Abstract

Evaluation of ill-posed problems like Intrinsic Image Decomposi- tion (IID) is challenging. IID involves decomposing an image into its constituent illumination-invariant Reflectance (R) and albedo- invariant Shading (S) components. Contemporary IID methods use Deep Learning models and require large datasets for training. The evaluation of IID is carried out on either synthetic Ground Truth images or sparsely annotated natural images. A scene can be split into reflectance and shading in multiple, valid ways. Comparison with one specific decomposition in the ground-truth images used by current IID evaluation metrics like LMSE, MSE, DSSIM, WHDR, SAW AP%, etc., is inadequate. Measuring R-S disentanglement is a better way to evaluate the quality of IID. Inspired by ML inter- pretability methods, we propose Concept Sensitivity Metrics (CSM) that directly measure disentanglement using sensitivity to relevant concepts. Activation vectors for albedo invariance and illumination invariance concepts are used for the IID problem. We evaluate and interpret three recent IID methods on our synthetic benchmark of controlled albedo and illumination invariance sets. We also compare our disentanglement score with existing IID evaluation metrics on both natural and synthetic scenes and report our observations. Our code and data are publicly available for reproducibility

Abstract

PERFORMANCE ANALYSIS OF 339 MLD SEWAGE TREATMENT PLANT AT AMBERPET – HYDERABAD. Veerannapet Santhosh Vishal1, Shaik Rehana2, N. Munilakshmi3, L Partha Praveen4 1- Research Scholar, International Institute of Information Technology, Gachibowli, Hyderbad, Telangana-500032. 2- 2- Assistant Professor, International Institute of Information Technology, Gachibowli, Hyderbad, Telangana - 500032. 3- 3- Assistant Professor, Department of Civil Engineering, Sri Venkateswara University College of Engineering, Tirupati, Andhra Pradesh – 517502. 4- 4- Research Scholar, Department of Civil Engineering, Sri Venkateswara University College of Engineering, Tirupati, Andhra Pradesh – 517502 * Corresponding author Email: santhoshvishal.v@research.iiit.ac.in Abstract Environmental and water resources have deteriorated due to rapid population growth, chemical industry effluents, agricultural practices, and climate changes. The primary cause of water contamination is due to sewage water pollution. Hence understanding and implementing an effective sewage treatment is necessary. Many cutting-edge techniques have been developed in recent years to increase the effectiveness of the removal of organic matter and nutrients by wastewater treatment plants (WWTP). To comprehend the effectiveness of wastewater treatment, the current study considered a sewage treatment plant (STP) located in Amberpet, Hyderabad. The capacity of the STP at Amberpet is 339 MLD (Million Litres per Day) and is evaluated by collecting 156 samples for 12 months (January 2018 – December 2018). An STP aims to minimize or remove organic debris, sediments, disease-causing organisms, and other pollutants in sewage water before disposing into the streams. The current study observed the removal efficiencies of the constituents Total Suspended Solids (TSS), Biological Oxygen Demand (BOD), Chemical Oxygen Demand (COD). This investigation assesses whether the effluents emitted into the river body are within the NRCD- set limitations (National River Conservative Directorate) as the treated sewage water is discharged into the Musi River (a tributary of Krishna Basin). The MSE values of different parameters like TSS, BOD, COD are 23.85, 28.54, 72.59. The RMSE values of TSS, BOD, COD are 4.88, 5.32, 8.52. The R2 values of TSS, BOD, COD are 0.95, 0.79, 0.90. Keywords: Wastewater Treatment Plant (WTTP), Biochemical Oxygen Demand, Chemical Oxygen Demand, Total suspended solids

Abstract

River water temperature signifies the health of the river body and regulates many physical and chemical parameters related to river water quality parameters, which speculatively depend on many factors. So far, most river water temperature models are either physical or data-driven models requiring large amounts of hydrological and meteorological observations. Many climate change studies have been conducted in relation to increasing stream water temperatures, but how it affects saturated dissolved oxygen levels have not been addressed. To address these, the present work aims to work with a hybrid model - Air2Stream as a function of air temperature and discharge and also demonstrates how the Air2Stream method can be used to generate accurate RWT predictions and subsequent DO concentrations in river water quality modeling. The Air2Stream model can be used to forecast river water temperature which combines the concepts of the heat budget equation that generalizes the physical processes and infers links between input and output data. The proposed modeling framework's effectiveness is demonstrated with three river gauging stations of Mantralayam, Shimoga and Keesara in the Krishna River basin. Model performance was evaluated by comparing simulated river water temperature time series with corresponding observations using the Nash-Sutcliffe efficiency (NSE) and Root Mean Square Error (RMSE) coefficients. Model results show that for all study sites, NSE values range from 0.76 to 0.97 for

Abstract

Massive knowledge graphs like Wikidata attempt to capture world knowledge about multiple entities. Recent approaches concentrate on automatically enriching these KGs from text. However a lot of information present in the form of natural text in low resource languages is often missed out. Cross Lingual Information Extraction aims at extracting factual information in the form of English triples from low resource Indian Language text. Despite its massive potential, progress made on this task is lagging when compared to Monolingual Information Extraction. In this paper, we propose the task of Cross Lingual Fact Extraction(CLFE) from text and devise an end-to-end generative approach for the same which achieves an overall F1 score of 77.46.

Abstract

There is a rapid increase in the cooperative learning paradigm in online learning settings, i.e., federated learning (FL). Unlike most FL settings, there are many situations where the agents are competitive. Each agent would like to learn from others, but the part of the information it shares for others to learn from could be sensitive; thus, it desires its privacy. This work investigates a group of agents working concurrently to solve similar combinatorial bandit problems while maintaining quality constraints. Can these agents collectively learn while keeping their sensitive information confidential by employing differential privacy? We observe that communicating can reduce the regret. However, differential privacy techniques for protecting sensitive information makes the data noisy and may deteriorate than help to improve regret. Hence, we note that it is essential to decide when to communicate and what shared data to learn to strike a functional balance between regret and privacy. For such a federated combinatorial MAB setting, we propose a Privacy-preserving Federated Combinatorial Bandit algorithm, P-FCB. We illustrate the efficacy of P-FCB through simulations. We further show that our algorithm provides an improvement in terms of regret while upholding quality threshold and meaningful privacy guarantees.

Abstract

Background Depression is an all-too-common mood disorder that has been linked in various ways to the cognitive concept of attention. The Attention Network Test, based on the influential taxonomy of attention originally proposed by Posner, can be used to measure the efficacy of three components or networks of attention: Alerting, Orienting and Executive Control. Our focus here is to discover how depression might affect these networks. Methods Studies related to attention and depression were selected for this meta-analytic review using the online Attention Network Test (ANT) Database (Arora, Lawrence & Klein, 2020) resource. Based on the inclusion and exclusion criteria, 5 publications were analyzed with a Bayesian hierarchical model to compare participants with and without a diagnosis of depression. Results The posterior distribution of our model revealed no credible differences in the Alerting and Orienting networks but showed credible non-zero values for Executive Control. This suggests that Executive Control is less efficient in individuals suffering from depression. Limitations As literature using the ANT with depressed participants is limited, the methodological variability between studies in this meta-analysis should be considered when interpreting these results. Conclusion This meta-analysis review is the first quantitative review that aimed to address the ANT-depression literature. A consistent finding of no alerting and no orienting deficit but a deficit in the executive control suggests that some, but not all, components of attention are impaired in depression.

Abstract

Cognitive impairment, alterations in mood, emotion dysregulation are just a few of the consequences of depression. Despite depression being reported as the most common mental disorder worldwide, examining depression or risks of depression is still challenging. Emotional reactivity has been observed to predict the risk of depression, but the results have been mixed for negative emotional reactivity (NER). To better understand the emotional response conflict, we asked our participants to describe their feeling in meaningful sentences alongside reporting their reactions to the emotionally evocative words. We presented a word on the screen and asked participants to perform two tasks, rate their feeling after reading the word using the self-assessment manikin (SAM) scale, and describe their feeling using the property generation task. The emotional content was analyzed using a novel machine-learning algorithm approach. We performed these two tasks in blocks and

Abstract

Hashtag segmentation is the task of breaking a hashtag into its constituent tokens. Hashtags often encode the essence of usergenerated posts, along with information like topic and sentiment, which are useful in downstream tasks. Hashtags prioritize brevity and are written in unique ways - transliterating and mixing languages, spelling variations, creative named entities. Benchmark datasets used for the hashtag segmentation task - STAN, BOUN - are small in size and extracted from a single set of tweets. However, datasets should reflect the variations in writing styles of hashtags and also account for domain and language specificity, failing which the results will misrepresent model performance. We argue that model performance should be assessed on a wider variety of hashtags, and datasets should be carefully curated. To this end, we propose HashSet, a dataset comprising of: a) 1.9k manually annotated dataset; b) 3.3M loosely supervised dataset. HashSet dataset is sampled from a different set of tweets when compared to existing datasets and provides an alternate distribution of hashtags to build and validate hashtag segmentation models. We show that the performance of SOTA models for Hashtag Segmentation drops substantially on proposed dataset, indicating that the proposed dataset provides an alternate set of hashtags to train and assess models. Datasets and results are released publicly and can be accessed from https://github.com/prashantkodali/HashSet

Abstract

Code mixing is the linguistic phenomenon where bilingual speakers tend to switch between two or more languages in conversations. Recent work on code-mixing in computational settings has leveraged social media code mixed texts to train NLP models. For capturing the variety of code mixing in, and across corpus, Language ID (LID) tags based measures (CMI) have been proposed. Syntactical variety/patterns of code-mixing and their relationship vis-a-vis computational model’s performance is under explored. In this work, we investigate a collection of English(en)-Hindi(hi) code-mixed datasets from a syntactic lens to propose, SyMCoM, an indicator of syntactic variety in code-mixed text, with intuitive theoretical bounds. We train SoTA en-hi PoS tagger, accuracy of 93.4%, to reliably compute PoS tags on a corpus, and demonstrate the utility of SyMCoM by applying it on various syntactical categories on a collection of datasets, and compare datasets using the measure.

Abstract

In the last two decades, Information and Communication Technologies (ICTs) have played a pivotal role in empowering rural populations in India by making knowledge more accessible. Digital Green is one such ICT that employs a participatory approach with smallholder farmers to produce instructional agricultural videos that encompass content specific to them. With the help of human mediators, they disseminate these videos to farmers using projectors to improve the adoption of agricultural practices. Digital Green’s web-based data tracker (CoCo) stores the attendance and adoption logs of millions of farmers, the videos screened to them and their demographic information. In our work, we leverage this data for a period of ten years between 2010-2020 across five states in India where Digital Green is most active and use it to conduct a holistic evaluation of the ICT. First, we find disparities in the adoption rates of farmers, following which we use statistical tests to identify the different factors that lead to these disparities as well as gender-based inequalities. We find that farmers with higher adoption rates adopt videos of shorter duration and belong to smaller villages. Second, to provide assistance to farmers facing challenges, we model the adoption of practices from a video as a prediction problem and experiment with different model architectures. Our classifier achieves accuracies ranging from 79% to 90% across the five states, demonstrating its potential for assisting future ethnographic investigations. Third, we use SHAP values in conjunction with our model for explaining the impact of various network, content and demographic features on adoption. Our research finds that farmers greatly benefit from past adopters of a video from their group and village. We also discover that videos with a low content-specificity benefit some farmers more than others. Next, we highlight the implications of our findings by translating them into recommendations for providing focused assistance, community building, video screening, revisiting participatory approach and mitigating inequalities. Lastly, we conclude with a discussion on how our work can assist future investigations into the lived experiences of farmers. CCS Concepts: • Human-centered computing → Empirical studies in collaborative and social computing. Additional Key Words and Phrases: Diagnosis, ICT4D, Agriculture, Social Networks