A hybrid extreme learning machine model with harris hawks optimisation algorithm: an optimised model for product demand forecasting applications

Accurate and real-time product demand forecasting is the need of the hour in the world of supply chain management. Predicting future product demand from historical sales data is a highly non-linear problem, subject to various external and environmental factors. In this work, we propose an optimised forecasting model - an extreme learning machine (ELM) model coupled with the Harris Hawks optimisation (HHO) algorithm to forecast product demand in an e-commerce company. ELM is preferred over traditional neural networks mainly due to its fast computational speed, which allows efficient demand forecasting in real-time. Our ELM-HHO model performed significantly better than ARIMA models that are commonly used in industries to forecast product demand. The performance of the proposed ELM-HHO model was also compared with traditional ELM, ELM auto-tuned using Bayesian Optimisation (ELM-BO), Gated Recurrent Unit (GRU) based recurrent neural network and Long Short Term Memory (LSTM) recurrent neural network models. Different performance metrics, i.e., Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Percentage Error (MPE) were used for the comparison of the selected models. Horizon forecasting at 3 days and 7 days ahead was also performed using the proposed approach. The results revealed that the proposed approach is superior to traditional product demand forecasting models in terms of prediction accuracy and it can be applied in real-time to predict future product demand based on the previous week’s sales data. In particular, considering RMSE of forecasting, the proposed ELM-HHO model performed 62.73% better than the statistical ARIMA(7,1,0) model, 40.73% better than the neural network based GRU model, 34.05% better than the neural network based LSTM model, 27.16% better than the traditional non-optimised ELM model with 100 hidden nodes and 11.63% better than the ELM-BO model in forecasting product demand for future 3 months. The novelty of the proposed approach lies in the way the fast computational speed of ELMs has been combined with the accuracy gained by tuning hyperparameters using HHO. An increased number of hyperparameters has been optimised in our methodology compared to available models. The majority of approaches to improve the accuracy of ELM so far have only focused on tuning the weights and the biases of the hidden layer. In our hybrid model, we tune the number of hidden nodes, the number of input time lags and even the type of activation function used in the hidden layer in addition to tuning the weights and the biases. This has resulted in a significant increase in accuracy over previous methods. Our work presents an original way of performing product demand forecasting in real-time in industry with highly accurate results which are much better than pre-existing demand forecasting models.

     

Learning Latent Representations of 3D Human Pose with Deep Neural Networks

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from an image to a 3D pose, which ignores the dependencies between human joints, or model these dependencies via a max-margin structured learning framework, which involves a high computational cost at inference time. In this paper, we introduce a Deep Learning regression architecture for structured prediction of 3D human pose from monocular images or 2D joint location heatmaps that relies on an overcomplete autoencoder to learn a high-dimensional latent pose representation and accounts for joint dependencies. We further propose an efficient Long Short-Term Memory network to enforce temporal consistency on 3D pose predictions. We demonstrate that our approach achieves state-of-the-art performance both in terms of structure preservation and prediction accuracy on standard 3D human pose estimation benchmarks.     

RImCom: Raster-order Image Compressor for Embedded Video Applications

This paper presents a real-time, rate controlled, end-to-end (encoder and decoder) hardware solution for memory compression of raster-order video streams—named RImCom (short for Raster-order Image Compression). RImCom offers up to 3x compression that is either lossless or lossy at very reasonable PSNR values. The 180 nm ASIC implementation of RImCom achieves 28 fps at Ultra-HD resolution in the slow corner of synthesis. RImCom can match the fps of the state-of-the-art in the literature with 20 % less area or can achieve twice the fps with 55 % more area. Our FPGA implementation is the only end-to-end FPGA solution in the literature to achieve to this day over 60 fps at Full-HD resolution and to offer rate control. This work was motivated by video processing applications that require the previous frame(s) besides the current frame. When processing HD video streams, even when only one previous frame is required besides the current frame, a significant size and bandwidth of memory is needed. If the current frame is compressed on-the-fly with RImCom or a similar solution and stored on DRAM, and the previous frame is read from DRAM and decompressed with a small IP block, then the overall system cost, power consumption, and electromagnetic radiation are reduced.     

Strategic Multiway Cut and Multicut Games

We consider cut games where players want to cut themselves off from different parts of a network. These games arise when players want to secure themselves from areas of potential infection. For the game-theoretic version of Multiway Cut, we prove that the price of stability is 1, i.e., there exists a Nash equilibrium as good as the centralized optimum. For the game-theoretic version of Multicut, we show that there exists a 2-approximate equilibrium as good as the centralized optimum. We also give poly-time algorithms for finding exact and approximate equilibria in these games.     

Partition Equilibrium Always Exists in Resource Selection Games

We consider the existence of Partition Equilibrium in Resource Selection Games. Super-strong equilibrium, where no subset of players has an incentive to change their strategies collectively, does not always exist in such games. We show, however, that partition equilibrium (introduced in (Feldman and Tennenholtz in SAGT, pp. 48–59, 2009) to model coalitions arising in a social context) always exists in general resource selection games, as well as how to compute it efficiently. In a partition equilibrium, the set of players has a fixed partition into coalitions, and the only deviations considered are by coalitions that are sets in this partition. Our algorithm to compute a partition equilibrium in any resource selection game (i.e., load balancing game) settles the open question from (Feldman and Tennenholtz in SAGT, pp. 48–59, 2009) about existence of partition equilibrium in general resource selection games. Moreover, we show how to always find a partition equilibrium which is also a Nash equilibrium. This implies that in resource selection games, we do not need to sacrifice the stability of individual players when forming solutions stable against coalitional deviations. In addition, while super-strong equilibrium may not exist in resource selection games, we show that its existence can be decided efficiently, and how to find one if it exists.     

Donor acceptor type neutral state green polymer bearing pyrrole as the donor unit

A new neutral state green polymer, poly (2,3-bis(4-tert-butylphenyl)-5,8-di(1H-pyrrol-2-yl) quinoxaline) (PTBPPQ) was synthesized and its potential use as an electrochromic material was investigated. Spectroelectrochemistry studies showed that polymer reveals two distinct absorption bands as expected for a donor–acceptor type polymer, at 408 and 745 nm. In addition, polymer has excellent switching properties with satisfactory optical contrasts and very short switching times. Outstanding optical contrast in the NIR region and stability make this polymer a great candidate for many applications. It should be noted that PTBPPQ is one of the few examples of neutral state green polymeric materials with superior switching properties. Hence, PTBPPQ can be used as a green polymeric material for display technologies.     

CPU load shedding for binary stream joins

We present an adaptive load shedding approach for windowed stream joins. In contrast to the conventional approach of dropping tuples from the input streams, we explore the concept ofselective processing for load shedding. We allow stream tuples to be stored in the windows and shed excessive CPU load by performing the join operations, not on the entire set of tuples within the windows, but on a dynamically changing subset of tuples that are learned to be highly beneficial. We support such dynamic selective processing through three forms of runtimeadaptations: adaptation to input stream rates, adaptation to time correlation between the streams and adaptation to join directions. Our load shedding approach enables us to integrateutility-based load shedding withtime correlation-based load shedding. Indexes are used to further speed up the execution of stream joins. Experiments are conducted to evaluate our adaptive load shedding in terms of output rate and utility. The results show that our selective processing approach to load shedding is very effective and significantly outperforms the approach that drops tuples from the input streams. Bugra Gedik received the B.S. degree in C.S. from the Bilkent University, Ankara, Turkey, and the Ph.D. degree in C.S. from the College of Computing at the Georgia Institute of Technology, Atlanta, GA, USA. He is with the IBM Thomas J. Watson Research Center, currently a member of the Software Tools and Techniques Group. Dr. Gedik's research interests lie in data intensive distributed computing systems, spanning data-centric peer-to-peer overlay networks, mobile and sensor-based distributed data management systems, and distributed data stream processing systems. His research focus is on developing system-level architectures and techniques to address scalability problems in distributed continual query systems and applications. He is the recipient of the ICDCS 2003 best paper award. He has served in the program committees of several international conferences, such as ICDE, MDM, and CollaborateCom. Kun-Lung Wu received the B.S. degree in E.E. from the National Taiwan University, Taipei, Taiwan, the M.S. and Ph.D. degrees in C.S. both from the University of Illinois at Urbana-Champaign. He is with the IBM Thomas J. Watson Research Center, currently a member of the Software Tools and Techniques Group. His recent research interests include data streams, continual queries, mobile computing, Internet technologies and applications, database systems and distributed computing. He has published extensively and holds many patents in these areas. Dr. Wu is a Senior Member of the IEEE Computer Society and a member of the ACM. He is the Program Co-Chair for the IEEE Joint Conference on e-Commerce Technology (CEC 2007) and Enterprise Computing, e-Commerce and e-Services (EEE 2007). He was an Associate Editor for the IEEE Trans. on Knowledge and Data Engineering, 2000–2004. He was the general chair for the 3rd International Workshop on E-Commerce and Web-Based Information Systems (WECWIS 2001). He has served as an organizing and program committee member on various conferences. He has received various IBM awards, including IBM Corporate Environmental Affair Excellence Award, Research Division Award, and several Invention Achievement Awards. He received a best paper award from IEEE EEE 2004. He is an IBM Master Inventor. Philip S. Yu received the B.S. Degree in E.E. from National Taiwan University, the M.S. and Ph.D. degrees in E.E. from Stanford University, and the M.B.A. degree from New York University. He is with the IBM Thomas J. Watson Research Center and currently manager of the Software Tools and Techniques group. His research interests include data mining, Internet applications and technologies, database systems, multimedia systems, parallel and distributed processing, and performance modeling. Dr. Yu has published more than 430 papers in refereed journals and conferences. He holds or has applied for more than 250 US patents. Dr. Yu is a Fellow of the ACM and a Fellow of the IEEE. He is associate editors of ACM Transactions on the Internet Technology and ACM Transactions on Knowledge Discovery in Data. He is a member of the IEEE Data Engineering steering committee and is also on the steering committee of IEEE Conference on Data Mining. He was the Editor-in-Chief of IEEE Transactions on Knowledge and Data Engineering (2001–2004), an editor, advisory board member and also a guest co-editor of the special issue on mining of databases. He had also served as an associate editor of Knowledge and Information Systems. In addition to serving as program committee member on various conferences, he will be serving as the general chair of 2006 ACM Conference on Information and Knowledge Management and the program chair of the 2006 joint conferences of the 8th IEEE Conference on E-Commerce Technology (CEC' 06) and the 3rd IEEE Conference on Enterprise Computing, E-Commerce and E-Services (EEE' 06). He was the program chair or co-chairs of the 11th IEEE Intl. Conference on Data Engineering, the 6th Pacific Area Conference on Knowledge Discovery and Data Mining, the 9th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery, the 2nd IEEE Intl. Workshop on Research Issues on Data Engineering: Transaction and Query Processing, the PAKDD Workshop on Knowledge Discovery from Advanced Databases, and the 2nd IEEE Intl. Workshop on Advanced Issues of E-Commerce and Web-based Information Systems. He served as the general chair of the 14th IEEE Intl. Conference on Data Engineering and the general co-chair of the 2nd IEEE Intl. Conference on Data Mining. He has received several IBM honors including 2 IBM Outstanding Innovation Awards, an Outstanding Technical Achievement Award, 2 Research Division Awards and the 84th plateau of Invention Achievement Awards. He received an Outstanding Contributions Award from IEEE Intl. Conference on Data Mining in 2003 and also an IEEE Region 1 Award for “promoting and perpetuating numerous new electrical engineering concepts” in 1999. Dr. Yu is an IBM Master Inventor. Ling Liu is an associate professor at the College of Computing at Georgia Tech. There, she directs the research programs in Distributed Data Intensive Systems Lab (DiSL), examining research issues and technical challenges in building large scale distributed computing systems that can grow without limits. Dr. Liu and the DiSL research group have been working on various aspects of distributed data intensive systems, ranging from decentralized overlay networks, exemplified by peer to peer computing, data grid computing, to mobile computing systems and location based services, sensor network computing, and enterprise computing systems. She has published over 150 international journal and conference articles. Her research group has produced a number of software systems that are either open sources or directly accessible online, among which the most popular ones are WebCQ and XWRAPElite. Dr. Liu is currently on the editorial board of several international journals, including IEEE Transactions on Knowledge and Data Engineering, International Journal of Very large Database systems (VLDBJ), International Journal of Web Services Research, and has chaired a number of conferences as a PC chair, a vice PC chair, or a general chair, including IEEE International Conference on Data Engineering (ICDE 2004, ICDE 2006, ICDE 2007), IEEE International Conference on Distributed Computing (ICDCS 2006), IEEE International Conference on Web Services (ICWS 2004). She is a recipient of IBM Faculty Award (2003, 2006). Dr. Liu's current research is partly sponsored by grants from NSF CISE CSR, ITR, CyberTrust, a grant from AFOSR, an IBM SUR grant, and an IBM faculty award.     

A novel quinoxaline bearing electroactive monomer: Pyrrole as the donor moiety

A novel electroactive monomer 5,8-di(1H-pyrrol-2-yl)-2,3-di(thiophen-2-yl)quinoxaline (PTQ) was successfully synthesized and its electrochromic properties were reported. Nuclear magnetic resonance (¹H NMR-¹³C NMR) and mass spectroscopy were used to characterize the monomer. The monomer was electrochemically polymerized in the presence of tetrabutylammonium perchlorate (TBAP) as supporting electrolyte in dichloromethane. Monomer reveals relatively low oxidation potential at +0.70 V. Spectroelectrochemical behaviors and switching ability of homopolymer were investigated by UV-vis spectroscopy and cyclic voltammetry. Two π-π* transitions were observed at 400 and 815 nm with a low band gap, 1.0 eV. Polymer possesses 66% optical contrast in the Near IR region, which may be promising in NIR electrochromic device applications.     

Exact and approximate equilibria for optimal group network formation

We consider a process called the Group Network Formation Game, which represents the scenario when strategic agents are building a network together. In our game, agents can have extremely varied connectivity requirements, and attempt to satisfy those requirements by purchasing links in the network. We show a variety of results about equilibrium properties in such games, including the fact that the price of stability is 1 when all nodes in the network are owned by players, and that doubling the number of players creates an equilibrium as good as the optimum centralized solution. For the general case, we show the existence of a 2-approximate Nash equilibrium that is as good as the centralized optimum solution, as well as how to compute good approximate equilibria in polynomial time. Our results essentially imply that for a variety of connectivity requirements, giving agents more freedom can paradoxically result in more efficient outcomes.     

Soft Electronics Manufacturing Using Microcontact Printing

This work describes a microcontact printing (µCP) process for reproducible manufacturing of liquid gallium alloy–based soft and stretchable electronics. One of the leading approaches to create soft and stretchable electronics involves embedding liquid metals (LM) into an elastomer matrix. Although the advantages of liquid metal–based electronics have been well established, their mainstream adoption and commercialization necessitates development of precise and scalable manufacturing methods. To address this need, a scalable µCP process is presented that uses surface‐functionalized, reusable rigid, or deformable stamps to transfer eutectic gallium–indium (EGaIn) patterns onto elastomer substrates. A novel approach is developed to create the surface‐functionalized stamps, enabling selective transfer of LM to desired locations on a substrate without residues or electrical shorts. To address the critical needs of precise and reproducible positioning, alignment, and stamping force application, a high‐precision automated µCP system is designed. After describing the approach, the precision of stamps is evaluated and EGaIn features (as small as 15 µm line width), as well as electrical functionality of printed circuits with and without deformation, are fabricated. The presented process addresses many of the limitations associated with the alternative fabrication processes, and thus provides an effective approach for scalable fabrication of LM‐based soft and stretchable microelectronics.