The ubiquity of smartphones and the growth computing resources, such as connectivity, processing, portability, power sensing, have greatly changed people's lives. Today, many contain a variety powerful sensors, including motion, location, network, direction sensors. Motion or inertial sensors (e.g., accelerometer), specifically, been widely used to recognize users' physical activities. This has opened doors for different interesting applications in several areas, health transportation. In...

The miniaturization of hardware components has lead to the development Wireless Sensor Networks (WSN) and networked-applications over them. Meanwhile, middleware systems have also been proposed in order both facilitating these applications providing common application services. for sensor networks, however, places new challenges developers due low availability resources processing capacity nodes. In this context, paper presents a WSN named Mires. Mires incorporates characteristics...

In this article, we introduce explainable methods to understand how Human Activity Recognition (HAR) mobile systems perform based on the chosen validation strategies. Our results a new way discover potential bias problems that overestimate prediction accuracy of an algorithm because inappropriate choice methodology. We show SHAP (Shapley additive explanations) framework, used in literature explain predictions any machine learning model, presents itself as tool can provide graphical insights...

Indoor positioning systems (IPSs) have emerged as a research topic in mobile computing, enabling the tracking and location of devices indoor environments. In model-based IPSs, received signal strength indicator (RSSI) is used to estimate distance between wireless receivers transmitters using propagation models. However, environment presents challenges that make estimation RSSI difficult. this article, we propose new IPS combines particle swarm optimization (PSO) with models improve accuracy...

Ad hoc and wireless sensor networks have recently emerged as successful technologies in a number of application domains. The need to build security services into them remains however considerable challenge the hardware used often shows serious processing energy limitations. This work evaluates impact mechanism on nodes network whole. Hence actual measurements were undertaken real platform order accurately establish consumption for various encryption algorithms; well baseline scenario...

This work proposes a new indoor positioning system, named KLIP, that uses the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means clustering algorithm to split environment into different sets of log-distance propagation models in order better characterize and further improve position estimation using Bayesian inference. Our proposed method is validated large-scale,...

The structure of dynamic websites comprised a set objects such as HTML tags, script functions, hyperlinks and advanced features in browsers lead to numerous resources interactiveness services currently provided on the Internet. However, these have also increased security risks attacks since they allow malicious codes injection or XSS (Cross-Site Scripting). remains at top lists greatest threats web applications recent years. This paper presents experimental results obtained automatic...

The recognition of users' physical activities through data analysis smartphone inertial sensors has aided the development several solutions in different domains such as transportation and healthcare. Mostly these have been supported by cloud communication technologies due to need using accurate classification models. In an attempt solve problems related orientation (e.g. landscape) user's body, new types features classified independent arisen last years. this context, paper presents...

The use of machine learning (ML) techniques in affective computing applications focuses on improving the user experience emotion recognition. collection input data (e.g., physiological signals), together with expert annotations are part established standard supervised methodology used to train human recognition models. However, these models generally require large amounts labeled data, which is expensive and impractical healthcare context, annotation requires even more knowledge. To address...

Indoor positioning systems (IPSs) allow the location and tracking of mobile devices in indoor environments where global system (GPS) does not provide satisfactory results. In model-based IPSs, it is common to use signal propagation models estimate distances between anchor nodes using received strength indicator (RSSI). However, fixed parameters path loss model characterize large-scale scenarios results degradation accuracy. this article, we propose adaptive (ADAM) system, a IPS that chooses...

The Internet of Things (IoT) application development is a complex task that requires wide range expertise. Currently, the IoT community lacks toolkit enables inexperienced developers to develop prototypes rapidly. Filling this gap, we propose based on model-driven approach, called Link. Link allows compose mash up applications through graphical domain-specific language can be easily configured and wired together create an application. Through visual components, encapsulates complexity...

In recent years, the consumption of electricity has increased considerably in industrial, commercial and residential sectors. This prompted a branch research which attempts to overcome this problem by applying different information communication technologies, turning houses buildings into smart environments. paper, we propose design an energy saving technique based on relationship between user's activities electrical appliances home The proposed method utilizes machine learning techniques...

Smartphones have emerged as a revolutionary technology for monitoring everyday life, and they played an important role in Human Activity Recognition (HAR) due to its ubiquity. The sensors embedded these devices allows recognizing human behaviors using machine learning techniques. However, not all solutions are feasible implementation smartphones, mainly because of high computational cost. In this context, the proposed method, called HAR-SR, introduces information theory quantifiers new...

Mobile sensing has allowed the emergence of a variety solutions related to monitoring and recognition human activities (HAR). Such have been implemented in smartphones for purpose better understanding behavior. However, such still suffer from limitations computing resources found on smartphones. In this sense, HAR area focused development low computational cost. general, strategies used are based shallow deep learning algorithms. The problem is that not all these feasible implementation due...

Human activity recognition (HAR) through sensors embedded in smartphones has allowed for the development of systems that are capable detecting and monitoring human behavior. However, such have been affected by high consumption computational resources (e.g., memory processing) needed to effectively recognize activities. In addition, existing HAR mostly based on supervised classification techniques, which feature extraction process is done manually, depends knowledge a specialist. To overcome...

We use Explainable Artificial Intelligence (XAI) to understand and assess the decisions made by ML models in Android malware detection. To evaluate detection, we conducted experiments using seven datasets. Our findings indicate that it is possible accurately identify across multiple However, each dataset may have a different collection of features available. also discuss implications incorporating expert-dependent into detection procedure. Such potential increase model accuracy detecting...

The inappropriate use of features intended to improve usability and interactivity web applications has resulted in the emergence various threats, including Cross-Site Scripting(XSS) attacks. In this work, we developed ETSS Detector, a generic modular vulnerability scanner that automatically analyzes find XSS vulnerabilities. Detector is able identify analyze all data entry points application generate specific code injection tests for each one. results shows correct filling input fields with...

Automatic nudity detection strategies play an important role in solutions focusing on controlling access to inappropriate content. These usually apply filter or similar approaches order detect digital images. In this paper we propose a strategy for based applying image zoning. Moreover, perform feature extraction using color and texture information, as well selection, pointing out the most relevant features. SVM is used classification. Experimental results demonstrate that effective...

The fast pace proliferation of Android malware continues to pose challenges cybersecurity research. To help reshape the future research, we introduce MH-100K, a dataset that provides holistic view through 101,975 APK samples, thousands diverse features and metadata. We use VirusTotal API ensure accurate threat evaluation, combining multiple detection methods for precision. Our findings suggest MH-100K is valuable resource providing new insights about landscape’s evolution.

Indoor Positioning Systems (IPSs) are used to locate mobile devices in indoor environments. Model-based IPSs have the advantage of not having an exhausting training and signal characterization environment, as required by fingerprint technique. However, most model-based done using fixed model parameters, treating whole scenario a uniform propagation. This might work for small scale experiments, but larger scenarios. In this paper, we propose PoDME (Positioning Dynamic Model Estimation), IPS...

Mobile and wearable devices have revolutionized the field of continuous user activity monitoring. However, analyzing vast intricate data captured by sensors these poses significant challenges. Deep neural networks shown remarkable accuracy in Human Activity Recognition (HAR), but their application on mobile is constrained limited computational resources. To address this limitation, we propose a novel method called Knowledge Distillation for (KD-HAR) that leverages knowledge distillation...