Shruti Jadon

Aryan Jadon, Avinash Patil, Shruti Jadon

Time Series Forecasting has been an active area of research due to its many applications ranging from network usage prediction, resource allocation, anomaly detection, and predictive maintenance. Numerous publications published in the last five years have proposed diverse sets of objective loss functions to address cases such as biased data, long-term forecasting, multicollinear features, etc. In this paper, we have summarized 14 well-known regression loss functions commonly used for time series forecasting and listed out the circumstances where their application can aid in faster and better model convergence. We have also demonstrated how certain categories of loss functions perform well across all data sets and can be considered as a baseline objective function in circumstances where the distribution of the data is unknown. Our code is available at GitHub: https://github.com/aryan-jadon/Regression-Loss-Functions-in-Time-Series-Forecasting-Tensorflow.

Shruti Jadon

In the current COVID-19 pandemic situation, there is an urgent need to screen infected patients quickly and accurately. Using deep learning models trained on chest X-ray images can become an efficient method for screening COVID-19 patients in these situations. Deep learning approaches are already widely used in the medical community. However, they require a large amount of data to be accurate. The open-source community collectively has made efforts to collect and annotate the data, but it is not enough to train an accurate deep learning model. Few-shot learning is a sub-field of machine learning that aims to learn the objective with less amount of data. In this work, we have experimented with well-known solutions for data scarcity in deep learning to detect COVID-19. These include data augmentation, transfer learning, and few-shot learning, and unsupervised learning. We have also proposed a custom few-shot learning approach to detect COVID-19 using siamese networks. Our experimental results showcased that we can implement an efficient and accurate deep learning model for COVID-19 detection by adopting the few-shot learning approaches even with less amount of data. Using our proposed approach we were able to achieve 96.4% accuracy an improvement from 83% using baseline models.

Shruti Jadon, Aryan Jadon

Since 2012, Deep learning has revolutionized Artificial Intelligence and has achieved state-of-the-art outcomes in different domains, ranging from Image Classification to Speech Generation. Though it has many potentials, our current architectures come with the pre-requisite of large amounts of data. Few-Shot Learning (also known as one-shot learning) is a sub-field of machine learning that aims to create such models that can learn the desired objective with less data, similar to how humans learn. In this paper, we have reviewed some of the well-known deep learning-based approaches towards few-shot learning. We have discussed the recent achievements, challenges, and possibilities of improvement of few-shot learning based deep learning architectures. Our aim for this paper is threefold: (i) Give a brief introduction to deep learning architectures for few-shot learning with pointers to core references. (ii) Indicate how deep learning has been applied to the low-data regime, from data preparation to model training. and, (iii) Provide a starting point for people interested in experimenting and perhaps contributing to the field of few-shot learning by pointing out some useful resources and open-source code. Our code is available at Github: https://github.com/shruti-jadon/Hands-on-One-Shot-Learning.

Shruti Jadon

Image Segmentation has been an active field of research as it has a wide range of applications, ranging from automated disease detection to self-driving cars. In the past five years, various papers came up with different objective loss functions used in different cases such as biased data, sparse segmentation, etc. In this paper, we have summarized some of the well-known loss functions widely used for Image Segmentation and listed out the cases where their usage can help in fast and better convergence of a model. Furthermore, we have also introduced a new log-cosh dice loss function and compared its performance on the NBFS skull-segmentation open-source data-set with widely used loss functions. We also showcased that certain loss functions perform well across all data-sets and can be taken as a good baseline choice in unknown data distribution scenarios. Our code is available at Github: https://github.com/shruti-jadon/Semantic-Segmentation-Loss-Functions.

Shruti Jadon

Plant disease detection is an essential factor in increasing agricultural production. Due to the difficulty of disease detection, farmers spray various pesticides on their crops to protect them, causing great harm to crop growth and food standards. Deep learning can offer critical aid in detecting such diseases. However, it is highly inconvenient to collect a large volume of data on all forms of the diseases afflicting a specific plant species. In this paper, we propose a new metrics-based few-shot learning SSM net architecture, which consists of stacked siamese and matching network components to address the problem of disease detection in low data regimes. We demonstrated our experiments on two datasets: mini-leaves diseases and sugarcane diseases dataset. We have showcased that the SSM-Net approach can achieve better decision boundaries with an accuracy of 92.7% on the mini-leaves dataset and 94.3% on the sugarcane dataset. The accuracy increased by ~10% and ~5% respectively, compared to the widely used VGG16 transfer learning approach. Furthermore, we attained F1 score of 0.90 using SSM Net on the sugarcane dataset and 0.91 on the mini-leaves dataset. Our code implementation is available on Github: https://github.com/shruti-jadon/PlantsDiseaseDetection.

Shruti Jadon

Image Segmentation has been an active field of research as it has a wide range of applications, ranging from automated disease detection to self-driving cars. In recent years, various research papers proposed different loss functions used in case of biased data, sparse segmentation, and unbalanced dataset. In this paper, we introduce SemSegLoss, a python package consisting of some of the well-known loss functions widely used for image segmentation. It is developed with the intent to help researchers in the development of novel loss functions and perform an extensive set of experiments on model architectures for various applications. The ease-of-use and flexibility of the presented package have allowed reducing the development time and increased evaluation strategies of machine learning models for semantic segmentation. Furthermore, different applications that use image segmentation can use SemSegLoss because of the generality of its functions. This wide range of applications will lead to the development and growth of AI across all industries.

Shruti Jadon, Jan Kanty Milczek, Ajit Patankar

Time-series forecasting has been an important research domain for so many years. Its applications include ECG predictions, sales forecasting, weather conditions, even COVID-19 spread predictions. These applications have motivated many researchers to figure out an optimal forecasting approach, but the modeling approach also changes as the application domain changes. This work has focused on reviewing different forecasting approaches for telemetry data predictions collected at data centers. Forecasting of telemetry data is a critical feature of network and data center management products. However, there are multiple options of forecasting approaches that range from a simple linear statistical model to high capacity deep learning architectures. In this paper, we attempted to summarize and evaluate the performance of well known time series forecasting techniques. We hope that this evaluation provides a comprehensive summary to innovate in forecasting approaches for telemetry data.

Shruti Jadon, Owen P. Leary, Ian Pan et al.

Automated segmentation of medical imaging is of broad interest to clinicians and machine learning researchers alike. The goal of segmentation is to increase efficiency and simplicity of visualization and quantification of regions of interest within a medical image. Image segmentation is a difficult task because of multiparametric heterogeneity within the images, an obstacle that has proven especially challenging in efforts to automate the segmentation of brain lesions from non-contrast head computed tomography (CT). In this research, we have experimented with multiple available deep learning architectures to segment different phenotypes of hemorrhagic lesions found after moderate to severe traumatic brain injury (TBI). These include: intraparenchymal hemorrhage (IPH), subdural hematoma (SDH), epidural hematoma (EDH), and traumatic contusions. We were able to achieve an optimal Dice Coefficient1 score of 0.94 using UNet++ 2D Architecture with Focal Tversky Loss Function, an increase from 0.85 using UNet 2D with Binary Cross-Entropy Loss Function in intraparenchymal hemorrhage (IPH) cases. Furthermore, using the same setting, we were able to achieve the Dice Coefficient score of 0.90 and 0.86 in cases of Extra-Axial bleeds and Traumatic contusions, respectively.

Tanvi Sahay, Ankita Mehta, Shruti Jadon

Schema Matching is a method of finding attributes that are either similar to each other linguistically or represent the same information. In this project, we take a hybrid approach at solving this problem by making use of both the provided data and the schema name to perform one to one schema matching and introduce the creation of a global dictionary to achieve one to many schema matching. We experiment with two methods of one to one matching and compare both based on their F-scores, precision, and recall. We also compare our method with the ones previously suggested and highlight differences between them.

Shruti Jadon, Aditya Acrot Srinivasan

The lack of a large amount of training data has always been the constraining factor in solving a lot of problems in machine learning, making One Shot Learning one of the most intriguing ideas in machine learning. It aims to learn information about object categories from one, or only a few training examples. This process of learning in deep learning is usually accomplished by proper objective function, i.e; loss function and embeddings extraction i.e; architecture. In this paper, we discussed about metrics based deep learning architectures for one shot learning such as Siamese neural networks and present a method to improve on their accuracy using Kafnets (kernel-based non-parametric activation functions for neural networks) by learning proper embeddings with relatively less number of epochs. Using kernel activation functions, we are able to achieve strong results which exceed those of ReLU based deep learning models in terms of embeddings structure, loss convergence, and accuracy.

Shruti Jadon, Mahmood Jasim

Video is one of the robust sources of information and the consumption of online and offline videos has reached an unprecedented level in the last few years. A fundamental challenge of extracting information from videos is a viewer has to go through the complete video to understand the context, as opposed to an image where the viewer can extract information from a single frame. Apart from context understanding, it almost impossible to create a universal summarized video for everyone, as everyone has their own bias of keyframe, e.g; In a soccer game, a coach person might consider those frames which consist of information on player placement, techniques, etc; however, a person with less knowledge about a soccer game, will focus more on frames which consist of goals and score-board. Therefore, if we were to tackle problem video summarization through a supervised learning path, it will require extensive personalized labeling of data. In this paper, we attempt to solve video summarization through unsupervised learning by employing traditional vision-based algorithmic methodologies for accurate feature extraction from video frames. We have also proposed a deep learning-based feature extraction followed by multiple clustering methods to find an effective way of summarizing a video by interesting key-frame extraction. We have compared the performance of these approaches on the SumMe dataset and showcased that using deep learning-based feature extraction has been proven to perform better in case of dynamic viewpoint videos.

Shruti Jadon, Anubhav Singhal, Suma Dawn

In this paper we show how the combination of Behaviour Tree and Utility Based AI architecture can be used to design more realistic bots for Military Simulators. In this work, we have designed a mathematical model of a simulator system which in turn helps in analyzing the results and finding out the various spaces on which our favorable situation might exist, this is done geometrically. In the mathematical model, we have explained the matrix formation and its significance followed up in dynamic programming approach we explained the possible graph formation which will led improvisation of AI, latter we explained the possible geometrical structure of the matrix operations and its impact on a particular decision, we also explained the conditions under which it tend to fail along with a possible solution in future works.