Search

Skilled employees are the most important pillars of an organization. Despite this, most organizations face high attrition and turnover rates. While several machine learning models have been developed to analyze attrition and its causal factors, the interpretations of those models remain opaque. In this paper, we propose the HR-DSS approach, which stands for Human Resource (HR) Decision Support System, and uses explainable AI for employee attrition problems. The system is designed to assist HR departments in interpreting the predictions provided by machine learning models. In our experiments, we employ eight machine learning models to provide predictions. We further process the results achieved by the best-performing model by the SHAP explainability process and use the SHAP values to generate natural language explanations which can be valuable for HR. Furthermore, using "What-if-analysis", we aim to observe plausible causes for attrition of an individual employee. The results show that by adjusting the specific dominant features of each individual, employee attrition can turn into employee retention through informative business decisions., Comment: Accepted at CIKM 2023 Applied Research Track

Knowledge Graphs, such as Wikidata, comprise structural and textual knowledge in order to represent knowledge. For each of the two modalities dedicated approaches for graph embedding and language models learn patterns that allow for predicting novel structural knowledge. Few approaches have integrated learning and inference with both modalities and these existing ones could only partially exploit the interaction of structural and textual knowledge. In our approach, we build on existing strong representations of single modalities and we use hypercomplex algebra to represent both, (i), single-modality embedding as well as, (ii), the interaction between different modalities and their complementary means of knowledge representation. More specifically, we suggest Dihedron and Quaternion representations of 4D hypercomplex numbers to integrate four modalities namely structural knowledge graph embedding, word-level representations (e.g.\ Word2vec, Fasttext), sentence-level representations (Sentence transformer), and document-level representations (sentence transformer, Doc2vec). Our unified vector representation scores the plausibility of labelled edges via Hamilton and Dihedron products, thus modeling pairwise interactions between different modalities. Extensive experimental evaluation on standard benchmark datasets shows the superiority of our two new models using abundant textual information besides sparse structural knowledge to enhance performance in link prediction tasks., Comment: ISWC2023 version

Knowledge Graph Embedding models have become an important area of machine learning.Those models provide a latent representation of entities and relations in a knowledge graph which can then be used in downstream machine learning tasks such as link prediction. The learning process of such models can be performed by contrasting positive and negative triples. While all triples of a KG are considered positive, negative triples are usually not readily available. Therefore, the choice of the sampling method to obtain the negative triples play a crucial role in the performance and effectiveness of Knowledge Graph Embedding models. Most of the current methods fetch negative samples from a random distribution of entities in the underlying Knowledge Graph which also often includes meaningless triples. Other known methods use adversarial techniques or generative neural networks which consequently reduce the efficiency of the process. In this paper, we propose an approach for generating informative negative samples considering available complementary knowledge about entities. Particularly, Pre-trained Language Models are used to form neighborhood clusters by utilizing the distances between entities to obtain representations of symbolic entities via their textual information. Our comprehensive evaluations demonstrate the effectiveness of the proposed approach on benchmark Knowledge Graphs with textual information for the link prediction task.

This paper studies the Graph Isomorphism Problem from a variational algorithmic perspective, specifically studying the Quadratic Unconstrained Binary Optimization (QUBO) formulation of the Graph Isomorphism Problem and subsequent execution using the Quantum Approximate Optimization Algorithm (QAOA) and the Variational Quantum Eigensolver (VQE). This study presents the results of these algorithms and the variations that occur therein for graphs of four and five nodes. The main findings of this paper include the clustering in the energy landscape for the QAOA in isomorphic graphs having an equal number of nodes and edges. This trend found in the QAOA study was further reinforced by studying the ground state energy reduction using VQEs. Furthermore, this paper examines the trend under which isomorphic pairs of graphs vary in the ground state energies, with varying edges and nodes., Comment: 7 pages, 3 figures

When working with algorithms on quantum devices, quantum memory becomes a crucial bottleneck due to low qubit count in NISQ-era devices. In this context, the concept of `divide and compute', wherein a quantum circuit is broken into several subcircuits and executed separately, while stitching the results of the circuits via classical post-processing, becomes a viable option, especially in NISQ-era devices. This paper introduces \textbf{Qurzon}, a proposed novel quantum compiler that incorporates the marriage of techniques of divide and compute with the state-of-the-art algorithms of optimal qubit placement for executing on real quantum devices. A scheduling algorithm is also introduced within the compiler that can explore the power of distributed quantum computing while paving the way for quantum parallelism for large algorithms. Several benchmark circuits have been executed using the compiler, thereby demonstrating the power of the divide and compute when working with real NISQ-era quantum devices.

In this paper, quantum algorithms are to be used to simulate glassy systems in toy models. To look for glassy behavior, the energy landscape and spin configurations of the transverse field Ising model in a longitudinal field are studied. The Variational Quantum Eigensolver (VQE) is used to obtain the ground-state energies and corresponding eigenstates for a $6 \times 6$ Ising lattice using 36 qubits and a 1-dimensional Ising chain of length 25. For the $8 \times 8$ Cellular Potts model, the original Hamiltonian is converted to an Ising formulation for the VQE to reduce to its ground state. The energy change during minimization is carefully analyzed to find whether the effects of interfacial tension among cells could probably induce glassiness in the cell system., Comment: Work extended with other new collaborators

This paper presents advancement towards making an efficient and viable wheel chair control system based on brain computer interface via electro-oculogram (EOG) signals. The system utilizes the movement of eye as the element of purpose for controlling the movement of the wheel chair. Skin-surface electrodes are placed over skin for the purpose of acquiring the electro-oculogram signal and with the help of differential amplifier the bio-potential is measured between the reference and the point of interest, afterwards these obtained low voltage pulses are amplified, then passed through a sallen-key filter for noise removal and smoothening. These pulses are then collected on to the micro-controller; based on these pulses motor is switched to move in either right or left direction. A prototype system was developed and tested. The system showed promising results. The test conducted showed 99.5% efficiency of movement in correct direction., Comment: Journal Article

This paper presents a novel approach towards the designing and development of a feasible and an embedded vehicle intrusion and theft control system using GSM (Global System for Mobile Communication) and GPS (Global Positioning System). The proposed system uses GSM technology as one of the distinguishing building blocks of the system. A GPS module Holux GR89 is used to trace the position of the vehicle and Mercury Switches are used to collect analog data continuously, in case of an intrusion, variations will be observed in sensors reading. Continuous readings from sensors are collected on to the microcontroller constantly and on the basis of those readings decision is taken whether an intrusion is made or not and in case of an intrusion a message from a predefined set of messages is generated to the owner of the vehicle and on reception of the message, the owner will have the luxury to take an action via an SMS either to lock the gears of the vehicle or seize the engine of the vehicle from a far-off place. A relay is used to control gears and engine of the vehicle while working with the microcontroller. A prototype system was built and tested. The results were very positive and encouraging., Comment: Journal Article

In recent times, developments in field of communication and robotics has progressed with leaps and bounds. In addition, the blend of both disciplines has contributed heavily in making human life easier and better. So in this work while making use of both the aforementioned technologies, a procedure for design and implementation of a mobile operated mechanical arm is proposed, that is, the proposed arm will be operated via a cellular device that connects with the receiver mounted on the robotic arm. Moreover, over the duration of a call, if any key is pressed from the cellular device than an indicator indistinct to the key pressed is noticed at the receiver side. This tone represents superimposition of two distinct frequencies and referred to as DTMF (dual tone multi-frequency). Further, the mechanical arm is handled via the DTMF tone. Also, the acquired tone at the receiver is taken into a micro-controller (ATMEGA16) using the DTMF decipher module i.e. MT8870. Further, the decipher module unwinds the DTMF signal into its corresponding two bit representation and then the matched number is transmitted to the micro-controller. The micro-controller is programmed to take an action based on the decoded value. Further, the micro-controller forwards control signals to the motor driver unit to move the arm in forward/backward or multi-directional course. Lastly, the mechanical arm is capable of picking and placing objects while being controlled wirelessly over GSM (Global System for Mobile Communications)., Comment: Journal Article

Some scenarios for planetesimal formation go through a phase of collapse of gravitationally bound clouds of mm-cm-sized pebbles. Such clouds can form for example through the streaming instability in protoplanetary disks. We model the collapse process with a statistical model to obtain the internal structure of planetesimals with solid radii between 10 and 1,000 km. In the collapse, pebbles collide and, depending on relative speed, collisions have different outcomes. A mixture of particle sizes inside a planetesimal leads to better packing capabilities and higher densities. In this paper we apply results from new laboratory experiments of dust aggregate collisions (presented in a companion paper) to model collision outcomes. We find that the internal structure of a planetesimal is strongly dependent on both its mass and the applied fragmentation model. Low-mass planetesimals have no/few fragmenting pebble collisions in the collapse phase and end up as porous pebble-piles. The amount of fragmenting collisions increases with increasing cloud mass, resulting in wider particle size distributions and higher density. The collapse is nevertheless "cold" in the sense that collision speeds are damped by the high collision frequency. This ensures that a significant fraction of large pebbles survive the collapse in all but the most massive clouds. Our results are in broad agreement with the observed increase in density of Kuiper belt objects with increasing size as exemplified by the recent characterization of the highly porous comet 67P/Churyumov-Gerasimenko., Comment: in APJ 2016