Search

Compiling high-level programs to target high-speed packet-processing pipelines is a challenging combinatorial optimization problem. The compiler must configure the pipeline's resources to match the high-level semantics of the program, while packing all of the program's computation into the pipeline's limited resources. State of the art approaches tackle individual aspects of this problem. Yet, they miss opportunities to efficiently produce globally high-quality outcomes. We argue that High-Level Synthesis (HLS), previously applied to ASIC/FPGA design, is the right framework to decompose the compilation problem for pipelines into smaller pieces with modular solutions. We design an HLS-based compiler that works in three phases. Transformation rewrites programs to use more abundant pipeline resources, avoiding scarce ones. Synthesis breaks complex transactional code into configurations of pipelined compute units. Allocation maps the program's compute and memory to the hardware resources. We prototype these ideas in a compiler, CaT, which targets the Tofino pipeline and a cycle-accurate simulator of a Verilog hardware model of an RMT pipeline. CaT can handle programs that existing compilers cannot currently run on pipelines, generating code faster than existing compilers, while using fewer pipeline resources.

The Indian agricultural sector being in a constant phase of upgradation, has been on the road to modernization for the last couple of years. The fundamental source of livelihood for over 70 percent of the population living in rural parts of the country is still agriculture. The average Indian farmer, although has access to raw and trend data pertaining to crop prices, yield and demand from Indian government and private websites, still struggles to make the right choices. They are constantly faced with the dilemma of choosing the right crop to address market demand and fetch them a decent profit. Since the process of shortlisting crops amongst the many suitable ones isn't completely scientific and usually dictated by area tradition, this project has aimed to address that issue by forecasting the price of those crops and uses that to create an optimal portfolio that the farmers can obtain to arrive at a data-driven decision for crop selection with optimal estimated ROI., Comment: 14 pages

Prompt tuning is a new few-shot transfer learning technique that only tunes the learnable prompt for pre-trained vision and language models such as CLIP. However, existing prompt tuning methods tend to learn spurious or entangled representations, which leads to poor generalization to unseen concepts. Towards non-spurious and efficient prompt learning from limited examples, this paper presents a novel \underline{\textbf{C}}ounterfactual \underline{\textbf{P}}rompt \underline{\textbf{L}}earning (CPL) method for vision and language models, which simultaneously employs counterfactual generation and contrastive learning in a joint optimization framework. Particularly, CPL constructs counterfactual by identifying minimal non-spurious feature change between semantically-similar positive and negative samples that causes concept change, and learns more generalizable prompt representation from both factual and counterfactual examples via contrastive learning. Extensive experiments demonstrate that CPL can obtain superior few-shot performance on different vision and language tasks than previous prompt tuning methods on CLIP. On image classification, we achieve 3.55\% average relative improvement on unseen classes across seven datasets; on image-text retrieval and visual question answering, we gain up to 4.09\% and 25.08\% relative improvements across three few-shot scenarios on unseen test sets respectively.

Four-dimensional scanning transmission electron microscopy (4D-STEM) has recently gained widespread attention for its ability to image atomic electric fields with sub-{\AA}ngstrom spatial resolution. These electric field maps represent the integrated effect of the nucleus, core electrons and valence electrons, and separating their contributions is non-trivial. In this paper, we utilized simultaneously acquired 4D-STEM center of mass (CoM) images and annular dark field (ADF) images to determine the electron charge density in monolayer MoS2. We find that both the core electrons and the valence electrons contribute to the derived electron charge density. However, due to blurring by the probe shape, the valence electron contribution forms a nearly featureless background while most of the spatial modulation comes from the core electrons. Our findings highlight the importance of probe shape in interpreting charge densities derived from 4D STEM.

Although the terms mood and emotion are closely related and often used interchangeably, they are distinguished based on their duration, intensity and attribution. To date, hardly any computational models have (a) examined mood recognition, and (b) modelled the interplay between mood and emotional state in their analysis. In this paper, as a first step towards mood prediction, we propose a framework that utilises both dominant emotion (or mood) labels, and emotional change labels on the AFEW-VA database. Experiments evaluating unimodal (trained only using mood labels) and multimodal (trained with both mood and emotion change labels) convolutional neural networks confirm that incorporating emotional change information in the network training process can significantly improve the mood prediction performance, thus highlighting the importance of modelling emotion and mood simultaneously for improved performance in affective state recognition., Comment: 5 pages, 5 figures

Algorithms that adjust the reactive power injection of converter-connected RES to minimize losses may compromise the converters' fault-ride-through capability. This can become crucial for the reliable operation of the distribution grids, as they could lose valuable resources to support grid voltage at the time they need them the most. This paper explores how two novel loss-minimizing algorithms can both achieve high reduction of the system losses during normal operation and remain connected to support the voltage during faults. The algorithms we propose are decentralized and model-free: they require no communication and no knowledge of the grid topology or the grid location of the converters. Using local information, they control the reactive power injection to minimize the system losses. In this paper, we extend these algorithms to ensure the low voltage ride through (LVRT) capability of the converters, and we integrate them with state-of-the-art Wavelet-CNN-LSTM RES forecasting methods that enhance their performance. We perform extensive simulations on the real-time digital simulation (RTDS) platform, where we demonstrate that the algorithms we propose can achieve a substantial decrease in power losses while remaining compliant with the grid codes for LVRT makes them suitable for the implementation across the distribution system.

We present \textbf{ACAD}, an \textbf{a}ffective \textbf{c}omputational \textbf{ad}vertising framework expressly derived from perceptual metrics. Different from advertising methods which either ignore the emotional nature of (most) programs and ads, or are based on axiomatic rules, the ACAD formulation incorporates findings from a user study examining the effect of within-program ad placements on ad perception. A linear program formulation seeking to achieve (a) \emph{{genuine}} ad assessments and (b) \emph{maximal} ad recall is then proposed. Effectiveness of the ACAD framework is confirmed via a validational user study, where ACAD-induced ad placements are found to be optimal with respect to objectives (a) and (b) against competing approaches., Comment: 13 pages, 13 figures

Multilingual speech recognition has drawn significant attention as an effective way to compensate data scarcity for low-resource languages. End-to-end (e2e) modelling is preferred over conventional hybrid systems, mainly because of no lexicon requirement. However, hybrid DNN-HMMs still outperform e2e models in limited data scenarios. Furthermore, the problem of manual lexicon creation has been alleviated by publicly available trained models of grapheme-to-phoneme (G2P) and text to IPA transliteration for a lot of languages. In this paper, a novel approach of hybrid DNN-HMM acoustic models fusion is proposed in a multilingual setup for the low-resource languages. Posterior distributions from different monolingual acoustic models, against a target language speech signal, are fused together. A separate regression neural network is trained for each source-target language pair to transform posteriors from source acoustic model to the target language. These networks require very limited data as compared to the ASR training. Posterior fusion yields a relative gain of 14.65% and 6.5% when compared with multilingual and monolingual baselines respectively. Cross-lingual model fusion shows that the comparable results can be achieved without using posteriors from the language dependent ASR., Comment: Accepted for Interspeech 2022

Water plays a significant role in various physicochemical and biological processes. Understanding and identifying water phases in various systems such as bulk, interface, and confined water is crucial in improving and engineering state-of-the-art nano-devices. Various order parameters have been developed to distinguish water phases, including bond-order parameters, local structure index, and tetrahedral order parameters. These order parameters are often developed with the assumption of homogenous bulk systems, while most applications involve heterogeneous and non-bulk systems, thus, limiting their generalizability. Our study develops a methodology based on the graph neural network to distinguish water phases directly from data and to learn features instead of predefining them. We provide comparisons between baseline methods trained using conventional order-parameters as features, and a graph neural network model trained using radial distance and hydrogen-bonding information for phase classification and phase transition of water in bulk, interface, and confined systems with continuous and discontinuous phase transitions., Comment: 31 pages; 7 figures

COVID-19, also known as Novel Coronavirus Disease, is a highly contagious disease that first surfaced in China in late 2019. SARS-CoV-2 is a coronavirus that belongs to the vast family of coronaviruses that causes this disease. The sickness originally appeared in Wuhan, China in December 2019 and quickly spread to over 213 nations, becoming a global pandemic. Fever, dry cough, and tiredness are the most typical COVID-19 symptoms. Aches, pains, and difficulty breathing are some of the other symptoms that patients may face. The majority of these symptoms are indicators of respiratory infections and lung abnormalities, which radiologists can identify. Chest x-rays of COVID-19 patients seem similar, with patchy and hazy lungs rather than clear and healthy lungs. On x-rays, however, pneumonia and other chronic lung disorders can resemble COVID-19. Trained radiologists must be able to distinguish between COVID-19 and an illness that is less contagious. Our AI algorithm seeks to give doctors a quantitative estimate of the risk of deterioration. So that patients at high risk of deterioration can be triaged and treated efficiently. The method could be particularly useful in pandemic hotspots when screening upon admission is important for allocating limited resources like hospital beds.

Businesses need content. In various forms and formats and for varied purposes. In fact, the content marketing industry is set to be worth $412.88 billion by the end of 2021. However, according to the Content Marketing Institute, creating engaging content is the #1 challenge that marketers face today. We under-stand that producing great content requires great writers who understand the business and can weave their message into reader (and search engine) friendly content. In this project, the team has attempted to bridge the gap between writers and projects by using AI and ML tools. We used NLP techniques to analyze thou-sands of publicly available business articles (corpora) to extract various defining factors for each writing sample. Through this project we aim to automate the highly time-consuming, and often biased task of manually shortlisting the most suitable writer for a given content writing requirement. We believe that a tool like this will have far reaching positive implications for both parties - businesses looking for suitable talent for niche writing jobs as well as experienced writers and Subject Matter Experts (SMEs) wanting to lend their services to content marketing projects. The business gets the content they need, the content writer/ SME gets a chance to leverage his or her talent, while the reader gets authentic content that adds real value.

The application of Deep Learning and Natural Language based ChatBots are growing rapidly in recent years. They are used in many fields like customer support, reservation system and as personal assistant. The Enterprises are using such ChatBots to serve their customers in a better and efficient manner. Even after such technological advancement, the expert advice does not reach the farmers on timely manner. The farmers are still largely dependent on their peers knowledge in solving the problems they face in their field. These technologies have not been effectively used to give the required information to farmers on timely manner. This project aims to implement a closed domain ChatBot for the field of Agriculture Farmers Assistant. Farmers can have conversation with the Chatbot and get the expert advice in their field. Farmers Assistant is based on RASA Open Source Framework. The Chatbot identifies the intent and entity from user utterances and retrieve the remedy from the database and share it with the user. We tested the Bot with existing data and it showed promising results.

Stock market prediction has been an active area of research for a considerable period. Arrival of computing, followed by Machine Learning has upgraded the speed of research as well as opened new avenues. As part of this research study, we aimed to predict the future stock movement of shares using the historical prices aided with availability of sentiment data. Two models were used as part of the exercise, LSTM was the first model with historical prices as the independent variable. Sentiment Analysis captured using Intensity Analyzer was used as the major parameter for Random Forest Model used for the second part, some macro parameters like Gold, Oil prices, USD exchange rate and Indian Govt. Securities yields were also added to the model for improved accuracy of the model. As the end product, prices of 4 stocks viz. Reliance, HDFC Bank, TCS and SBI were predicted using the aforementioned two models. The results were evaluated using RMSE metric.

The Indian Agricultural sector generates huge employment accounting for over 54% of countrys workforce. Its overall stand in GDP is close to 14%. However, this sector has been plagued by knowledge and infrastructure deficit, especially in the rural sectors. Like other sectors, the Indian Agricultural sector has seen rapid digitization with use of technology and Kisan Call Center (KCC) is one such example. It is a Government of India initiative launched on 21st January 2004 which is a synthesis of two hitherto separate sectors the Information Technology and Agriculture sector. However, studies have shown to have constrains to KCC beneficiaries, especially in light of network congestion and incomplete knowledge of the call center representatives. With the advent of new technologies, like first-generation SMS based and next-generation social media tools like WhatsApp, farmers in India are digitally more connected to the agricultural information services. Previous studies have shown that the KCC dataset can be used as a viable alternative for Chat-bot. We will base our study with the available KCC dataset to build an NLP model by getting the semantic similarity of the queries made by farmers in the past and use it to automatically answer future queries. We will attempt to make a WhatsApp based chat-bot to easily communicate with farmers using RASA as a tool.

With the advancement in AI, deep learning techniques are widely used to design robust classification models in several areas such as medical diagnosis tasks in which it achieves good performance. In this paper, we have proposed the CNN model (Convolutional Neural Network) for the classification of Chest X-ray images for Radiological Society of North America Pneumonia (RSNA) datasets. The study also tries to achieve the same RSNA benchmark results using the limited computational resources by trying out various approaches to the methodologies that have been implemented in recent years. The proposed method is based on a non-complex CNN and the use of transfer learning algorithms like Xception, InceptionV3/V4, EfficientNetB7. Along with this, the study also tries to achieve the same RSNA benchmark results using the limited computational resources by trying out various approaches to the methodologies that have been implemented in recent years. The RSNA benchmark MAP score is 0.25, but using the Mask RCNN model on a stratified sample of 3017 along with image augmentation gave a MAP score of 0.15. Meanwhile, the YoloV3 without any hyperparameter tuning gave the MAP score of 0.32 but still, the loss keeps decreasing. Running the model for a greater number of iterations can give better results.

With over 50 million car sales annually and over 1.3 million deaths every year due to motor accidents we have chosen this space. India accounts for 11 per cent of global death in road accidents. Drivers are held responsible for 78% of accidents. Road safety problems in developing countries is a major concern and human behavior is ascribed as one of the main causes and accelerators of road safety problems. Driver distraction has been identified as the main reason for accidents. Distractions can be caused due to reasons such as mobile usage, drinking, operating instruments, facial makeup, social interaction. For the scope of this project, we will focus on building a highly efficient ML model to classify different driver distractions at runtime using computer vision. We would also analyze the overall speed and scalability of the model in order to be able to set it up on an edge device. We use CNN, VGG-16, RestNet50 and ensemble of CNN to predict the classes.

The purpose of this work is, to provide a YOLOv5 deep learning-based social distance monitoring framework using an overhead view perspective. In addition, we have developed a custom defined model YOLOv5 modified CSP (Cross Stage Partial Network) and assessed the performance on COCO and Visdrone dataset with and without transfer learning. Our findings show that the developed model successfully identifies the individual who violates the social distances. The accuracy of 81.7% for the modified bottleneck CSP without transfer learning is observed on COCO dataset after training the model for 300 epochs whereas for the same epochs, the default YOLOv5 model is attaining 80.1% accuracy with transfer learning. This shows an improvement in accuracy by our modified bottleneck CSP model. For the Visdrone dataset, we are able to achieve an accuracy of upto 56.5% for certain classes and especially an accuracy of 40% for people and pedestrians with transfer learning using the default YOLOv5s model for 30 epochs. While the modified bottleneck CSP is able to perform slightly better than the default model with an accuracy score of upto 58.1% for certain classes and an accuracy of ~40.4% for people and pedestrians.

This paper presents an extension of Naor's analysis on the join-or-balk problem in observable M/M/1 queues. While all other Markovian assumptions still hold, we explore this problem assuming uncertain arrival rates under the distributionally robust settings. We first study the problem with the classical moment ambiguity set, where the support, mean, and mean-absolute deviation of the underlying distribution are known. Next, we extend the model to the data-driven setting, where decision makers only have access to a finite set of samples. We develop three optimal joining threshold strategies from the perspective of an individual customer, a social optimizer, and a revenue maximizer, such that their respective worst-case expected benefit rates are maximized. Finally, we compare our findings with Naor's original results and the traditional sample average approximation scheme.

The new alternative is to use deep learning to inpaint any image by utilizing image classification and computer vision techniques. In general, image inpainting is a task of recreating or reconstructing any broken image which could be a photograph or oil/acrylic painting. With the advancement in the field of Artificial Intelligence, this topic has become popular among AI enthusiasts. With our approach, we propose an initial end-to-end pipeline for inpainting images using a complete Machine Learning approach instead of a conventional application-based approach. We first use the YOLO model to automatically identify and localize the object we wish to remove from the image. Using the result obtained from the model we can generate a mask for the same. After this, we provide the masked image and original image to the GAN model which uses the Contextual Attention method to fill in the region. It consists of two generator networks and two discriminator networks and is also called a coarse-to-fine network structure. The two generators use fully convolutional networks while the global discriminator gets hold of the entire image as input while the local discriminator gets the grip of the filled region as input. The contextual Attention mechanism is proposed to effectively borrow the neighbor information from distant spatial locations for reconstructing the missing pixels. The third part of our implementation uses SRGAN to resolve the inpainted image back to its original size. Our work is inspired by the paper Free-Form Image Inpainting with Gated Convolution and Generative Image Inpainting with Contextual Attention.

India is the second largest producer of fruits and vegetables in the world, and one of the largest consumers of fruits like Banana, Papaya and Mangoes through retail and ecommerce giants like BigBasket, Grofers and Amazon Fresh. However, adoption of technology in supply chain and retail stores is still low and there is a great potential to adopt computer-vision based technology for identification and classification of fruits. We have chosen banana fruit to build a computer vision based model to carry out the following three use-cases (a) Identify Banana from a given image (b) Determine sub-family or variety of Banana (c) Determine the quality of Banana. Successful execution of these use-cases using computer-vision model would greatly help with overall inventory management automation, quality control, quick and efficient weighing and billing which all are manual labor intensive currently. In this work, we suggest a machine learning pipeline that combines the ideas of CNNs, transfer learning, and data augmentation towards improving Banana fruit sub family and quality image classification. We have built a basic CNN and then went on to tune a MobileNet Banana classification model using a combination of self-curated and publicly-available dataset of 3064 images. The results show an overall 93.4% and 100% accuracy for sub-family/variety and for quality test classifications respectively.

The research and data science community has been fascinated with the development of automatic systems for the detection of key events in a video. Special attention in this field is given to sports video analytics which could help in identifying key events during a match and help in preparing a strategy for the games going forward. For this paper, we have chosen Football (soccer) as a sport where we would want to create highlights for a given match video, through a computer vision model that aims to identify important events in a Soccer match to create highlights of the match. We built the models based on Faster RCNN and YoloV5 architectures and noticed that for the amount of data we used for training Faster RCNN did better than YoloV5 in detecting the events in the match though it was much slower. Within Faster RCNN using ResNet50 as a base model gave a better class accuracy of 95.5% as compared to 92% with VGG16 as base model completely outperforming YoloV5 for our training dataset. We tested with an original video of size 23 minutes and our model could reduce it to 4:50 minutes of highlights capturing almost all important events in the match.

Process mining techniques enable the analysis of a wide variety of processes using event data. Among the available process mining techniques, most consider a single process perspective at a time-in the shape of a model or log. In this paper, we have developed a tool that can compare and visualize the same process under different constraints, allowing to analyze multiple aspects of the process. We describe the architecture, structure and use of the tool, and we provide an open-source full implementation., Comment: 2 pages, 2 figures, 6 references

We present LASER, an image-based Monte Carlo Localization (MCL) framework for 2D floor maps. LASER introduces the concept of latent space rendering, where 2D pose hypotheses on the floor map are directly rendered into a geometrically-structured latent space by aggregating viewing ray features. Through a tightly coupled rendering codebook scheme, the viewing ray features are dynamically determined at rendering-time based on their geometries (i.e. length, incident-angle), endowing our representation with view-dependent fine-grain variability. Our codebook scheme effectively disentangles feature encoding from rendering, allowing the latent space rendering to run at speeds above 10KHz. Moreover, through metric learning, our geometrically-structured latent space is common to both pose hypotheses and query images with arbitrary field of views. As a result, LASER achieves state-of-the-art performance on large-scale indoor localization datasets (i.e. ZInD and Structured3D) for both panorama and perspective image queries, while significantly outperforming existing learning-based methods in speed., Comment: CVPR2022-Oral

The impact of Music on the mood or emotion of the listener is a well-researched area in human psychology and behavioral science. In Indian classical music, ragas are the melodic structure that defines the various styles and forms of the music. Each raga has been found to evoke a specific emotion in the listener. With the advent of advanced capabilities of audio signal processing and the application of machine learning, the demand for intelligent music classifiers and recommenders has received increased attention, especially in the 'Music as a service' cloud applications. This paper explores a novel framework to leverage the raga-rasa association in Indian classical Music to build an intelligent classifier and its application in music recommendation system based on user's current mood and the mood they aspire to be in.