Performance evaluation of baseline-dependent window functions with several weighing functions
- Authors: Vanqa, Kamvulethu
- Date: 2024-04-04
- Subjects: Radio interferometers , Data compression (Computer science) , Window function , Gradient descent , Computer algorithms , Time smearing
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/435850 , vital:73206
- Description: Radio interferometric data volume is exponentially increasing with the potential to cause slow processing and data storage issues for radio observations recorded at high time and frequency resolutions. This necessitates that a sort of data compression is imposed. The conventional method to compress the data is averaging across time and frequency. However, this results in amplitude loss and source distortion at the edges of the field of view. To reduce amplitude loss and source distortion, baseline-dependent window functions (BDWFs) are proposed in theliterature. BDWFs are visibility data compression methods using window functions to retainthe signals within a field of interest (FoI) and to suppress signals outside this FoI. However,BDWFs are used with window functions as discussed in the signal processing field without any optimisation. This thesis evaluates the performance of BDWFs and then proposes to use machine learning with gradient descent to optimize the window functions employed in BDWFs. Results show that the convergence of the objective function is limited due to the band-limited nature of the window functions in the Fourier space. BDWFs performance is also investigated and discussed using several weighting schemes. Results show that there exists an optimal parameter tuning (not necessarily unique) that suggests an optimal combination of BDWFs and density sampling. With this, ∼ 4 % smearing is observed within the FoI, and ∼ 80 % source suppression is achieved outside the FoI using the MeerKAT telescope at 1.4 GHz, sampled at 1 s and 184.3 kHz then averaged with BDWFs to achieve a compression factor of 4 in time and 3 in frequency. , Thesis (MA) -- Faculty of Science, Mathematics, 2024
- Full Text:
- Date Issued: 2024-04-04
- Authors: Vanqa, Kamvulethu
- Date: 2024-04-04
- Subjects: Radio interferometers , Data compression (Computer science) , Window function , Gradient descent , Computer algorithms , Time smearing
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/435850 , vital:73206
- Description: Radio interferometric data volume is exponentially increasing with the potential to cause slow processing and data storage issues for radio observations recorded at high time and frequency resolutions. This necessitates that a sort of data compression is imposed. The conventional method to compress the data is averaging across time and frequency. However, this results in amplitude loss and source distortion at the edges of the field of view. To reduce amplitude loss and source distortion, baseline-dependent window functions (BDWFs) are proposed in theliterature. BDWFs are visibility data compression methods using window functions to retainthe signals within a field of interest (FoI) and to suppress signals outside this FoI. However,BDWFs are used with window functions as discussed in the signal processing field without any optimisation. This thesis evaluates the performance of BDWFs and then proposes to use machine learning with gradient descent to optimize the window functions employed in BDWFs. Results show that the convergence of the objective function is limited due to the band-limited nature of the window functions in the Fourier space. BDWFs performance is also investigated and discussed using several weighting schemes. Results show that there exists an optimal parameter tuning (not necessarily unique) that suggests an optimal combination of BDWFs and density sampling. With this, ∼ 4 % smearing is observed within the FoI, and ∼ 80 % source suppression is achieved outside the FoI using the MeerKAT telescope at 1.4 GHz, sampled at 1 s and 184.3 kHz then averaged with BDWFs to achieve a compression factor of 4 in time and 3 in frequency. , Thesis (MA) -- Faculty of Science, Mathematics, 2024
- Full Text:
- Date Issued: 2024-04-04
Towards an artificial intelligence-based agent for characterising the organisation of primes
- Authors: Oyetunji, Nicole Armlade
- Date: 2024-04-04
- Subjects: Numbers, Prime , Odd number , Machine learning , Deep learning (Machine learning) , Mathematical forecasting , Neural networks (Computer science) , Artificial intelligence
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/435389 , vital:73153
- Description: Machine learning has experienced significant growth in recent decades, driven by advancements in computational power and data storage. One of the applications of machine learning is in the field of number theory. Prime numbers hold significant importance in mathematics and its applications, for example in cryptography, owing to their distinct properties. Therefore, it is crucial to efficiently obtain the complete list of primes below a given threshold, with low relatively computational cost. This study extensively explores a deterministic scheme, proposed by Hawing and Okouma (2016), that is centered around Consecutive Composite Odd Numbers, showing the link between these numbers and prime numbers by examining their internal structure. The main objective of this dissertation is to develop two main artificial intelligence agents capable of learning and recognizing patterns within a list of consecutive composite odd numbers. To achieve this, the mathematical foundations of the deterministic scheme are used to generate a dataset of consecutive composite odd numbers. This dataset is further transformed into a dataset of differences to simplify the prediction problem. A literature review is conducted which encompasses research from the domains of machine learning and deep learning. Two main machine learning algorithms are implemented along with their variations, Long Short-Term Memory Networks and Error Correction Neural Networks. These models are trained independently on two separate but related datasets, the dataset of consecutive composite odd numbers and the dataset of differences between those numbers. The evaluation of these models includes relevant metrics, for example, Root Mean Square Error, Mean Absolute Percentage Error, Theil U coefficient, and Directional Accuracy. Through a comparative analysis, the study identifies the top-performing 3 models, with a particular emphasis on accuracy and computational efficiency. The results indicate that the LSTM model, when trained on difference data and coupled with exponential smoothing, displays superior performance as the most accurate model overall. It achieves a RMSE of 0.08, which significantly outperforms the dataset’s standard deviation of 0.42. This model exceeds the performance of basic estimator models, implying that a data-driven approach utilizing machine learning techniques can provide valuable insights in the field of number theory. The second best model, the ECNN trained on difference data combined with exponential smoothing, achieves an RMSE of 0.28. However, it is worth mentioning that this model is the most computationally efficient, being 32 times faster than the LSTM model. , Thesis (MSc) -- Faculty of Science, Mathematics, 2024
- Full Text:
- Date Issued: 2024-04-04
- Authors: Oyetunji, Nicole Armlade
- Date: 2024-04-04
- Subjects: Numbers, Prime , Odd number , Machine learning , Deep learning (Machine learning) , Mathematical forecasting , Neural networks (Computer science) , Artificial intelligence
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/435389 , vital:73153
- Description: Machine learning has experienced significant growth in recent decades, driven by advancements in computational power and data storage. One of the applications of machine learning is in the field of number theory. Prime numbers hold significant importance in mathematics and its applications, for example in cryptography, owing to their distinct properties. Therefore, it is crucial to efficiently obtain the complete list of primes below a given threshold, with low relatively computational cost. This study extensively explores a deterministic scheme, proposed by Hawing and Okouma (2016), that is centered around Consecutive Composite Odd Numbers, showing the link between these numbers and prime numbers by examining their internal structure. The main objective of this dissertation is to develop two main artificial intelligence agents capable of learning and recognizing patterns within a list of consecutive composite odd numbers. To achieve this, the mathematical foundations of the deterministic scheme are used to generate a dataset of consecutive composite odd numbers. This dataset is further transformed into a dataset of differences to simplify the prediction problem. A literature review is conducted which encompasses research from the domains of machine learning and deep learning. Two main machine learning algorithms are implemented along with their variations, Long Short-Term Memory Networks and Error Correction Neural Networks. These models are trained independently on two separate but related datasets, the dataset of consecutive composite odd numbers and the dataset of differences between those numbers. The evaluation of these models includes relevant metrics, for example, Root Mean Square Error, Mean Absolute Percentage Error, Theil U coefficient, and Directional Accuracy. Through a comparative analysis, the study identifies the top-performing 3 models, with a particular emphasis on accuracy and computational efficiency. The results indicate that the LSTM model, when trained on difference data and coupled with exponential smoothing, displays superior performance as the most accurate model overall. It achieves a RMSE of 0.08, which significantly outperforms the dataset’s standard deviation of 0.42. This model exceeds the performance of basic estimator models, implying that a data-driven approach utilizing machine learning techniques can provide valuable insights in the field of number theory. The second best model, the ECNN trained on difference data combined with exponential smoothing, achieves an RMSE of 0.28. However, it is worth mentioning that this model is the most computationally efficient, being 32 times faster than the LSTM model. , Thesis (MSc) -- Faculty of Science, Mathematics, 2024
- Full Text:
- Date Issued: 2024-04-04
Selected medicinal plants leaves identification: a computer vision approach
- Authors: Deyi, Avuya
- Date: 2023-10-13
- Subjects: Deep learning (Machine learning) , Machine learning , Convolutional neural network , Computer vision in medicine , Medicinal plants
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/424552 , vital:72163
- Description: Identifying and classifying medicinal plants are valuable and essential skills during drug manufacturing because several active pharmaceutical ingredients (API) are sourced from medicinal plants. For many years, identifying and classifying medicinal plants have been exclusively done by experts in the domain, such as botanists, and herbarium curators. Recently, powerful computer vision technologies, using machine learning and deep convolutional neural networks, have been developed for classifying or identifying objects on images. A convolutional neural network is a deep learning architecture that outperforms previous advanced approaches in image classification and object detection based on its efficient features extraction on images. In this thesis, we investigate different convolutional neural networks and machine learning algorithms for identifying and classifying leaves of three species of the genus Brachylaena. The three species considered are Brachylaena discolor, Brachylaena ilicifolia and Brachylaena elliptica. All three species are used medicinally by people in South Africa to treat diseases like diabetes. From 1259 labelled images of those plants species (at least 400 for each species) split into training, evaluation and test sets, we trained and evaluated different deep convolutional neural networks and machine learning models. The VGG model achieved the best results with 98.26% accuracy from cross-validation. , Thesis (MSc) -- Faculty of Science, Mathematics, 2023
- Full Text:
- Date Issued: 2023-10-13
- Authors: Deyi, Avuya
- Date: 2023-10-13
- Subjects: Deep learning (Machine learning) , Machine learning , Convolutional neural network , Computer vision in medicine , Medicinal plants
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/424552 , vital:72163
- Description: Identifying and classifying medicinal plants are valuable and essential skills during drug manufacturing because several active pharmaceutical ingredients (API) are sourced from medicinal plants. For many years, identifying and classifying medicinal plants have been exclusively done by experts in the domain, such as botanists, and herbarium curators. Recently, powerful computer vision technologies, using machine learning and deep convolutional neural networks, have been developed for classifying or identifying objects on images. A convolutional neural network is a deep learning architecture that outperforms previous advanced approaches in image classification and object detection based on its efficient features extraction on images. In this thesis, we investigate different convolutional neural networks and machine learning algorithms for identifying and classifying leaves of three species of the genus Brachylaena. The three species considered are Brachylaena discolor, Brachylaena ilicifolia and Brachylaena elliptica. All three species are used medicinally by people in South Africa to treat diseases like diabetes. From 1259 labelled images of those plants species (at least 400 for each species) split into training, evaluation and test sets, we trained and evaluated different deep convolutional neural networks and machine learning models. The VGG model achieved the best results with 98.26% accuracy from cross-validation. , Thesis (MSc) -- Faculty of Science, Mathematics, 2023
- Full Text:
- Date Issued: 2023-10-13
Semantic segmentation of astronomical radio images: a computer vision approach
- Authors: Kupa, Ramadimetse Sydil
- Date: 2023-03-29
- Subjects: Semantic segmentation , Radio astronomy , Radio telescopes , Deep learning (Machine learning) , Image segmentation
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/422378 , vital:71937
- Description: The new generation of radio telescopes, such as the MeerKAT, ASKAP (Australian Square Kilometre Array Pathfinder) and the future Square Kilometre Array (SKA), are expected to produce vast amounts of data and images in the petabyte region. Therefore, the amount of incoming data at a specific point in time will overwhelm any current traditional data analysis method being deployed. Deep learning architectures have been applied in many fields, such as, in computer vision, machine vision, natural language processing, social network filtering, speech recognition, machine translation, bioinformatics, medical image analysis, and board game programs. They have produced results which are comparable to human expert performance. Hence, it is appealing to apply it to radio astronomy data. Image segmentation is one such area where deep learning techniques are prominent. The images from the new generation of telescopes have a high density of radio sources, making it difficult to classify the sources in the image. Identifying and segmenting sources from radio images is a pre-processing step that occurs before sources are put into different classes. There is thus a need for automatic segmentation of the sources from the images before they can be classified. This work uses the Unet architecture (originally developed for biomedical image segmentation) to segment radio sources from radio astronomical images with 99.8% accuracy. After segmenting the sources we use OpenCV tools to detect the sources on the mask images, then the detection is translated to the original image where borders are drawn around each detected source. This process automates and simplifies the pre-processing of images for classification tools and any other post-processing tool that requires a specific source as an input. , Thesis (MSc) -- Faculty of Science, Physics and Electronics, 2023
- Full Text:
- Date Issued: 2023-03-29
- Authors: Kupa, Ramadimetse Sydil
- Date: 2023-03-29
- Subjects: Semantic segmentation , Radio astronomy , Radio telescopes , Deep learning (Machine learning) , Image segmentation
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/422378 , vital:71937
- Description: The new generation of radio telescopes, such as the MeerKAT, ASKAP (Australian Square Kilometre Array Pathfinder) and the future Square Kilometre Array (SKA), are expected to produce vast amounts of data and images in the petabyte region. Therefore, the amount of incoming data at a specific point in time will overwhelm any current traditional data analysis method being deployed. Deep learning architectures have been applied in many fields, such as, in computer vision, machine vision, natural language processing, social network filtering, speech recognition, machine translation, bioinformatics, medical image analysis, and board game programs. They have produced results which are comparable to human expert performance. Hence, it is appealing to apply it to radio astronomy data. Image segmentation is one such area where deep learning techniques are prominent. The images from the new generation of telescopes have a high density of radio sources, making it difficult to classify the sources in the image. Identifying and segmenting sources from radio images is a pre-processing step that occurs before sources are put into different classes. There is thus a need for automatic segmentation of the sources from the images before they can be classified. This work uses the Unet architecture (originally developed for biomedical image segmentation) to segment radio sources from radio astronomical images with 99.8% accuracy. After segmenting the sources we use OpenCV tools to detect the sources on the mask images, then the detection is translated to the original image where borders are drawn around each detected source. This process automates and simplifies the pre-processing of images for classification tools and any other post-processing tool that requires a specific source as an input. , Thesis (MSc) -- Faculty of Science, Physics and Electronics, 2023
- Full Text:
- Date Issued: 2023-03-29
- «
- ‹
- 1
- ›
- »