In the thesis, we aimed at building a robust UAV(drone) detection algorithm through which, one drone could detect another drone in flight. Though this was a straight forward object detection problem, the biggest challenge we faced for drone detection is the limited amount of drone images for training. To address this issue, we used Generative Adversarial Networks, CycleGAN to be precise, for the generation of realistic looking fake images which were indistinguishable from real data. CycleGAN is a classic example of Image to Image Translation technique, and we this applied in our situation where synthetic images from one domain were transformed into another domain, containing real data. The model, once trained, was capable of generating realistic looking images from synthetic data without the presence of real images. Following this, we employed a state of the art object detection model, YOLO(You Only Look Once), to build a Drone Detection model that was trained on the generated images. Finally, the performance of this model was compared against different datasets in order to evaluate its performance. / Master of Science / In the recent years, technologies like Deep Learning and Machine Learning have seen many rapid developments. Among the many applications they have, object detection is one of the widely used application and well established problems. In our thesis, we deal with a scenario where we have a swarm of drones and our aim is for one drone to recognize another drone in its field of vision. As there was no drone image dataset readily available, we explored different ways of generating realistic data to address this issue. Finally, we proposed a solution to generate realistic images using Deep Learning techniques and trained an object detection model on it where we evaluated how well it has performed against other models.

In this work, we present different deep learning-based digital pre-distorters and compare them based on their performance towards improving the linearity of highly non-linear power amplifiers. The simulation results show that BiLSTM based DPDs work the best in terms of improving the linearity performance. We also compare two methodologies of direct learning and indirect learning to develop deep learning-based digital pre-distorters (DL-DPDs) models and evaluate their improvement on the linearity of Power Amplifiers (PA). We carry out a theoretical analysis on the differences between these training methodologies and verify their performance with simulation results on class-AB and class-F⁻¹ PAs. The simulation results show that both the learning methods lead to an improvement of more than 12 dB and 11dB in the linearity of class-AB and class-F⁻¹ PAs respectively, with indirect learning DL-DPD offering marginally better performance. Moreover, we compare the DL-DPD with memory polynomial models and show that using the former gives a significant improvement over the memory polynomials. Furthermore, we discuss the advantages of exploiting a BiLSTM based neural network architecture for designing direct/indirect DPDs. We demonstrate that BiLSTM DPD can be used to pre distort signals of any size without the drop in linearity. Moreover, based on the insights we develop a frequency domain loss using which further increased the linearity of the PA. / Master of Science / Wireless communication devices have fundamentally changed the way we interact with people. This increased the user's reliance on communication devices and significantly grew the need for higher data rates and faster internet speeds. But one major obstacle inside the transmitter chain (antenna) with increasing the data rates is the power amplifier, which distorts the signals at these higher powers. This distortion will reduce the efficiency and reliability of communication systems, greatly decreasing the quality of communication. So, we developed a high-performance DPD using deep learning to combat this issue. In this paper, we compare different deep learning-based DPDs and analyze which offers better performance. We also contrast two training methodologies to learn these DL-DPDs, theoretically and with simulation to arrive at which method offers better performing DPDs. We do these experiments on two different types of power amplifiers, and signals of any length. We design a new loss function, such that optimizing it leads to better DL-DPDs.

Thesis (M.S.)--Mississippi State University. Department of Computer Science. / Title from title screen. Includes bibliographical references.

published_or_final_version / abstract / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

Concern about feeding an ever increasing population has long been one of humankind’s most pressing problems. This has been addressed throughout history by introducing into farming systems changes allowing them to produce more per unit of land area. However, these changes have also been linked to negative effects on the socio economic and environmental sphere, that have created the need for an integral understanding of this phenomenon. This thesis describes the application of learning machine methods to induct a relationship between the spectral response of farms’ land cover and their intensification levels from a sample of farming of Urdaneta municipality, Aragua state of Venezuela. Data collection like this is a necessary first steep to implement cost-effective methods that can help policymakers to conduct succesful planing tasks, especially in countries such as Venezuela where, in spite of there being areas capable of agricultural production, nearly 50% of the internal food requirements of recent years have been satisfied by importations. In this work, farm intensification levels are investigated through a sample of farms of Urdaneta Municipality, Aragua state of Venezuela. This area is characterised by a wide diversity of farming systems ranging from crop to crop-livestock systems and an increasing population density in regions capable of livestock and arable farming, making it a representative case of the main tropical rural zones. The methodology applied can be divided into two main phases. First an unsupervised classification was performed by applying principal component analysis and agglomerative cluster methods to a set of land use and land management indicators, with the aim to segregate farms into homogeneous groups from the intensification point of view. This procedure resulted in three clusters which were named extensive, semi-intensive and intensive. The land use indicators included the percentage area within each farm devoted to annual crops, orchard and pasture, while the land management indicators were percentage of cultivated land under irrigation, stocking rate, machinery and equipment index and permanent and temporary staff ratio, all of them built from data held on the 1996- 1997 venezuelan agricultural census. The previous clusters reached were compared to the ones obtained by applying the learning machine method known as self-organizing map, which is also an unsupervised classification technique, as a way to confirm the groups’ existence. In the second stage, the learning machine known as kernel adatron algorithm was implemented seeking to identify the intensification level of Urdaneta farms from a landsat image, which consisted of two sequential steps: namely training and validation. In the training step, a predetermined number of instances randomly selected from the data set were analysed looking for a pattern to establish a relationship between the label and the spectral response in an iterative process which was concluded when the machine found a linear function capable of separating the two classes with a maximum margin. The supervised classification finishes with the validation in which the kernel adatron classifies the unseen samples by using a generalisation of the relationships learned while training. Results suggest that farm intensification levels can be effectively derived from multi-spectral data by adopting a machine learning approach like the one described.

The analysis and automatic affect estimation system from human expression has been acknowledged as an active research topic in computer vision community. Most reported affect recognition systems, however, only consider subjects performing well-defined acted expression, in a very controlled condition, so they are not robust enough for real-life recognition tasks with subject variation, acoustic surrounding and illumination change. In this thesis, an artificial intelligence system is proposed to continuously (represented along a continuum e.g., from -1 to +1) estimate affect behaviour in terms of latent dimensions (e.g., arousal and valence) from naturalistic human expressions. To tackle the issues, feature representation and machine learning strategies are addressed. In feature representation, human expression is represented by modalities such as audio, video, physiological signal and text modality. Hand- crafted features is extracted from each modality per frame, in order to match with consecutive affect label. However, the features extracted maybe missing information due to several factors such as background noise or lighting condition. Haar Wavelet Transform is employed to determine if noise cancellation mechanism in feature space should be considered in the design of affect estimation system. Other than hand-crafted features, deep learning features are also analysed in terms of the layer-wise; convolutional and fully connected layer. Convolutional Neural Network such as AlexNet, VGGFace and ResNet has been selected as deep learning architecture to do feature extraction on top of facial expression images. Then, multimodal fusion scheme is applied by fusing deep learning feature and hand-crafted feature together to improve the performance. In machine learning strategies, two-stage regression approach is introduced. In the first stage, baseline regression methods such as Support Vector Regression are applied to estimate each affect per time. Then in the second stage, subsequent model such as Time Delay Neural Network, Long Short-Term Memory and Kalman Filter is proposed to model the temporal relationships between consecutive estimation of each affect. In doing so, the temporal information employed by a subsequent model is not biased by high variability present in consecutive frame and at the same time, it allows the network to exploit the slow changing dynamic between emotional dynamic more efficiently. Following of two-stage regression approach for unimodal affect analysis, fusion information from different modalities is elaborated. Continuous emotion recognition in-the-wild is leveraged by investigating mathematical modelling for each emotion dimension. Linear Regression, Exponent Weighted Decision Fusion and Multi-Gene Genetic Programming are implemented to quantify the relationship between each modality. In summary, the research work presented in this thesis reveals a fundamental approach to automatically estimate affect value continuously from naturalistic human expression. The proposed system, which consists of feature smoothing, deep learning feature, two-stage regression framework and fusion using mathematical equation between modalities is demonstrated. It offers strong basis towards the development artificial intelligent system on estimation continuous affect estimation, and more broadly towards building a real-time emotion recognition system for human-computer interaction.

Data can be represented in multiple views. Traditional multi-view learning methods (i.e., co-training, multi-task learning) focus on improving learning performance using information from the auxiliary view, although information from the target view is sufficient for learning task. However, this work addresses a semi-supervised case of multi-view learning, the surrogate supervision multi-view learning, where labels are available on limited views and a classifier is obtained on the target view where labels are missing. In surrogate multi-view learning, one cannot obtain a classifier without information from the auxiliary view. To solve this challenging problem, we propose discriminative and generative approaches. / Graduation date: 2013

Thesis (Ph. D.)--Rutgers University, 2009. / "Graduate Program in Computer Science." Includes bibliographical references (p. 238-261).

Thesis (M.S.)--University of Texas at El Paso, 2008. / Title from title screen. Vita. CD-ROM. Includes bibliographical references. Also available online.

Thesis (Ph. D.)--University of Washington, 2007. / Vita. Includes bibliographical references (p. 120-127).