Advanced Materials Research Vols. 403-408

Abstract: This design of the network establishes communication between the bunch of robots and control room, through the set of controllers and Machine learning core controller, and uses UHF for internal communication. Here, the machine learning main controller communicates with the control room through the WiMAX and keeps control over all slave miniature unmanned vehicles or robots. During the entire operation, it gets the plan and instruction from the control room, as well as it keeps learning the entire situation to handle any critical problem. Finally, this paper presents a queen bees algorithm and mathematical explanation for control and movement of all robots or Unmanned Vehicles for complex tasks.

Abstract: In this paper, an autonomous mobile robot has been designed and fabricated which can be used in both indoor and outdoor for industrial and household applications. Here using six servo motors and four DC motors with their controllers (servo controller and L293D DC Motor controller) the mobile robot can pick any object from its workspace and by avoiding collision it can place the object in the desired location. ASCII ultrasonic sensor and motion sensor are used along with ATmega 2560 microcontroller which is programmed to take the sensors output as its input and controls the dc motor and servo motors to pick and place objects and avoid obstacle during motion of the mobile robot. Here low-cost solar panels have been used to recharge the Li-ion batteries used for the motors and microcontroller in case of outdoor environment. The obstacle avoidance and path planning algorithms have been developed and a case study has been presented in this paper.

Abstract: This study deals with the control and synchronization chaos using Generalized Backstepping Method (GBM). This new method to control nonlinear systems was called generalized backstepping method because of its similarity to Backstepping Method (BM) but its more abilities to control systems than it. GBM could achieve better performance than BM in respect of lower signal control, short settling time and overshoot, control ability of MIMO systems and non strictly feedback systems. GBM consists of parameters which accept positive values. The parameters are usually chosen optional. The system responded differently for each value. This paper introduce a novel adaptive neuro fuzzy control method which trained by different error data to achieve optimal parameters. So with optimal parameters controller can stabilize the Lu chaos in much quicker than GBM.

Abstract: This paper considers the development of a brain driven car, which would be of great help to the physically disabled people. Since these cars will rely only on what the individual is thinking they will hence not require any physical movement on the part of the individual. The car integrates signals from a variety of sensors like video, weather monitor, anti-collision etc. it also has an automatic navigation system in case of emergency. The car works on the asynchronous mechanism of artificial intelligence. It’s a great advance of technology which will make the disabled, able.

Abstract: Parallel algorithms and parallel processing have revolutionized the machine’s performance and output efficiency. Parallel Random Access Machines are being used excessively for complex input processing and effective output data generation. PRAM algorithms are a class of algorithms defined for parallel computation in polynomial time complexity. Thought process is one of the key procedure that distinctly identifies humans rather animals from machines. Machines proposed to be effective computers have failed when it has come in light to learn and produce new ideas. The study here proposes the Idea Generation Algorithm with all necessary details. The algorithm uses parallel set of processors with a systolic array for data processing. The recognition of optimal output based on the associated weights and the feedback provided by to self-organizing neural network. The network provided with an unsupervised learning is proposed to provide the machine with its own set of ideas thus resulting in achievement of “thought process” in Machines. The algorithm stands as a template for any thought process development and identification in machines. Any system with capability and use of idea generation algorithm shall be with inherent learning and intelligence.

Abstract: Routers in Internet face the problem of congestion due to the increased use of Internet. AQM algorithm is a solution to the problem of congestion control in the Internet routers. As data traffic is bursty in routers, burstiness must be handled without comprising the high link utilization and low queuing delay. Congested link causes many problems such as large delay, unfairness among flows, underutilization of the link and packet drops in burst. There are various existing algorithms that have been evolved over the past few years to solve these problems of congestion in routers. RED based algorithms only use queue length as congestion indicator to indicate congestion. In this paper, we propose an AQM scheme that considers only the advantages of these queue length based and uses the flow information and satisfies the QOS requirements of the network. This proposed scheme aims to provide good service under unresponsive load and shields the responsive flows from unresponsive flows to offer a good QOS to all users.

Abstract: In automated manufacturing palletising operations, the Pallet Loading Problem (PLP) usually deals with generating optimal pallet patterns of placing boxes on a rectangular pallet. For a given pattern, the boxes can be placed in different set of sequences each affecting efficiency and productivity of robotic palletisation. Therefore, merely getting an optimal pallet pattern does not guarantee an optimal pattern placement strategy. Very few published literature is available to address this problem, and so there is a need to develop a methodology that considers the palletisers physical characteristics and limitations in robotic palletising systems. This paper presents development of an algorithm to determine the placement sequence in robotic pallet pattern formation with the aim of improving the operational efficiency in robotic palletisation.

Abstract: Iris localization is considered the most difficult part in iris identification algorithms because it defines the inner and outer boundaries of iris region used for feature analysis. Several researches were taken in the subject of iris finding and segmentation. The main objective here is to remove any non-useful information, namely the pupil segment and the part outside the iris. Duda and Hart used Hough transforms to detect the contours and curves. Daugman proposed an integro-differential operator to find both the pupil and the iris contour. Daugman’s method is claimed to be the most efficient one. This paper proposes an implementation for Daugman's algorithm, which was found incompatible with visible light illuminated images. Then this paper proposes algorithm enhancement for solving this problem.

Abstract: As the electrical industry restructures, many of the traditional algorithms for controlling generating units need modification or replacement. In the past, utilities had to produce power to satisfy their customers with the objective to minimize costs and actual demand/reserve were met. But it is not necessary in a restructured system. The main objective of restructured system is to maximize their own profit without the responsibility of satisfying the forecasted demand. The PBUC is a highly dimensional mixed-integer optimization problem, which might be very difficult to solve. Hence a new software tool is developed in java using Memory Management Algorithm (MMA) by Best Fit (BF) & Worst Fit (WF) allocation for web based application. The proposed method MMA using Best Fit & Worst Fit allocation for generator scheduling in order to receive the maximum profit by considering the softer demand. Also this method gives an idea regarding how much power and reserve should be sold in markets. The Madurai Power Grid Corporation in Tamil Nadu, India demonstrates the effectiveness of the proposed approach; extensive studies have also been performed for different power systems consisting of 3, 10and 7 generating units. Simulations of the proposed are carried out for maximizing profit and computation time and results are compared with existing methods.

Abstract: The purpose of this study is to develop an alternate in-air input device which is intended to make interaction with computers easier for amputees. This paper proposes the design and utility of accelerometer controlled Myoelectric Human Computer Interface (HCI). This device can function as a PC mouse. The two dimensional position control of the mouse cursor is done by an accelerometer-based method. The left click and right click and other extra functions of this device are controlled by the Electromyographic (EMG) signals. Artificial Neural Networks (ANNs) are used to decode the intended movements during run-time. ANN is a pattern recognition based classification. An amputee can control it using phantom wrist gestures or finger movements.