Abstract

This paper proposes deep architectures for learning instance-specific abstain (reject) option multiclass classifiers. The proposed approach uses novel bounded multiclass abstention loss for multiclass classification as a performance measure. This approach uses rejection cost as the rejection parameter in con- trast to coverage-based approaches. To show the effectiveness of the proposed approach, we experiment with several real-world datasets and compare them with state-of-the-art coverage-based and cost-of-rejection-based techniques. The ex- perimental results show that the proposed method improves performance over the state-of-the-art approaches.

Abstract

The increase of IoT devices and the emergence of smart cities have revolutionized urban development, offering numerous benefits while addressing environmental concerns. This has caused an increase in the usage of IoT frameworks, and the need for efficient architecture and standardized ontology is imminent. In this regard, we propose a distributed, multi-layered data platform architecture comprising the Data Monitoring Layer (DML), Data Storage Layer (DSL), Data Enhancement Layer (DEnL), and Data Exchange Layer (DEL). Our architecture achieves interoperability, facilitates data transfer between nodes, enables telemetry data retrieval, and ensures cross-platform and cross-device compatibility. It addresses the challenges of handling increased sensor data and user demands by providing high throughput and scalability support. We investigated Smart City Living Lab at IIIT Hyderabad an existing large-scale system deployed within a 66-acre campus. This system consists of 291 nodes. By studying this deployed system, we were able to gather valuable real-world data, allowing us to analyze the challenges and potential solutions related to data architecture. Our results show improvements of up to 41.23\% in throughput and a decrease in latency by 29.19\% for data insertion from the sensor nodes. The retrieval by the data client gives an increase of over 800\% in both throughput and number of requests through DENL. These metrics are compared to a centralised data platform architecture. We conclude by discussing the implications of our findings and suggesting future work.

Abstract

This paper talks over an efficient VLSI realization of the simplified arithmetic radix-2 Decimation In Time (DIT) Fast Fourier Transform (FFT) technique. High performance FFT processors are used in several types of signal processing, and in order to fulfil these performance demands, the processor must be parallel and pipelined. This enhanced radix-2 method is used to create an improved ASIC design that implements a fully pipelined and parallel architecture for the hardware realization of a 64 point FFT. This scheme uses lesser multipliers by reducing bit-width of twiddle representation for improved power, area and speed with a considerable Signal to Noise Ratio (SNR). A reduction of 32.8% is obtained in the area occupied, 25.08% reduction in power consumption and 20.8% improvement in speed in comparison to the Cooley–Tukey FFT realization. Compared with serial implementation an improvement of 90

Abstract

Respiratory diseases contribute to a majority of deaths worldwide every year. Diseases such as asthma, bronchitis and pneumonia also adversely impact a person’s social and economic conditions. They can seriously threaten their health if left undiagnosed and untreated. Techniques such as auscultation are used in the diagnosis of most respiratory diseases. However, using such techniques requires an experienced physician and the diagnosis is subjective. To overcome these challenges, in this work, a portable handheld system has been proposed and a proof of concept implemented to detect and classify respiratory diseases automatically through the use of convolutional neural networks (CNN) running on mobile platforms. Mel spectrograms are generated from the audio signals and fed to the CNN for classification. This work makes use of the publicly available HF Lung dataset. The classification accuracy achieved by the current implementation using a Raspberry Pi for processing is 80.55% with a sensitivity of 95.65% and specificity of 98.80% on the HF Lung dataset.

Abstract

One of the widely used peak reduction methods in smart grids is demand response, where one analyzes the shift in customers’ (agents’) usage patterns in response to the signal from the dis- tribution company. Often, these signals are in the form of incentives offered to agents. This work studies the effect of incentives on the prob- abilities of accepting such offers in a real-world smart grid simulator, PowerTAC. We first show that there exists a function that depicts the prob- ability of an agent reducing its load as a func- tion of the discounts offered to them. We call it reduction probability (RP). RP function is fur- ther parametrized by the rate of reduction (RR), which can differ for each agent. We provide an optimal algorithm, MJS–EXPRESPONSE, that outputs the discounts to each agent by maximiz- ing the expected reduction under a budget con- straint. When RRs are unknown, we propose a Multi-Armed Bandit (MAB) based online algo- rithm, namely MJSUCB–EXPRESPONSE, to learn RRs. Experimentally we show that it exhibits sub- linear regret. Finally, we showcase the efficacy of the proposed algorithm in mitigating demand peaks in a real-world smart grid system using the Power- TAC simulator as a test bed.

Abstract

This study investigates the impact of loss-framing and individual risk attitude on the willingness- to purchase insurance products, utilizing a game-like interface in a choice architecture. The application presents events as experienced in real-life , as a young adult searching for employment to retirement. Both financial and emotional loss-framing events are followed by choices to purchase insurance. The participant cohorts considered were undergraduate students and older participants, the latter group was further subdivided by income and education. From the within-subject analysis, the preliminary findings reveal that the loss framing effect on insurance consumption is higher in the younger population though contingent on the insurance product type. Health and accident insurance shows a negative correlation with risk attitudes for the younger age and a positive correlation with accident insurance for older participants. Risk attitude and life insurance products willingness-to-purchase showed no dependency. The findings elucidate the role of age, income, family responsibilities, and risk attitude in purchasing insurance products. Importantly, it confirms the correlation between age and the effect heuristics of framing/nudging.

Abstract

Climate classification simplifies the representation of expected climate conditions by eliminating the need to describe each climatic parameter. Climate classification is frequently used as a basis for recommendations through codes and standards for buildings because a given climate has nearly similar design conditions. Furthermore, building energy efficiency programmes are designed based on the climatic classification to determine appropriate design strategies to eliminate the under-design or over-design of buildings for similar climatic regions. This necessitates the use of realistic and reliable climate classifications. Over the past two decades, numerous research studies have proposed climate classification methods. However, there is a lack of universal acceptance of climate classification methodology to balance complexity and accuracy. This research provides an overview of various climate classification …

Abstract

This work proposes a resource efficient robust control scheme for missile-target engagement scenarios subjected to external disturbances. The robustness is achieved by using an annular event-triggered artificial time-delayed control (ET-TDC) methodology with input saturation. The ET-TDC philosophy uses the TDC strategy through a dynamic predefined triggering mechanism which overcomes the requirement to update the control periodically for every sampling instant, unlike conventional TDC and other robust control schemes. Thus, the proposed methodology, can tackle uncertainties with minimal a priori knowledge while significantly reducing the over-utilization of system resources. In addition, the adopted event triggered mechanism facilitates further conservation of energy which might be crucial for mid-to-long range engagement scenarios. The closed-loop stability is derived analytically and the simulation

Abstract

In this paper we show an effective means of integrating data driven frameworks to sampling based optimal control to vastly reduce the compute time for easy adoption and adaptation to real time applications such as on-road autonomous driving in the presence of dynamic actors. Presented with training examples, a spatio-temporal CNN learns to predict the optimal mean control over a finite horizon that precludes further resampling, an iterative process that makes sampling based optimal control formulations difficult to adopt in real time settings. Generating control samples around the network-predicted optimal mean retains the advantage of sample diversity while enabling real time rollout of trajectories that avoids multiple dynamic obstacles in an on-road navigation setting. Further the 3D CNN architecture implicitly learns the future trajectories of the dynamic agents in the scene resulting in successful collision free …

Abstract

Sign language is a rich form of communication, uniquely conveying meaning through a combination of gestures, facial expressions, and body movements. Existing research in sign language generation has predominantly focused on text-to-sign pose generation, while speech-to-sign pose generation remains relatively underexplored. Speech-to-sign language generation models can facilitate effective communication between the deaf and hearing communities. In this paper, we propose an architecture that utilises prosodic information from speech audio and semantic context from text to generate sign pose sequences. In our approach, we adopt a multi-tasking strategy that involves an additional task of predicting Facial Action Units (FAUs). FAUs capture the intricate facial muscle movements that play a crucial role in conveying specific facial expressions during sign language generation.