Alireza PourafzalChalmers University of Technology
Alireza Pourafzal
PhD in ICT
About
24
Publications
2,386
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
33
Citations
Introduction
Education
September 2016 - February 2019
September 2012 - September 2016
Publications
Publications (24)
preprint version can be found in:
https://doi.org/10.36227/techrxiv.21915093.v1 #############################################################
A novel low-cost microwave sensor system is proposed for accurate sensing of the real relative permittivity of materials under test (MUT). The proposed solution eliminates the need for using advanced measure...
In our recent publication, we introduce a novel frequency estimation method for one-dimensional complex signals in complex white Gaussian noise, named Low complexity Unitary Principal-singular-vector Utilization for Model Analysis (LUPUMA). This method stands out due to its low space and time complexity, offering uniform estimation variance across...
Vertical cavity surface-emitting laser (VCSEL)-based optical interconnects (OI) are crucial for high-speed data transmission in data centers, supercomputers, and vehicles, yet their performance is challenged by harsh and fluctuating thermal conditions. This paper addresses these challenges by integrating an ordinary differential equation (ODE) solv...
We're excited to present the initial pre-release (beta version) of the RFID Communication Simulation. This version is a significant step in our ongoing project, providing a sneak peek into our comprehensive simulation tool for RFID signal transmission in various real-world scenarios.
Note: This is a pre-release version, which means it is not yet p...
A novel low-cost microwave sensor system is proposed for accurate sensing of the real relative permittivity of materials under test (MUT). The proposed solution eliminates the need for using advanced measurement devices such as the vector network analyzer (VNA) for sensor characterization. The proposed sensor system is built on a software-defined r...
A novel low-cost microwave sensor system is proposed for accurate sensing of the real relative permittivity of materials under test (MUT). The proposed solution eliminates the need for using advanced measurement devices such as the vector network analyzer (VNA) for sensor characterization. The proposed sensor system is built on a software-defined r...
A deep learning method is developed for chaotic time series classification. We investigate the chaotic state of a dynamical system, based on the output of the system. One of the main obstacles in time series classification is mapping a high-dimensional vector into a scalar value. To reduce the dimensions, it is common to use an average pooling laye...
In this work, a hybrid radio frequency (RF)- and acoustic-based activity recognition system was developed to demonstrate the advantage of combining two non-invasive sensors in Human Activity Recognition (HAR) systems and smart assisted living. We used a hybrid approach, employing RF and acoustic signals to recognize falling, walking, sitting on a c...
In this paper, the problem of entropy-based classification of time-series into stochastic, chaotic, and periodic is addressed, followed by proposing an alternative joint-entropy approach to time series classification. These data-driven methods describe the behavior of a signal, using the association of the entropy of a time-series with emergence an...
In this paper, a more accurate diagonal approximation of the covariance matrix in the frequency domain is investigated. For this purpose, First, the frequency snapshot model approximation is revised and the imposed error between the approximated and true value is formulated. Then, by using Taylor series, the problem of inverse matrix approximation...
Chaotic behavior may be observed in many natural and human-made time series, thus one of the first things to acquire is the knowledge on their chaotic behavior. Several approaches including model-based and data-driven classifications are utilized to address this issue; however, the computational burden arisen with the higher performance seems to be...
Questions
Questions (2)
Are deep learning models really the key to unlocking hidden insights in time series data, or are they just overhyped? And what about classic approaches like ARMA - are they still relevant in today's world of machine learning? Please join the conversation and share your valuable insights and perspectives on the power and limitations of deep learning in time series analysis, and whether we should be looking towards alternative approaches.
As the use of machine learning continues to expand across industries, it's important to understand the challenges that come with implementing these models in real-world applications. Whether it's issues with data quality, interpretability, or scalability, it's crucial to be aware of the potential roadblocks and ways to overcome them. That's why I'm reaching out to the ResearchGate community to ask: what are the main challenges in implementing machine learning models in real-world applications, and how can they be addressed? I'm particularly interested in hearing from researchers and practitioners who have experience in this area, and I believe this discussion could be valuable to anyone who is working with or considering using machine learning in their own work.
Thank you in advance for your insights and contributions!