The highly successful architecture and protocols of today's Internet may operate poorly in environments characterized by very long delay paths and frequent network partitions. These problems are exacerbated by end nodes with limited power or memory resources. Often deployed in mobile and extreme environments lacking continuous connectivity, many such networks have their own specialized protocols, and do not utilize IP. To achieve interoperability between them, we propose a network architecture and application interface structured around optionally-reliable asynchronous message forwarding, with limited expectations of end-to-end connectivity and node resources. The architecture operates as an overlay above the transport layers of the networks it interconnects, and provides key services such as in-network data storage and retransmission, interoperable naming, authenticated forwarding and a coarse-grained class of service.

/pdf/a-delay-tolerant-network-architecture-for-challenged-4nomv5ym6e.pdf

A delay-tolerant network architecture for challenged internets

This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closed-loop behavior is adaptive, distributed, asynchronous, and verifiably correct.

Coverage control for mobile sensing networks

Methods for interpreting and understanding deep neural networks

Logistic regression and artificial neural network classification models: a methodology review

The Dynamic Source Routing protocol (DSR) is a simple and efficient
routing protocol designed specifically for use in multi-hop wireless
ad hoc networks of mobile nodes. DSR allows the network to be
completely self-organizing and self-configuring, without the need for
any existing network infrastructure or administration. The protocol is
composed of the two mechanisms of "Route Discovery" and "Route
Maintenance", which work together to allow nodes to discover and
maintain source routes to arbitrary destinations in the ad hoc
network. The use of source routing allows packet routing to be
trivially loop-free, avoids the need for up-to-date routing
information in the intermediate nodes through which packets are
forwarded, and allows nodes forwarding or overhearing packets to cache
the routing information in them for their own future use. All aspects
of the protocol operate entirely on-demand, allowing the routing
packet overhead of DSR to scale automatically to only that needed to
react to changes in the routes currently in use. This document
specifies the operation of the DSR protocol for routing unicast IP
packets in multi-hop wireless ad hoc networks.

/pdf/the-dynamic-source-routing-protocol-dsr-for-mobile-ad-hoc-1hk2pcx117.pdf

The Dynamic Source Routing Protocol (DSR) for Mobile Ad Hoc Networks for IPv4

The Transmission Control Protocol.

Multilayer feedforward networks are often used for modeling complex relationships between the data sets. Deleting unimportant data components in the training sets could lead to smaller networks and reduced-size data vectors. This can be achieved by analyzing the total disturbance of network outputs due to perturbed inputs. The search for redundant data components is performed for networks with continuous outputs and is based on the concept in sensitivity of linearized neural networks. The formalized criteria and algorithm for pruning data vectors are formulated and illustrated with examples. >

Sensitivity analysis for minimization of input data dimension for feedforward neural network

https://olek.matthewm.com.pl/cv//pubs/Perturbation%20method%20for%20deleting%20redundant%20inputs%20of%20perceptron%20networks.pdf

Perturbation method for deleting redundant inputs of perceptron networks

This paper presents a survey on embedded systems design and applications. Several platforms for embedded systems, including microcontrollers, microprocessors, field-programmable gate arrays, digital signal processors, and application-specific integrated circuits are discussed and compared. A survey of embedded system-based industrial applications is presented. Examples of real-life design decisions specific to development of such systems are also presented. The carefully selected three design case study examples include industrial control of wind tunnel with emphasis on actuator control, a mobile robot navigation system with emphasis on integration and synchronization of several subsystems, and optimized implementation of computationally intensive control system on a small microcontroller system.

Comparison of Embedded System Design for Industrial Applications

Efficient second order algorithm for training feedforward neural networks is presented. The algorithm has a similar convergence rate as the Lavenberg-Marquardt (LM) method and it is less computationally intensive and requires less memory. This is especially important for large neural networks where the LM algorithm becomes impractical. Algorithm was verified with several examples.

/pdf/efficient-algorithm-for-training-neural-networks-with-one-1qa8fkohhu.pdf

Aleksander Malinowski

Papers

The Transmission Control Protocol.

Sensitivity analysis for minimization of input data dimension for feedforward neural network

Perturbation method for deleting redundant inputs of perceptron networks

Comparison of Embedded System Design for Industrial Applications

Efficient algorithm for training neural networks with one hidden layer