1.
Mohamed Baza, Andrew Salazar, Mohamed Mahmoud, Mohamed Abdallah, Kemal Akkaya
On sharing models instead of data using mimic learning for smart health applications Proceedings Article
In: 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT), pp. 231–236, IEEE, 2020.
Abstract | Links | BibTeX | Tags: Data Science/Management
@inproceedings{nokey,
title = {On sharing models instead of data using mimic learning for smart health applications},
author = {Mohamed Baza and Andrew Salazar and Mohamed Mahmoud and Mohamed Abdallah and Kemal Akkaya},
url = {https://ieeexplore.ieee.org/abstract/document/9089457/},
year = {2020},
date = {2020-02-02},
booktitle = {2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT)},
pages = {231–236},
publisher = {IEEE},
school = {Florida International University},
abstract = {Electronic health records (EHR) systems contain vast amounts of medical information about patients. These data can be used to train machine learning models that can predict health status, as well as to help prevent future diseases or disabilities. However, getting patients' medical data to obtain well-trained machine learning models is a challenging task. This is because sharing the patients' medical records is prohibited by law in most countries due to patients privacy concerns. In this paper, we tackle this problem by sharing the models instead of the original sensitive data by using the mimic learning approach. The idea is first to train a model on the original sensitive data, called the teacher model. Then, using this model, we can transfer its knowledge to another model, called the student model, without the need to learn the original data used in training the teacher model. The student model is then shared to the},
keywords = {Data Science/Management},
pubstate = {published},
tppubtype = {inproceedings}
}
Electronic health records (EHR) systems contain vast amounts of medical information about patients. These data can be used to train machine learning models that can predict health status, as well as to help prevent future diseases or disabilities. However, getting patients' medical data to obtain well-trained machine learning models is a challenging task. This is because sharing the patients' medical records is prohibited by law in most countries due to patients privacy concerns. In this paper, we tackle this problem by sharing the models instead of the original sensitive data by using the mimic learning approach. The idea is first to train a model on the original sensitive data, called the teacher model. Then, using this model, we can transfer its knowledge to another model, called the student model, without the need to learn the original data used in training the teacher model. The student model is then shared to the
2.
Kemal Akkaya, Murat Demirbas, R Savas Aygun
The impact of data aggregation sensor networks on the performance of wireless Journal Article
In: WIRELESS COMMUNICATIONS & MOBILE COMPUTING, vol. 8, iss. 2, no. 2, pp. 171–193, 2008.
Abstract | Links | BibTeX | Tags: Data Science/Management
@article{nokey,
title = {The impact of data aggregation sensor networks on the performance of wireless},
author = {Kemal Akkaya and Murat Demirbas and R Savas Aygun},
url = {https://scholar.google.com/scholar?cluster=4617247807715070526&hl=en&oi=scholarr},
year = {2008},
date = {2008-02-01},
journal = {WIRELESS COMMUNICATIONS & MOBILE COMPUTING},
volume = {8},
number = {2},
issue = {2},
pages = {171–193},
publisher = {WILEY-BLACKWELL},
school = {Florida International University},
abstract = {With the increasing need for different energy saving mechanisms in Wireless Sensor Networks (WSNs), data aggregation techniques for reducing the number of data transmissions by eliminating redundant information have been studied as a significant research problem. These studies have shown that data aggregation in WSNs may produce various trade-offs among some network related performance metrics such as energy, latency, accuracy, fault-tolerance and security. In this paper, we investigate the impact of data aggregation on these networking metrics by surveying the existing data aggregation protocols in WSNs. Our aim is twofold: First, providing a comprehensive summary and comparison of the existing data aggregation techniques with respect to different networking metrics. Second, pointing out both the possible future research issues and the need for collaboration between data management and},
keywords = {Data Science/Management},
pubstate = {published},
tppubtype = {article}
}
With the increasing need for different energy saving mechanisms in Wireless Sensor Networks (WSNs), data aggregation techniques for reducing the number of data transmissions by eliminating redundant information have been studied as a significant research problem. These studies have shown that data aggregation in WSNs may produce various trade-offs among some network related performance metrics such as energy, latency, accuracy, fault-tolerance and security. In this paper, we investigate the impact of data aggregation on these networking metrics by surveying the existing data aggregation protocols in WSNs. Our aim is twofold: First, providing a comprehensive summary and comparison of the existing data aggregation techniques with respect to different networking metrics. Second, pointing out both the possible future research issues and the need for collaboration between data management and
3.
Kemal Akkaya, Ismail Ari
In-network data aggregation in wireless sensor networks Journal Article
In: Handbook of Computer Networks: LANs, MANs, WANs, the Internet, and Global, Cellular, and Wireless Networks. Wiley Online Library, vol. 2, pp. 1131–1146, 2007.
Abstract | Links | BibTeX | Tags: Data Science/Management
@article{nokey,
title = {In-network data aggregation in wireless sensor networks},
author = {Kemal Akkaya and Ismail Ari},
url = {https://www.researchgate.net/profile/Ismail-Ari/publication/286733183_In-Network_Data_Aggregation_in_Wireless_Sensor_Networks/links/5e0daff14585159aa4ab72d7/In-Network-Data-Aggregation-in-Wireless-Sensor-Networks.pdf},
year = {2007},
date = {2007-11-23},
journal = {Handbook of Computer Networks: LANs, MANs, WANs, the Internet, and Global, Cellular, and Wireless Networks. Wiley Online Library},
volume = {2},
pages = {1131–1146},
school = {Florida International University},
abstract = {Advances in microelectronics have enabled the development of exceptionally tiny sensor nodes that have the ability of measuring ambient conditions such as temperature, pressure, humidity, light intensity, and motion (Akyildiz et al. 2002). The sensed data can then be transmitted through an on-board radio transmitter to a single or multiple base stations (BSs) where it can be further processed. The tiny size and inexpensive cost of such emerging sensor nodes has encouraged practitioners to explore using them collaboratively in a network formed in ad hoc manner. Such networked sensor system not only is cost-effective but also can provide fast and accurate information gathering in remote and risky areas. Figure 1 depicts a typical sensor network architecture. The BS acts as a gateway for linking the sensors to multiple command nodes.The past few years have witnessed increased interest in the potential use of wireless sensor networks (WSNs) in applications such as disaster management, combat field reconnaissance, border protection, and security surveillance (Mainwaring et al. 2002; Burrell, Brooke, and Beckwith 2004; Agora et al. 2004, 2005). It is envisioned that WSNs will be part of the future Internet where real-time information will be queried through sensors deployed almost everywhere in our living environments. This direction suggests that gathering and processing large volumes of data from WSNs will continue to be one of the most important problems for researchers in coming years. However, because sensors have severe resource constraints in terms of power, processing capability, memory, and storage, it is challenging to},
keywords = {Data Science/Management},
pubstate = {published},
tppubtype = {article}
}
Advances in microelectronics have enabled the development of exceptionally tiny sensor nodes that have the ability of measuring ambient conditions such as temperature, pressure, humidity, light intensity, and motion (Akyildiz et al. 2002). The sensed data can then be transmitted through an on-board radio transmitter to a single or multiple base stations (BSs) where it can be further processed. The tiny size and inexpensive cost of such emerging sensor nodes has encouraged practitioners to explore using them collaboratively in a network formed in ad hoc manner. Such networked sensor system not only is cost-effective but also can provide fast and accurate information gathering in remote and risky areas. Figure 1 depicts a typical sensor network architecture. The BS acts as a gateway for linking the sensors to multiple command nodes.The past few years have witnessed increased interest in the potential use of wireless sensor networks (WSNs) in applications such as disaster management, combat field reconnaissance, border protection, and security surveillance (Mainwaring et al. 2002; Burrell, Brooke, and Beckwith 2004; Agora et al. 2004, 2005). It is envisioned that WSNs will be part of the future Internet where real-time information will be queried through sensors deployed almost everywhere in our living environments. This direction suggests that gathering and processing large volumes of data from WSNs will continue to be one of the most important problems for researchers in coming years. However, because sensors have severe resource constraints in terms of power, processing capability, memory, and storage, it is challenging to
Citations: 18671
h-index: 54
i10-index: 162