Abstract

The people with Major Depressive Disorder (MDD) exhibit the symptoms of tonal variations in their speech compared to the healthy counterparts. However, these tonal variations not only confine to the state of MDD but also on the language, which has unique tonal patterns. This work analyzes automatic speech-based depression detection across two languages, English and Malayalam, which exhibits distinctive prosodic and phonemic characteristics. We propose an approach that utilizes speech data collected along with self-reported labels from participants reading sentences from IViE corpus, in both English and Malayalam. The IViE corpus consists of five sets of sentences: simple sentences, WH-questions, questions without morphosyntactic markers, inversion questions and coordinations, that can naturally prompt speakers to speak in different tonal patterns. Convolutional Neural Networks (CNNs) are employed for detecting depression from speech. The CNN model is trained to identify acoustic features associated with depression in speech, focusing on both languages. The model's performance is evaluated on the collected dataset containing recordings from both depressed and non-depressed speakers, analyzing its effectiveness in detecting depression across the two languages. Our findings and collected data could contribute to the development of language-agnostic speech-based depression detection systems, thereby enhancing accessibility for diverse populations.

Abstract

Mental health conditions such as depression and anxiety are pervasive issues that affect millions of individuals worldwide. Understanding the intricate relationship between emotional perception and mental health is crucial. This work develops a database named IIITSaint-EmoMDB containing Malayalam language speech samples annotated with emotion ratings at valence and arousal scale using three annotators considering four emotion labels: happy, sad, angry and neutral. In addition to emotion ratings, emotional perception is rated from 150 participants according to the circumplex model of va-lence and arousal. The database also consists of self-reported mental health scores of those participants based on PHQ-9 and GAD-7 questionnaire. Our preliminary analysis of comparing the participants' emotional perception based PHQ-9 and GAD-7 scores revealed that the depressed category showed the highest improvement.

Abstract

Depression, a pervasive mental health issue, highlights the critical need for early detection and effective intervention. A database (InStant-EMDB) is developed to analyze varia tions in the spoken responses of individuals with depression compared to healthy counterparts. Spoken responses are ob tained from English and Malayalam bilingual speakers who respond spontaneously to a set of 15 emotionally evocative words. These words are sourced from the Affective Norms for English Words (ANEW) dataset, which includes valence and arousal ratings for each word. The speech in both English and Malayalam is manually transcribed to accurately reflect the spoken content. The dataset also contains self-reported af fective ratings and data from a mental health survey (PHQ-9) collected from the participants to determine their mental state, which we considered the self-reported depression labels. A preliminary analysis is conducted on the collected speech us ing current state-of-the-art deep learning models such as Con volutional Neural Networks (CNN), Long Short-Term Mem ory networks (LSTM) and Bi-directional Long Short-Term Memory networks (Bi-LSTM). Although distinct linguistic patterns exhibited by individuals struggling with depression are successfully identified by all three models in both Malay alam and English spoken responses, the highest accuracy is achieved by the LSTM models. Our findings and dataset em phasize the potential of linguistic patterns as valuable cues for the early identification and intervention of depression and could contribute to enhancing accessibility for diverse popu lations.

Abstract

In safety-critical RL settings, the inclusion of an additional cost function is often favoured over the arduous task of modifying the reward function to ensure the agent's safe behaviour. However, designing or evaluating such a cost function can be prohibitively expensive. For instance, in the domain of self-driving, designing a cost function that encompasses all unsafe behaviours (eg, aggressive lane changes, risky overtakes) is inherently complex, it must also consider all the actors present in the scene making it expensive to evaluate. In such scenarios, the cost function can be learned from feedback collected offline in between training rounds. This feedback can be system generated or elicited from a human observing the training process. Previous approaches have not been able to scale to complex environments and are constrained to receiving feedback at the state level which can be expensive to collect. To this end, we introduce an approach that scales to more complex domains and extends beyond state-level feedback, thus, reducing the burden on the evaluator. Inferring the cost function in such settings poses challenges, particularly in assigning credit to individual states based on trajectory-level feedback. To address this, we propose a surrogate objective that transforms the problem into a state-level supervised classification task with noisy labels, which can be solved efficiently. Additionally, it is often infeasible to collect feedback for every trajectory generated by the agent, hence, two fundamental questions arise:(1) Which trajectories should be presented to the human? and (2) How many trajectories are necessary for effective learning?

Abstract

Preserving the privacy of preferences (or rewards) of a sequential decision-making agent when decisions are observable is crucial in many physical and cybersecurity domains. For instance, in wildlife monitoring, forest rangers must conduct surveillance without revealing animal locations to poachers. This paper addresses privacy preservation in planning over a sequence of actions in MDPs, where the reward function represents the preference structure to be protected. Observers can use Inverse RL (IRL) to learn these preferences, making this a challenging task. Current research on Differential Privacy (DP) in this setting fails to ensure a lower bound on the minimum expected reward and offers theoretical guarantees that are inadequate against IRL-based observers. To bridge this gap, we propose a novel approach rooted in the theory of deception. Deception includes two models: dissimulation (hiding the truth) and simulation (showing the wrong). As our first contribution, we theoretically demonstrate a significant privacy leak in the current dissimulation-based method. Our second contribution is a novel RL-based planning algorithm that uses simulation to effectively address these privacy concerns while ensuring a guarantee on the expected reward. Through experimentation on multiple benchmark problems, we show that our proposed approach outperforms existing methods in preserving the privacy of reward functions.

Abstract

Bell non-locality and steering are archetypal characteristics of quantum mechanics that mark a significant departure from conventional classical notions. They basically refer to the presence of quantum correlations between separated systems which violate a non-local inequality, the violation otherwise is not possible if we restrict ourselves only to classical correlations. In view of the importance of such unique correlations, one may be interested to generate more states exhibiting non-locality starting from a few, a protocol which is termed as broadcasting. However, in the present submission, we show using universal Buzek–Hillary (BH) quantum cloning machine that, if one restricts to broadcasting through local quantum cloning, then such non-locality cannot be broadcasted. Our study is done in the purview of the Bell-CHSH inequality and the CJWR [E G Cavalcanti et al, Phys. Rev. A 80, 032112 (2009)] steering inequality. It is observed that when the number of measurement settings is greater than 6, some of the output states are steerable after the application of local optimal BH cloners. We found that, under some restrictions, if the Werner and Bell diagonal states are subjected to such procedures, then the resultant state is rendered unsteerable. We extended this study to three qubit systems and found that genuine tripartite non-locality cannot be broadcasted using universal BH local quantum cloners, when the Svetlichny’s inequality was considered. For two qubit systems, we considered simulated general local unitaries over Werner and Bell-diagonal states and found that for none of these states, broadcasting on non-locality and 3-steerability is possible.

Abstract

Free-chlorine concentration monitoring is of importance in public and industrial water supplies. Current colorimetric methods, which include test strips, spectrophotometric kits, etc. either lack precision or are expensive and labor intensive. In this study, we present a fully automated, cost-effective method of measurement of free chlorine concentration in real -time. The setup includes an automatic powder dispenser, an automatic liquid dispenser, a sample chamber, and an LED-light-dependent resistor sensor pair. The liquid sample is mixed with a coloring reagent and its color is measured using the sensor pair. Different regression algorithms were trained on the sensor data and tuned to predict the corresponding free-chlorine concentration with maximum accuracy. The system eliminates the need for color matching, reduces the time taken per test, and can be used to predict concentrations of multiple analytes, including ammonia-nitrogen, dissolved oxygen, etc., by adding corresponding colorimetry agents. This allows for a fully automated, real-time water testing system.

Abstract

Analysis of foot pressure, also known as plantar pressure analysis, plays a pivotal role in biomedical assessments related to posture and gait analysis. Extensive research has been conducted on leveraging this technique for clinical purposes, leading to the development of flexible pressure sensors. In this letter, we present the use of in-shoe flexible pressure sensor array for determining the nature of the walking surface. The sensor system is fabricated using eight low-cost and robust, in-shoe pressure sensors that leverage the piezoresistivity of velostat. The sensor array was characterized for four different surface types. Random Forest (RF) algorithm was used to classify the surfaces with 86% accuracy. Based on this analysis, we propose a novel method for analyzing various surfaces based on their attributes such as firmness, rigidity, and penetrability.

Abstract

The rapid proliferation of Internet of Things (IoT) devices and applications has resulted in an increasing demand for Low Power and Wide Area Network (LPWAN) solutions. The adoption of IoT networks still faces several challenges, despite the rapid advancement of low-power communication technology. Homogenizing this sector requires allowing interoperability between many technologies, which is now one of the largest obstacles. In this article, we present the design and implementation of the hybrid LPWAN architecture that can accomplish wide-area communication coverage and low-power consumption for IoT applications by leveraging two LPWAN technologies, Wireless Smart Ubiquitous Network (Wi-SUN) and Long Range (LoRa). In particular, LoRa is used for long-range communication, and Wi-SUN for a low-latency mesh network. Additionally, we implemented smart street light controlling system as a real-world deployment at the university campus to showcase the efficiency of the hybrid network. Our results demonstrate that the hybrid LPWAN architecture provides a better coverage and capacity while consuming less power than that of the LoRa or Wi-SUN network. The results of this study demonstrate the effectiveness of the proposed hybrid LPWAN architecture as a viable solution for next-generation IoT applications.

Abstract

Affordable healthcare, particularly for elderly persons, is an important goal with aging of the world population. Cloud-connected smart sensor systems are an important part of the healthcare ecosystem. In this letter, we present an affordable large area flexible pressure sensor array using a piezoresistive thin film. The dimensions of the sensor are 180 cm × 90 cm, according to the dimensions of a standard single bed mattress. The sensor array consists of eight vertical sensor strips with a high aspect ratio of 120, highest reported so far for a flexible piezoresistive sensor. The measured output of the sensors showed a high signal-to-noise ratio, with loaded and unloaded sensor resistances of 11 pm 3 Omega and 219.2 pm 0.5 kOmega, respectively. The fabrication process has been designed to be conducive to roll-to-roll manufacturing processes to increase scalability and reduce cost. With a sampling frequency of 10 Hz, the sensor array provides real-time information about user position and possible fall events.