11563 research outputs found
Sort by
Cascade-trained deep reinforcement learning for PID gain optimization in precise joint position control of 6-DoF robotic arm
No full textThe problem of precise joint position tracking has remained as a core challenge for a 6-DoF Cobot arm, especially due to often scenario of an arbitrary waypoint reference trajectory generated due to human interactions. To tackle this problem, we propose a novel cascade training based Deep Reinforcement Learning (DRL) algorithm that tunes the PID controller gains for each joint simultaneously, ensuring accurate positional tracking for all joints. This also addresses the problem of overestimation of control parameters by ensuring that performance criteria are met in a phased manner during the training process. The tuned DRL based PID clearly outperforms the conventional PID control by accurately tracking the arbitrary waypoints given to each joints of the Cobot arm. We show the efficacy of the proposed method through exhaustive simulations and performing quantitative analysis of various key performance criteria like- Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Average Control Effort (ACE) error for the Cobot. The obtained results of DRL-PID control, when compared with its conventional PID counterpart, clearly depict the superiority of the proposed DRL-PID scheme via a cascade training approach. We have also remarked on some trade off and implementation aspects of the proposed control policy for the Cobot based applications. This method has the potential to be applicable to similar complex dynamical systems like a Cobot, where arbitrary reference and human interactions are prime concerns
Exploring structures-properties and interactions of acrylic-hydrogel adsorbents with metal ions and organics using nuclear magnetic resonance and Fourier transform infrared spectroscopies
No full textNowadays, multifunctional acrylic hydrogels are becoming extremely popular because of their prospective applications stemmed from improved durability, water retention capacity, recyclability, sustainability, and binding capacity through structural alterations at molecular/supramolecular level. Detailed spectrochemical investigations based on nuclear magnetic resonance (NMR) and Fourier transform infrared (FTIR) analyses are mandatory for overall structural elucidation as well as the detection, quantification, and alteration of diverse functionalities influencing strength, population, and reversible/irreversible nature of inter-/intra-molecular covalent and non-covalent interactions inside the unloaded/loaded acrylic hydrogels, status of dispersion and aggregation, nature of water cluster, oxidation/reduction of adsorbed metal ions, and adsorption-desorption mechanism(s). Analyzing and comparing 1H/13C NMR spectra; spatial arrangement and involvement of various protons/carbons in covalent and non-covalent interactions; C–C, C–N, and C–O coupling; polymerization; incorporation of individual components; crosslinking; grafting; spacial arrangement of protons/carbons; and in situ comonomer formation can be understood from the alteration of signals through shielding and deshielding effects of electron clouds. Regarding this, FTIR spectra can indicate various key events including conventional/nonconventional hydrogen bonding interactions, protonation/deprotonation, mode of coordination, and reversible/irreversible nature of bonds. Accordingly, present review covers the principles of NMR and FTIR analyses followed by the collection, compilation, and discussion of major peaks, reason(s) for the variation in the peak shifting, and associated significances. Subsequently, factors responsible behind the alterations in spectrochemical data and key findings of these spectroscopic techniques are summarized and discussed in understanding the structures, properties, and interactions of acrylic hydrogels/similar polymeric materials with metal ions/organics
How Good is your Drawing? Quantifying Graphomotor Skill Using a Portable Platform
No full textGraphomotor skill essential for completing various academic activities such as drawing of shapes or handwriting of text is conventionally judged based on observation in terms of graphic output�s similarity with a reference and often tends to miss other aspects, like one�s pen-tip velocity that can affect the quality of the graphic output. Thus, there exists a need to quantify one�s graphomotor skills while incorporating both pen-tip velocity and the quality of the graphic output (in terms of similarity/dissimilarity with a reference template). Hence, we have developed a tablet-based platform to quantify one�s graphomotor skill in terms of a Graphomotor Skill Index (a single numeric value obtained as a linear combination of pen-tip velocity and quality of graphic output). A feasibility study with eight pairs of typically developing children and those with Autism indicated that the Graphomotor Skill Index can capture heterogeneity in their graphomotor skills suggesting the potential of the platform for assessment of one�s graphomotor skill. � 2022 Elsevier B.V., All rights reserved
Classifying EEG Signals of�Mind-Wandering Across Different Styles of�Meditation
No full textIn the modern world, it is easy to get lost in thought, partly because of the vast knowledge available at our fingertips via smartphones that divide our cognitive resources and partly because of our intrinsic thoughts. In this work, we aim to find the differences in the neural signatures of mind-wandering and meditation that are common across different meditative styles. We use EEG recording done during meditation sessions by experts of different meditative styles, namely shamatha, zazen, dzogchen, and visualization. We evaluate the models using the leave-one-out validation technique to train on three meditative styles and test the fourth left-out style. With this method, we achieve an average classification accuracy of above 70%, suggesting that EEG signals of meditation techniques have a unique neural signature across meditative styles and can be differentiated from mind-wandering states. In addition, we generate lower-dimensional embeddings from higher-dimensional ones using t-SNE, PCA, and LLE algorithms and observe visual differences in embeddings between meditation and mind-wandering. We also discuss the general flow of the proposed design and contributions to the field of neuro-feedback-enabled mind-wandering detection and correction devices. � 2022 Elsevier B.V., All rights reserved
Boxicity and cubicity of divisor graphs and power graphs
No full textThe boxicity (cubicity) of an undirected graph ? is the smallest non-negative integer k such that ? can be represented as the intersection graph of axis-parallel rectangular boxes (unit cubes) in Rk. An undirected graph is classified as a comparability graph if it is isomorphic to the comparability graph of some partial order. This paper studies boxicity and cubicity for subclasses of comparability graphs.
We initiate the study of boxicity and cubicity of a special class of algebraically defined comparability graphs, namely the power graphs. The power graph of a group is an undirected graph whose vertex set is the group itself, with two elements being adjacent if one is a power of the other. We analyse the case when the underlying groups of power graphs are cyclic. Another important family of comparability graphs is divisor graphs, which arises from a number-theoretically defined poset, namely the divisibility poset. We consider a subclass of divisor graphs, denoted by D(n), where the vertex set is the set of positive divisors of a natural number n.
We first show that to study the boxicity (cubicity) of the power graph of the cyclic group of order n, it is sufficient to study the boxicity (cubicity) of D(n). We derive estimates, tight up to a factor of 2, for the boxicity and cubicity of D(n). The exact estimates hold good for power graphs of cyclic groups
Capturing rapid nanomaterial transformations with cross-platform operando characterization
No full textThe inability to observe the rapid, initial transformations that dictate nanomaterial fate constitutes a fundamental scientific gap, forcing risk assessments to rely on retrospective, incomplete data. A paradigm shift to real-time, operando characterization is vital to build the predictive understanding required for the development of safe and sustainable nanomaterials and applications
Unveiling the Multi-Annotation Process: Examining the Influence of Annotation Quantity and Instance Difficulty on Model Performance
No full textThe NLP community has long advocated for the construction of multi-annotator datasets to better capture the nuances of language interpretation, subjectivity, and ambiguity. This paper conducts a retrospective study to show how performance scores can vary when a dataset expands from a single annotation per instance to multiple annotations. We propose a novel multi-annotator simulation process to generate datasets with varying annotation budgets. We show that similar datasets with the same annotation budget can lead to varying performance gains. Our findings challenge the popular belief that models trained on multi-annotation examples always lead to better performance than models trained on single or few-annotation examples. � 2025 Elsevier B.V., All rights reserved
The Routledge International Handbook of Himalayan Environments, Development and Wellbeing
No full textShifting dynamics of peoples, livelihoods and territories, influenced by global warming, require new ways of thinking and new kinds of politics beyond the sovereignties of idealized traditional European nation-states. The Routledge International Handbook of Himalayan Environments, Development and Wellbeing features over 70 scholars from the social sciences, humanities and natural sciences who explore the interrelationships between environmental change, development and wellbeing across the entire Himalayan region - from the Indian Himalayas in the east to Bhutan, Nepal, Tibet (TAR), India and Gilgit-Baltistan in the west. Within over 50 chapters, the handbook presents engaging field-based research on the region's socio-cultural diversity, climate adaptation and socio-economic transformation. It examines creative ways Himalayan communities adapt, seek wellbeing and respond to environmental and development challenges. Lessons about learning from Indigenous and local peoples, about governance of forests and water, and grassroots conservation practices from the Himalayan region can help inform global networks of researchers and practitioners. The handbook will interest scholars, students, stakeholders and the public about the evolving relationships between Himalayan peoples, territories and global warming, offering insights into people's creative ways for understanding, adapting, and seeking wellbeing in environmental relations and development possibilities
