Vincenzo Gattulli

Bio: Vincenzo Gattulli is an academic researcher from University of Bari. The author has contributed to research in topics: Deep learning & Support vector machine. The author has co-authored 4 publications.

Double Deep Q Network with In-Parallel Experience Generator

Abstract: In this paper, an algorithm, for in-parallel, greedy experience generator (briefly IPE, In Parallel Experiences), has been crafted, and added to the Double Deep Q-Learning algorithm The algorithm aims to perturbs the weights of the online network, and as results, the network, trying to recover from the perturbed weights, escapes from the local minima DDQN with IPE takes about the double of time of the previous to compute, but even if it slows down the learning rate in terms of wall clock time, the solution converges faster in terms of number of epochs

Non-Invasive Personalized In-Store Location-Based Marketing: A Practical Use Case

Abstract: This chapter shows a practical end-to-end solution that allows the integration of noninvasive location-based marketing advertisements finally binding physical and virtual in-store customer presence. The goal of the solution is to digitalize the business and improve the customer experience with the indoor proximity-based iBeacon technology for personalized marketing advertising. The architecture uses cheap battery powered iBeacon devices, Android App and a recommender system for sending noninvasive advertisement in the right moment to the right customer. The intelligent combination of loyalty programs, personalized location-based marketing campaigns, and connection to existing CRM systems will enable the desirable increase in customer loyalty by also creating ideal circumstances for custom omnichannel marketing.

Effective Machine Learning Solutions for Punctual Weather Parameter Forecasting in a Real Missing Data Scenario

Abstract: This work considers the Internet of Things (IoT) and machine learning (ML) applied to the agricultural sector within a real-working scenario. More specifically, the aim is to punctually forecast tw...

DeepKnuckle: Deep Learning for Finger Knuckle Print Recognition

Abstract: Biometric technology has received a lot of attention in recent years. One of the most prevalent biometric traits is the finger-knuckle print (FKP). Because the dorsal region of the finger is not exposed to surfaces, FKP would be a dependable and trustworthy biometric. We provide an FKP framework that uses the VGG-19 deep learning model to extract deep features from FKP images in this paper. The deep features are collected from the VGG-19 model’s fully connected layer 6 (F6) and fully connected layer 7 (F7). After applying multiple preprocessing steps, such as combining features from different layers and performing dimensionality reduction using principal component analysis (PCA), the extracted deep features are put to the test. The proposed system’s performance is assessed using experiments on the Delhi Finger Knuckle Dataset employing a variety of common classifiers. The best identification result was obtained when the Artificial neural network (ANN) classifier was applied to the principal components of the averaged feature vector of F6 and F7 deep features, with 95% of the data variance preserved. The findings also demonstrate the feasibility of employing these deep features in an FKP recognition system.

Feature selection of pre-trained shallow CNN using the QLESCA optimizer: COVID-19 detection as a case study

Abstract: According to the World Health Organization, millions of infections and a lot of deaths have been recorded worldwide since the emergence of the coronavirus disease (COVID-19). Since 2020, a lot of computer science researchers have used convolutional neural networks (CNNs) to develop interesting frameworks to detect this disease. However, poor feature extraction from the chest X-ray images and the high computational cost of the available models introduce difficulties for an accurate and fast COVID-19 detection framework. Moreover, poor feature extraction has caused the issue of ‘the curse of dimensionality’, which will negatively affect the performance of the model. Feature selection is typically considered as a preprocessing mechanism to find an optimal subset of features from a given set of all features in the data mining process. Thus, the major purpose of this study is to offer an accurate and efficient approach for extracting COVID-19 features from chest X-rays that is also less computationally expensive than earlier approaches. To achieve the specified goal, we design a mechanism for feature extraction based on shallow conventional neural network (SCNN) and used an effective method for selecting features by utilizing the newly developed optimization algorithm, Q-Learning Embedded Sine Cosine Algorithm (QLESCA). Support vector machines (SVMs) are used as a classifier. Five publicly available chest X-ray image datasets, consisting of 4848 COVID-19 images and 8669 non-COVID-19 images, are used to train and evaluate the proposed model. The performance of the QLESCA is evaluated against nine recent optimization algorithms. The proposed method is able to achieve the highest accuracy of 97.8086% while reducing the number of features from 100 to 38. Experiments prove that the accuracy of the model improves with the usage of the QLESCA as the dimensionality reduction technique by selecting relevant features.

The Use of Big Data Combined with Artificial Intelligence Neural Network Technology in Urban Spatial Evaluation System

Abstract: This exploration aims to promote the development of urbanization in China and improve the utilization rate of urban resources. First, intensive theory and spatial economics are studied. Next, an input-output urban spatial evaluation system is established based on intensive theory and data envelopment analysis (DEA). Then, deep learning (DL) is adopted for optimization, and an urban space evaluation system based on DL is proposed. Finally, the reliability level of the urban space evaluation system is tested. The results show that the model's input and output index α values are above 0.9, and the overall reliability level is higher than 0.9, indicating that the urban space evaluation system has a high reliability. The training results of the DL model show that the mean absolute error (MAE) of model prediction decreases gradually with the increase of training time and training times. When the training lasts for 5 min, each index' MAE is basically stable between 0.22 and 0.23, and the evaluation accuracy is obvious. The urban space evaluation system based on DL has higher evaluation accuracy, reaching 83.40%. Therefore, this exploration can provide research experience for promoting the effective utilization of urban resources and provide a reference for formulating an urbanization evaluation index system suitable for China's national conditions.

Leveraging Deep Learning to Fingerprint Spoof Detectors: Hitherto and Futuristic Perspectives

Abstract: Fingerprints being the most widely employed biometric trait, due to their high acceptability and low sensing cost, have replaced the traditional methods of human authentication. Although, the deployment of these biometrics-based recognition systems is accelerating, they are still susceptible to spoofing attacks where an attacker presents a fake artifact generated from silicone, candle wax, gelatin, etc. To safeguard sensor modules from these attacks, there is a requirement of an anti-deception mechanism known as fingerprint spoof detectors (FSD) also known as anti-spoofing mechanisms. A lot of research work has been carried out to design fingerprint anti-spoofing techniques in the past decades and currently, it is oriented towards deep learning (DL)-based modeling. In the field of fingerprint anti-spoofing, since the 2014, the paradigm has shifted from manually crafted features to deep features engineering. Hence, in this study, we present a detailed analysis of the recent developments in DL based FSDs. Additionally, we provide a brief comparative study of standard evaluation protocols that include benchmark anti-spoofing datasets as well as performance evaluation metrics. Although significant progress has been witnessed in the field of DL-based FSDs, still challenges are manifold. Therefore, we investigated these techniques critically to list open research issues along with their viable remedies that may put forward a future direction for the research community. The majority of the research work reveals that deep feature extraction for fingerprint liveness detection demonstrates promising performance in the case of cross-sensor scenarios. Though convolution neural network (CNN) models extract deep-level features to improve the classification accuracy, their increased complexity and training overhead is a tradeoff between both the parameters. Furthermore, enhancing the performance of presentation attack detection (PAD) techniques in the cross-material scenario is still an open challenge for researchers.