Search

In this paper, we introduce ConversaSynth, a framework designed to generate synthetic conversation audio using large language models (LLMs) with multiple persona settings. The framework first creates diverse and coherent text-based dialogues across various topics, which are then converted into audio using text-to-speech (TTS) systems. Our experiments demonstrate that ConversaSynth effectively generates highquality synthetic audio datasets, which can significantly enhance the training and evaluation of models for audio tagging, audio classification, and multi-speaker speech recognition. The results indicate that the synthetic datasets generated by ConversaSynth exhibit substantial diversity and realism, making them suitable for developing robust, adaptable audio-based AI systems., Comment: This work has been submitted for consideration at the WI-IAT'24 to be held in December 2024

Generalized large language models (LLMs) such as GPT-4 may not provide specific answers to queries formulated by materials science researchers. These models may produce a high-level outline but lack the capacity to return detailed instructions on manufacturing and material properties of novel alloys. Enhancing a smaller model with specialized domain knowledge may provide an advantage over large language models which cannot be retrained quickly enough to keep up with the rapid pace of research in metal additive manufacturing (AM). We introduce "AMGPT," a specialized LLM text generator designed for metal AM queries. The goal of AMGPT is to assist researchers and users in navigating the extensive corpus of literature in AM. Instead of training from scratch, we employ a pre-trained Llama2-7B model from Hugging Face in a Retrieval-Augmented Generation (RAG) setup, utilizing it to dynamically incorporate information from $\sim$50 AM papers and textbooks in PDF format. Mathpix is used to convert these PDF documents into TeX format, facilitating their integration into the RAG pipeline managed by LlamaIndex. Expert evaluations of this project highlight that specific embeddings from the RAG setup accelerate response times and maintain coherence in the generated text., Comment: 54 pages, 4 figures

The emergence of natural language processing has revolutionized the way users interact with tabular data, enabling a shift from traditional query languages and manual plotting to more intuitive, language-based interfaces. The rise of large language models (LLMs) such as ChatGPT and its successors has further advanced this field, opening new avenues for natural language processing techniques. This survey presents a comprehensive overview of natural language interfaces for tabular data querying and visualization, which allow users to interact with data using natural language queries. We introduce the fundamental concepts and techniques underlying these interfaces with a particular emphasis on semantic parsing, the key technology facilitating the translation from natural language to SQL queries or data visualization commands. We then delve into the recent advancements in Text-to-SQL and Text-to-Vis problems from the perspectives of datasets, methodologies, metrics, and system designs. This includes a deep dive into the influence of LLMs, highlighting their strengths, limitations, and potential for future improvements. Through this survey, we aim to provide a roadmap for researchers and practitioners interested in developing and applying natural language interfaces for data interaction in the era of large language models., Comment: 20 pages, 4 figures, 5 tables. Accepted by IEEE TKDE

Freezing of gait is a Parkinson's Disease symptom that episodically inflicts a patient with the inability to step or turn while walking. While medical experts have discovered various triggers and alleviating actions for freezing of gait, the underlying causes and prediction models are still being explored today. Current freezing of gait prediction models that utilize machine learning achieve high sensitivity and specificity in freezing of gait predictions based on time-series data; however, these models lack specifications on the type of freezing of gait events. We develop various deep learning models using the transformer encoder architecture plus Bidirectional LSTM layers and different feature sets to predict the three different types of freezing of gait events. The best performing model achieves a score of 0.427 on testing data, which would rank top 5 in Kaggle's Freezing of Gait prediction competition, hosted by THE MICHAEL J. FOX FOUNDATION. However, we also recognize overfitting in training data that could be potentially improved through pseudo labelling on additional data and model architecture simplification., Comment: 5 pages

In treating gastrointestinal cancer using radiotherapy, the role of the radiation oncologist is to administer high doses of radiation, through x-ray beams, toward the tumor while avoiding the stomach and intestines. With the advent of precise radiation treatment technology such as the MR-Linac, oncologists can visualize the daily positions of the tumors and intestines, which may vary day to day. Before delivering radiation, radio oncologists must manually outline the position of the gastrointestinal organs in order to determine position and direction of the x-ray beam. This is a time consuming and labor intensive process that may substantially prolong a patient's treatment. A deep learning (DL) method can automate and expedite the process. However, many deep neural networks approaches currently in use are black-boxes which lack interpretability which render them untrustworthy and impractical in a healthcare setting. To address this, an emergent field of AI known as Explainable AI (XAI) may be incorporated to improve the transparency and viability of a model. This paper proposes a deep learning pipeline that incorporates XAI to address the challenges of organ segmentation., Comment: 5 pages, 8 figures, 13th Joint Symposium on Computational Intelligence (JSCI13)

A hierarchy of type universes is a rudimentary ingredient in the type theories of many proof assistants to prevent the logical inconsistency resulting from combining dependent functions and the type-in-type rule. In this work, we argue that a universe hierarchy is not the only option for a type theory with a type universe. Taking inspiration from Leivant's Stratified System F, we introduce Stratified Type Theory (StraTT), where rather than stratifying universes by levels, we stratify typing judgements and restrict the domain of dependent functions to strictly lower levels. Even with type-in-type, this restriction suffices to enforce consistency. In StraTT, we consider a number of extensions beyond just stratified dependent functions. First, the subsystem subStraTT employs McBride's crude-but-effective stratification (also known as displacement) as a simple form of level polymorphism where global definitions with concrete levels can be displaced uniformly to any higher level. Second, to recover some expressivity lost due to the restriction on dependent function domains, the full StraTT includes a separate nondependent function type with a "floating" domain whose level matches that of the overall function type. Finally, we have implemented a prototype type checker for StraTT extended with datatypes and inference for level and displacement annotations, along with a small core library. We have proven subStraTT to be consistent and StraTT to be type safe, but consistency of the full StraTT remains an open problem, largely due to the interaction between floating functions and cumulativity of judgements. Nevertheless, we believe StraTT to be consistent, and as evidence have verified the failure of some well-known type-theoretic paradoxes using our implementation., Comment: 26 pages, 4 figures

The emergence of virtual companions is transforming the evolution of intelligent systems that effortlessly cater to the unique requirements of users. These advanced systems not only take into account the user present capabilities, preferences, and needs but also possess the capability to adapt dynamically to changes in the environment, as well as fluctuations in the users emotional state or behavior. A virtual companion is an intelligent software or application that offers support, assistance, and companionship across various aspects of users lives. Various enabling technologies are involved in building virtual companion, among these, Augmented Reality (AR), and Virtual Reality (VR) are emerging as transformative tools. While their potential for use in virtual companions or digital assistants is promising, their applications in these domains remain relatively unexplored. To address this gap, a systematic review was conducted to investigate the applications of VR, AR, and MR immersive technologies in the development of virtual companions. A comprehensive search across PubMed, Scopus, and Google Scholar yielded 28 relevant articles out of a pool of 644. The review revealed that immersive technologies, particularly VR and AR, play a significant role in creating digital assistants, offering a wide range of applications that brings various facilities in the individuals life in areas such as addressing social isolation, enhancing cognitive abilities and dementia care, facilitating education, and more. Additionally, AR and MR hold potential for enhancing Quality of life (QoL) within the context of virtual companion technology. The findings of this review provide a valuable foundation for further research in this evolving field.

Child dehydration is a significant health concern, especially among children under 5 years of age who are more susceptible to diarrhea and vomiting. In Afghanistan, severe diarrhea contributes to child mortality due to dehydration. However, there is no evidence of research exploring the potential of machine learning techniques in diagnosing dehydration in Afghan children under five. To fill this gap, this study leveraged various classifiers such as Random Forest, Multilayer Perceptron, Support Vector Machine, J48, and Logistic Regression to develop a predictive model using a dataset of sick children retrieved from the Afghanistan Demographic and Health Survey (ADHS). The primary objective was to determine the dehydration status of children under 5 years. Among all the classifiers, Random Forest proved to be the most effective, achieving an accuracy of 91.46%, precision of 91%, and AUC of 94%. This model can potentially assist healthcare professionals in promptly and accurately identifying dehydration in under five children, leading to timely interventions, and reducing the risk of severe health complications. Our study demonstrates the potential of machine learning techniques in improving the early diagnosis of dehydration in Afghan children.

Social Engineering has emerged as a significant threat in cyber security. In a dialog based attack, by having enough of a potential victim's personal data to be convincing, a social engineer impersonates the victim in order to manipulate the attack's target into revealing sufficient information for accessing the victim's accounts etc. We utilise the developing understanding of human information processing in the Information Sciences to characterise the vulnerability of the target to manipulation and to propose a form of countermeasure. Our focus is on the possibility of the social engineer being able to build the victim's profile by, in part, inferring personal attribute values from statistical information available either informally, from general knowledge, or, more formally, from some public database. We use an orthogonalised log linear analysis of data in the form of a contingence table to develop a measure of how susceptible particular subtables are to probabilistic inference as the basis for our proposed countermeasure. This is based on the observation that inference relies on a high degree of non-uniformity and exploits the orthogonality of the analysis to define the measure in terms of subspace projections., Comment: 28 pages, 1 figure

Purpose: Health recommenders act as important decision support systems, aiding patients and medical professionals in taking actions that lead to patients' well-being. These systems extract the information which may be of particular relevance to the end-user, helping them in making appropriate decisions. The present study proposes a feature recommender, as a part of a disease management system, that identifies and recommends the most important risk factors for an illness. Methods: A novel mutual information and ensemble-based feature ranking approach for identifying critical risk factors in healthcare prognosis is proposed. Results: To establish the effectiveness of the proposed method, experiments have been conducted on four benchmark datasets of diverse diseases (clear cell renal cell carcinoma (ccRCC), chronic kidney disease, Indian liver patient, and cervical cancer risk factors). The performance of the proposed recommender is compared with four state-of-the-art methods using recommender systems' performance metrics like average precision@K, precision@K, recall@K, F1@K, reciprocal rank@K. The method is able to recommend all relevant critical risk factors for ccRCC. It also attains a higher accuracy (96.6% and 98.6% using support vector machine and neural network, respectively) for ccRCC staging with a reduced feature set as compared to existing methods. Moreover, the top two features recommended using the proposed method with ccRCC, viz. size of tumor and metastasis status, are medically validated from the existing TNM system. Results are also found to be superior for the other three datasets. Conclusion: The proposed recommender can identify and recommend risk factors that have the most discriminating power for detecting diseases.

The term personality may be expressed in terms of the individual differences in characteristics pattern of thinking, feeling, and behavior. This work presents several machine learning techniques including Naive Bayes, Support Vector Machines, and Recurrent Neural Networks to predict people personality from text based on Myers-Briggs Type Indicator (MBTI). Furthermore, this project applies CRISP-DM, which stands for Cross-Industry Standard Process for Data Mining, to guide the learning process. Since, CRISP-DM is kind of iterative development, we have adopted it with agile methodology, which is a rapid iterative software development method, in order to reduce the development cycle to be minimal., Comment: 10 pages, 14 figures, this work was presented at the 11th Joint Symposium on Computational Intelligence (JSCI11)

We develop a new analysis for portfolio optimisation with options, tackling the three fundamental issues with this problem: asymmetric options' distributions, high dimensionality and dependence structure. To do so, we propose a new dependency matrix, built upon conditional probabilities between options' payoffs, and show how it can be computed in closed form given a copula structure of the underlying asset prices. The empirical evidence we provide highlights that this approach is efficient, fast and easily scalable to large portfolios of (mixed) options., Comment: 29 pages, 24 pictures, 5 tables

The current COVID-19 pandemic has put a huge challenge on the Indian health infrastructure. With more and more people getting affected during the second wave, the hospitals were over-burdened, running out of supplies and oxygen. In this scenario, prediction of the number of COVID-19 cases beforehand might have helped in the better utilization of limited resources and supplies. This manuscript deals with the prediction of new COVID-19 cases, new deaths and total active cases for multiple days in advance. The proposed method uses gated recurrent unit networks as the main predicting model. A study is conducted by building four models that are pre-trained on the data from four different countries (United States of America, Brazil, Spain and Bangladesh) and are fine-tuned or retrained on India's data. Since the four countries chosen have experienced different types of infection curves, the pre-training provides a transfer learning to the models incorporating diverse situations into account. Each of the four models then give a multiple days ahead predictions using recursive learning method for the Indian test data. The final prediction comes from an ensemble of the predictions of the combination of different models. This method with two countries, Spain and Brazil, is seen to achieve the best performance amongst all the combinations as well as compared to other traditional regression models., Comment: 8 pages, 7 figures

For the modeling, design and planning of future energy transmission networks, it is vital for stakeholders to access faithful and useful power flow data, while provably maintaining the privacy of business confidentiality of service providers. This critical challenge has recently been somewhat addressed in [1]. This paper significantly extends this existing work. First, we reduce the potential leakage information by proposing a fundamentally different post-processing method, using public information of grid losses rather than power dispatch, which achieve a higher level of privacy protection. Second, we protect more sensitive parameters, i.e., branch shunt susceptance in addition to series impedance (complete pi-model). This protects power flow data for the transmission high-voltage networks, using differentially private transformations that maintain the optimal power flow consistent with, and faithful to, expected model behaviour. Third, we tested our approach at a larger scale than previous work, using the PGLib-OPF test cases [10]. This resulted in the successful obfuscation of up to a 4700-bus system, which can be successfully solved with faithfulness of parameters and good utility to data analysts. Our approach addresses a more feasible and realistic scenario, and provides higher than state-of-the-art privacy guarantees, while maintaining solvability, fidelity and feasibility of the system.

Contemporary proof assistants such as Coq require that recursive functions be terminating and corecursive functions be productive to maintain logical consistency of their type theories, and some ensure these properties using syntactic checks. However, being syntactic, they are inherently delicate and restrictive, preventing users from easily writing obviously terminating or productive functions at their whim. Meanwhile, there exist many sized type theories that perform type-based termination and productivity checking, including theories based on the Calculus of (Co)Inductive Constructions (CIC), the core calculus underlying Coq. These theories are more robust and compositional in comparison. So why haven't they been adapted to Coq? In this paper, we venture to answer this question with CIC$\widehat{*}$, a sized type theory based on CIC. It extends past work on sized types in CIC with additional Coq features such as global and local definitions. We also present a corresponding size inference algorithm and implement it within Coq's kernel; for maximal backward compatibility with existing Coq developments, it requires no additional annotations from the user. In our evaluation of the implementation, we find a severe performance degradation when compiling parts of the Coq standard library, inherent to the algorithm itself. We conclude that if we wish to maintain backward compatibility, using size inference as a replacement for syntactic checking is wildly impractical in terms of performance., Comment: 55 pages with 22 figures and 3 tables. Submitted to the Journal of Functional Programming. For associated artifact, see https://doi.org/10.5281/zenodo.5661975

For a prime power $q$, we show that the discriminants of monic polynomials in $\mathbb{F}_q[x]$ of a fixed degree $m$ are equally distributed if $\gcd(q-1,m(m-1))=2$ when $q$ is odd and $\gcd(q-1,m(m-1))=1$ if $q$ is even. A theorem in the converse direction is proved when $q-1$ is squarefree.