ORCID Profile
0000-0002-3846-6282
Current Organisations
CSIRO Energy
,
CSIRO
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: IOP Publishing
Date: 07-2021
DOI: 10.1088/1742-6596/1962/1/012016
Abstract: Manual irrigation is still widely used in agricultural field using traditional drip and can watering. However, traditional irrigation systems are inefficient and inexact, leading to either insufficient or excessive watering. Moreover, it is difficult for farmers to predict suitable quantities at the appropriate time. Manual monitoring of the crop field may also lead to human error and is potentially risky for rural areas. Farmers may also not be aware of intrusions if they are not on location. Therefore, this project is designed to develop a smart monitoring and automated irrigation system to provide not only efficient water consumption based on specific conditions, but also enables real-time monitoring of the environment. Furthermore, this system prevents damage to plants and reduces the likelihood of plant theft. This system uses NodeMCU ESP32 as a microcontroller that collects environmental data such as humidity, temperature, soil moisture levels from sensors. The NodeMCU is integrated with a relay and RTC module to irrigate plants at specific times and is also equipped with a passive infrared sensor to detect intruders near the crop-field. Upon detection, an ESP32 camera is used to automatically capture the current conditions and farmers will be subsequently notified. Warnings are also sent to farmers upon detection of unwanted circumstances such as extreme temperature, which could prevent instances of open burning. The utility of the developed prototype is evident in the way it automatically irrigates the crop field without human intervention. Farmers may monitor and manually control the irrigation process using an attached Android application. Additionally, they may manually activate a buzzer warn off any potential malicious actors.
Publisher: IEEE
Date: 11-2009
Publisher: IEEE
Date: 08-2021
Publisher: IEEE
Date: 12-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2023
Publisher: Elsevier BV
Date: 2016
Publisher: Springer Science and Business Media LLC
Date: 06-07-2012
Publisher: Inderscience Publishers
Date: 2018
Publisher: IEEE
Date: 07-2010
DOI: 10.1109/NCA.2010.46
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2020
Publisher: Elsevier BV
Date: 02-2022
Publisher: IOP Publishing
Date: 07-2021
DOI: 10.1088/1742-6596/1962/1/012051
Abstract: Coronavirus (COVID-19) is an alarming disease outbreak that has affected more than 180 countries worldwide. It has caused close to 2.5 million deaths and has infected 114 million of the global population as of February 2021. This unprecedented pandemic, has caused severe socio-economic problems globally, catching many sectors off-guard and in a state of suspended uncertainty. While vaccines are just starting to circulate, there is still a need to practice new social norms, including social distancing during daily activities such as supermarket shopping. As such, contactless technology is critically needed and preferable to minimize physical contact and mitigate virus spread. In this paper, an automated shopping cart is proposed as a potential solution to avoid item scanning at cashiers and long queues at payment counters. This innovation leads to reduced risk of exposure to COVID-19. This is done by integrating a typical shopping trolley with Internet of Things (IoT) technology. A radio frequency identification (RFID) tag is attached to every product and automatically read whenever they are placed in a shopping cart. Payment and weighing processes can be conducted at the trolley itself which reduces direct and prolonged contact with both cashiers and other patrons, and at both checkout queues and weighing counters. This proves to be a critical way to break transmission chains.
Publisher: IEEE
Date: 12-2010
Publisher: Elsevier BV
Date: 12-2017
Publisher: IEEE
Date: 08-2011
DOI: 10.1109/NCA.2011.40
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2013
Publisher: MDPI AG
Date: 27-04-2023
DOI: 10.3390/S23094346
Abstract: The use of artificial intelligence (AI) to detect phishing emails is primarily dependent on large-scale centralized datasets, which has opened it up to a myriad of privacy, trust, and legal issues. Moreover, organizations have been loath to share emails, given the risk of leaking commercially sensitive information. Consequently, it has been difficult to obtain sufficient emails to train a global AI model efficiently. Accordingly, privacy-preserving distributed and collaborative machine learning, particularly federated learning (FL), is a desideratum. As it is already prevalent in the healthcare sector, questions remain regarding the effectiveness and efficacy of FL-based phishing detection within the context of multi-organization collaborations. To the best of our knowledge, the work herein was the first to investigate the use of FL in phishing email detection. This study focused on building upon a deep neural network model, particularly recurrent convolutional neural network (RNN) and bidirectional encoder representations from transformers (BERT), for phishing email detection. We analyzed the FL-entangled learning performance in various settings, including (i) a balanced and asymmetrical data distribution among organizations and (ii) scalability. Our results corroborated the comparable performance statistics of FL in phishing email detection to centralized learning for balanced datasets and low organizational counts. Moreover, we observed a variation in performance when increasing the organizational counts. For a fixed total email dataset, the global RNN-based model had a 1.8% accuracy decrease when the organizational counts were increased from 2 to 10. In contrast, BERT accuracy increased by 0.6% when increasing organizational counts from 2 to 5. However, if we increased the overall email dataset by introducing new organizations in the FL framework, the organizational level performance improved by achieving a faster convergence speed. In addition, FL suffered in its overall global model performance due to highly unstable outputs if the email dataset distribution was highly asymmetric.
Location: Australia
No related grants have been discovered for Mahathir Almashor.