- VeSoNet: Traffic-Aware Content Caching for Vehicular Social Networks based on Path Planning and Deep Reinforcement Learning - Vehicular social networking is an emerging application of the promising Internet of Vehicles (IoV) which aims to achieve the seamless integration of vehicular networks and social networks. However, the unique characteristics of vehicular networks such as high mobility and frequent communication interruptions make content delivery to end-users under strict delay constrains an extremely challenging task. In this paper, we propose a social-aware vehicular edge computing architecture that solves the content delivery problem by using some of the vehicles in the network as edge servers that can store and stream popular content to close-by end-users. The proposed architecture includes three components. First, we propose a social-aware graph pruning search algorithm that computes and assigns the vehicles to the shortest path with the most relevant vehicular content providers. Secondly, we use a traffic-aware content recommendation scheme to recommend relevant content according to their social context. This scheme uses graph embeddings in which the vehicles are represented by a set of low-dimension vectors (vehicle2vec) to store information about previously consumed content. Finally, we propose a Deep Reinforcement Learning (DRL) method to optimize the content provider vehicles distribution across the network. The results obtained from a realistic traffic simulation show the effectiveness and robustness of the proposed system when compared to the state-of-the-art baselines.
- Important Sentence Identification in Legal Cases Using Multi-Class Classification - The advancement of Natural Language Processing (NLP) is spreading through various domains in forms of practical applications and academic interests. Inherently, the legal domain contains a vast amount of data in text format. Therefore it requires the application of NLP to cater to the analytically demanding needs of the domain. Identifying important sentences, facts and arguments in a legal case is such a tedious task for legal professionals. In this research we explore the usage of sentence embeddings for multi-class classification to identify important sentences in a legal case, in the perspective of the main parties present in the case. In addition, a task-specific loss function is defined in order to improve the accuracy restricted by the straightforward use of categorical cross entropy loss.
- framework for comprehensible multi-modal detection of cyber threats - Detection of malicious activities in corporate environments is a very complex task and much effort has been invested into research of its automation. However, vast majority of existing methods operate only in a narrow scope which limits them to capture only fragments of the evidence of malware's presence. Consequently, such approach is not aligned with the way how the cyber threats are studied and described by domain experts. In this work, we discuss these limitations and design a detection framework which combines observed events from different sources of data. Thanks to this, it provides full insight into the attack life cycle and enables detection of threats that require this coupling of observations from different telemetries to identify the full scope of the incident. We demonstrate applicability of the framework on a case study of a real malware infection observed in a corporate network.
- Detecting Fake Points of Interest from Location Data - The pervasiveness of GPS-enabled mobile devices and the widespread use of location-based services have resulted in the generation of massive amounts of geo-tagged data. In recent times, the data analysis now has access to more sources, including reviews, news, and images, which also raises questions about the reliability of Point-of-Interest (POI) data sources. While previous research attempted to detect fake POI data through various security mechanisms, the current work attempts to capture the fake POI data in a much simpler way. The proposed work is focused on supervised learning methods and their capability to find hidden patterns in location-based data. The ground truth labels are obtained through real-world data, and the fake data is generated using an API, so we get a dataset with both the real and fake labels on the location data. The objective is to predict the truth about a POI using the Multi-Layer Perceptron (MLP) method. In the proposed work, MLP based on data classification technique is used to classify location data accurately. The proposed method is compared with traditional classification and robust and recent deep neural methods. The results show that the proposed method is better than the baseline methods.
- Catching Unusual Traffic Behavior using TF-IDF-based Port Access Statistics Analysis - Detecting the anomalous behavior of traffic is one of the important actions for network operators. In this study, we applied term frequency - inverse document frequency (TF-IDF), which is a popular method used in natural language processing, to detect unusual behavior from network access logs. We mapped the term and document concept to the port number and daily access history, respectively, and calculated the TF-IDF. With this approach, we could obtain ports frequently observed in fewer days compared to other port access activities. Such access behaviors are not always malicious activities; however, such information is a good indicator for starting a deeper analysis of traffic behavior. Using a real-life dataset, we could detect two bot-oriented accesses and one unique UDP traffic.
Monday, November 15. 2021
Interesting Papers - III
Interesting Papers - II
- Survey of Human Activity Recognition in Smart Homes Based on IoT Sensors Algorithms: Taxonomies, Challenges, and Opportunities with Deep Learning - Recent advances in Internet of Things (IoT) technologies and the reduction in the cost of sensors have encouraged the development of smart environments, such as smart homes. Smart homes can offer home assistance services to improve the quality of life, autonomy and health of their residents, especially for the elderly and dependent. To provide such services, a smart home must be able to understand the daily activities of its residents. Techniques for recognizing human activity in smart homes are advancing daily. But new challenges are emerging every day. In this paper, we present recent algorithms, works, challenges and taxonomy of the field of human activity recognition in a smart home through ambient sensors. Moreover, since activity recognition in smart homes is a young field, we raise specific problems, missing and needed contributions. But also propose directions, research opportunities and solutions to accelerate advances in this field.
- Network Migration Problem: A Logic-based Benders Decomposition Approach Driven by Column Generation and Constraint Programming - Telecommunication networks frequently face technological advancements and need to upgrade their infrastructure. Adapting legacy networks to the latest technology requires synchronized technicians responsible for migrating the equipment. The goal of the network migration problem is to find an optimal plan for this process. This is a defining step in the customer acquisition of telecommunications service suppliers, and its outcome directly impacts the network owners' purchasing behaviour. We propose the first exact method for the network migration problem, a logic-based Benders decomposition approach that benefits from a hybrid constraint programming-based column generation in its master problem and a constraint programming model in its subproblem. This integrated solution technique is applicable to any integer programming problem with similar structure, most notably the vehicle routing problem with node synchronization constraints. Comprehensive evaluation of our method over instances based on six real networks demonstrates the computational efficiency of the algorithm in obtaining quality solutions. We also show the merit of each incorporated optimization paradigm in achieving this performance.
- Analysis of the Effectiveness of Face-Coverings on the Death Ratio of COVID-19 Using Machine Learning - The recent outbreak of the COVID-19 led to the death of millions of people worldwide. To stave off the spread of the virus, the authorities in the US employed different strategies, including the mask mandate order issued by the states' governors. In the current work, we defined a parameter called the average death ratio as the monthly average of the number of daily deaths to the monthly average number of daily cases. We utilized survey data to quantify people's abidance by the mask mandate order. Additionally, we implicitly addressed the extent to which people abide by the mask mandate order that may depend on some parameters like population, income, and education level. Using different machine learning classification algorithms, we investigated how the decrease or increase in death ratio for the counties in the US West Coast correlates with the input parameters. The results showed that for most counties there, the mask mandate order decreased the death ratio reflecting the effectiveness of this preventive measure on the West Coast. Additionally, the changes in the death ratio demonstrated a noticeable correlation with the socio-economic condition of each county. Moreover, the results showed a promising classification accuracy score as high as around 90%.
- Deep Learning Technique using Low Sampling rate for residential Non Intrusive Load Monitoring - Individual device loads and energy consumption feedback is one of the important approaches for pursuing users to save energy in residences. This can help in identifying faulty devices and wasted energy by devices when left On unused. The main challenge is to identity and estimate the energy consumption of individual devices without intrusive sensors on each device. Non-intrusive load monitoring (NILM) or energy disaggregation, is a blind source separation problem which requires a system to estimate the electricity usage of individual appliances from the aggregated household energy consumption. In this paper, we propose a novel deep neural network-based approach for performing load disaggregation on low frequency power data obtained from residential households. We combine a series of one-dimensional Convolutional Neural Networks and Long Short Term Memory (1D CNN-LSTM) to extract features that can identify active appliances and retrieve their power consumption given the aggregated household power value. We used CNNs to extract features from main readings in a given time frame and then used those features to classify if a given appliance is active at that time period or not. Following that, the extracted features are used to model a generation problem using LSTM. We train the LSTM to generate the disaggregated energy consumption of a particular appliance. Our neural network is capable of generating detailed feedback of demand-side, providing vital insights to the end-user about their electricity consumption. The algorithm was designed for low power offline devices such as ESP32. Empirical calculations show that our model outperforms the state-of-the-art on the Reference Energy Disaggregation Dataset (REDD).
Interesting Papers - I
- Roadmap for Enabling a Future-Proof In-Network Computing Data Plane Ecosystem - As the vision of in-network computing becomes more mature, we see two parallel evolutionary trends. First, we see the evolution of richer, more demanding applications that require capabilities beyond programmable switching ASICs. Second, we see the evolution of diverse data plane technologies with many other future capabilities on the horizon. While some point solutions exist to tackle the intersection of these trends, we see several ecosystem-level disconnects today; e.g., the need to refactor applications for new data planes, lack of systematic guidelines to inform the development of future data plane capabilities, and lack of holistic runtime frameworks for network operators. In this paper, we use a simple-yet-instructive emerging application-data plane combination to highlight these disconnects. Drawing on these lessons, we sketch a high-level roadmap and guidelines for the community to tackle these to create a more thriving "future-proof" data plane ecosystem.
- Recommendations on using VPN over SATCOM - VPN are a secured tunnel that help service providers to exchange data over non-secured networks. There is a large variety of VPN solutions that have variable deployment impacts on the target architecture as well as performance limitations or opportunities. This technical report compares Wireguard and OpenVPN for various SATCOM deployment scenarios and topologies.
- How Developers and Managers Define and Trade Productivity for Quality - In this paper, we present the findings from a survey study to investigate how developers and managers define and trade-off developer productivity and software quality (two related lenses into software development). We found that developers and managers, as cohorts, are not well aligned in their views of what it means to be productive (developers think of productivity in terms of activity, while more managers think of productivity in terms of performance). We also found that developers are not accurate at predicting their managers' views of productivity. In terms of quality, we found that individual developers and managers have quite varied views of what quality means to them, but as cohorts they are closely aligned in their different views, with the majority in both groups defining quality in terms of robustness. Over half of the developers and managers reported that quality can be traded for higher productivity and why this trade-off can be justified, while one third consider quality as a necessary part of productivity that cannot be traded. We also present a new descriptive framework for quality, TRUCE, that we synthesize from the survey responses. We call for more discussion between developers and managers about what they each consider as important software quality attributes, and to have open debate about how software quality relates to developer productivity and what trade-offs should or should not be made.
- Algorithmic Theory of Metacognition in Minds and Machines - Humans sometimes choose actions that they themselves can identify as sub-optimal, or wrong, even in the absence of additional information. How is this possible? We present an algorithmic theory of metacognition based on a well-understood trade-off in reinforcement learning (RL) between value-based RL and policy-based RL. To the cognitive (neuro)science community, our theory answers the outstanding question of why information can be used for error detection but not for action selection. To the machine learning community, our proposed theory creates a novel interaction between the Actor and Critic in Actor-Critic agents and notes a novel connection between RL and Bayesian Optimization. We call our proposed agent the Metacognitive Actor Critic (MAC). We conclude with showing how to create metacognition in machines by implementing a deep MAC and showing that it can detect (some of) its own suboptimal actions without external information or delay.
(Page 1 of 1, totaling 3 entries)