Computer Science Community Research Articles

Sentiment Analysis on Multiple Indian Languages

Sentiment analysis has become popular in the computer science community as it is essential for moderating and analyzing information across the internet. There are various applications for sentiment analysis, such as opinion mining, social media monitoring, and market research. Sentiment analysis in Indian languages is gaining importance due to the growth of content on social media, news articles, and other online platforms in Indian languages. Since India is a diversified country it has many languages that are used by millions of people but many Indian languages do not have enough resources for moderation on the internet to analyze the sentiment in the text to use them for either eradicating hate speech or to improve the productivity of companies by the understanding of customer needs from reviews. This paper explains an approach that helps in analyzing the sentiment which helps in content moderation and avoiding negativity on the internet. This approach uses the BERT algorithm for sentiment analysis in English. All the text in other languages will be translated into English and their sentiment is then analyzed. In this approach, we use the BERT algorithm for sentiment analysis on translated English text. This approach works well because sentiment analysis using BERT gives higher accuracy and the translation of text from Indian languages is made easy by the advent of natural language processing. By combining both the above-discussed processes we can analyze the sentiment in multiple Indian languages.

Good Enough

The computer science community has always faced the challenge of what is “good enough” software. The challenge remains unsolved and will remain that way under the prevailing mindset of a quantitative formula. This message offers a more pragmatic approach.

SoK: Managing risks of linkage attacks on data privacy

Novel attacks on dataset privacy are usually met with the same range of responses: surprise that a route to information gain exists from information previously thought to be safe; disputes around the viability or validity of the attack in real-world contexts; and, in the case of the computer science community, a drive to produce techniques that provably protect against the new class of attack. The result is a disjointed landscape with no shared approach to modelling threats to dataset privacy, and a toolbox of technically complex systems whose guarantees come with narrow assumptions and whose application in real-world contexts is hard to achieve. In this paper we aim to understand these issues by charting the history of dataset privacy attacks and systematising breaches through the lens of data linkage. We show how identification or information gain on a dataset's subjects can be expressed as data linkage, and use this to present a taxonomy of threat models which we apply to ninety-four attacks from across the literature. Our work demonstrates that dataset privacy must be approached first as a risk management problem, rather than one of strict guarantees, an approach which aligns well with law and practice. Our taxonomy of attacker intents provides a coherent language for expressing the wide variety of threat models in dataset privacy, and a framework for understanding how risks identified under one model can be understood within another. We also present insights around the factors that affect the feasibility and severity of attacks, and proposals for practical techniques that can be used for risk appraisal and management by practitioners, researchers, and regulators alike.

Auto-Gait

Many patients with neurological disorders, such as Ataxia, do not have easy access to neurologists, -especially those living in remote localities and developing/underdeveloped countries. Ataxia is a degenerative disease of the nervous system that surfaces as difficulty with motor control, such as walking imbalance. Previous studies have attempted automatic diagnosis of Ataxia with the help of wearable biomarkers, Kinect, and other sensors. These sensors, while accurate, do not scale efficiently well to naturalistic deployment settings. In this study, we propose a method for identifying ataxic symptoms by analyzing videos of participants walking down a hallway, captured with a standard monocular camera. In a collaboration with 11 medical sites located in 8 different states across the United States, we collected a dataset of 155 videos along with their severity rating from 89 participants (24 controls and 65 diagnosed with or are pre-manifest spinocerebellar ataxias). The participants performed the gait task of the Scale for the Assessment and Rating of Ataxia (SARA). We develop a computer vision pipeline to detect, track, and separate the participants from their surroundings and construct several features from their body pose coordinates to capture gait characteristics such as step width, step length, swing, stability, speed, etc. Our system is able to identify and track a patient in complex scenarios. For example, if there are multiple people present in the video or an interruption from a passerby. Our Ataxia risk-prediction model achieves 83.06% accuracy and an 80.23% F1 score. Similarly, our Ataxia severity-assessment model achieves a mean absolute error (MAE) score of 0.6225 and a Pearson's correlation coefficient score of 0.7268. Our model competitively performed when evaluated on data from medical sites not used during training. Through feature importance analysis, we found that our models associate wider steps, decreased walking speed, and increased instability with greater Ataxia severity, which is consistent with previously established clinical knowledge. Furthermore, we are releasing the models and the body-pose coordinate dataset to the research community - the largest dataset on ataxic gait (to our knowledge). Our models could contribute to improving health access by enabling remote Ataxia assessment in non-clinical settings without requiring any sensors or special cameras. Our dataset will help the computer science community to analyze different characteristics of Ataxia and to develop better algorithms for diagnosing other movement disorders.

A conversation with Grace IbukunOluwa Ufeoshi

Ubiquity's senior editor Dr. Bushra Anjum chats with Grace IbukunOluwa Ufeoshi, a data science professional and AI entrepreneur, about her passion for preparing the underprivileged African youth for the future of work in the IT ecosystem. They discuss IbukunOluwa's journey as a computer science educator and community leader, and her latest initiatives to equip young people with the requisite skills needed to apply AI in solving real social and business problems---especially in areas of socio-economic development across Africa.

A Bridge to Machine Learning for Zero Computer Science Community: A Machine Learning Path with Linear Regression

Based on LinkedIn poll results, professionals from non-computer science backgrounds have developed an interest in data science and most intend to enter the field through Machine Learning, but do not know where to start (Webb et al., 2021) The aim of this study is to introduce an ideal systematic approach and workflow to get started with Machine Learning. Since the Linear Regression algorithm is the main algorithm used to introduce the concept of Machine Learning, it was chosen for this study to lay a fundamental platform. Using the proposed algorithm and appropriate python libraries, efficient methods of explanatory data analysis and procedural steps towards model training are also explained. Briefly, this study gives an insight on how to approach other Machine Learning algorithms as well. The first steps in Machine Learning involve data pre-processing. The dataset was chosen to meet data manipulation techniques suitable for people without a computer science background.

Multiscale Computational Approaches toward the Understanding of Materials

AbstractHerewith, an overview of the group's collaborative research efforts on the development and deployment of computational approaches to understand materials and tools at different length and time scales is presented. The techniques employed range from quantum mechanical approaches based on the density functional theory to classical atomistic and coarse‐grained force field methods, targeting molecular systems composed of a few to several million atoms at different levels of detail. These new tools and molecular models are presented to the computational materials science community so they can be used in more realistic molecular modelling studies of the properties of materials and their dependence on subtle modifications of their structures. The review concludes by presenting a selection of recent computational case‐studies oriented toward the understanding of the synthesis of materials, the interpretation of unexpected experimental results, the prediction of material properties, and the materials selection based on their characteristics for applications in areas such as gas adsorption/separation, corrosion protection, and catalysis.

Insights into Multi-Model Federated Learning: An Advanced Approach for Air Quality Index Forecasting

The air quality index (AQI) forecast in big cities is an exciting study area in smart cities and healthcare on the Internet of Things. In recent years, a large number of empirical, academic, and review papers using machine learning (ML) for air quality analysis have been published. However, most of those studies focused on traditional centralized processing on a single machine, and there had been few surveys of federated learning (FL) in this field. This overview aims to fill this gap and provide newcomers with a broader perspective to inform future research on this topic, especially for the multi-model approach. In this survey, we went over the works that previous scholars have conducted in AQI forecast both in traditional ML approaches and FL mechanisms. Our objective is to comprehend previous research on AQI prediction including methods, models, data sources, achievements, challenges, and solutions applied in the past. We also convey a new path of using multi-model FL, which has piqued the computer science community’s interest recently.

Effects of random forest modeling decisions on biogeochemical time series predictions

AbstractRandom forests (RF) are an increasingly popular machine learning approach used to model biogeochemical processes in the Earth system. While RF models are robust to many assumptions that complicate deterministic models, there are several important parameterization decisions for appropriate use and optimal model fit. We explored the role that parameter decisions, including training/testing data splitting strategies, variable selection, and hyperparameters play on RF goodness‐of‐fit by constructing models using 1296 unique parameter combinations to predict concentrations of nitrate, a key nutrient for biogeochemical cycling in aquatic ecosystems. Models were built on long‐term, publicly available water quality and meteorology time series collected by the National Estuarine Research Reserve monitoring network for two contrasting ecosystems representing freshwater and brackish estuaries. We found that accounting for temporal dependence when splitting data into training and testing subsets was key for avoiding over‐estimation of model predictive power. In addition, variable selection, the ratio of training to testing data, and to a lesser degree, variables per split and number of trees, were significant parameters for optimizing RF goodness‐of‐fit. We also explored how model parameter decisions influenced interpretation of the relative importance of predictors to the model, and model predictor‐dependent variable relationships, with results suggesting that both data structure and model parameterization influence these factors. Because much of the current RF literature is written for the computational and statistical science communities, the primary goal of this study is to provide guidelines for aquatic scientists new to machine learning to apply RF techniques appropriately to aquatic biogeochemical datasets.

Survey of United States Related Domains: Secure Network Protocol Analysis

Over time, the HTTP Protocol has undergone significant evolution. HTTP was the internet's foundation for data communication. When network security threats became prevalent, HTTPS became a widely accepted technology for assisting in a domain defense. HTTPS supported two security protocols: secure socket layer (SSL) and transport layer security (TLS). Additionally, the HTTP Strict Transport Security (HSTS) protocol was included to strengthen the HTTPS protocol. Numerous cyber-attacks occurred in the United States, and many of these attacks could have been avoided simply by implementing domains with the most up-to-date HTTP security mechanisms. This study seeks to accomplish two objectives: 1. Determine the degree to which US-related domains are configured optimally for HTTP security protocol setup; 2. Create a generic scoring system for a domain's network security based on the following factors: SSL version, TLS version, and presence of HSTS to easily determine where a domain stands. We found through our analysis and scoring system incorporation that US-related domains showed a positive trend for secure network protocol setup, but there is still room for improvement. In order to safeguard unwanted cyber-attacks, current HTTPS domains need to be extensively investigated to identify if they possess lower version protocol support. Due to the infrequent occurrence of HSTS in the evaluated domains, the computer science community necessitates further HSTS education.

Comparing fuzzy cognitive maps: Methods and their applications in team communication

As fuzzy cognitive mapping becomes more ubiquitous and transferable between fields, there is a growing necessity to be able to compare its results. However, despite the abundance of measures for this purpose, the act of comparing these maps is not widespread. This paper gathers different analysis measures and demonstrates how they can be used for fuzzy cognitive map (FCM) comparison. For this, various measures are described and applied to communication FCMs, specifically when differentiating team performance levels. This paper shows how existing measures can be applied and interpreted, and identifies gaps in the current methods of FCM comparison. Relevance to Industry: This research can aid the communication, human systems engineering, and computer science communities in identifying appropriate measures for analysis and comparison of their FCMs. Our results indicate the need for transdisciplinary work on the application and comparison of FCMs.

Covariance’s Loss is Privacy’s Gain: Computationally Efficient, Private and Accurate Synthetic Data

AbstractThe protection of private information is of vital importance in data-driven research, business and government. The conflict between privacy and utility has triggered intensive research in the computer science and statistics communities, who have developed a variety of methods for privacy-preserving data release. Among the main concepts that have emerged are anonymity and differential privacy. Today, another solution is gaining traction, synthetic data. However, the road to privacy is paved with NP-hard problems. In this paper, we focus on the NP-hard challenge to develop a synthetic data generation method that is computationally efficient, comes with provable privacy guarantees and rigorously quantifies data utility. We solve a relaxed version of this problem by studying a fundamental, but a first glance completely unrelated, problem in probability concerning the concept of covariance loss. Namely, we find a nearly optimal and constructive answer to the question how much information is lost when we take conditional expectation. Surprisingly, this excursion into theoretical probability produces mathematical techniques that allow us to derive constructive, approximately optimal solutions to difficult applied problems concerning microaggregation, privacy and synthetic data.

Identifying spreading influence nodes for social networks

The identification of spreading influence nodes in social networks, which studies how to detect important individuals in human society, has attracted increasing attention from physical and computer science, social science and economics communities. The identification algorithms of spreading influence nodes can be used to evaluate the spreading influence, describe the node’s position, and identify interaction centralities. This review summarizes the recent progress about the identification algorithms of spreading influence nodes from the viewpoint of social networks, emphasizing the contributions from physical perspectives and approaches, including the microstructure-based algorithms, community structure-based algorithms, macrostructure-based algorithms, and machine learning-based algorithms. We introduce diffusion models and performance evaluation metrics, and outline future challenges of the identification of spreading influence nodes.

Future challenges on focused fluid migration in sedimentary basins: Insight from field data, laboratory experiments and numerical simulations

In a present context of sustainable energy and hazard mitigation, understanding fluid migration in sedimentary basins – large subsea provinces of fine saturated sands and clays – is a crucial challenge. Such migration leads to gas or liquid expulsion at the seafloor, whichmay be the signature of deep hydrocarbon reservoirs, or precursors to violent subsea fluid releases. If the former may orient future exploitation, the latter represent strong hazards for anthropic activities such as offshore production, CO$_2$ storage, transoceanic telecom fibers or deep-sea mining. However, at present, the dynamics of fluid migration in sedimentary layers, in particular the upper 500 m, still remains unknown in spite of its strong influence on fluid distribution at the seafloor. Understanding the mechanisms controlling fluid migration and release requires the combination of accurate field data, laboratory experiments and numerical simulations. Each technique shall lead to the understanding of the fluid structures, the mechanisms at stake, and deep insights into fundamental processes ranging from the grain scale to the kilometers-long natural pipes in the sedimentary layers.Here we review the present available techniques, advances and challenges still open for the geosciences, physics, and computer science communities.

Collaborative Speculations on Future Themes for Participatory Design in Germany

Abstract Participatory Design means recognizing that those who will be affected by a future technology should have an active say in its creation. Yet, despite continuous interest in involving people as future users and consumers into designing novel and innovative future technology, participatory approaches in technology design remain relatively underdeveloped in the German HCI community. This article brings together the diversity of voices, domains, perspectives, approaches, and methods that collectively shape Participatory Design in Germany. In the following, we (1) outline our understanding of participatory practice and how it is different from mere user involvement; (2) reflect current issues of participatory and fair technology design within the German Participatory Design community; and (3) discuss tensions relevant to the field, that we expect to arise in the future, and which we derived from our 2021 workshop through a speculative method. We contribute an introduction and an overview of current themes and a speculative outlook on future issues of Participatory Design in Germany. It is meant to inform, provoke, inspire and, ultimately, invite participation within the wider Computer Science community.

On the role of metaheuristic optimization in bioinformatics

AbstractMetaheuristic algorithms are employed to solve complex and large‐scale optimization problems in many different fields, from transportation and smart cities to finance. This paper discusses how metaheuristic algorithms are being applied to solve different optimization problems in the area of bioinformatics. While the text provides references to many optimization problems in the area, it focuses on those that have attracted more interest from the optimization community. Among the problems analyzed, the paper discusses in more detail the molecular docking problem, the protein structure prediction, phylogenetic inference, and different string problems. In addition, references to other relevant optimization problems are also given, including those related to medical imaging or gene selection for classification. From the previous analysis, the paper generates insights on research opportunities for the Operations Research and Computer Science communities in the field of bioinformatics.

Covid19/IT the digital side of Covid19: A picture from Italy with clustering and taxonomy.

The Covid19 pandemic has significantly impacted on our lives, triggering a strong reaction resulting in vaccines, more effective diagnoses and therapies, policies to contain the pandemic outbreak, to name but a few. A significant contribution to their success comes from the computer science and information technology communities, both in support to other disciplines and as the primary driver of solutions for, e.g., diagnostics, social distancing, and contact tracing. In this work, we surveyed the Italian computer science and engineering community initiatives against the Covid19 pandemic. The 128 responses thus collected document the response of such a community during the first pandemic wave in Italy (February-May 2020), through several initiatives carried out by both single researchers and research groups able to promptly react to Covid19, even remotely. The data obtained by the survey are here reported, discussed and further investigated by Natural Language Processing techniques, to generate semantic clusters based on embedding representations of the surveyed activity descriptions. The resulting clusters have been then used to extend an existing Covid19 taxonomy with the classification of related research activities in computer science and information technology areas, summarizing this work contribution through a reproducible survey-to-taxonomy methodology.

Leveraging Knowledge Graphs and Deep Learning for automatic art analysis

The growing availability of large collections of digitized artworks has disclosed new opportunities to develop intelligent systems for the automatic analysis of fine arts. Among other benefits, these tools can foster a deeper understanding of fine arts, ultimately supporting the spread of culture. However, most of the systems proposed in the literature are only based on visual features of digitized artwork images, which are sometimes only integrated with some metadata and textual comments. A Knowledge Graph (KG) that integrates a rich body of information about artworks, artists, painting schools, etc., in a unified structured framework, can provide a valuable resource for more powerful information retrieval and knowledge discovery tools in the artistic domain. To this end, in this paper we present ArtGraph:11ArtGraph and associated code are publicly available on https://doi.org/10.5281/zenodo.6337958.. an artistic KG based on WikiArt and DBpedia. The graph already provides knowledge discovery capabilities without having to train a learning system. In addition, we propose a novel KG-enabled fine art classification method based on ArtGraph, which is used to perform artwork attribute prediction tasks. The method extracts embeddings from ArtGraph and injects them as “contextual” knowledge into a Deep Learning model. Compared to the state-of-the-art, the proposed model provides encouraging results, suggesting that the exploitation of KGs in combination with Deep Learning can pave the way for bridging the gap between the Humanities and Computer Science communities.

A new adaptive sampling algorithm for big data classification

The exponential growth of the quantity of data that circulates on the web led to the emergence of the big data phenomenon. This fact is a natural consequence of the proliferation of social media, mobile devices, the abundance of free online storage, and new technologies like the internet of things. Subsequently, big data has created several challenges to the computer science community, among which the large size of data is the most challenging. Traditional machine learning algorithms used mostly for insight extraction find themselves inadequate, even on high-performance computer architectures. For instance, big data analytics algorithms can overcome the size issue by either: (1) adapting the existing machine learning techniques to the scale of the big data; or, (2) by sampling big datasets, choosing randomly much smaller subsets of the data population, to meet what current algorithms can handle. In the present work, we aim to proceed through the second alternative to address the size challenge in the big data context. We propose intelligent sampling techniques based on Scalable Simple Random Sampling (ScaSRS) and Subsampled Double Bootstrap (SDB). Test results carried out on public generic datasets show that our proposal is able to address the size dimension efficiently. The proposed algorithms were evaluative on a classification task where the obtained results provided significant improvement compared to the state-of-the-art.

A Survey on Evaluating Usability of Visual Studio

Programing plays an important role in Computer Science (CS) students during their degrees. The study was conducted to evaluate the Microsoft visual studio programming tool to find out usability issues and provides the recommendations. The main goal of this research was to initiate dialog in the CS community to address usability issues can provide better interface to improve the usability of such kind of programming framework. It has been examined by evaluating qualitatively and quantitatively the interface with novice and expert users. Quantitative assessment is done in university with the help of usability testing in order to explore the usability problems of programming tool Visual Studio with the help of quantitative evaluation where satisfaction level is measured. System Usability Scale (SUS) questionnaire and After Scenario Questionnaire (ASQ) is used for the opinion of the participants after usability testing that help to improve the interface of the tool. Qualitative evaluation-usability inspection technique termed as heuristic evaluation is used by Nielson heuristics to improve the usability of the interface. Experiment was conducting at Bahria University Lahore campus in programing course lab under controlled environment. Overall SUS score was 48% of first semester bachelors of information technology (BSIT) students that is below the threshold satisfaction value which recommends that usability issues should be identified. Experts evaluated the interface by 10 Nielson heuristics and highlighted major and, minor issues. Proper interface was suggested by the experts to produce better result.