arXiv subjects

Joy Bose

Publications and source records attributed to Joy Bose.

36 records · Page 2Linked to original sources

arXiv2025

Automated Code Review Using Large Language Models at Ericsson: An Experience Report

Code review is one of the primary means of assuring the quality of released software along with testing and static analysis. However, code review requires experienced developers who may not always have the time to perform an in-depth review of code. Thus, automating code review can help alleviate the cognitive burden on experienced software developers allowing them to focus on their primary activities of writing code to add new features and fix bugs. In this paper, we describe our experience in using Large Language Models towards automating the code review process in Ericsson. We describe the development of a lightweight tool using LLMs and static program analysis. We then describe our preliminary experiments with experienced developers in evaluating our code review tool and the encouraging results.

cs.SE↗

arXiv2025

A Scalable and High Availability Solution for Recommending Resolutions to Problem Tickets

Resolution of incidents or problem tickets is a common theme in service industries in any sector, including billing and charging systems in telecom domain. Machine learning can help to identify patterns and suggest resolutions for the problem tickets, based on patterns in the historical data of the tickets. However, this process may be complicated due to a variety of phenomena such as data drift and issues such as missing data, lack of data pertaining to resolutions of past incidents, too many similar sounding resolutions due to free text and similar sounding text. This paper proposes a robust ML-driven solution employing clustering, supervised learning, and advanced NLP models to tackle these challenges effectively. Building on previous work, we demonstrate clustering-based resolution identification, supervised classification with LDA, Siamese networks, and One-shot learning, Index embedding. Additionally, we present a real-time dashboard and a highly available Kubernetes-based production deployment. Our experiments with both the open-source Bitext customer-support dataset and proprietary telecom datasets demonstrate high prediction accuracy.

cs.LG↗

arXiv2025

Pendulum Model of Spiking Neurons

We propose a biologically inspired model of spiking neurons based on the dynamics of a damped, driven pendulum. Unlike traditional models such as the Leaky Integrate-and-Fire (LIF) neurons, the pendulum neuron incorporates second-order, nonlinear dynamics that naturally give rise to oscillatory behavior and phase-based spike encoding. This model captures richer temporal features and supports timing-sensitive computations critical for sequence processing and symbolic learning. We present an analysis of single-neuron dynamics and extend the model to multi-neuron layers governed by Spike-Timing Dependent Plasticity (STDP) learning rules. We demonstrate practical implementation with python code and with the Brian2 spiking neural simulator, and outline a methodology for deploying the model on neuromorphic hardware platforms, using an approximation of the second-order equations. This framework offers a foundation for developing energy-efficient neural systems for neuromorphic computing and sequential cognition tasks.

cs.NE↗

arXiv2025

Predicting Locations of Cell Towers for Network Capacity Expansion

Network capacity expansion is a critical challenge for telecom operators, requiring strategic placement of new cell sites to ensure optimal coverage and performance. Traditional approaches, such as manual drive tests and static optimization, often fail to consider key real-world factors including user density, terrain features, and financial constraints. In this paper, we propose a machine learning-based framework that combines deep neural networks for signal coverage prediction with spatial clustering to recommend new tower locations in underserved areas. The system integrates geospatial, demographic, and infrastructural data, and incorporates budget-aware constraints to prioritize deployments. Operating within an iterative planning loop, the framework refines coverage estimates after each proposed installation, enabling adaptive and cost-effective expansion. While full-scale simulation was limited by data availability, the architecture is modular, robust to missing inputs, and generalizable across diverse deployment scenarios. This approach advances radio network planning by offering a scalable, data-driven alternative to manual methods.

cs.NI↗

arXiv2025

A Hybrid Framework for Real-Time Data Drift and Anomaly Identification Using Hierarchical Temporal Memory and Statistical Tests

Data Drift is the phenomenon where the generating model behind the data changes over time. Due to data drift, any model built on the past training data becomes less relevant and inaccurate over time. Thus, detecting and controlling for data drift is critical in machine learning models. Hierarchical Temporal Memory (HTM) is a machine learning model developed by Jeff Hawkins, inspired by how the human brain processes information. It is a biologically inspired model of memory that is similar in structure to the neocortex, and whose performance is claimed to be comparable to state of the art models in detecting anomalies in time series data. Another unique benefit of HTMs is its independence from training and testing cycle; all the learning takes place online with streaming data and no separate training and testing cycle is required. In sequential learning paradigm, Sequential Probability Ratio Test (SPRT) offers some unique benefit for online learning and inference. This paper proposes a novel hybrid framework combining HTM and SPRT for real-time data drift detection and anomaly identification. Unlike existing data drift methods, our approach eliminates frequent retraining and ensures low false positive rates. HTMs currently work with one dimensional or univariate data. In a second study, we also propose an application of HTM in multidimensional supervised scenario for anomaly detection by combining the outputs of multiple HTM columns, one for each dimension of the data, through a neural network. Experimental evaluations demonstrate that the proposed method outperforms conventional drift detection techniques like the Kolmogorov-Smirnov (KS) test, Wasserstein distance, and Population Stability Index (PSI) in terms of accuracy, adaptability, and computational efficiency. Our experiments also provide insights into optimizing hyperparameters for real-time deployment in domains such as Telecom.

cs.LG↗

arXiv2025

Static Program Analysis Guided LLM Based Unit Test Generation

We describe a novel approach to automating unit test generation for Java methods using large language models (LLMs). Existing LLM-based approaches rely on sample usage(s) of the method to test (focal method) and/or provide the entire class of the focal method as input prompt and context. The former approach is often not viable due to the lack of sample usages, especially for newly written focal methods. The latter approach does not scale well enough; the bigger the complexity of the focal method and larger associated class, the harder it is to produce adequate test code (due to factors such as exceeding the prompt and context lengths of the underlying LLM). We show that augmenting prompts with \emph{concise} and \emph{precise} context information obtained by program analysis %of the focal method increases the effectiveness of generating unit test code through LLMs. We validate our approach on a large commercial Java project and a popular open-source Java project.

cs.SE↗

arXiv2023

Effect of Mindfulness and Mindful Art on Beginners and Experienced Meditators

Mindfulness meditation has been proven to be effective in treating a range of mental and physical conditions. Mindful Art is a type of mindfulness meditation that comprises sessions of drawing, painting and sculpturing with mindfulness for a given length of time. To date, the efficacy of mindful art has not been systematically studied. In this paper, we describe an experimental pilot study on two groups of participants, a beginner group of 21 participants and an experienced meditation group of 9 participants, who had previously practiced mindfulness meditation for more than one year. The beginner group was instructed in mindfulness sitting and moving meditation, while the experienced group was instructed in mindful art making in addition to mindfulness meditation. The instructions were delivered remotely over Tencent Conference and WeChat. The sessions were of 90 minutes duration each, twice per week, with 45 minutes of home practice daily and the length of the study was 21 days. The blood pressure, pulse rate and breathing rates, as well as the subjective degree of relaxation were recorded at every session. At the end of the study, the experienced group reported higher average difference in breath rate and relaxation within each session, while the beginner group reported a greater degree of improvement in breath rate and relaxation over the period of the study, although their scores were lower on average than the experienced group.

cs.HC↗

arXiv2021

Sparse Distributed Memory using Spiking Neural Networks on Nengo

We present a Spiking Neural Network (SNN) based Sparse Distributed Memory (SDM) implemented on the Nengo framework. We have based our work on previous work by Furber et al, 2004, implementing SDM using N-of-M codes. As an integral part of the SDM design, we have implemented Correlation Matrix Memory (CMM) using SNN on Nengo. Our SNN implementation uses Leaky Integrate and Fire (LIF) spiking neuron models on Nengo. Our objective is to understand how well SNN-based SDMs perform in comparison to conventional SDMs. Towards this, we have simulated both conventional and SNN-based SDM and CMM on Nengo. We observe that SNN-based models perform similarly as the conventional ones. In order to evaluate the performance of different SNNs, we repeated the experiment using Adaptive-LIF, Spiking Rectified Linear Unit, and Izhikevich models and obtained similar results. We conclude that it is indeed feasible to develop some types of associative memories using spiking neurons whose memory capacity and other features are similar to the performance without SNNs. Finally we have implemented an application where MNIST images, encoded with N-of-M codes, are associated with their labels and stored in the SNN-based SDM.

cs.NE↗

arXiv2021

Modeling Effect of Lockdowns and Other Effects on India Covid-19 Infections Using SEIR Model and Machine Learning

The SEIR model is a widely used epidemiological model used to predict the rise in infections. This model has been widely used in different countries to predict the number of Covid-19 cases. But the original SEIR model does not take into account the effect of factors such as lockdowns, vaccines, and re-infections. In India the first wave of Covid started in March 2020 and the second wave in April 2021. In this paper, we modify the SEIR model equations to model the effect of lockdowns and other influencers, and fit the model on data of the daily Covid-19 infections in India using lmfit, a python library for least squares minimization for curve fitting. We modify R0 parameter in the standard SEIR model as a rectangle in order to account for the effect of lockdowns. Our modified SEIR model accurately fits the available data of infections.

cs.LG↗

arXiv2020

Extraction of Relevant Images for Boilerplate Removal in Web Browsers

Boilerplate refers to unwanted and repeated parts of a webpage (such as ads or table of contents) that distracts the user from reading the core content of the webpage, such as a news article. Accurate detection and removal of boilerplate content from a webpage can enable the users to have a clutter free view of the webpage or news article. This can be useful in features like reader mode in web browsers. Current implementations of reader mode in web browsers such as Firefox, Chrome and Edge perform reasonably well for textual content in webpages. However, they are mostly heuristic based and not flexible when the webpage content is dynamic. Also they often do not perform well for removing boilerplate content in the form of images and multimedia in webpages. For detection of boilerplate images, one needs to have knowledge of the actual layout of the images in the webpage, which is only possible when the webpage is rendered. In this paper we discuss some of the issues in relevant image extraction. We also present the design of a testing framework to measure accuracy and a classifier to extract relevant images by leveraging a headless browser solution that gives the rendering information for images.

cs.IR↗

arXiv2019

Field Label Prediction for Autofill in Web Browsers

Automatic form fill is an important productivity related feature present in major web browsers, which predicts the field labels of a web form and automatically fills values in a new form based on the values previously filled for the same field in other forms. This feature increases the convenience and efficiency of users who have to fill similar information in fields in multiple forms. In this paper we describe a machine learning solution for predicting the form field labels, implemented as a web service using Azure ML Studio.

cs.HC↗

arXiv2019

Analysis of Software Engineering for Agile Machine Learning Projects

The number of machine learning, artificial intelligence or data science related software engineering projects using Agile methodology is increasing. However, there are very few studies on how such projects work in practice. In this paper, we analyze project issues tracking data taken from Scrum (a popular tool for Agile) for several machine learning projects. We compare this data with corresponding data from non-machine learning projects, in an attempt to analyze how machine learning projects are executed differently from normal software engineering projects. On analysis, we find that machine learning project issues use different kinds of words to describe issues, have higher number of exploratory or research oriented tasks as compared to implementation tasks, and have a higher number of issues in the product backlog after each sprint, denoting that it is more difficult to estimate the duration of machine learning project related tasks in advance. After analyzing this data, we propose a few ways in which Agile machine learning projects can be better logged and executed, given their differences with normal software engineering projects.

cs.SE↗

arXiv2019

Evaluating Usage of Images for App Classification

App classification is useful in a number of applications such as adding apps to an app store or building a user model based on the installed apps. Presently there are a number of existing methods to classify apps based on a given taxonomy on the basis of their text metadata. However, text based methods for app classification may not work in all cases, such as when the text descriptions are in a different language, or missing, or inadequate to classify the app. One solution in such cases is to utilize the app images to supplement the text description. In this paper, we evaluate a number of approaches in which app images can be used to classify the apps. In one approach, we use Optical character recognition (OCR) to extract text from images, which is then used to supplement the text description of the app. In another, we use pic2vec to convert the app images into vectors, then train an SVM to classify the vectors to the correct app label. In another, we use the captionbot.ai tool to generate natural language descriptions from the app images. Finally, we use a method to detect and label objects in the app images and use a voting technique to determine the category of the app based on all the images. We compare the performance of our image-based techniques to classify a number of apps in our dataset. We use a text based SVM app classifier as our base and obtained an improved classification accuracy of 96% for some classes when app images are added.

cs.CV↗

arXiv2019

Semi-Supervised Method using Gaussian Random Fields for Boilerplate Removal in Web Browsers

Boilerplate removal refers to the problem of removing noisy content from a webpage such as ads and extracting relevant content that can be used by various services. This can be useful in several features in web browsers such as ad blocking, accessibility tools such as read out loud, translation, summarization etc. In order to create a training dataset to train a model for boilerplate detection and removal, labeling or tagging webpage data manually can be tedious and time consuming. Hence, a semi-supervised model, in which some of the webpage elements are labeled manually and labels for others are inferred based on some parameters, can be useful. In this paper we present a solution for extraction of relevant content from a webpage that relies on semi-supervised learning using Gaussian Random Fields. We first represent the webpage as a graph, with text elements as nodes and the edge weights representing similarity between nodes. After this, we label a few nodes in the graph using heuristics and label the remaining nodes by a weighted measure of similarity to the already labeled nodes. We describe the system architecture and a few preliminary results on a dataset of webpages.

stat.ML↗

arXiv2018

IoT2Vec: Identification of Similar IoT Devices via Activity Footprints

We consider a smart home or smart office environment with a number of IoT devices connected and passing data between one another. The footprints of the data transferred can provide valuable information about the devices, which can be used to (a) identify the IoT devices and (b) in case of failure, to identify the correct replacements for these devices. In this paper, we generate the embeddings for IoT devices in a smart home using Word2Vec, and explore the possibility of having a similar concept for IoT devices, aka IoT2Vec. These embeddings can be used in a number of ways, such as to find similar devices in an IoT device store, or as a signature of each type of IoT device. We show results of a feasibility study on the CASAS dataset of IoT device activity logs, using our method to identify the patterns in embeddings of various types of IoT devices in a household.

cs.HC↗

arXiv2018

A Bias Aware News Recommendation System

In this era of fake news and political polarization, it is desirable to have a system to enable users to access balanced news content. Current solutions focus on top down, server based approaches to decide whether a news article is fake or biased, and display only trusted news to the end users. In this paper, we follow a different approach to help the users make informed choices about which news they want to read, making users aware in real time of the bias in news articles they were browsing and recommending news articles from other sources on the same topic with different levels of bias. We use a recent Pew research report to collect news sources that readers with varying political inclinations prefer to read. We then scrape news articles on a variety of topics from these varied news sources. After this, we perform clustering to find similar topics of the articles, as well as calculate a bias score for each article. For a news article the user is currently reading, we display the bias score and also display other articles on the same topic, out of the previously collected articles, from different news sources. This we present to the user. This approach, we hope, would make it possible for users to access more balanced articles on given news topics. We present the implementation details of the system along with some preliminary results on news articles.

cs.IR↗

arXiv2018

VR Content Capture using Aligned Smartphones

There are a number of dedicated 3D capture devices in the market, but generally they are unaffordable and do not make use of existing smartphone cameras, which are generally of decent quality. Due to this, while there are several means to consume 3D or VR content, there is currently lack of means to capture 3D content, resulting in very few 3D videos being publicly available. Some mobile applications such as Camerada enable 3D or VR content capture by combining the output of two existing smartphones, but users would have to hold the cameras in their hand, making it difficult to align properly. In this paper we present the design of a system to enable 3D content capture using one or more smartphones, taking care of alignment issues so as to get optimal alignment of the smartphone cameras. We aim to keep the distance between the cameras constant and equal to the inter-pupillary distance of about 6.5 cm. Our solution is applicable for one, two and three smartphones. We have a mobile app to generate a template given the dimensions of the smartphones, camera positions and other specifications. The template can be printed by the user and cut out on 2D cardboard, similar to Google cardboard. Alternatively, it can be printed using a 3D printer. During video capture, with the smartphones aligned using our printed template, we capture videos which are then combined to get the optimal 3D content. We present the details of a small proof of concept implementation. Our solution would make it easier for people to use existing smartphones to generate 3D content.

cs.HC↗

arXiv2016

Attention Sensitive Web Browsing

With a number of cheap commercial dry EEG kits available today, it is possible to look at user attention driven scenarios for interaction with the web browser. Using EEG to determine the user's attention level is preferable to using methods such as gaze tracking or time spent on the webpage. In this paper we use the attention level in three different ways. First, as a control mechanism, to control user interface elements such as menus or buttons. Second, to make the web browser responsive to the current attention level. Third, as a means for the web developer to control the user experience based on the level of attention paid by the user, thus creating attention sensitive websites. We present implementation details for each of these, using the NeuroSky MindWave sensor. We also explore issues in the system, and possibility of an EEG based web standard.

cs.HC↗