Analisi e applicazione dei processi di data mining al flusso informativo di sistemi real-time: Adattamento di un algoritmo di apprendimento automatico per la caratterizzazione e la ricerca di frequent patterns su macchine automatiche

La tesi da me svolta durante questi ultimi sei mesi è stata sviluppata presso i laboratori di ricerca di IMA S.p.a.. IMA (Industria Macchine Automatiche) è una azienda italiana che naque nel 1961 a Bologna ed oggi riveste il ruolo di leader mondiale nella produzione di macchine automatiche per il packaging di medicinali. Vorrei subito mettere in luce che in tale contesto applicativo l’utilizzo di algoritmi di data-mining risulta essere ostico a causa dei due ambienti in cui mi trovo. Il primo è quello delle macchine automatiche che operano con sistemi in tempo reale dato che non presentano a pieno le risorse di cui necessitano tali algoritmi. Il secondo è relativo alla produzione di farmaci in quanto vige una normativa internazionale molto restrittiva che impone il tracciamento di tutti gli eventi trascorsi durante l’impacchettamento ma che non permette la visione al mondo esterno di questi dati sensibili. Emerge immediatamente l’interesse nell’utilizzo di tali informazioni che potrebbero far affiorare degli eventi riconducibili a un problema della macchina o a un qualche tipo di errore al fine di migliorare l’efficacia e l’efficienza dei prodotti IMA. Lo sforzo maggiore per riuscire ad ideare una strategia applicativa è stata nella comprensione ed interpretazione dei messaggi relativi agli aspetti software. Essendo i dati molti, chiusi, e le macchine con scarse risorse per poter applicare a dovere gli algoritmi di data mining ho provveduto ad adottare diversi approcci in diversi contesti applicativi: • Sistema di identificazione automatica di errore al fine di aumentare di diminuire i tempi di correzione di essi. • Modifica di un algoritmo di letteratura per la caratterizzazione della macchina. La trattazione è così strutturata: • Capitolo 1: descrive la macchina automatica IMA Adapta della quale ci sono stati forniti i vari file di log. Essendo lei l’oggetto di analisi per questo lavoro verranno anche riportati quali sono i flussi di informazioni che essa genera. • Capitolo 2: verranno riportati degli screenshoot dei dati in mio possesso al fine di, tramite un’analisi esplorativa, interpretarli e produrre una formulazione di idee/proposte applicabili agli algoritmi di Machine Learning noti in letteratura. • Capitolo 3 (identificazione di errore): in questo capitolo vengono riportati i contesti applicativi da me progettati al fine di implementare una infrastruttura che possa soddisfare il requisito, titolo di questo capitolo. • Capitolo 4 (caratterizzazione della macchina): definirò l’algoritmo utilizzato, FP-Growth, e mostrerò le modifiche effettuate al fine di poterlo impiegare all’interno di macchine automatiche rispettando i limiti stringenti di: tempo di cpu, memoria, operazioni di I/O e soprattutto la non possibilità di aver a disposizione l’intero dataset ma solamente delle sottoporzioni. Inoltre verranno generati dei DataSet per il testing di dell’algoritmo FP-Growth modificato.

Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Modelli e Strumenti di Classifciazione Automatica per il Controllo dell'Accesso su Piattaforme Big Data

Dall'analisi dei big data si possono trarre degli enormi benefici in svariati ambiti applicativi. Uno dei fattori principali che contribuisce alla ricchezza dei big data, consiste nell'uso non previsto a priori di dati immagazzinati in precedenza, anche in congiunzione con altri dataset eterogenei: questo permette di trovare correlazioni significative e inaspettate tra i dati. Proprio per questo, il Valore, che il dato potenzialmente porta con sè, stimola le organizzazioni a raccogliere e immagazzinare sempre più dati e a ricercare approcci innovativi e originali per effettuare analisi su di essi. L’uso fortemente innovativo che viene fatto dei big data in questo senso e i requisiti tecnologici richiesti per gestirli hanno aperto importanti problematiche in materia di sicurezza e privacy, tali da rendere inadeguati o difficilmente gestibili, gli strumenti di sicurezza utilizzati finora nei sistemi tradizionali. Con questo lavoro di tesi si intende analizzare molteplici aspetti della sicurezza in ambito big data e offrire un possibile approccio alla sicurezza dei dati. In primo luogo, la tesi si occupa di comprendere quali sono le principali minacce introdotte dai big data in ambito di privacy, valutando la fattibilità delle contromisure presenti all’attuale stato dell’arte. Tra queste anche il controllo dell’accesso ha riscontrato notevoli sfide causate dalle necessità richieste dai big data: questo elaborato analizza pregi e difetti del controllo dell’accesso basato su attributi (ABAC), un modello attualmente oggetto di discussione nel dibattito inerente sicurezza e privacy nei big data. Per rendere attuabile ABAC in un contesto big data, risulta necessario l’ausilio di un supporto per assegnare gli attributi di visibilità alle informazioni da proteggere. L’obiettivo di questa tesi consiste nel valutare fattibilità, caratteristiche significative e limiti del machine learning come possibile approccio di utilizzo.

"Cloudy": un'applicazione di assistenza allo shopping basata sulle API di Marketcloud

In questo lavoro di tesi si è analizzato il problema di creare un sistema di assistenza allo shopping integrabile in applicazioni e-commerce web e mobile sviluppate con le tecnologie messe a disposizione da Marketcloud, ovvero un progetto che punta a fornire strumenti per la realizzazione, la manutenzione, la gestione, la diffusione e la pubblicizzazione di tali applicazioni limitando i costi e le problematiche di sviluppo a carico delle aziende che intendono fornire servizi di e-commerce. Dopo aver discusso gli aspetti principali del progetto Marketcloud, sono state analizzate le necessità delle aziende interessate allo sviluppo del sistema di assistenza in esame, così come le aspettative degli utenti (i clienti) finali, ed è stato discusso perché fosse necessario e preferibile, nel caso in esame, non utilizzare soluzioni già presenti sul mercato. Infine, è stata progettata ed implementata un’applicazione web che includesse tale sistema e che fosse immediatamente integrabile tra i servizi già sviluppati da Marketcloud, testandone risultati, prestazioni, problemi e possibili sviluppi futuri. Al termine del lavoro di implementazione, il sistema e l'applicazione garantiscono all'utente finale l'utilizzo di tre funzioni: ricerca per categoria, ricerca libera, recommendation di prodotti. Per gestire la ricerca libera, è stato implementato un sistema di filtri successivi, ed una rete neurale multi-livello dotata di un opportuno algoritmo di machine learning per poter apprendere dalle scelte degli utenti; per la recommendation di prodotti, è stato utilizzato un sistema di ranking (classificazione). Le prestazioni della rete neurale sono state oggetto di attenta analisi.

Automated Intervertebral Disc Detection from Low Resolution, Sparse MRI Images for the Planning of Scan Geometries

Robust and accurate identification of intervertebral discs from low resolution, sparse MRI scans is essential for the automated scan planning of the MRI spine scan. This paper presents a graphical model based solution for the detection of both the positions and orientations of intervertebral discs from low resolution, sparse MRI scans. Compared with the existing graphical model based methods, the proposed method does not need a training process using training data and it also has the capability to automatically determine the number of vertebrae visible in the image. Experiments on 25 low resolution, sparse spine MRI data sets verified its performance.

Energy-Economical Heuristically Based Control of Compass Gait Walking on Stochastically Varying Terrain

Investigation uses simulation to explore the inherent tradeoffs ofcontrolling high-speed and highly robust walking robots while minimizing energy consumption. Using a novel controller which optimizes robustness, energy economy, and speed of a simulated robot on rough terrain, the user can adjust their priorities between these three outcome measures and systematically generate a performance curveassessing the tradeoffs associated with these metrics.

A MULTILEVEL MODEL TO ADDRESS BATCH EFFECTS IN COPY NUMBER ESTIMATION USING SNP ARRAYS

Submicroscopic changes in chromosomal DNA copy number dosage are common and have been implicated in many heritable diseases and cancers. Recent high-throughput technologies have a resolution that permits the detection of segmental changes in DNA copy number that span thousands of basepairs across the genome. Genome-wide association studies (GWAS) may simultaneously screen for copy number-phenotype and SNP-phenotype associations as part of the analytic strategy. However, genome-wide array analyses are particularly susceptible to batch effects as the logistics of preparing DNA and processing thousands of arrays often involves multiple laboratories and technicians, or changes over calendar time to the reagents and laboratory equipment. Failure to adjust for batch effects can lead to incorrect inference and requires inefficient post-hoc quality control procedures that exclude regions that are associated with batch. Our work extends previous model-based approaches for copy number estimation by explicitly modeling batch effects and using shrinkage to improve locus-specific estimates of copy number uncertainty. Key features of this approach include the use of diallelic genotype calls from experimental data to estimate batch- and locus-specific parameters of background and signal without the requirement of training data. We illustrate these ideas using a study of bipolar disease and a study of chromosome 21 trisomy. The former has batch effects that dominate much of the observed variation in quantile-normalized intensities, while the latter illustrates the robustness of our approach to datasets where as many as 25% of the samples have altered copy number. Locus-specific estimates of copy number can be plotted on the copy-number scale to investigate mosaicism and guide the choice of appropriate downstream approaches for smoothing the copy number as a function of physical position. The software is open source and implemented in the R package CRLMM available at Bioconductor (http:www.bioconductor.org).

Moving from sustainable management to sustainable governance of natural resources: The role of social learning processes in rural India, Bolivia and Mali

The present paper discusses a conceptual, methodological and practical framework within which the limitations of the conventional notion of natural resource management (NRM) can be overcome. NRM is understood as the application of scientific ecological knowledge to resource management. By including a consideration of the normative imperatives that arise from scientific ecological knowledge and submitting them to public scrutiny, ‘sustainable management of natural resources’ can be recontextualised as ‘sustainable governance of natural resources’. This in turn makes it possible to place the politically neutralising discourse of ‘management’ in a space for wider societal debate, in which the different actors involved can deliberate and negotiate the norms, rules and power relations related to natural resource use and sustainable development. The transformation of sustainable management into sustainable governance of natural resources can be conceptualised as a social learning process involving scientists, experts, politicians and local actors, and their corresponding scientific and non-scientific knowledges. The social learning process is the result of what Habermas has described as ‘communicative action’, in contrast to ‘strategic action’. Sustainable governance of natural resources thus requires a new space for communicative action aiming at shared, intersubjectively validated definitions of actual situations and the goals and means required for transforming current norms, rules and power relations in order to achieve sustainable development. Case studies from rural India, Bolivia and Mali explore the potentials and limitations for broadening communicative action through an intensification of social learning processes at the interface of local and external knowledge. Key factors that enable or hinder the transformation of sustainable management into sustainable governance of natural resources through social learning processes and communicative action are discussed.

IDENTIFICATION OF GENES CONTROLLING BIOLOGICAL PROCESSES AND PATHWAYS THROUGH STATISTICAL ANALYSIS AND NETWORK RECONSTRUCTION

The developmental processes and functions of an organism are controlled by the genes and the proteins that are derived from these genes. The identification of key genes and the reconstruction of gene networks can provide a model to help us understand the regulatory mechanisms for the initiation and progression of biological processes or functional abnormalities (e.g. diseases) in living organisms. In this dissertation, I have developed statistical methods to identify the genes and transcription factors (TFs) involved in biological processes, constructed their regulatory networks, and also evaluated some existing association methods to find robust methods for coexpression analyses. Two kinds of data sets were used for this work: genotype data and gene expression microarray data. On the basis of these data sets, this dissertation has two major parts, together forming six chapters. The first part deals with developing association methods for rare variants using genotype data (chapter 4 and 5). The second part deals with developing and/or evaluating statistical methods to identify genes and TFs involved in biological processes, and construction of their regulatory networks using gene expression data (chapter 2, 3, and 6). For the first part, I have developed two methods to find the groupwise association of rare variants with given diseases or traits. The first method is based on kernel machine learning and can be applied to both quantitative as well as qualitative traits. Simulation results showed that the proposed method has improved power over the existing weighted sum method (WS) in most settings. The second method uses multiple phenotypes to select a few top significant genes. It then finds the association of each gene with each phenotype while controlling the population stratification by adjusting the data for ancestry using principal components. This method was applied to GAW 17 data and was able to find several disease risk genes. For the second part, I have worked on three problems. First problem involved evaluation of eight gene association methods. A very comprehensive comparison of these methods with further analysis clearly demonstrates the distinct and common performance of these eight gene association methods. For the second problem, an algorithm named the bottom-up graphical Gaussian model was developed to identify the TFs that regulate pathway genes and reconstruct their hierarchical regulatory networks. This algorithm has produced very significant results and it is the first report to produce such hierarchical networks for these pathways. The third problem dealt with developing another algorithm called the top-down graphical Gaussian model that identifies the network governed by a specific TF. The network produced by the algorithm is proven to be of very high accuracy.

DYNAMICS AND CONTROL OF REACTIVE DISTILLATION PROCESS FOR MONOMER SYNTHESIS OF POLYCARBONATE PLANTS

Polycarbonate (PC) is an important engineering thermoplastic that is currently produced in large industrial scale using bisphenol A and monomers such as phosgene. Since phosgene is highly toxic, a non-phosgene approach using diphenyl carbonate (DPC) as an alternative monomer, as developed by Asahi Corporation of Japan, is a significantly more environmentally friendly alternative. Other advantages include the use of CO2 instead of CO as raw material and the elimination of major waste water production. However, for the production of DPC to be economically viable, reactive-distillation units are needed to obtain the necessary yields by shifting the reaction-equilibrium to the desired products and separating the products at the point where the equilibrium reaction occurs. In the field of chemical reaction engineering, there are many reactions that are suffering from the low equilibrium constant. The main goal of this research is to determine the optimal process needed to shift the reactions by using appropriate control strategies of the reactive distillation system. An extensive dynamic mathematical model has been developed to help us investigate different control and processing strategies of the reactive distillation units to increase the production of DPC. The high-fidelity dynamic models include extensive thermodynamic and reaction-kinetics models while incorporating the necessary mass and energy balance of the various stages of the reactive distillation units. The study presented in this document shows the possibility of producing DPC via one reactive distillation instead of the conventional two-column, with a production rate of 16.75 tons/h corresponding to start reactants materials of 74.69 tons/h of Phenol and 35.75 tons/h of Dimethyl Carbonate. This represents a threefold increase over the projected production rate given in the literature based on a two-column configuration. In addition, the purity of the DPC produced could reach levels as high as 99.5% with the effective use of controls. These studies are based on simulation done using high-fidelity dynamic models.

Human urinary metabolomic profile of PPARalpha induced fatty acid beta-oxidation

Activation of the peroxisome proliferator-activated receptor alpha (PPARalpha) is associated with increased fatty acid catabolism and is commonly targeted for the treatment of hyperlipidemia. To identify latent, endogenous biomarkers of PPARalpha activation and hence increased fatty acid beta-oxidation, healthy human volunteers were given fenofibrate orally for 2 weeks and their urine was profiled by UPLC-QTOFMS. Biomarkers identified by the machine learning algorithm random forests included significant depletion by day 14 of both pantothenic acid (>5-fold) and acetylcarnitine (>20-fold), observations that are consistent with known targets of PPARalpha including pantothenate kinase and genes encoding proteins involved in the transport and synthesis of acylcarnitines. It was also concluded that serum cholesterol (-12.7%), triglycerides (-25.6%), uric acid (-34.7%), together with urinary propylcarnitine (>10-fold), isobutyrylcarnitine (>2.5-fold), (S)-(+)-2-methylbutyrylcarnitine (5-fold), and isovalerylcarnitine (>5-fold) were all reduced by day 14. Specificity of these biomarkers as indicators of PPARalpha activation was demonstrated using the Ppara-null mouse. Urinary pantothenic acid and acylcarnitines may prove useful indicators of PPARalpha-induced fatty acid beta-oxidation in humans. This study illustrates the utility of a pharmacometabolomic approach to understand drug effects on lipid metabolism in both human populations and in inbred mouse models.

Semiotic Analysis in the Study of Social Work

Research and professional practices have the joint aim of re-structuring the preconceived notions of reality. They both want to gain the understanding about social reality. Social workers use their professional competence in order to grasp the reality of their clients, while researchers’ pursuit is to open the secrecies of the research material. Development and research are now so intertwined and inherent in almost all professional practices that making distinctions between practising, developing and researching has become difficult and in many aspects irrelevant. Moving towards research-based practices is possible and it is easily applied within the framework of the qualitative research approach (Dominelli 2005, 235; Humphries 2005, 280). Social work can be understood as acts and speech acts crisscrossing between social workers and clients. When trying to catch the verbal and non-verbal hints of each others’ behaviour, the actors have to do a lot of interpretations in a more or less uncertain mental landscape. Our point of departure is the idea that the study of social work practices requires tools which effectively reveal the internal complexity of social work (see, for example, Adams & Dominelli & Payne 2005, 294 – 295). The boom of qualitative research methodologies in recent decades is associated with much profound the rupture in humanities, which is called the linguistic turn (Rorty 1967). The idea that language is not transparently mediating our perceptions and thoughts about reality, but on the contrary it constitutes it was new and even confusing to many social scientists. Nowadays we have got used to read research reports which have applied different branches of discursive analyses or narratologic or semiotic approaches. Although differences are sophisticated between those orientations they share the idea of the predominance of language. Despite the lively research work of today’s social work and the research-minded atmosphere of social work practice, semiotics has rarely applied in social work research. However, social work as a communicative practice concerns symbols, metaphors and all kinds of the representative structures of language. Those items are at the core of semiotics, the science of signs, and the science which examines people using signs in their mutual interaction and their endeavours to make the sense of the world they live in, their semiosis. When thinking of the practice of social work and doing the research of it, a number of interpretational levels ought to be passed before reaching the research phase in social work. First of all, social workers have to interpret their clients’ situations, which will be recorded in the files. In some very rare cases those past situations will be reflected in discussions or perhaps interviews or put under the scrutiny of some researcher in the future. Each and every new observation adds its own flavour to the mixture of meanings. Social workers have combined their observations with previous experience and professional knowledge, furthermore, the situation on hand also influences the reactions. In addition, the interpretations made by social workers over the course of their daily working routines are never limited to being part of the personal process of the social worker, but are also always inherently cultural. The work aiming at social change is defined by the presence of an initial situation, a specific goal, and the means and ways of achieving it, which are – or which should be – agreed upon by the social worker and the client in situation which is unique and at the same time socially-driven. Because of the inherent plot-based nature of social work, the practices related to it can be analysed as stories (see Dominelli 2005, 234), given, of course, that they are signifying and told by someone. The research of the practices is concentrating on impressions, perceptions, judgements, accounts, documents etc. All these multifarious elements can be scrutinized as textual corpora, but not whatever textual material. In semiotic analysis, the material studied is characterised as verbal or textual and loaded with meanings. We present a contribution of research methodology, semiotic analysis, which has to our mind at least implicitly references to the social work practices. Our examples of semiotic interpretation have been picked up from our dissertations (Laine 2005; Saurama 2002). The data are official documents from the archives of a child welfare agency and transcriptions of the interviews of shelter employees. These data can be defined as stories told by the social workers of what they have seen and felt. The official documents present only fragmentations and they are often written in passive form. (Saurama 2002, 70.) The interviews carried out in the shelters can be described as stories where the narrators are more familiar and known. The material is characterised by the interaction between the interviewer and interviewee. The levels of the story and the telling of the story become apparent when interviews or documents are examined with the use of semiotic tools. The roots of semiotic interpretation can be found in three different branches; the American pragmatism, Saussurean linguistics in Paris and the so called formalism in Moscow and Tartu; however in this paper we are engaged with the so called Parisian School of semiology which prominent figure was A. J. Greimas. The Finnish sociologists Pekka Sulkunen and Jukka Törrönen (1997a; 1997b) have further developed the ideas of Greimas in their studies on socio-semiotics, and we lean on their ideas. In semiotics social reality is conceived as a relationship between subjects, observations, and interpretations and it is seen mediated by natural language which is the most common sign system among human beings (Mounin 1985; de Saussure 2006; Sebeok 1986). Signification is an act of associating an abstract context (signified) to some physical instrument (signifier). These two elements together form the basic concept, the “sign”, which never constitutes any kind of meaning alone. The meaning will be comprised in a distinction process where signs are being related to other signs. In this chain of signs, the meaning becomes diverged from reality. (Greimas 1980, 28; Potter 1996, 70; de Saussure 2006, 46-48.) One interpretative tool is to think of speech as a surface under which deep structures – i.e. values and norms – exist (Greimas & Courtes 1982; Greimas 1987). To our mind semiotics is very much about playing with two different levels of text: the syntagmatic surface which is more or less faithful to the grammar, and the paradigmatic, semantic structure of values and norms hidden in the deeper meanings of interpretations. Semiotic analysis deals precisely with the level of meaning which exists under the surface, but the only way to reach those meanings is through the textual level, the written or spoken text. That is why the tools are needed. In our studies, we have used the semiotic square and the actant analysis. The former is based on the distinctions and the categorisations of meanings, and the latter on opening the plotting of narratives in order to reach the value structures.

Head Tracking Based Avatar Control for Virtual Environment Teamwork Training

Virtual environments (VE) are gaining in popularity and are increasingly used for teamwork training purposes, e.g., for medical teams. One shortcoming of modern VEs is that nonverbal communication channels, essential for teamwork, are not supported well. We address this issue by using an inexpensive webcam to track the user's head. This tracking information is used to control the head movement of the user's avatar, thereby conveying head gestures and adding a nonverbal communication channel. We conducted a user study investigating the influence of head tracking based avatar control on the perceived realism of the VE and on the performance of a surgical teamwork training scenario. Our results show that head tracking positively influences the perceived realism of the VE and the communication, but has no major influence on the training outcome.

Active Learning – Teaching Immunizations

Introduction or Statement of Problem: It is often challenging to get students in a large classroom setting actively involved in a classroom discussion. In order to help students appreciate the effects of low immunization rates, a classroom activity was developed using active learning techniques. This allowed the students to identify and appreciate the complexity of the issues concerning childhood immunizations. [See PDF for complete abstract]

Improved detection of amnestic MCI by means of discriminative vector quantization of single-trial cognitive ERP responses

Cognitive event-related potentials (ERPs) are widely employed in the study of dementive disorders. The morphology of averaged response is known to be under the influence of neurodegenerative processes and exploited for diagnostic purposes. This work is built over the idea that there is additional information in the dynamics of single-trial responses. We introduce a novel way to detect mild cognitive impairment (MCI) from the recordings of auditory ERP responses. Using single trial responses from a cohort of 25 amnestic MCI patients and a group of age-matched controls, we suggest a descriptor capable of encapsulating single-trial (ST) response dynamics for the benefit of early diagnosis. A customized vector quantization (VQ) scheme is first employed to summarize the overall set of ST-responses by means of a small-sized codebook of brain waves that is semantically organized. Each ST-response is then treated as a trajectory that can be encoded as a sequence of code vectors. A subject's set of responses is consequently represented as a histogram of activated code vectors. Discriminating MCI patients from healthy controls is based on the deduced response profiles and carried out by means of a standard machine learning procedure. The novel response representation was found to improve significantly MCI detection with respect to the standard alternative representation obtained via ensemble averaging (13% in terms of sensitivity and 6% in terms of specificity). Hence, the role of cognitive ERPs as biomarker for MCI can be enhanced by adopting the delicate description of our VQ scheme.