Md. Lutfur Rahman","doi":"10.1109/ICREST.2019.8644349","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644349","url":null,"abstract":"We are living in the fourth industrial revolution. Our life is becoming more comfortable and smarter with the help of rapid upgrade of technology. Internet of things (IoT) is playing a massive role in this. One of the major sides of IoT is a smart home. As we are in the era of never-ending growth of the internet and its application, smart home system or home automation system is highly increasing to provide comfort in life and improving the quality of life. In this paper, we present an IoT based low-cost smart home automation system. This system is based on a web portal which controlled by an ESP32 Wi-Fi module. Also, a custom-made private home web server is developed for maintaining the current states of home appliances.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126660723","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 : 1900-01-01DOI: 10.1109/ICREST.2019.8644169
Md. Arif Abdulla Samy, Md. Abdullah Al Rakib Hassan, Md. Humayun Kabir Chy, Md. Naimul Hoque, Abdullah Al-Imran, Md. Nahian Al Subri Ivan
Hot water is a very essential component to be utilized for residential, business and mechanical purposes. Different assets i.e. coal, diesel, gas, power and so forth, are utilized to warm water, which is very costly process. Sunlight based water warming framework is one of them and more affordable than others. The extent of the frameworks relies upon accessibility of sun-oriented radiation, temperature necessity of client, topographical condition and game plan of the nearby planetary group and so forth. The primary target of this research was converting the solar energy into thermal energy and controlling the desired hot water temperature for water heating purposes. In this paper, closed loop solar water heating system was used. A solenoid valve was used to control the supply water which will be going to the user. To control the hot water, temperature feedback control system was used which can sense the water temperature using temperature sensor. The temperature of condenser was sensed by using LM35 temperature sensor also. To increase the efficiency of the collector an additional dual-axis concentrator was used. The research was successful to increase water temperature up to 19°C and stable it.
{"title":"Water Heating System Using Solar Concentration and Temperature Feedback: A Aost Efficient Approach","authors":"Md. Arif Abdulla Samy, Md. Abdullah Al Rakib Hassan, Md. Humayun Kabir Chy, Md. Naimul Hoque, Abdullah Al-Imran, Md. Nahian Al Subri Ivan","doi":"10.1109/ICREST.2019.8644169","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644169","url":null,"abstract":"Hot water is a very essential component to be utilized for residential, business and mechanical purposes. Different assets i.e. coal, diesel, gas, power and so forth, are utilized to warm water, which is very costly process. Sunlight based water warming framework is one of them and more affordable than others. The extent of the frameworks relies upon accessibility of sun-oriented radiation, temperature necessity of client, topographical condition and game plan of the nearby planetary group and so forth. The primary target of this research was converting the solar energy into thermal energy and controlling the desired hot water temperature for water heating purposes. In this paper, closed loop solar water heating system was used. A solenoid valve was used to control the supply water which will be going to the user. To control the hot water, temperature feedback control system was used which can sense the water temperature using temperature sensor. The temperature of condenser was sensed by using LM35 temperature sensor also. To increase the efficiency of the collector an additional dual-axis concentrator was used. The research was successful to increase water temperature up to 19°C and stable it.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116216899","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 : 1900-01-01DOI: 10.1109/ICREST.2019.8644079
K. Meah, Jason Forsyth, J. Moscola
An effective and efficient sensor network is an essential component of an automated urban greenhouse (AUG). This paper describes a design process that prototyped a smart sensor network as part of a capstone design project. This smart sensor network communicates among sensing, power and automation, and visualization and user interface aspects of the AUG to provide automatic monitoring of lighting, heating, watering, and ventilation. This automated urban greenhouse, along with the sensor network, is being installed at a local elementary school in downtown York, Pennsylvania. It will serve as an educational tool and create awareness of the importance of fresh foods.
{"title":"A Smart Sensor Network for an Automated Urban Greenhouse","authors":"K. Meah, Jason Forsyth, J. Moscola","doi":"10.1109/ICREST.2019.8644079","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644079","url":null,"abstract":"An effective and efficient sensor network is an essential component of an automated urban greenhouse (AUG). This paper describes a design process that prototyped a smart sensor network as part of a capstone design project. This smart sensor network communicates among sensing, power and automation, and visualization and user interface aspects of the AUG to provide automatic monitoring of lighting, heating, watering, and ventilation. This automated urban greenhouse, along with the sensor network, is being installed at a local elementary school in downtown York, Pennsylvania. It will serve as an educational tool and create awareness of the importance of fresh foods.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125647897","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 : 1900-01-01DOI: 10.1109/ICREST.2019.8644259
Md Fahim Rizwan, Rayed Farhad, Farhan Mashuk, Fakhrul Islam, M. H. Imam
This study represents a design of a detection system of stress through machine learning using some available bio signals in human body. Stress can be commonly defined as the disturbance in psychological equilibrium. Stress detection is one of the major research areas in biomedical engineering as proper detection of stress can conveniently prevent many psychological and physiological problems like cardiac rhythm abnormalities or arrhythmia. There are several bio-signals available (i.e. ECG, EMG, Respiration, GSR etc.) which are helpful in detecting stress levels as these signals shows characteristic changes with stress induction. In this paper, ECG was selected as the primary candidate because of the easily available recording (i.e. several mobile clinical grade recorders are available now in the market) and ECG feature extraction techniques. Another advantage of ECG is that respiratory signal information can also be detected form ECG which is known as EDR (ECG derived Respiration) without having separate sensor system for respiration measurement. Features of ECG signals are distinctive and collection of the signals is cost-efficient. From ECG we derived RR interval, QT interval, and EDR features for the development of the model. For the implementation of a supervised machine learning (SVM) method in MATLAB, Physionet’s "drivedb" database was used as the training dataset and validation. SVM was chosen for classification, as there are two classes of labeled data; ‘stressed’ or ‘non-stressed’. Several SVM model types were verified by changing the feature number and Kernel type. Our results showed an accuracy level of 98.6% with Gaussian Kernel function and using all available features (RR, QT and EDR), which also emphasizes the importance of respiratory information in stress detection through Machine Learning.
{"title":"Design of a Biosignal Based Stress Detection System Using Machine Learning Techniques","authors":"Md Fahim Rizwan, Rayed Farhad, Farhan Mashuk, Fakhrul Islam, M. H. Imam","doi":"10.1109/ICREST.2019.8644259","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644259","url":null,"abstract":"This study represents a design of a detection system of stress through machine learning using some available bio signals in human body. Stress can be commonly defined as the disturbance in psychological equilibrium. Stress detection is one of the major research areas in biomedical engineering as proper detection of stress can conveniently prevent many psychological and physiological problems like cardiac rhythm abnormalities or arrhythmia. There are several bio-signals available (i.e. ECG, EMG, Respiration, GSR etc.) which are helpful in detecting stress levels as these signals shows characteristic changes with stress induction. In this paper, ECG was selected as the primary candidate because of the easily available recording (i.e. several mobile clinical grade recorders are available now in the market) and ECG feature extraction techniques. Another advantage of ECG is that respiratory signal information can also be detected form ECG which is known as EDR (ECG derived Respiration) without having separate sensor system for respiration measurement. Features of ECG signals are distinctive and collection of the signals is cost-efficient. From ECG we derived RR interval, QT interval, and EDR features for the development of the model. For the implementation of a supervised machine learning (SVM) method in MATLAB, Physionet’s \"drivedb\" database was used as the training dataset and validation. SVM was chosen for classification, as there are two classes of labeled data; ‘stressed’ or ‘non-stressed’. Several SVM model types were verified by changing the feature number and Kernel type. Our results showed an accuracy level of 98.6% with Gaussian Kernel function and using all available features (RR, QT and EDR), which also emphasizes the importance of respiratory information in stress detection through Machine Learning.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125669717","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 : 1900-01-01DOI: 10.1109/ICREST.2019.8644354
Tahsin M. Rahman, Saima Siddiqua, Siam E. Rabby, Nahid Hasan, M. H. Imam
This paper introduces the idea of detecting the presence of kidney disease through machine learning based classification modelling, by processing the patient’s ECG signal. Recent studies and ongoing researches have showed that patients undergoing kidney problems start developing cardiac problems- scientifically known as the Cardio Renal Syndrome (CRS) which can lead to a sudden cardiac arrest in the last stages of their disease. Since cardio-vascular diseases and the chronic kidney disease is inter-related, this model can be used for patients undergoing cardio-vascular problems to determine whether their kidneys have been effected or not. If the Chronic Kidney Disease (CKD) can be diagnosed at an earlier stage, it may give the patient some time to help reverse the disease or at least slow its progression by taking necessary medical steps. For this model, digitized ECG data was collected from open access databases such as PTB (for kidney patients) and Fantasia (for healthy people) from Physionet Database (www.physionet.org) and the model was later validated using different data from the same online database. The validation process gave satisfactory results, as the model could successfully classify the users from being healthy or a kidney patient. In our study, we found an accuracy level of 97.6% which was the highest using both features QT and RR interval, in comparison to the accuracy that was found when either one of the features was used.
{"title":"Early Detection of Kidney Disease Using ECG Signals Through Machine Learning Based Modelling","authors":"Tahsin M. Rahman, Saima Siddiqua, Siam E. Rabby, Nahid Hasan, M. H. Imam","doi":"10.1109/ICREST.2019.8644354","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644354","url":null,"abstract":"This paper introduces the idea of detecting the presence of kidney disease through machine learning based classification modelling, by processing the patient’s ECG signal. Recent studies and ongoing researches have showed that patients undergoing kidney problems start developing cardiac problems- scientifically known as the Cardio Renal Syndrome (CRS) which can lead to a sudden cardiac arrest in the last stages of their disease. Since cardio-vascular diseases and the chronic kidney disease is inter-related, this model can be used for patients undergoing cardio-vascular problems to determine whether their kidneys have been effected or not. If the Chronic Kidney Disease (CKD) can be diagnosed at an earlier stage, it may give the patient some time to help reverse the disease or at least slow its progression by taking necessary medical steps. For this model, digitized ECG data was collected from open access databases such as PTB (for kidney patients) and Fantasia (for healthy people) from Physionet Database (www.physionet.org) and the model was later validated using different data from the same online database. The validation process gave satisfactory results, as the model could successfully classify the users from being healthy or a kidney patient. In our study, we found an accuracy level of 97.6% which was the highest using both features QT and RR interval, in comparison to the accuracy that was found when either one of the features was used.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131755348","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 : 1900-01-01DOI: 10.1109/ICREST.2019.8644306
M. Abrar, A. Hasan
Sustainable energy generation at a low cost is a great challenge for developing countries like Bangladesh. The conventional power resources are expensive and scarce. With the recent economic growth of Bangladesh, the energy demand is increasing day by day. It has become very challenging to fulfil the energy demand with the conventional energy sources. Therefore, it is required to find the alternative way for power generation with the available energy sources. The alternative resources have to be available, cheap and environmentally friendly. The electricity generation from waste is becoming popular nowadays as renewable energy sources. This paper represents the biomass potential for power generation in Chittagong city, Bangladesh through literature review and software simulation. It is found that about 49 MW of electricity can be produced from the wastes that can not only address the power lacking but also waste management system.
{"title":"Power Generation from Waste in Chittagong City, Bangladesh- A Sustainable Approach to Mitigate The Energy Crisis","authors":"M. Abrar, A. Hasan","doi":"10.1109/ICREST.2019.8644306","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644306","url":null,"abstract":"Sustainable energy generation at a low cost is a great challenge for developing countries like Bangladesh. The conventional power resources are expensive and scarce. With the recent economic growth of Bangladesh, the energy demand is increasing day by day. It has become very challenging to fulfil the energy demand with the conventional energy sources. Therefore, it is required to find the alternative way for power generation with the available energy sources. The alternative resources have to be available, cheap and environmentally friendly. The electricity generation from waste is becoming popular nowadays as renewable energy sources. This paper represents the biomass potential for power generation in Chittagong city, Bangladesh through literature review and software simulation. It is found that about 49 MW of electricity can be produced from the wastes that can not only address the power lacking but also waste management system.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133840812","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 : 1900-01-01DOI: 10.1109/ICREST.2019.8644477
Md. Mamun Hossain, T. Ahmed, Zahid Ahsan, Shuvra Saha, K. Firoz
With the exponential increase in demand of power all over the world, the limited natural fuel resources are being stressed every hour. No matter the abundance, these resources are bound to deplete completely in far future. Humankind is now moving onto such methods for electricity generation which can meet our demand and preserve the nature’s reserves simultaneously. Concentrated Solar Power (CSP) uses the heat from the Sun to produce mechanical thus electrical power. It was chosen a preexisting method (Euro Dish) and modified it to a level suitable for small-scale/personal use. This is an obstacle in the way of making this technology and method popular and usable on a mass scale, let alone on a personal scale. In this paper, stirling engine was used as a heat engine with concentrated solar power. It also shows the comparison between concentrated solar power (CSP) and photovoltaic (PV) system. The primary objective, to generate mechanical power from Stirling engine and converting it into electrical power through a dc generator of low r.p.m., was completed with minor inefficiencies and discrepancies.
{"title":"Concentrated Solar Power Dish Stirling Technology in Prospect of Energy Crisis in Bangladesh","authors":"Md. Mamun Hossain, T. Ahmed, Zahid Ahsan, Shuvra Saha, K. Firoz","doi":"10.1109/ICREST.2019.8644477","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644477","url":null,"abstract":"With the exponential increase in demand of power all over the world, the limited natural fuel resources are being stressed every hour. No matter the abundance, these resources are bound to deplete completely in far future. Humankind is now moving onto such methods for electricity generation which can meet our demand and preserve the nature’s reserves simultaneously. Concentrated Solar Power (CSP) uses the heat from the Sun to produce mechanical thus electrical power. It was chosen a preexisting method (Euro Dish) and modified it to a level suitable for small-scale/personal use. This is an obstacle in the way of making this technology and method popular and usable on a mass scale, let alone on a personal scale. In this paper, stirling engine was used as a heat engine with concentrated solar power. It also shows the comparison between concentrated solar power (CSP) and photovoltaic (PV) system. The primary objective, to generate mechanical power from Stirling engine and converting it into electrical power through a dc generator of low r.p.m., was completed with minor inefficiencies and discrepancies.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116911681","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 : 1900-01-01DOI: 10.1109/ICREST.2019.8644194
Md. Hasan Al Banna, Md Ali Haider, Md. Jaber Al Nahian, M. Islam, K. A. Taher, M. S. Kaiser
The forensic investigation on digital images is to assess the authenticity of images without the embedded security on the images. The camera model identification is the first step for image forensic investigation. The paper proposes the deep Convolutional Neural Network and transfer learning approach for extracting features from an images dataset. An open image dataset of 3900 images have been created using three camera models. Three state-of-the-art machine learning algorithms such as SVM, logistic regression and random forest based classifiers have been used for evaluating identification accuracy.
{"title":"Camera Model Identification using Deep CNN and Transfer Learning Approach","authors":"Md. Hasan Al Banna, Md Ali Haider, Md. Jaber Al Nahian, M. Islam, K. A. Taher, M. S. Kaiser","doi":"10.1109/ICREST.2019.8644194","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644194","url":null,"abstract":"The forensic investigation on digital images is to assess the authenticity of images without the embedded security on the images. The camera model identification is the first step for image forensic investigation. The paper proposes the deep Convolutional Neural Network and transfer learning approach for extracting features from an images dataset. An open image dataset of 3900 images have been created using three camera models. Three state-of-the-art machine learning algorithms such as SVM, logistic regression and random forest based classifiers have been used for evaluating identification accuracy.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116920888","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 : 1900-01-01DOI: 10.1109/ICREST.2019.8644474
Azril Haniz, G. Tran, K. Sakaguchi, J. Takada, Toshihiro Yamaguchi, T. Mitsui, S. Arata
A radio map can be generally defined as a database which contains comprehensive information of radio propagation channel parameters. Due to local spectrum regulations, radio map operators may be unable to transmit radio waves at certain frequency bands, thus preventing the construction of radio maps through direct measurements. This paper proposes a regression-based method to predict the radio map at an arbitrary center frequency using a multi-frequency radio map. A measurement campaign was conducted in a university campus, where radio maps at two center frequencies were utilized to predict the radio map at a different frequency. Results showed that the proposed technique could achieve a root mean squared error (RMSE) of about 2:5 dB on average, which is roughly 5 dB lower than the RMSE when using conventional techniques.
{"title":"Construction and Interpolation of a Multi-frequency Radio Map","authors":"Azril Haniz, G. Tran, K. Sakaguchi, J. Takada, Toshihiro Yamaguchi, T. Mitsui, S. Arata","doi":"10.1109/ICREST.2019.8644474","DOIUrl":"https://doi.org/10.1109/ICREST.2019.8644474","url":null,"abstract":"A radio map can be generally defined as a database which contains comprehensive information of radio propagation channel parameters. Due to local spectrum regulations, radio map operators may be unable to transmit radio waves at certain frequency bands, thus preventing the construction of radio maps through direct measurements. This paper proposes a regression-based method to predict the radio map at an arbitrary center frequency using a multi-frequency radio map. A measurement campaign was conducted in a university campus, where radio maps at two center frequencies were utilized to predict the radio map at a different frequency. Results showed that the proposed technique could achieve a root mean squared error (RMSE) of about 2:5 dB on average, which is roughly 5 dB lower than the RMSE when using conventional techniques.","PeriodicalId":108842,"journal":{"name":"2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126595771","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：