Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch? To address this question, we considered four distinct medical imaging applications in three specialties (radiology, cardiology, and gastroenterology) involving classification, detection, and segmentation from three different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner. Our experiments consistently demonstrated that 1) the use of a pre-trained CNN with adequate fine-tuning outperformed or, in the worst case, performed as well as a CNN trained from scratch; 2) fine-tuned CNNs were more robust to the size of training sets than CNNs trained from scratch; 3) neither shallow tuning nor deep tuning was the optimal choice for a particular application; and 4) our layer-wise fine-tuning scheme could offer a practical way to reach the best performance for the application at hand based on the amount of available data.

Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

IEEE Transactions on Pattern Analysis and Machine Intelligence

The WAVES investigation on the WIND spacecraft will provide comprehensive measurements of the radio and plasma wave phenomena which occur in Geospace. Analyses of these measurements, in coordination with the other onboard plasma, energetic particles, and field measurements will help us understand the kinetic processes that are important in the solar wind and in key boundary regions of the Geospace. These processes are then to be interpreted in conjunction with results from the other ISTP spacecraft in order to discern the measurements and parameters for mass, momentum, and energy flow throughout geospace. This investigation will also contribute to observations of radio waves emitted in regions where the solar wind is accelerated. The WAVES investigation comprises several innovations in this kind of instrumentation: among which the first use, to our knowledge, of neural networks in real-time on board a scientific spacecraft to analyze data and command observation modes, and the first use of a wavelet transform-like analysis in real time to perform a spectral analysis of a broad band signal.

/pdf/waves-the-radio-and-plasma-wave-investigation-on-the-wind-ngfb2pv1t7.pdf

Waves: The Radio and Plasma Wave Investigation on the Wind Spacecraft

The installation of a 10 MeV electron injector as a Project for the RaceTrack Microtron at the Institute of Accelerating Systems & Applications (IASA) 1 is presented. This Maquette line is composed by a 5 MeV injector linac with RF structures of the side-coupled type, followed by a 4m-booster section of the same type. This system will provide a realistic test facility for all subsystems (power station, klystron, wave-guiding, chiller, control, interlock and safety system), with exception of recirculations of the IASA cascade RTM facility. It is envisioned that its beams will be used for applied physics research.

/pdf/the-iasa-10-mev-cw-linac-2rsgx47q6y.pdf

THE IASA 10 MeV CW-LINAC

This paper presents a novel hardware architecture for the approximation of the base-2 logarithm of integers at a high accuracy and with low resource requirements. The generalized piecewise linear approximation approach allows the utilization of a very large number of linear segments for the approximation of the logarithm function, whereas state of the art architectures are limited to a maximum of six segments. In the proposed implementation, up to 1024 linear segments are employed. The exploitation of the capabilities of modern FPGAs, such as large BlockRAMs and fast multipliers allow a high frequency potential combined with low resource requirements, resulting in a pipelined implementation that only requires up to 329 slices, one BlockRAM and one multiplier. The selected number of segments affects the approximation error, which is lower than the comparable architectures by up to five orders of magnitude. The properties of the proposed architecture render it suitable for use as a generic component in systems that require fast, accurate and resource-efficient logarithm calculation.

A generalized architecture for efficient multi-segment logarithm approximation

cDNA microarrays, one of the most fundamental and powerful biotechnology tools, is being utilized in a variety of biomedical applications as it enables scientists to simultaneously analyze the expression levels of thousands of genes over different samples. One of the most essential processes of cDNA microarray experiments is the image analysis one, which is divided into three phases, namely, gridding, spot-segmentation and intensity extraction. Although its two former phases appear relatively straightforward, they are in fact rather challenging procedures due to the nature of microarray images. For their implementation, the currently available software programs require human intervention, which significantly affects the biological conclusions reached during microarray experiments. In this chapter, the basic process of analyzing a microarray image is described and advanced evolutionary algorithms implementing the automatic gridding and segmentation processes are presented. In reality, both of these algorithms are based on optimization problems which are solved by using evolutionary genetic algorithms. Contrary to existing software systems, the proposed methods are fully automatic as they do not require any human intervention; they are also noise resistant and yield excellent results even under adverse conditions. Last but not least, they outperform other software programs as well as established techniques.

/pdf/advanced-evolutionary-algorithms-for-intelligent-microarray-78csto4w2n.pdf

Advanced evolutionary algorithms for intelligent microarray image analysis

Real-time video communication over the internet and other heterogeneous IP networks has become a significant part of modern communications, underlining the need for highly effi‐ cient video coding algorithms. The most desirable characteristic of such an algorithm would be the ability to maintain satisfactory visual quality while achieving good compression. Ad‐ ditional advantageous characteristics would be low computational complexity and real-time performance, allowing the algorithm to be used in a wide variety of less powerful comput‐ ers. Transmission of video over the network would benefit by the ability to adapt to the net‐ work's end-to-end bandwidth and transmitter/receiver resources, as well as by resistance to packet losses that might occur. Additionally, scalability and resistance to noise would be highly advantageous characteristics for a modern video compression algorithm. Most state of the art video compression techniques like the H.264, DivX/Xvid, MPEG2 fail to achieve real time performance without the use of dedicated hardware due to their high computa‐ tional complexity. Moreover, in order to achieve optimal compression and quality they de‐ pend on multipass statistical and structural analysis of the whole video content, which cannot happen in cases of live video stream generation as in the case of video-conferencing.

/pdf/a-real-time-video-encoding-scheme-based-on-the-contourlet-3eblozobhu.pdf

A Real-Time Video Encoding Scheme Based on the Contourlet Transform

This paper presents a novel adaptive vision system for accurate segmentation of tissue structures in echographic medical images. The proposed vision system incorporates a level-set deformable model based on a modified Mumford-Shah functional, which is estimated over sparse foreground and background regions in the image. This functional is designed so that it copes with the intensity inhomogeneity that characterizes echographic medical images. Moreover, a parameter tuning mechanism has been considered for the adaptation of the deformable model parameters. Experiments were conducted over a range of echographic images displaying abnormal structures of the breast and of the thyroid gland. The results show that the proposed adaptive vision system stands as an efficient, effective and nearly objective tool for segmentation of echographic images.

/pdf/adaptive-vision-system-for-segmentation-of-echographic-bh8eu1jtnf.pdf

Dimitris Maroulis

Papers

THE IASA 10 MeV CW-LINAC

A generalized architecture for efficient multi-segment logarithm approximation

Advanced evolutionary algorithms for intelligent microarray image analysis

A Real-Time Video Encoding Scheme Based on the Contourlet Transform

Adaptive vision system for segmentation of echographic medical images based on a modified mumford-shah functional