Advertisement

Computer Intelligent Systems for Manufacture and Control

  • Tetyana Baydyk
  • Ernst Kussul
  • Donald C. Wunsch II
Chapter
Part of the Computational Intelligence Methods and Applications book series (CIMA)

Abstract

Automation of production and assembly processes is one of the important tasks in micromechanics. To produce totally automated micro factory or automate the solar concentrator production and assembly, it is necessary to develop a computer vision system that can replace an operator. A computer vision system may have several functions, for example, recognition of objects on the image of working area, recognition of mutual position of several components on the image, and measurement of component size, etc. We select several tasks that are connected with the micromechanics area and automatization—for example, size measurement of micro components. The object of measurement is a micro piston. Micro pistons are the components of heat engines that transfer the heat energy from solar concentrator to electrical energy. The goal of this work is the research and development of the LIRA (Limited Receptive Area) neural network and its application to measure the micro piston size. To obtain micro piston sizes, it is necessary to recognize its boundaries in the image. We propose to use LIRA neural network to extract and classify piston boundaries. In this chapter, we describe and analyze the preliminary results of LIRA application to micro piston boundaries recognition. Experiments with the recognition system have given us the information to improve the structure and parameters of the developed neural network. Experiments with the LIRA neural network showed the necessity to accelerate its processing time by implementing the neural network algorithms with electronic schemes such as Altera. The advantage of the neural network is its parallel structure and possibility of the training. FPGA allows the implementation of these parallel algorithms in a single device. This chapter contains brief description of ensemble neuron networks and some results of storage capacity estimation. We propose to apply this ensemble neural network to the problem of selection of adequate maneuver for robot-manipulator or for mobile robot.

References

  1. 1.
    Trimmer, W.S. (ed.): Micromechanics and MEMS Classic and Seminal Papers to 1990. IEEE Press, New York (1996)Google Scholar
  2. 2.
    Kussul, E., Rachkovskij, D., Baidyk, T., Talayev, S.: Micromechanical engineering: a basis for the low cost manufacturing of mechanical microdevices using microequipment. J. Micromech. Microeng. 6(4), 410–425 (1996)Google Scholar
  3. 3.
    Eberhart, R.: Overview of computational intelligence and biomedical engineering applications. In: Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 3, pp. 1125–1129 (1998)Google Scholar
  4. 4.
    Hui, T., Brown, D., Haynes, B., Wang, X.: Embedded e-diagnostic for distributed industrial machinery. In: IEEE International Symposium on Computational Intelligence for Measurement Systems and Applications, pp. 156–161 (2003)Google Scholar
  5. 5.
    Awadallah, M., Morcos, M.: Application of AI tools in fault diagnosis of electrical machines and drives. An overview. IEEE Trans. Energy Convers. 18(2), 245–251 (2003)Google Scholar
  6. 6.
    Werbos, P.: Advanced forecasting methods for global crisis warning and models of intelligence. Gen. Syst. Yearb. 22, 25–38 (1977)Google Scholar
  7. 7.
    Bottou, L., Cortes, C., Denker, J., Drucker, H., Guyon, L., Jackel, L., LeCun, J., Muller, U., Sackinger, E., Simard, P., Vapnik, V.: Comparison of classifier methods: a case study in handwritten digit recognition. In: Proceedings of 12th IAPR International Conference on Pattern Recognition, vol. 2, pp. 77–82 (1994)Google Scholar
  8. 8.
    Fukushima, K.: Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Netw. 1, 119–130 (1988)Google Scholar
  9. 9.
    Roska, T., Rodriguez-Vazquez, A.: Toward visual microprocessors. Proc. IEEE. 90(7), 1244–1257 (2002)Google Scholar
  10. 10.
    Baidyk, T.: Application of flat image recognition technique for automation of micro device production. In: Proceedings of the International Conference on Advanced Intelligent Mechatronics “AIM’01”, Italy, pp. 488–494 (2001)Google Scholar
  11. 11.
    Baidyk, T., Kussul, E.: Application of neural classifier for flat image recognition in the process of microdevice assembly. In: Proceedings of IEEE International Join Conference on Neural Networks, USA, vol. 1, pp. 160–164 (2002)Google Scholar
  12. 12.
    Kussul, E., Baidyk, T., Wunsch, D.: Neural Networks and Micromechanics, p. 221. Springer, Berlin (2010)zbMATHGoogle Scholar
  13. 13.
    Baidyk, T., Kussul, E.: Redes Neuronales, visión computacional y micro-mecánica, p. 157. Editorial Itaca-UNAM, México (2009)Google Scholar
  14. 14.
    Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. Wiley, New York (2001)zbMATHGoogle Scholar
  15. 15.
    Schwartz, R., Setauket, N.: Method and a circuit for determine a contour in an image. United States Patent N4, 433, 912, 28 Feb 1984Google Scholar
  16. 16.
    Toledo, G., Kussul, E., Baidyk, T.: Neural classifier for micro work piece recognition. Image Vis. Comput. 24(8), 827–836 (2006)Google Scholar
  17. 17.
    Baidyk, T., Kussul, E., Makeyev, O., Caballero, A., Ruiz, L., Carrera, G., Velasco, G.: Flat image recognition in the process of microdevice assembly. Pattern Recogn. Lett. 25(1), 107–118 (2004)Google Scholar
  18. 18.
    Rosenblatt, F.: Principles of Neurodynamics. Spartan Books, Washington, DC (1962). 215 ppzbMATHGoogle Scholar
  19. 19.
    Kussul, E., Baidyk, T.: Improved method of handwritten digit recognition tested on MNIST database. Image Vis. Comput. 22(12), 971–981 (2004)Google Scholar
  20. 20.
    Baidyk, T., Kussul, E., Hernandez Acosta, M.: LIRA neural network application for microcomponent measurement. Int. J. Appl. Math. Informat. 6(4), 173–180 (2012)Google Scholar
  21. 21.
    Baidyk, T., Kussul, E., Hernandez Acosta, M., Vega, A.: Research and development of a recognition system for measurements in micromechanics. ICMEAE 2013 (The International Conference on Mechatronics, Electronics and Automotive Engineering 2013), Cuernavaca, México, 19–22 November 2013, pp. 53–58Google Scholar
  22. 22.
    Hernandez Acosta, M., Baydyk, T., Kussul, E., Roldán Serrato, K.L., Olvera Tapia, O.: Measurements in micromechanics based on computer vision. In: The 12th All-Ukrainian International Conference on Signal/Image Processing and Pattern Recognition, UkrObraz, Kijv, Ukraine, 3–7 November 2014, pp. 119–122Google Scholar
  23. 23.
    Vega, A., Baidyk, T., Kussul, E., Pérez Silva, J.L.: FPGA realization of the LIRA neural classifier. Opt. Mem. Neural Netw. (Information Optics). 20(3), 168–180 (2011)Google Scholar
  24. 24.
    Vega, A., Baidyk, T., Kussul, E., Pérez Silva, J.L.: FPGA based LIRA neural classifier. In: IEEE CERMA 2011 (Congreso de Electróonica, Robótica, y Mecánica Automotriz), World Trade Center, Morelos, Cuernavaca, Mexico, 15–18 Noviembre 2011, pp. 65–70Google Scholar
  25. 25.
    Vega, A., Luis Pérez, J., Baydyk, T., Kussul, E.: Development and implementation of the LIRA neural classifier. In: Proceedings of the World Congress on Engineering and Computer Science 2010 (AIENG), San Francisco, USA, 20–22 October 2010, pp. 822–826Google Scholar
  26. 26.
    Lai, C.Y., Lewis, F.L., Venkatakrishnan, R.X., Ge, S.S., Liew, T.: Disturbance and friction compensations in hard disk drives using neural networks. IEEE Trans. Ind. Electron. 57(2), 784–792 (2010)Google Scholar
  27. 27.
    Ge, S.S., Wang, C.: Adaptive neural control of uncertain MIMO nonlinear systems. IEEE Trans. Neural Netw. 15(3), 674–692 (2004)Google Scholar
  28. 28.
    Kosmatopoulos, E.B., Polycarpou, M.M., Christodoulou, M.A., Ioannou, P.A.: High-order neural network structures for identification of dynamical systems. IEEE Trans. Neural Netw. 6(2), 422–431 (1995)Google Scholar
  29. 29.
    Lewis, F.L., Yesildirek, A., Liu, K.: Multilayer neural-net robot controller with guaranteed tracking performance. IEEE Trans. Neural Netw. 7(2), 388–399 (1996)Google Scholar
  30. 30.
    Lewis, F.L., Jagannathan, S., Yesildirek, A.: Neural Network Control of Robot Manipulators and Nonlinear Systems. Taylor & Francis, London (1999)Google Scholar
  31. 31.
    Cirsttea, M., Danu, A., McCormick, M., Nicula, D.: A VHDL success story: electric drive system using neural controller. In: Proceedings of the IEEE VHDL International Users Forum Fall, Workshop, pp. 118–122 (2000)Google Scholar
  32. 32.
    Botros, N.M., Abdul-Aziz, M.: Hardware implementation of an artificial neural network using field programmable gate arrays (FPGA’s). IEEE Trans. Ind. Electron. 41(6), 665–667 (1994)Google Scholar
  33. 33.
    McBader, S., Lee, P., Sartori, A.: The impact of modern FPGA architectures on neural hardware: a case study of the TOTEM neural processor. Proc. IEEE Int. Joint Conf. Neural Netw. 4, 3149–3154 (2004)Google Scholar
  34. 34.
    Jung, S., Kim, S.S.: Hardware implementation of a real-time neural network controller with a DSP and a FPGA for nonlinear systems. IEEE Trans. Ind. Electron. 54(1), 265–271 (2007)Google Scholar
  35. 35.
    Wasserman, P.D.: Neural Computing. Theory and Practice. Von Nostrand Reinhold, New York (1989)Google Scholar
  36. 36.
    Hecht-Nielsen, R.: Neurocomputing. Addison Wesley, Reading, MA (1990)Google Scholar
  37. 37.
    Lee, Y.J., Lee, J., Kim, Y.B., Ayers, J., Volkovskii, A., Selverston, A., Abarbanel, H., Rabinovich, M.: Low power real time electronic neuron VLSI design using subthreshold techniques. IEEE Circuits Syst. 4, 744–747 (2004)Google Scholar
  38. 38.
    Padrón, J.L.P., Herrera, A., Prieto, R.: Dynamical behavior of an electronic neuron of commutation. In: Proceedings of the Mexican international Conference on Artificial Intelligence: Advances in Artificial intelligence, 11–14 April 2000. Lecture Notes in Computer Science, vol. 1793, pp. 338–349. Springer, London (2000)Google Scholar
  39. 39.
    McCulloch, W.S., Pitts, W.A.: A logical calculus of the ideas imminent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943)MathSciNetzbMATHGoogle Scholar
  40. 40.
    Shin’Ichiro, K., Makoto, I., Nozomu, H.: Analog LSI neuron model inspired by biological excitable membrane. Syst. Comput. Jpn. 36(6), 84–91 (2005)Google Scholar
  41. 41.
    Szlavik, R.B., Bhuiyan, A.K., Carver, A., Jenkins, F.: Neural-electronic inhibition simulated with a neuron model implemented in SPICE. IEEE Eng. Med. Biol. 14(1), 109–115 (2006)Google Scholar
  42. 42.
    Requena, I., Delgado, M.: A model of fuzzy neuron. In: Proceedings of the 2nd International Conference on Fuzzy Logic Neural Networks (IIZUKA’90), Iizuka, Japan, 20–24 July 1990, pp. 13–26Google Scholar
  43. 43.
    Rasche, C., Douglas, R.J.: An improved silicon neuron. Analog Integr. Circuits Signal Process. 23(3), 227–236 (2000)Google Scholar
  44. 44.
    Pérez, J.L., Miranda, A.I., Garcés, A.M.: A neuron model with parabolic burst response. Adv. Artif. Intell. Eng. Cybern. X, 6–10 (2003)Google Scholar
  45. 45.
    Dunin-Barkovskii, V.L., Osovets, N.B.: Neural network with formed dynamics of activity. Radiophys. Quantum Electron. 37(9), 687–693 (1994)Google Scholar
  46. 46.
    Kryzhanovsky, B.V., Kryzhanovsky, V.M.: Distinguishing features of a small Hopfield model with clipping of synapses. Opt. Mem. Neural Netw. 17(3), 193–200 (2008)Google Scholar
  47. 47.
    Kussul, E., Baidyk, T.: LIRA neural classifier for handwritten digit recognition and visual controlled microassembly. Neurocomputing. 69(16–18), 2227–2235 (2006)Google Scholar
  48. 48.
    Kussul, E., Baidyk, T., Wunsch, D., Makeyev, O., Martín, A.: Permutation coding technique for image recognition systems. IEEE Trans. Neural Netw. 17(6), 1566–1579 (2006)Google Scholar
  49. 49.
    Ososkov, G.: Effective neural network approach to image recognition and control. In: Proceedings of International Conference on Physics and Control, vol. 1, pp. 242–246 (2003)Google Scholar
  50. 50.
    Vitabile, S., Gentile, A., Sorbello, F.: A neural network based automatic road signs recognizer. In: Proceedings of the 2002 International Joint Conference on Neural Networks, vol. 3, pp. 2315–2320 (2002)Google Scholar
  51. 51.
    Clarke, T.J.W., Prage, R.W.R., Fallside, F.: The modified Kanerva model: theory and results for real-time word recognition. IEE Proc.-F. 138(1), 25–31 (1991)Google Scholar
  52. 52.
    University program design laboratory package user guide, 32 pp. Altera Corporation (2001)Google Scholar
  53. 53.
    Kussul, E.M.: Associative neuron structures. Naukova Dumka, Kiev (1992). 144 pp. (in Russian)Google Scholar
  54. 54.
    Kohonen, T.: Self-organizing maps, 3rd edn, p. 460. Springer, Berlin (2001)zbMATHGoogle Scholar
  55. 55.
    Mikaelyan, A.L.: Neuro-holographic processing methods and availability of neural nanostructure development. Inform. Technol. Comput. Syst. 1, 9–19 (2004)Google Scholar
  56. 56.
    Kryzhanovsky, B.V., Litinskii, L.B.: The vector models of associative memory. In: Neuroinformatics-2003, MIFI Session, Moscow, Russia, pp. 72–85 (2003)Google Scholar
  57. 57.
    Nakano, K.: Associatron – a model of associative memory. IEEE Trans. Syst. Man Cybern. SMC–2(3), 380–388 (1972)Google Scholar
  58. 58.
    Amosov, N.M., Baidyk, T.N., Goltsev, A.D., et al.: Neurocomputers and Intelligent Robots, p. 272. Nauk. Dumka, Kiev (1991). (in Russian)Google Scholar
  59. 59.
    Kussul, E., Baidyk, T.: Structure of neural ensemble. In: The RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, Rostov-on-Don, Russia, pp. 423–434 (1992)Google Scholar
  60. 60.
    Frolov, A., Husek, D., Muraviev, I.: Informational efficiency of sparsely encoded Hopfield-like associative memory. In: Neuroinformatics-2003, MIFI Session, Moscow, Russia, pp. 28–70 (2003)Google Scholar
  61. 61.
    Tsodyks, M.V.: Associative memory in asymmetric diluted network with low level of activity. Europhys. Lett. 7(3), 203–208 (1988)Google Scholar
  62. 62.
    Hebb, D.O.: The organization of behaviour, p. 319. Wiley, New York (1949)Google Scholar
  63. 63.
    Milner, P.M.: The cell ensemble: Mark 2. Psychol. Rev. 64(4), 242–252 (1957)Google Scholar
  64. 64.
    Milner, P.: The autonomous brain: a neural theory of attention and learning, p. 153. Lawrence Erlbaum Associates, Mahwah, NJ (1999)Google Scholar
  65. 65.
    Baidyk, T.N.: Neural networks and artificial intelligence Problems. Naukova Dumka, Kiev (2001). 264 pp. (in Russian)Google Scholar
  66. 66.
    Goltsev, A.D.: Neural networks with the assembly organization. Naukova Dumka, Kiev (2005). 200 pp. (in Russian)zbMATHGoogle Scholar
  67. 67.
    Breitenberg, V.: Cell ensembles in the cerebral cortex. Lect. Notes Biomath. 21, 171–178 (1978)Google Scholar
  68. 68.
    Palm, G., Sommer, F.T.: Information capacity in recurrent McCulloch-Pitts networks with sparsely coded memory states. Network. 3, 177–186 (1992)zbMATHGoogle Scholar
  69. 69.
    Knoblauch, A.: Neural associative memory for brain modeling and information retrieval. Inf. Process. Lett. 95(6), 537–544 (2005)MathSciNetzbMATHGoogle Scholar
  70. 70.
    Kussul, E., Baidyk, T., López, B., Lopez, P., Velasco, G., Caballero, A., Ruiz, L., Silva, H.: Wireboard prototyping method. J. Appl. Res. Technol. 4(1), 75–81 (2006)Google Scholar
  71. 71.
    Kussul, E., Baydyk, T., De Luca Pennacchia, A.: Tarjetas para circuitos electrónicos con ranuras para conexiones. Prioridad de 6.02.2009, IMPIl, Patente MX 320896 B, 14.05.2014Google Scholar
  72. 72.
    De Luca Pennacchia, A., Kussul, E., Baydyk, T.: Método de fabricación de las tarjetas con ranuras para circuitos electrónicos. IMPI, Prioridad de 20.08.2009, Patente No 307903, 7.03.2013Google Scholar
  73. 73.
    Baydyk, T., Kussul, E., De Luca Penaccio, A.: Método para elaborar tarjetas para circuitos electrónicos con ranuras para conexiones y alambrar de manera automatizada sus rutas de interconexión interna. Patente MX 318460 B, Prioridad de 30.04.2010, IMPI, 12.03.2014Google Scholar
  74. 74.
    Baturone, I., Moreno-Velo, F.J., Blanco, V., Ferruz, J.: Design of embedded DSP-based fuzzy controllers for autonomous mobile robots. IEEE Trans. Ind. Electron. 55(2), 928–936 (2008)Google Scholar
  75. 75.
    Gupta, R., Masoud, A., Chow, M.-Y.: A delay-tolerant potential-field-based network implementation of an integrated navigation system. IEEE Trans. Ind. Electron. 57(2), 769–783 (2010)Google Scholar
  76. 76.
    Martínez-Salvador, B., Pérez-Francisco, M., Del Pobil, A.: Collision detection between robot arms and people. J. Intell. Robot. Syst. 38, 105–119 (2003)Google Scholar
  77. 77.
    Fraile, J., Paredis, Ch., Wang, C.-H., Khosha, P.: Agent-based planning and control of a multi-manipulator assembly system. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1219–1225 (1999)Google Scholar
  78. 78.
    Brooks, R.: Solving the find-path problem by good representation of free space. In: Proceedings of the 2nd American Association for Artificial Intelligence, pp. 381–386 (1982)Google Scholar
  79. 79.
    Khatib, O.: Real-time obstacle avoidance for manipulators and mobile robots. Intern. J. Robot. Res. 5(1), 90–98 (1986)Google Scholar
  80. 80.
    Lozano-Pérez, T., Wesley, M.: An algorithm for planning collision-free paths among polyhedral obstacles. Commun. ACM. 22(10), 560–570 (1979)Google Scholar
  81. 81.
    Lei, G.: A neuron model with fluid properties for solving labyrinthine puzzle. Biol. Cybern. 64, 61–67 (1990)zbMATHGoogle Scholar
  82. 82.
    Plumer, E.: Cascading a systolic and a feedforward neural network for navigation and obstacle avoidance using potential fields. Prepared for Ames Research Center, Contract NGT-50 642, NASA Contractor Rep. 177 575 (1991)Google Scholar
  83. 83.
    Plumer, E.: Neural network structure for navigation using potential fields. In: International Joint Conference on Neural Networks, IJCNN, pp. 327–332 (1992)Google Scholar
  84. 84.
    Menezes, S.A., Dias, P.J.: Avoiding obstacles using a connectionist network. In: Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS’97, pp. 1236–1242 (1997)Google Scholar
  85. 85.
    Goltsev, A., Kussul, E.: Controlling the motion of a moving robot using a neuroid network. Trans. Autom. Remote Control. 43(5, part 1), 606–611 (1982)Google Scholar
  86. 86.
    Creed, R., Denny-Brown, D., Eccles, J., Lidell, E., Sherrington, C.: Reflex Activity of the Spinal Cord. Oxford University Press, London (1932)Google Scholar
  87. 87.
    Hubel, D.: Columns and their function in the primate visual cortex. In: Reichardt, W., Poggio, T. (eds.) Theoretical Approaches in Neurobiology. MIT Press, Cambridge, MA (1981)Google Scholar
  88. 88.
    Gerstein, G., Bedenbaugh, P., Aersten, M.H.J.: Neuronal assemblies. IEEE Trans. Biomed. Eng. 36(1), 4–14 (1989)Google Scholar
  89. 89.
    Kussul, E., Baidyk, T., Makeyev, O.: Pairwise permutation coding neural classifier. In: IEEE International Joint Conference on Neural Networks, IJCNN 2007, Orlando, FL, 12–17 August 2007, pp. 1471.1–1471.6Google Scholar
  90. 90.
    Amosov, N.M., Kussul, E.M., Fomenko, V.D.: Transport robot with neural network control system. In: 4th International Joint Conference on Artificial Intelligence IJCAI 1975, Tbilisi, Georgia, vol. 9, pp. 9.1–9.10 (1975)Google Scholar
  91. 91.
    Masoud, S.A., Masoud, A.A.: Motion planning in the presence of directional and obstacle avoidance constraints using nonlinear anisotropic, harmonic potential fields: a physical metaphor. IEEE Trans. Syst. Man Cybern. Part A: Syst. Hum. 32(6), 705–723 (2002)Google Scholar
  92. 92.
    Baidyk, T., Kussul, E.: Ensemble neural networks. Opt. Mem. Neural Netw. (Information Optics). 18(4), 295–303 (2009)Google Scholar
  93. 93.
    Palm, G.: Neural Assemblies – Studies of Brain Functions, vol. 7. Springer, New York (1982)Google Scholar
  94. 94.
    Calderon Reyes, D., Baydyk, T., Kussul, E.: Ensembles’ structures in neural networks. In: 1st International Congress on Instrumentation and Applied Sciences ICIAS, SOMI XXV, Cancun, Quintana Roo, Mexico, 26–29 October 2010, p. 6Google Scholar
  95. 95.
    Calderon, D., Baidyk, T., Kussul, E.: Information coding with neural ensembles for a mobile robot. In: IEEE International Joint Conference on Neural Networks, San Jose, CA, 31 July–5 August 2011, pp. 828–835Google Scholar
  96. 96.
    Calderon, D., Baidyk, T., Kussul, E.: Hebbian ensemble neural network for robot movement control. Opt. Mem. Neural Netw. 22(3), 166–183 (2013)Google Scholar
  97. 97.
    Baidyk, T., Kussul, E., De Luca, A., Vega, A., Calderon Reyes, D., Rodriquez-Mendoza, J.: Ensembles in neural networks. In: Proceedings of the Tenth All-Ukrainian International Conference, Kyjiv, Ukraine, 25–29 October 2010, pp. 23–26Google Scholar
  98. 98.
    Kussul, E., Makeyev, O., Baidyk, T., Calderon Reyes, D.: Neural network with ensembles. In: WCCI 2010, IEEE World Congress on Computational Intelligence (IJCNN 2010), Barcelona, Spain, 18–23 July 2010, pp. 2955–2961Google Scholar
  99. 99.
    Espinola, A., Romay, A., Baydyk, T., Kussul, E.: Robust vision system to illumination changes in a color-dependent task. In: Proceedings of the 2011 IEEE International Conference on Robotics and Biomimetics (IEEE-ROBIO 2011), Phuket, Thailand, 7–12 December 2011, pp. 521–526Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Tetyana Baydyk
    • 1
  • Ernst Kussul
    • 1
  • Donald C. Wunsch II
    • 2
  1. 1.Instituto de Ciencias Aplicadas y Tecnología (ICAT)Universidad Nacional Autónoma de México (UNAM)Mexico CityMexico
  2. 2.Dept. of Electrical and Computer EngineeringMissouri University of Science and TechnologyRollaUSA

Personalised recommendations