Real-time SLAM with dense 3D mapping is computationally challenging, especially on resource-limited devices. The recent development of 3D Gaussian Splatting (3DGS) offers a promising approach for real-time dense 3D reconstruction. However, existing 3DGS-based SLAM systems struggle to balance hardware simplicity, speed, and map quality. Most systems excel in one or two of the aforementioned aspects but rarely achieve all. A key issue is the difficulty of initializing 3D Gaussians while concurrently conducting SLAM. To address these challenges, we present Monocular GSO (MGSO), a novel real-time SLAM system that integrates photometric SLAM with 3DGS. Photometric SLAM provides dense structured point clouds for 3DGS initialization, accelerating optimization and producing more efficient maps with fewer Gaussians. As a result, experiments show that our system generates reconstructions with a balance of quality, memory efficiency, and speed that outperforms the state-of-the-art. Furthermore, our system achieves all results using RGB inputs. We evaluate the Replica, TUM-RGBD, and EuRoC datasets against current live dense reconstruction systems. Not only do we surpass contemporary systems, but experiments also show that we maintain our performance on laptop hardware, making it a practical solution for robotics,$A / R$, and other real-time applications.

In this paper, we propose a collaborative centralized 3D mapping and localization framework that harnesses the capabilities of both SLAM (Simultaneous Localization And Mapping) and XR (eXtended Reality). On one hand, our framework allows for integrating local maps generated by a multitude of heterogeneous agents (e.g. robots) into a unified map. On the other hand, it allows human intervention at multiple levels: first, humans can inspect and intervene in the mapping process in situ to produce 3D maps, overlay virtual assets, and add annotations, all of which can contribute towards enhanced autonomy and navigation. Second, beyond the mapping aspect, a human can also intervene in the localization task of any collaborating robot by inspecting and correcting its generated paths, and, if necessary, enforcing a desired trajectory. Experiments inside two real settings demonstrated the superiority of the proposed system.

BACKGROUND: The practice of medicine has evolved significantly during the past decade, with the emergence of Machine Learning (ML) that offers the opportunity of personalized patient-tailored care. However, ML models still face some challenges when classifying patients where clear-cut boundaries between classes are hard to identify. In this work, we propose an ML architecture to improve the sensitivity of detecting patients in intermediate "hard-to-classify" classes. METHODS: The proposed architecture replaces a single classifier with a group of cascaded increasingly specialized classifiers: the 'Human-like', the 'Segregating', and the 'Deep' classifiers. Its effectiveness is tested, using 8 ML algorithms (Logistic Regression, Support Vector Machine, K-Nearest Neighbor, Decision Tree, Random Forest, XGBoost, CatBoost, and Artificial Neural Network) to predict the feeling of protection among healthcare workers during the COVID-19 pandemic, based on a global online survey, then validated on two other outputs. RESULTS: The results show, for most algorithms, an enhanced detection of data points belonging to intermediate classes (up to 14% absolute increase in accuracy), as well as an overall improvement in the models' accuracies (up to 5.8% absolute increase). The validation experiments yielded similar results with improved accuracies for most algorithms when compared to the single classifier architecture. CONCLUSION: This novel architecture is proving to be a very promising tool for improving accuracy of the models when classifying patients in intermediate classes, regardless of the algorithm used. Accuracy-improvement for likert-type scale measures offers an opportunity for rapidly identifying "risk-profiles" during emergencies and beyond. This applies equally to patients and healthcare providers, with potential for improving quality of care and strengthening patient-centered healthcare systems that prioritize healthcare providers' wellbeing.

Manually teleoperating a flying robot can be a demanding task, especially for users with limited levels of experience. This is primarily due to the non-linear properties of such robots in addition to the difficulty of controlling various degrees of freedom at the same time. 3D Autocomplete helps mitigate such limitations by assisting the users in teleoperation. It aids in teleoperating 3D motions, such as helical motions, which are more challenging to the users. The proposed framework uses Artificial Intelligence (AI) to predict just-in-time the user’s intended motion and then, if the user accepts, completes it autonomously in 3D. The AI component of 3D Autocomplete was presented in our previous work, where we introduced a deep learning model and an algorithm to predict as early as possible the user’s desired motion. Moving forward in this work, we focus on synthesizing and completing the user-intended motion autonomously. Also, we introduce a Mixed Reality (MR) user interface for better human-robot interaction. Finally, we evaluate our system subjectively and objectively through human-subject experiments. Autocomplete outperformed traditional method on all criteria with at least 30% improvement in all objective measures.

Simultaneous Localization and Mapping (SLAM) has emerged as a prime autonomous mobile agent localization algorithm. Despite the global research effort to improve SLAM, its mapping component remains limited and serves little more than to satisfy the coupled localization problem. We present a collaborative 3D SLAM approach leveraging the power of augmented reality (AR). The system introduces a trio of diverse agents, each with its unique capability to become an active member in the mapping process: mobile robots, human operators, and AR head-mounted display (AR-HMD). A 3D complementary mapping pipeline is developed to utilize the built-in SLAM capabilities of the AR-HMD as shareable data. Our system aligns and merges the AR-HMD and the robot’s local map automatically, triggered by a human-dictated initial guess. The created merged map proves advantageous in scenarios where the robot is restricted from navigating in certain areas. To correct map imperfections resulting from problematic objects such as transparent or reflective surfaces, the fused map is overlayed onto the environment, and hand gestures are used to add or delete 3D map features in real-time. Our system is implemented in both a lab and a real industrial warehouse setup. The results show a significant improvement in the map quality and mapping duration.

This paper presents an integrated approach to Visual SLAM, merging online sequential photometric calibration within a Hybrid direct-indirect visual SLAM (H-SLAM). Photometric calibration helps normalize pixel intensity values under different lighting conditions, and thereby improves the direct component of our H-SLAM. A tangential benefit also results to the indirect component of H-SLAM given that the detected features are more stable across variable lighting conditions. Our proposed photometrically calibrated H-SLAM is tested on several datasets, including the TUM monoVO as well as on a dataset we created. Calibrated H-SLAM outperforms other state of the art direct, indirect, and hybrid Visual SLAM systems in all the experiments. Furthermore, in online SLAM tested at our site, it also significantly outperformed the other SLAM Systems.

Tele-operating aerial vehicles without any automated assistance is challenging due to various limitations, especially for inexperienced users. Autocomplete addresses this problem by automatically identifying and completing the user's intended motion. Such a framework uses machine learning to recognize and classify human inputs as one of a set of motion primitives, and then, if the human operator accepts, synthesizes the motion in order to complete the desired motion. This has been shown to improve the performance of the system and reduce operator workload. Previous Autocomplete systems focused on different 2D motions (line, arc, sine,..). However, since most UAVs tasks are in a 3D world, this paper introduces 3D Autocomplete for 3D motions. Moreover, the proposed framework presents just-in-time prediction of the 3D motions by proposing a change point detection technique, which allows the framework to autonomously identify when to conduct a prediction. Also, it deals with variable motion sizes. Real time simulation results show that the proposed framework is capable of predicting the user intentions after change point detection.

Network Address Translation (NAT) was developed to overcome the IPv4 address exhaustion problem. NAT allows multiple devices on a local network to share a single public IP address. However, NAT can result in communication concerns, security flaws, network administration issues, and difficulties locating network faults. This paper addresses the limitations of existing NAT detection techniques through adoption of an innovative machine learning-based approach. The NAT detection model achieves promising results by utilizing novel traffic features. The current techniques used in NAT detection face challenges in terms of explainability and transparency. To address this issue, our proposed method integrates explainable artificial intelligence (XAI) techniques to increase the transparency and interpretability of NAT detection models, thereby improving their efficiency and effectiveness. The results obtained from explain ability highlight the significance of incorporating new features in NAT detection. Furthermore, explainable results indicate that the presence of NAT is closely correlated with specific features.

Robots have become ubiquitous tools in various industries and households, highlighting the importance of human-robot interaction (HRI). This has increased the need for easy and accessible communication between humans and robots. Recent research has focused on the intersection of virtual assistant technology, such as Amazon’s Alexa, with robots and its effect on HRI. This paper presents the Virtual Assistant, Human, and Robots in the loop (VAHR) system, which utilizes bidirectional communication to control multiple robots through Alexa. VAHR’s performance was evaluated through a human-subjects experiment, comparing objective and subjective metrics of traditional keyboard and mouse interfaces to VAHR. The results showed that VAHR required 41% less Robot Attention Demand and ensured 91% more Fan-out time compared to the standard method. Additionally, VAHR led to a 62.5% improvement in multi-tasking, highlighting the potential for efficient human-robot interaction in physically- and mentally-demanding scenarios. However, subjective metrics revealed a need for human operators to build confidence and trust with this new method of operation.

Remote controlling robots without any automated help is difficult due to various limitations. Autocomplete mitigates this difficulty by automatically detecting and completing the intended motions on robots from the input of the user. Such an approach can improve the system performance and reduce the load on the operator. Usually, recognizing intended motions is achieved using pre-trained Deep Learning (DL) models. In this paper, we introduce personalization to the autocomplete teleoperation framework when new operators take over by customizing the autocomplete DL model using incremental learning. Also, we tackle the problem of concept drift that arises in real-life applications; the data distribution of already learned classes may change in unforeseen ways as new observations of these classes come sequentially over time. We create and update an exemplar set using new observations of the classes online so that the model can be trained to adapt to the new observations. Several scenarios have been evaluated to balance the speed of learning with the accuracy of the model, and results demonstrate the effectiveness of the proposed models and their advantage in adapting to the specific operator versus our previous framework: personalization using transfer learning with full feedback.

Network Address Translation (NAT) is an address remapping technique placed at the borders of stub domains. It is present in almost all routers and CPEs. Most NAT devices implement Port Address Translation (PAT), which allows the mapping of multiple private IP addresses to one public IP address. Based on port number information, PAT matches the incoming traffic to the corresponding "hidden" client. In an enterprise context, and with the proliferation of unauthorized wired and wireless NAT routers, NAT can be used for re-distributing an Intranet or Internet connection or for deploying hidden devices that are not visible to the enterprise IT or under its oversight, thus causing a problem known as shadow IT. Thus, it is important to detect NAT devices in an intranet to prevent this particular problem. Previous methods in identifying NAT behavior were based on features extracted from traffic traces per flow. In this paper, we propose a method to identify NAT devices using a machine learning approach from aggregated flow features. The approach uses multiple statistical features in addition to source and destination IPs and port numbers, extracted from passively collected traffic data. We also use aggregated features extracted within multiple window sizes and feed them to a machine learning classifier to study the effect of timing on NAT detection. Our approach works completely passively and achieves an accuracy of 96.9% when all features are utilized.

Teleoperation of robots can be challenging, especially for novice users with little to no experience at such tasks. The difficulty is largely due to the numerous degrees of freedom users must control and their limited perception bandwidth. To help mitigate these challenges, we propose in this paper a solution which relies on artificial intelligence to understand user intended motion and then on mixed reality to communicate the estimated trajectories to the users in an intuitive manner. User intended motion is estimated using a deep learning network trained on a dataset of motion primitives. During teleoperation, the estimated motions are augmented onto a first-person live video feed from the robot. Finally, if a suggested motion is accepted by the user, the robot is driven along that trajectory in an autonomous manner. We validate our proposed mixed reality teleoperation scheme with simulation experiments on a drone and demonstrate, through subjective and objective evaluation, its advantages over other teleoperation methods.

Research has proved that supposedly secure encrypted network traffic is actually threatened by privacy and security violations from many aspects. This is mainly due to flow features leaking evidence about user activity and data content. Currently, adversaries can use statistical traffic analysis to create classifiers for network applications and infer users’ sensitive data. In this article, we propose a system that optimally prevents traffic feature leaks. In our first algorithm, we model the packet length probability distribution of the source app to be protected and that of the target app that the source app will resemble. We define a model that mutates the packet lengths of a source app to those lengths from the target app having similar bin probability. This would confuse a classifier by identifying a mutated source app as the target app. In our second obfuscation algorithm, we present an optimized scheme resulting in a trade-off between privacy and complexity overhead. For this reason, we propose a mathematical model for network obfuscation. We formulate analytically the problem of selecting the target app and the length from the target app to mutate to. Then, we propose an algorithm to solve it dynamically. Extensive evaluation of the proposed models, on real app traffic traces, shows significant obfuscation efficiency with relatively acceptable overhead. We were able to reduce a classification accuracy from 91.1% to 0.22% using the first algorithm, with 11.86% padding overhead. The same classification accuracy was reduced to 1.76% with only 0.73% overhead using the second algorithm.

Controlling and manning robots from a remote location is difficult because of the limitations one faces in perception and available degrees of actuation. Although humans can become skilled teleoperators, the amount of training time required to acquire such skills is typically very high. In this paper, we propose a novel solution (named Autocomplete) to aid novice teleoperators in manning robots adroitly. At the input side, Autocomplete relies on machine learning to detect and categorize human inputs as one from a group of motion primitives. Once a desired motion is recognized, at the actuation side an automated command replaces the human input in performing the desired action. So far, Autocomplete can recognize and synthesize lines, arcs, full circles, 3-D helices, and sine trajectories. Autocomplete was tested in simulation on the teleoperation of an unmanned aerial vehicle, and results demonstrate the advantages of the proposed solution versus manual steering.

Whether for localization, path planning, or scene manipulation, complete and accurate scene reconstruction is an essential component of robotic operation. Due to their low cost and versatility, vision-based scene reconstruction methods have been the subject of research for decades. However, a major disadvantage of vision-based methods is that they require the scene to be populated with distinctive features that can be unambiguously matched across different images. In the absence of these features, such as in planar homogeneously painted surfaces, the scene reconstruction fails. This paper proposes a novel idea, where the user can virtually texturize planar surfaces at run-time to be used for the scene reconstruction. To do so, the corners of planes are tracked across the images and used to warp virtual texture patches to the correct perspective. Two methods are then proposed, one that actively tracks the corners as long as they are in view, and one that requires the camera poses to augment planes once their corners are no longer visible. The conducted experiments demonstrate the effectiveness of our approach as it increases the number of points in scene reconstructions. The end result is a denser scene reconstruction where textureless planes, typically not recovered in traditional methods, are reconstructed.

Summary Network convergence is an important aspect in networks because it can limit the damage resulting from network failures and changes. Consequently, a lot of research considered comparing the performance of different routing protocols, whether in IP or SDN, to assess their convergence speed and reaction to failures. We previously modeled OSPF vs SDN networks in general network deployments and studied their comparative convergence delays for different network conditions. However, the type of network and the architecture choices also affect performance. Consequently in this paper, we model network convergence for two network architectures, datacenters and WANs, to discern the difference in SDN and IP convergence processes and speeds when the network type and characteristics change.

In this work, we are proposing an intuitive Augmented SLAM method (A-SLAM) that allows the user to interact, in real-time, with a robot running SLAM to correct for pose and map errors. We built an AR application that works on HoloLens and allows the operator to view the robot's map superposed on the physical environment and edit it. Through map editing, the operator can account for errors affecting real environment's representation by adding navigation-forbidden areas to the map in addition to the ability to correct errors affecting the localization. The proposed system allows the operator to edit the robot's pose (based on SLAM request) and can be extended to sending navigation goals to the robot, viewing the planned path to evaluate it before execution, and teleoperating the robot. The proposed solution could be applied on any 2D-based SLAM algorithm and can easily be extended to 3D SLAM techniques. We validated our system through experimentation on pose correction and map editing. Experiments demonstrated that through A-SLAM, SLAM runtime is cut to half, post-processing of maps is totally eliminated, and high quality occupancy grid maps could be achieved with minimal added computational and hardware costs.

In this paper, we are proposing a collaborative SLAM system between a team of three heterogeneous agents: a robot, a human operator, and an augmented reality head mounted display (ARHMD). The system allows for online editing of a map produced by a robot running SLAM. Through hand gestures, the user can edit, in real time, the robot map that is augmented on top of the physical environment. Moreover, the proposed system leverages the built-in SLAM capabilities of the AR-HMD to correct the robot's map and map areas that are not yet discovered by the robot. Our method aims to combine the unique and complementary capabilities of each of the three different agents to produce the maximum possible mapping accuracy in the minimum amount of time. The proposed system is implemented on ROS and Unity. Experiments performed demonstrate the considerably superior SLAM outputs in terms of reducing mapping time, eliminating maps post-processing, and increasing mapping accuracy.

Mobile ads are plagued with fraudulent clicks which is a major challenge for the advertising community. Although popular ad networks use many techniques to detect click fraud, they do not protect the client from possible collusion between publishers and ad networks. In addition, ad networks are not able to monitor the user’s activity for click fraud detection once they are redirected to the advertising site after clicking the ad. We propose a new crowdsource-based system called Click Fraud Crowdsourcing (CFC) that collaborates with both advertisers and ad networks in order to protect both parties from any possible click fraudulent acts. The system benefits from both a global view, where it gathers multiple ad requests corresponding to different ad network-publisher-advertiser combinations, and a local view, where it is able to track the users’ engagement in each advertising website. The results demonstrated that our approach offers a lower false positive rate (0.1) when detecting click fraud as opposed to proposed solutions in the literature, while maintaining a high true positive rate (0.9). Furthermore, we propose a new mobile ad charging model that benefits from our system to charge advertisers based on the duration spent in the advertiser’s website.

Hybrid Networks, defined as networks that include both SDN and IP nodes, were considered as a natural consequence of the incremental deployment of SDN in the current all-IP world. However, under some circumstances, the centralized control plane of SDN offers advantages over the traditional distributed one. This drove our work as we design a hybrid network in which each node adaptively switches its control state between centralized and distributed given the prevailing network conditions. The proposed optimization problem delivered the expected network behavior; the network was fully centralized when conditions were favorable for full centralization, and it was fully distributed when conditions favored full distributivity. For random conditions, we were able to capture the behavior of network nodes with time and with different decision thresholds.

In this paper we develop a real-time human augmented mapping system. This approach replaces the traditional offline post processing of maps by a user-friendly system allowing for online editing capabilities. A wide number of applications that acquire accurate mapping of the environment could benefit from such a solution. The proposed framework consists of two main parts: 2D map building using LIDAR, encoders, and IMU; and a user interface for human map augmentation. The first part is built over Gmapping ROS package, while the second is developed in Unity software. Realworld experiments validated the ability of our system to correct for sensor noise and various mapping errors, thus increasing the accuracy of the obtained maps without additional computational costs.

Multi-Path TCP (MPTCP) boosts network performance of applications by aggregating bandwidth over multiple paths using sub-flows of the same TCP connection. However, MPTCP suffers from three limitations: (1) it is an end-to-end protocol with no control over the network routes, and sub-flows might end up traversing the same links, (2) it has no dynamic control over choosing the optimal number of sub-flows to achieve maximum throughput, (3) its performance may degrade due to the large number of out-of-order caused by the heterogeneous paths traversed. Software Defined Networking (SDN), being centralized by nature, provides a global view of the network. When integrated with MPTCP, SDN improves resource utilization as we show in this paper. We propose an SDN-enhanced MPTCP that achieves higher data rates while transferring big-data in large-scale L2 networks such as those found in datacenters. Test results show a 20% to 30% increase in the throughput over regular MPTCP.

Software-defined networks (SDN) are vulnerable to most of the attacks that traditional networks are vulnerable to. In addition, SDN has introduced new vulnerabilities through its unique architecture such as those related to the southbound and northbound controller interfaces. In this paper, we introduce a lightweight flow-based Intrusion Detection System (IDS) that periodically gathers statistical information about flows from SDN OpenFlow switches, and analyzes traffic information by extracting and aggregating a set of features. The proposed IDS system proved to be accurate with a high detection rate at 0.98 measured by the F1 score of the classification model and a relatively low false alarm rate.

Software Defined Networking (SDN) is the new promise towards an easily configured and centrally controlled network. Based on this centralized control, SDN technology has proved its positive impact in the world of network communications from different aspects. Consistency in SDN, as in any rule-based network, is an essential feature that every communication system should possess. In this paper, we propose an SDN verification layer based on formal techniques to establish flow consistency between SDN switches before the flow insertion process takes place. We show how such an approach can be used to prevent loopbacks, deadlocks, security domain breaches, and to verify the time delay for a controller to update a switch versus the switch to forward a packet. This last point ensures that the update process is synchronized and no packet would be checked against old rules during this update process. The solution lies in introducing a verification plane enabling our verification module to interact with a third party verification tool (UPPAAL) translating the controller's view of the network to a state machine and verifying each flow before being installed. The verification tool checks each flow against a predefined set of rules by applying the new flow to the scheme and testing if a packet can pass from point A to B without violating these rules. Our evaluation shows the capability of the proposed system to enforce different levels of consistency verification in case of flow update and topology change in a SDN network.

Security and privacy are among the most pressing concerns that have evolved with the Internet. As networks expanded and became more open, security practices shifted to ensure protection of the ever growing Internet, its users, and data. Today, the Internet of Things (IoT) is emerging as a new type of network that connects everything to everyone, everywhere. Consequently, the margin of tolerance for security and privacy becomes narrower because a breach may lead to large-scale irreversible damage. One feature that helps alleviate the security concerns is authentication. While different authentication schemes are used in vertical network silos, a common identity and authentication scheme is needed to address the heterogeneity in IoT and to integrate the different protocols present in IoT. We propose in this paper an identity-based authentication scheme for heterogeneous IoT. The correctness of the proposed scheme is tested with the AVISPA tool and results showed that our scheme is immune to masquerade, man-in-the-middle, and replay attacks.

Internet of Things (IoT) is considered to be the Internet of the future. Thus, a lot of effort is being invested in finding the best design for a global IoT architecture. Recently, Software-Defined Networking (SDN) surfaced as a new networking paradigm that aims to centralize the network control and to separate the control and the data planes. Thus, one can benefit from SDN to abstract the major management complexities residing in this ubiquitous network of networks. Therefore, dealing with the huge amount of generated data in such network will be a major challenge; so, adopting advanced data technologies (cloud and fog computing) will be essential for the new architecture. In this paper, we review work done concerning the application of SDN to the IoT. Also, we propose and analyze a new SDN-based IoT architecture characterized by the centralization of the network control and the decentralization of the data management.

Mobile advertising using in-app ads has increased in popularity along with the substantial number of current free mobile applications and games in the app stores. This relatively new type of advertising has raised several concerns during the past few years, such as the battery consumption that it entails and the network traffic overhead that it consumes to download the ads. While several efforts revealed key observations regarding ads-related energy and bandwidth consumption, they did not compare these two types of consumptions among different ad networks. Unlike some previous work that just mentioned the ad networks associated with the tested apps, our work evaluates bandwidth and energy consumption and compares them among several popular ad networks that support ads for Android applications. The experimental procedure followed in this study demonstrated that resource consumption varies significantly among networks based on our statistical tests. In addition, this study highlights a common behavior when fetching ads, where ads are fetched at the beginning of app runtime and displayed throughout the application session.

In this paper, we propose a 3G to Wi-Fi offloading Android-based application. Due to growing demand for a high-speed mobile data connection around the clock, 3G networks begin to face high congestion levels rendering the mobile service providers unable to meet customer expectations. Despite the existence of various solutions, offloading to Wi-Fi proves to be an optimal one as it takes advantage of the resources that Wi-Fi offers in terms of availability and bandwidth. The proposed application measures the download speed of an online page on both Wi-Fi and 3G networks simultaneously. After comparing the results, the device gets switched to the best network. This enables operators to manage their networks more adequately and to improve users experience.

In this paper, we present DAGGER, a distributed architecture for collaborating mobile hosts and telecom operators for the granular mitigation of mobile-based attacks. Due to the growing usage of network resources by mobile handsets and the increasing spread of malicious applications among those handsets, it has become vital for mobile operators to join the fight against mobile-based attacks in order to protect their resources and infrastructure. Several security solutions are available in the market for telecom operators to detect anomalies. DAGGER extends those solutions and enables the operators to not only detect the subscriber(s) that generated anomalies, but also to granularly identify the malicious applications behind those abnormalities, allowing the operators to terminate the malwares themselves rather than shutdown the network connection for the mobile subscriber(s). We present an Android host-based component and define the distributed host-network communication procedure in order to identify malicious applications causing network anomalies and thus to terminate such applications.

Finding good entropy sources, designing deterministic (pseudo) random number generators, or simply finding suitable non-deterministic random number generators are major challenges. The goal of this paper is to evaluate the use of three motion sensors present in smartphones as potential nondeterministic, true random bit generators (TRNG). This paper focuses in particular on sensors present in Samsung Galaxy S3 and S4 devices. Data from the sensors was collected and submitted to the NIST STS v-2.1.1 test suite and the resulting bits were found fit enough to be used as the output of a TRNG. In addition, 4 SHA versions were used to whiten the data (as per NIST recommendation). Their conditioning performance was compared to each other, and found to be very close.

One of the main concerns for application developers is user satisfaction. Before installing any application from an app market, users first look at the app rating and the number of times it was downloaded. However, ratings are not made by experts, are subjective, and require user involvement; therefore, a large number of reviews are needed before the ratings become statistically reliable. One way to obtain user input transparently is to collect data from devices through crowdsourcing. In this work, we present CrowdApp, a crowdsourcing-based application that continuously runs in the background and collects data from the device without any active user participation (transparent crowdsourcing). Then it computes a score for every app installed on the device. The application was tested on Android. Our results show that there is a high correlation (> 0.8) between CrowdApp scores and Google Play scores. More importantly, CrowdApp scores also agreed with subjective ratings by the users themselves at the end of the experiment period.

In this paper, we propose a new method to detect malicious activities on mobile devices by examining an application's runtime behavior. To this end, we use the Xposed framework to build a monitoring module that generates behavior profiles for applications. The module integrates with our intrusion detection system which then analyzes and reports on the profiles. We use this tool to detect malicious behavior patterns using both a custom-written malware and a real one. We also detect behavior patterns for some popular applications from the Google Play Store to expose their functionality. The results show that standard techniques that are used to evade static analysis are not effective against our monitoring approach. This approach can also be generalized to detect unknown malware or expose exact application behavior to the user.

Two Radio Resource Control states have been proposed in LTE and implemented to ensure low UE power consumption and high network resource availability. Transiting between these two states optimizes network performance if tuned properly. Currently, a UE switches from the LTE_ACTIVE state to the LTE_IDLE state after a pre-configured static inactivity duration. This paper seeks to demonstrate that no static timeout is optimal for all users at all times. In addition, a user-level dynamic decision algorithm is proposed to have fine-grain user level optimization. Since achieving better efficiency is related to context awareness, we present a solution that allows the UE to auto-learn its traffic behavior. The dynamic algorithm was applied to five different user load scenarios of combined application and legacy traffic, and the results showed that we are able to attain power savings of up to 30% when compared to the fixed timeout case.

With the global widespread usage of the Internet, more and more cyber-attacks are being performed. Many of these attacks utilize IP address spoofing. This paper describes IP spoofing attacks and the proposed methods currently available to detect or prevent them. In addition, it presents a statistical analysis of the Hop Count parameter used in our proposed IP spoofing detection algorithm. We propose an algorithm, inspired by the Hop Count Filtering (HCF) technique, that changes the learning phase of HCF to include all the possible available Hop Count values. Compared to the original HCF method and its variants, our proposed method increases the true positive rate by at least 9% and consequently increases the overall accuracy of an intrusion detection system by at least 9%. Our proposed method performs in general better than HCF method and its variants.

If we are to one day rely on robots as assistive devices they should be capable of mitigating the impact of random disturbances and avoid falling. Humans are surprisingly apt at remaining on their feet when pushed; they rely on reflexes such as bending the ankles and/or the hips, or by taking a step if the magnitude of the disturbance is relatively large. This paper presents a fall avoidance scheme that is capable of applying both ankle and hip strategies on a humanoid robot. While both strategies serve the same purpose, the hip strategy can absorb larger disturbances but has a higher energy overhead and should be avoided when it is not necessary. Our system is capable of detecting at the onset of a disturbance if an ankle or hip strategy is more appropriate. The decision is taken based on a 'decision surface' that is delimited by threshold values of the robot's state variables. The control is based on the intuitive Virtual Model Control (VMC) approach. The system is tested on a simulated robot developed under Gazebo. Results show successful fall avoidance with an ability to choose the optimum fall avoidance strategy.

The need to automate the detection of agitation and the detection of agitation transition for dementia patients is a significant facilitator for caregivers. This research aims at detecting the transitional phase toward agitation, as well as agitation detection of subjects, using soft computing techniques that do not require supervision beyond the training phase. Three vital signs are monitored: Heart Rate (HR), Galvanic Skin Response (GSR), and Skin Temperature (ST). These measures are fed into two proposed SVM architectures which are based on the definition of a new confidence measure: "Confidence-Based SVM” and "Confidence-Based Multilevel SVM.” Results show very high detection accuracy of agitation and agitation transition, a quick adaptation to the subject, and a strong correlation between the physiological signals monitored and the emotional states of the subjects. Another challenge that is successfully addressed in this paper is the ability to train the classifier on a limited group of subjects, and then test it on subjects not belonging to the training group. The result is a learning algorithm that is "Subject-Independent.”

One of the major limitations in the development of ultrasensitive electrochemical biosensors based on one-dimensional nanostructure is the difficulty involved with reliably fabricating nanoelectrode arrays (NEAs). In previous work, a simple, robust and scalable wafer-scale fabrication method to produce multiplexed biosensors is introduced. Each sensor chip consists of nine individually addressable arrays that uses electron beam patterned vertically aligned carbon nanofibers (VACNFs) as the sensing element. To ensure nanoelectrode behavior with higher sensitivity, VACNFs were precisely grown on 100 nm Ni dots with 1 ¿m spacing on each micro pad. However, in order to examine the quality and measure the height and diameter of the VACNFs, some surface detection and measurement tool at the nanoscale level is needed. In this paper, we introduce an approach to measure these nano-scale features through atomic force microscope (AFM). With this method, both the 2D and 3D images of sample surface are generated and the sizes of carbon nanofibers and cavities are obtained. Furthermore, statistical analysis is carried out to enable improvement of VACNFs growth and fabrication.

Extending the life of a sensor network while maintaining an acceptable level of accuracy continues to be a critical challenge in long-lived applications requiring months and years of continuous operation. In this paper, we present an approach to address this challenge, namely selective querying based on the transinformation value of nodes relative to the query being executed. The approach is distributed whereby decisions are made by individual nodes and cluster heads based on information locally available. Simulation results establish the feasibility of this approach and show significant gains in the lifetime of the network.

Rapid advances in the field of sensing and sensor networks are opening the door to many new possibilities. One of the main challenges is the localization of the sensor nodes. In this paper we discuss the issue of localization in the context of sensor network assisted telerobotics. The sensor network is used to feedback information to the robot or remote operator to be used to efficiently and safely navigate. We show that coarse localization results in comparable performance to accurate and fine localization. This finding relaxes the requirement from localization algorithms and would open the door to a new class of reduced complexity and reduced overhead localization algorithms. Experimental results are provided to highlight the concepts developed and compare performance

In this paper we investigate the accuracy of human perception of haptic force direction applied to the hand. Haptic interfaces are commonly used in many applications and understanding the limitations of human perception would facilitate the design of these interfaces and the associated applications. The literature contains work related to force perception; however, none of which address the issue of the accuracy of haptic force direction perception. We discuss the design and implementation of the experiment used to evaluate the accuracy. Also presented are results related to training effects, fatigue and accuracy across angular regions

Presently, there are a myriad of virtual reality applications being devised for the full spectrum of disciplines. Of particular interest are military and healthcare applications. The importance of simulators for training becomes clear for critical tasks such as flight or surgery. Moreover, there is merit to be found in simulators that educate nurses for critical procedures, especially for procedures that have the potential to cause serious pain and injury. The application presented in this paper is nasotracheal suctioning. This application trains and evaluates in an intuitive way, using force feedback, an elaborate visual interface, and a variety of auditory cues (sounds and verbal instructions). It allows the practitioner to perform this procedure repeatedly in a safe environment before conducting it on a live patient

Sensor networks are attracting attention in several fields. However, the feasibility of such networks faces several challenges, two of which are data fusion and error reduction. This paper presents data fusion and high level error correction algorithms for sensor networks. These algorithms are scalable and general, and thus can be applied to networks of any size using any type of sensors. The data fusion procedure developed results in significant reduction of data sent without reducing the amount of information provided. This allows for real-time remote monitoring of information across low bandwidth connections such as the Internet. The high level error reduction is accomplished using a probability matrix and results in a significant amount of error elimination. A sensor network capable of tracking object motion is constructed to evaluate the performance of the two algorithms. The experimental results obtained confirmed the theory presented.

Significant research has been conducted in the field of Internet-based teleoperation. However, there is a lack of objective performance measures beyond completion time, which is dependent on several external factors to the system. This paper develops the concept of event-synchronization for supermedia enhanced Internet based teleoperation systems. Supermedia is the term used to refer to the different feedback streams; for example, video, haptic, temperature and others. This performance measure or system property is not affected by external factors; such as, the human operator and the communication characteristics. In addition, the design, which is based on Petri net theory, of systems satisfying this property is detailed. The experimental results obtained using a mobile manipulator bilateral teleoperation system, are given.

The coordination of multi-robots is required in many scenarios for efficiency and task completion. Combined with teleoperation capabilities, coordinating robots provide a powerful tool. Add to this the Internet and now it is possible for multi-experts at multi-remote sites to control multi-robots in a coordinated fashion. For this to be feasible there are several hurdles to be crossed including Internet type delays, uncertainties in the environment and uncertainties in the object manipulated. In addition, there is a need to measure and control the quality of tele-coordination. This paper proposes a measure for the quality of tele-coordination, referred to as the coordination index, and details the design procedure that ensures a system performs at a required index. The theory developed was tested by bilaterally tele-coordinating two mobile manipulators via the Internet. The experimental results confirmed the theory presented.

With the rapid development of information technology, Internet has evolved from a simple data-sharing media to an amazing information world where people can enjoy different kinds of services. Recently, the use of the Internet has been expanded to the field of automation, i.e. using the Internet as a tool to control equipment located at remote sites. This paper presents a cooperative robot system consisting of a robot hand and a mobile robot carrying a stereo vision, which can be tele-operated by operators at different sites via the Internet. To overcome the instability and reliability problem caused by the random time delay of the Internet communication, we adopt an event as the reference for controller design of the system. A vision-based method is adopted to maintain interactions among the operations. Results obtained in teleoperation experiments among Hong Kong, the mainland China, and USA will be demonstrated to confirm the usefulness and effectiveness of the developed method and system.

In real-time Internet based teleoperation, different robotic tasks have different dexterity requirements during task progress and thus different network resources are required for safe and reliable task accomplishment. In order to control remote manipulators efficiently and smoothly via the Internet, dynamic bandwidth allocation is crucial to successful accomplishment of robotic tasks controlled by remote operator. In this paper, a novel bandwidth allocation mechanism is developed based on the online measured task dexterity index of current dexterous tasks so that operators can control remote manipulators efficiently and smoothly even under poor network quality. Experiments have been conducted to demonstrate the effectiveness of the presented resource (bandwidth) allocation algorithm in Internet based teleoperation system.

This paper introduces new planning and control methods for supermedia-enhanced real-time telerobotic operations via the Internet. Supermedia is the collection of video, audio, haptic information, temperature, and other sensory feedback. However, when the communication medium used, such as the Internet, introduces random communication time delay, several challenges and difficulties arise. Most importantly, random communication delay causes instability, loss of transparency, and desynchronization in real-time closed-loop telerobotic systems. Due to the complexity and diversity of such systems, the first challenge is to develop a general and efficient modeling and analysis tool. This paper proposes the use of Petri net modeling to capture the concurrency and complexity of Internet-based teleoperation. Combined with the event-based planning and control method, it also provides an efficient analysis and design tool to study the stability, transparency, and synchronization of such systems. In addition, the concepts of event transparency and event synchronization are introduced and analyzed. This modeling and control method has been applied to the design of several supermedia-enhanced Internet-based telerobotic systems, including the bilateral control of mobile robots and mobile manipulators. These systems have been experimentally implemented in three sites test bed consisting of robotic laboratories in the USA, Hong Kong, and Japan. The experimental results have verified the theoretical development and further demonstrated the stability, event transparency, and event synchronization of the systems.

This paper concentrates on transparency and synchronization of supermedia in Internet based teleoperation. Supermedia is used to describe the collection of all the feedback streams in teleoperations, such as haptic, video, audio, temperature and others. Transparency and synchronization are introduced and analyzed from the event-based control perspective. The concepts of event-transparency and event-synchronization for event-based control telerobotic systems are developed and their implications are studied. To illustrate those concepts and their benefits, the teleoperation of a mobile manipulator via the Internet, where haptic, video and temperature information is fed back to the operator, is discussed. Experimental results will verify the event-transparency and event-synchronization of this event-based telerobotic system.

Despite the enormous research efforts in creating new applications with MEMS, the research efforts at the backend such as packaging and assembly are relatively limited. We present our ongoing development of a polyvinylidene fluoride (PVDF) multi-direction micro-force sensing system that can be potentially used for force-reflective manipulation of micro-mechanical devices or micro-organisms over remote distances. Thus far, we have successfully demonstrated 1D and 2D sensing systems that are able to sense force information when a micro-manipulation probe-tip is used to lift a micro mass supported by 2 /spl mu/m/spl times/30 /spl mu/m/spl times/200 /spl mu/m polysilicon beams. Hence, we have shown that force detection in the 50 /spl mu/N range is possible with PVDF sensors integrated with commercial micro-manipulation probe-tips.

This paper presents theoretical and experimental results on supermedia enhanced human/machine cooperative control of robot formations. Supermedia is the collection of all feedback streams rendered for the operator; such as video, haptic, temperature and others. The core idea is to utilize machine intelligence for the control of a robot formation. However, once this intelligence is insufficient to cope with unexpected events, human intervention is an option. To accomplish this, without the need for replanning, perceptive planning and control theory is utilized. This would allow the cooperation of human and machine for the control of the robot formation. To increase the flexibility and efficiency of such systems, commands of different levels of complexity can be issued. This gives rise to a hierarchical command structure, which can be described by a hierarchical perceptive frame that is modeled using automata and languages.

Robotic operations carried out via the Internet face several challenges and difficulties. These range from human-computer interfacing and human-robot interaction to overcoming random time delay and task synchronization. These limitations are intensified when multi-operators at multisites are collaboratively teleoperating multirobots to achieve a certain task. In this paper, a new modeling and control method for Internet-based cooperative teleoperation is developed. Combining Petri net model and event-based planning and control theory, the new method provides an efficient way to model the concurrence and complexity of the Internet-based cooperative teleoperation. It also provides an efficient analysis tool to study the stability, transparency and synchronization of the system. Furthermore, the new modeling and control method enables us to design an Internet-based cooperative telerobotic system that is reliable, safe and intelligent. This new method has been experimentally implemented in a three site test bed consisting of robotic laboratories in the USA, Hong Kong and Japan. The experimental results have verified the theoretical development and further demonstrated the advantages of the new modeling and control method.

The development of a medical surgical tool, packaged with micro sensors for transmission of supermedia information over the Internet is described in this paper. We define supermedia as a set of communication media, which encompasses acoustic, force, visual, audio, temperature, tactile, and chemical (e.g., taste and smell) information, and which can be physically experienced by a communicator. In this project, we specifically develop supermedia capability for a bone-reaming system that is used for intramedullary fixation procedure of fractured bone treatments. Thus far, transmission of temperature, force, and pressure information from MEMS sensors over the Internet has been demonstrated. Force-reflective control over the Internet using force information from a micro tip has also been shown. We have also packaged a MEMS pressure sensor inside a bone reaming guide-rod and proved that pressure variations inside a long cavity that simulated the environment inside a bone can be monitored, even with the guide-rod rotating up to 600 rpm. This paper describes our experimental methods and gives the experimental results for these accomplishments.

The use of the Internet is no longer limited to the transmission of data. In the past few years many successful attempts have been made to use the Internet as a command transmission media; through which control can be sent to remote systems and feedback can be obtained. But with this media come several limitations: delay, lost packets and disconnection. All of these limitations may cause instability in the system especially if the system loop is closed. All the previous work addressing these problems assumed several conditions; for example, time delay is constant or has an upper bound, control is not in real-time. A new real-time control approach is presented that deals with these limitations without any assumptions made regarding delay. The approach is based on event-based control, which was implemented on a mobile robot over the Internet. The commands sent to the robot are velocity and the feedback is force based on the environment. It will be shown that this approach results in a stable system. In addition, a new force feedback generation method is used.

The e-world, also known as the Internet, has added a new dimension to many of the traditional concepts in industrial applications and everyday life. The use of robots has dramatically expanded the potential of e-services. Individuals with particular expertise can perform highly accurate and fairly complicated tasks remotely via the Internet. This increase in the human reachability is faced by several obstacles. Reliable and efficient robot facilitated services via the Internet face several challenges. These range from human-computer interfacing and overcoming random time delay to task synchronization and human-robot interaction. These limitations intensify when many operators in many sites are involved. This paper provides new theoretical and experimental results on these challenges. Specifically, multisite cooperative control of an Internet based mobile manipulator is presented. The two main characteristics of this system are Internet based real-time closed loop control and coordinated operation. In addition, it is shown that despite random time delay the stability and synchronization of the system were achieved using event-based control.