arXiv subjects

Anand Paul

Publications and source records attributed to Anand Paul.

8 recordsLinked to original sources

arXiv2025

Gesture2Music: A Low-Latency Real-Time Framework for Continuous Gesture-Driven Music Generation

Gesture-driven music generation is an emerging human-computer interaction paradigm for touch-free and expressive musical interaction. However, many existing approaches treat the task as isolated gesture classification or map gestures to symbolic outputs such as MIDI followed by a separate rendering stage, which limits temporal continuity and real-time responsiveness. This work presents Gesture2Music, a low-latency streaming framework for continuous gesture-driven music generation from live webcam feed. The system processes sequences of body and hand landmarks and uses a causal temporal convolutional network (TCN) to predict note-level musical control events, including pitch, octave, onset, sustain, amplitude, and activity state. Because available gesture-note datasets typically contain only isolated single-note recordings rather than continuous performance sequences, a synthetic stream generation strategy is introduced to construct continuous gesture streams by concatenating single-note clips and deriving heuristic temporal event labels. Temporal consistency and spectral proxy losses are further used to reduce prediction jitter and encourage audio-consistent outputs. During inference, predicted musical events are rendered into continuous music using predefined note samples with rhythmic quantization and scale-constrained filtering for improved musical stability. Experiments on a custom gesture-to-music dataset with 21 gesture-note classes spanning seven tones across three pitch levels demonstrate stable real-time performance, low inference latency of 30\,ms, and improved temporal continuity.

cs.MM↗

arXiv2025

Sequencing, task failures, and capacity when failures are driven by a non-homogeneous Poisson process

We study the optimal sequencing of a batch of tasks on a machine subject to random disruptions driven by a non-homogeneous Poisson process (NHPP), such that every disruption requires the interrupted task to be re-processed from scratch, and partially completed work on a disrupted task is wasted. The NHPP models random disruptions whose frequency varies systematically with time. In general the time taken to process a given batch of tasks depends on the order in which the tasks are processed. We find conditions under which the simplest possible sequencing rules - shortest processing time first (SPT) and longest processing time first (LPT) - suffice to minimize the completion time of a batch of tasks.

math.PR↗

arXiv2024

Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning

Activation functions govern how recurrent networks regulate and transmit information across temporal dependencies. Despite advances in sequence modelling, gated recurrent units (GRUs) still depend on the standard sigmoid and tanh nonlinearities, which can produce weak gate separation and unstable learning, particularly when training data are limited. We introduce squared sigmoid-tanh (SST), a parameter-free activation that squares the gate nonlinearity to increase contrast between near-zero- and high-activations, thereby promoting sharper information filtering during GRU updates. We incorporate SST into GRU gating and evaluate it across low-data settings spanning sign language recognition, human activity recognition, and time-series forecasting and classification. Across tasks, SST-GRU consistently surpasses standard sigmoid/tanh GRU, with the largest improvements observed in the smallest-data domains, while adding negligible computational cost. We further examine gate activation statistics and training dynamics, showing that SST improves training stability, which aligns with its performance gains in data-scarce settings. SST is a parameter-free modification that complements more complex architectural advances by improving gating selectivity in low-data sequence learning.

cs.LG↗

arXiv2023

A Fitness-assignment Method for Evolutionary Constrained Multi-objective Optimization

The effectiveness of Constrained Multi-Objective Evolutionary Algorithms (CMOEAs) depends on their ability to reach the different feasible regions during evolution, by exploiting the information present in infeasible solutions, in addition to optimizing the several conflicting objectives. Over the years, researchers have proposed several CMOEAs to handle Constrained Multi-objective Optimization Problems (CMOPs). However, most of the proposed CMOEAs with scalable performance are too complex because they are either multi-staged or multi-population-based algorithms. Consequently, to ensure the simplicity of CMOEAs, researchers have proposed different fitness-assignment-based CMOEAs by combining different fitness-assignment-based methods used to solve unconstrained multi-objective problems with information regarding the feasibility of each solution. The main performance drawback of such methods is that it is difficult to design a fitness assignment method that can account for constraint violation in addition to convergence and diversity. Hence in this paper, we propose an effective single-population fitness assignment-based CMOEA referred to as IcSDE+ that can explore different feasible regions in the search space. IcSDE+ is a fitness assignment-based algorithm, that is an efficient fusion of constraint violation (c), Shift-based Density Estimation (SDE), and sum of objectives (+). The performance of IcSDE+ is favorably compared against 9 state-of-the-art CMOEAs on 6 different benchmark suites with diverse characteristics.

cs.NE↗

arXiv2021

Nonnegative Matrix Factorization to understand Spatio-Temporal Traffic Pattern Variations during COVID-19: A Case Study

Due to the rapid developments in Intelligent Transportation System (ITS) and increasing trend in the number of vehicles on road, abundant of road traffic data is generated and available. Understanding spatio-temporal traffic patterns from this data is crucial and has been effectively helping in traffic plannings, road constructions, etc. However, understanding traffic patterns during COVID-19 pandemic is quite challenging and important as there is a huge difference in-terms of people's and vehicle's travel behavioural patterns. In this paper, a case study is conducted to understand the variations in spatio-temporal traffic patterns during COVID-19. We apply nonnegative matrix factorization (NMF) to elicit patterns. The NMF model outputs are analysed based on the spatio-temporal pattern behaviours observed during the year 2019 and 2020, which is before pandemic and during pandemic situations respectively, in Great Britain. The outputs of the analysed spatio-temporal traffic pattern variation behaviours will be useful in the fields of traffic management in Intelligent Transportation System and management in various stages of pandemic or unavoidable scenarios in-relation to road traffic.

cs.LG↗

arXiv2020

I/Q Imbalance Aware Nonlinear Wireless-Powered Relaying of B5G Networks: Security and Reliability Analysis

Physical layer security is known as a promising paradigm to ensure security for the beyond 5G (B5G) networks in the presence of eavesdroppers. In this paper, we elaborate on a tractable analysis framework to evaluate the reliability and security of wireless-powered decode-and-forward (DF) multi-relay networks. The nonlinear energy harvesters, in-phase and quadrature-phase imbalance (IQI) and channel estimation errors (CEEs) are taken into account in the considered system. To further improve the secure performance, two relay selection strategies are presented: 1) suboptimal relay selection (SRS); 2) optimal relay selection (ORS). Specifically, exact analytical expressions for the outage probability (OP) and the intercept probability (IP) are derived in closed-form. For the IP, we consider that the eavesdropper can wiretap the signal from the source or the relay. In order to obtain more useful insights, we carry out the asymptotic analysis and diversity orders for the OP in the high signal-to-noise ratio (SNR) regime under non-ideal and ideal conditions. Numerical results show that: 1) Although the mismatches of amplitude/phase of transmitter (TX)/receiver (RX) limit the OP performance, it can enhance IP performance; 2) Large number of relays yields better OP performance; 3) There are error floors for the OP because of the CEEs; 4) There is a trade-off for the OP and IO to obtain the balance between reliability and security.

eess.SP↗

arXiv2020

A.I. based Embedded Speech to Text Using Deepspeech

Deepspeech was very useful for development IoT devices that need voice recognition. One of the voice recognition systems is deepspeech from Mozilla. Deepspeech is an open-source voice recognition that was using a neural network to convert speech spectrogram into a text transcript. This paper shows the implementation process of speech recognition on a low-end computational device. Development of English-language speech recognition that has many datasets become a good point for starting. The model that used results from pre-trained model that provide by each version of deepspeech, without change of the model that already released, furthermore the benefit of using raspberry pi as a media end-to-end speech recognition device become a good thing, user can change and modify of the speech recognition, and also deepspeech can be standalone device without need continuously internet connection to process speech recognition, and even this paper show the power of Tensorflow Lite can make a significant difference on inference by deepspeech rather than using Tensorflow non-Lite.This paper shows the experiment using Deepspeech version 0.1.0, 0.1.1, and 0.6.0, and there is some improvement on Deepspeech version 0.6.0, faster while processing speech-to-text on old hardware raspberry pi 3 b+.

eess.AS↗

arXiv2010

Morphological dilation image coding with context weights prediction

This paper proposes an adaptive morphological dilation image coding with context weights prediction. The new dilation method is not to use fixed models, but to decide whether a coefficient needs to be dilated or not according to the coefficient's predicted significance degree. It includes two key dilation technologies: 1) controlling dilation process with context weights to reduce the output of insignificant coefficients, and 2) using variable-length group test coding with context weights to adjust the coding order and cost as few bits as possible to present the events with large probability. Moreover, we also propose a novel context weight strategy to predict coefficient's significance degree more accurately, which serves for two dilation technologies. Experimental results show that our proposed method outperforms the state of the art image coding algorithms available today.

cs.IT↗