Search results for "ML"
showing 10 items of 1465 documents
Integration of a structural features-based preclassifier and a man-machine interactive classifier for a fast multi-stroke character recognition
2003
A transputer-based parallel machine for handwritten character recognition is proposed. An algorithm based on structural features and on a tree classifier was used to accomplish the pre-classification of the unknown sample in order to speed up the recognition process. The algorithm for the final classification is based on the description of the strokes through Fourier descriptors. The learning phase is accomplished through a man-machine interactive process. The proposed system can expand its knowledge base. A special representation of this knowledge base is proposed in order to record a great amount of data in a suitable way. A fast multistroke handwritten isolated character recognition syst…
A Fuzzy One Class Classifier for Multi Layer Model
2009
The paper describes an application of a fuzzy one-class classifier (FOC ) for the identification of different signal patterns embedded in a noise structured background. The classification phase is applied after a preprocessing phase based on a Multi Layer Model (MLM ) that provides a preliminary signal segmentation in an interval feature space. The FOC has been tested on synthetic and real microarray data in the specific problem of DNA nucleosome and linker regions identification. Results have shown, in both cases, a good recognition rate.
ALTERNATIVE MODELS FOR BUILDING ENERGY PERFORMANCE ASSESSMENT
2020
The research activity carried out during the three years of the PhD course attended, at the Engineering Department of the University of Palermo, was aimed at the identification of an alternative predictive model able to solve the traditional building thermal balance in a simple but reliable way, speeding up any first phase of energy planning. Nowadays, worldwide directives aimed at reducing energy consumptions and environmental impacts have focused the attention of the scientific community on improving energy efficiency in the building sector. The reduction of energy consumption and CO2 emissions for heating and cooling needs of buildings is an important challenge for the European Union, be…
An Experimental Comparison between an Ironless and a Traditional Permanent Magnet Linear Generator for Wave Energy Conversion
2022
Permanent Magnet Linear Generators (PMLGs) are currently being studied for sea wave energy harvesting. Typically, a PMLG consists of an iron-made armature and a moving translator. The permanent magnets adoption produces parasitic effects, such as cogging force, and the machine weight increment. A solution could be the adoption of an ironless configuration, accepting a power density reduction. This paper investigates the use of ironless PMLGs in sea wave energy conversion systems by an experimental comparative analysis between an iron PMLG prototype and an ironless PMLG prototype, which share the same geometry. The main electrical and mechanical parameters (resistance, mass, and magnetic fie…
Valorisation of SWRO brines in a remote island through a circular approach: Techno-economic analysis and perspectives
2022
Nowadays, small remote islands rely heavily on desalination technologies to overcome freshwater scarcity. Unfortunately, these technologies are accompanied by the production of brines which can affect the receiving water bodies i.e., the aquatic ecosystem. Yet, it is extremely appealing how such brines constitute an abundant source of valuable raw materials (such as magnesium). In this work, a novel hybrid system is introduced to capture the value of seawater reverse osmosis (SWRO) brines produced in the minor Sicilian island of Pantelleria. The “Minimal Liquid Discharge” (MLD) process consists of: (i) Nanofiltration NF (separation of bivalent from monovalent ions), (ii) Mg Reactive Crystal…
Twitter Analysis for Real-Time Malware Discovery
2017
In recent years, the increasing number of cyber-attacks has gained the development of innovative tools to quickly detect new threats. A recent approach to this problem is to analyze the content of Social Networks to discover the rising of new malicious software. Twitter is a popular social network which allows millions of users to share their opinions on what happens all over the world. The subscribers can insert messages, called tweet, that are usually related to international news. In this work, we present a system for real-time malware alerting using a set of tweets captured through the Twitter API’s, and analyzed by means of a Bayes naïve classifier. Then, groups of tweets discussing th…
An Ontology-Based Autonomic System for Ambient Intelligence Scenarios
2014
Pervasive computing and Ambient Intelligence (AmI) demonstrate that computer systems which directly interact with users are characterized by increasing size and complexity, so that the human user will still not be able to adequately manage them for a long time to come. As a response to this trend, the Autonomic Computing paradigm aims to design and develop systems able to self-configure and self-manage. The research reported here is part of an AmI project that proposes a multi-tier cognitive architecture for aggregating sensory information at different levels of abstraction. In such an architecture, a central reasoning component is able to understand the environmental state and the user’s p…
Efficient FPGA Implementation of a Knowledge-Based Automatic Speech Classifier
2005
Speech recognition has become common in many application domains, from dictation systems for professional practices to vocal user interfaces for people with disabilities or hands-free system control. However, so far the performance of Automatic Speech Recognition (ASR) systems are comparable to Human Speech Recognition (HSR) only under very strict working conditions, and in general far lower. Incorporating acoustic-phonetic knowledge into ASR design has been proven a viable approach to rise ASR accuracy. Manner of articulation attributes such as vowel, stop, fricative, approximant, nasal, and silence are examples of such knowledge. Neural networks have already been used successfully as dete…
XPL and the Synchronization of Multimodal User Interfaces based on Design Pattern
2008
The great diversity of presentations in software applications deals with fulfilment of various types of user interface constructions related to different programming languages. Furthermore, the growing interest for multimodal applications entails that their user interfaces have to support multiple access channels within a single development framework. User Interfaces Design Patterns (UIDPs) are helpful to define interaction schemas between user and computer and they provide remarkable tools for the design and reuse of software components. This paper describes the eXtensible Presentation architecture and Language (XPL), a framework aimed at streamlining multi-channel interface design process…
An Emotional Talking Head for a Humoristic Chatbot
2011
The interest about enhancing the interface usability of applications and entertainment platforms has increased in last years. The research in human-computer interaction on conversational agents, named also chatbots, and natural language dialogue systems equipped with audio-video interfaces has grown as well. One of the most pursued goals is to enhance the realness of interaction of such systems. For this reason they are provided with catchy interfaces using humanlike avatars capable to adapt their behavior according to the conversation content. This kind of agents can vocally interact with users by using Automatic Speech Recognition (ASR) and Text To Speech (TTS) systems; besides they can c…