http://www.csun.edu/~andrzej/COMP529-S05/papers/Mesh%20Networks%20Survey.pdf

Wireless mesh networks: a survey

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

Visual surveillance in dynamic scenes, especially for humans and vehicles, is currently one of the most active research topics in computer vision. It has a wide spectrum of promising applications, including access control in special areas, human identification at a distance, crowd flux statistics and congestion analysis, detection of anomalous behaviors, and interactive surveillance using multiple cameras, etc. In general, the processing framework of visual surveillance in dynamic scenes includes the following stages: modeling of environments, detection of motion, classification of moving objects, tracking, understanding and description of behaviors, human identification, and fusion of data from multiple cameras. We review recent developments and general strategies of all these stages. Finally, we analyze possible research directions, e.g., occlusion handling, a combination of twoand three-dimensional tracking, a combination of motion analysis and biometrics, anomaly detection and behavior prediction, content-based retrieval of surveillance videos, behavior understanding and natural language description, fusion of information from multiple sensors, and remote surveillance.

/pdf/a-survey-on-visual-surveillance-of-object-motion-and-302zsaqo09.pdf

A survey on visual surveillance of object motion and behaviors

At the dawn of the fourth industrial revolution, we are witnessing a fast and widespread adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the shift towards a more algorithmic society. However, even with such unprecedented advancements, a key impediment to the use of AI-based systems is that they often lack transparency. Indeed, the black-box nature of these systems allows powerful predictions, but it cannot be directly explained. This issue has triggered a new debate on explainable AI (XAI). A research field holds substantial promise for improving trust and transparency of AI-based systems. It is recognized as the sine qua non for AI to continue making steady progress without disruption. This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI. Through the lens of the literature, we review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.

Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.

Security has become a primary concern in order to provide protected communication between mobile nodes in a hostile environment. Unlike the wireline networks, the unique characteristics of mobile ad hoc networks pose a number of nontrivial challenges to security design, such as open peer-to-peer network architecture, shared wireless medium, stringent resource constraints, and highly dynamic network topology. These challenges clearly make a case for building multifence security solutions that achieve both broad protection and desirable network performance. In this article we focus on the fundamental security problem of protecting the multihop network connectivity between mobile nodes in a MANET. We identify the security issues related to this problem, discuss the challenges to security design, and review the state-of-the-art security proposals that protect the MANET link- and network-layer operations of delivering packets over the multihop wireless channel. The complete security solution should span both layers, and encompass all three security components of prevention, detection, and reaction.

/pdf/security-in-mobile-ad-hoc-networks-challenges-and-solutions-5daykqei41.pdf

Security in mobile ad hoc networks: challenges and solutions

Rate adaptation is a mechanism unspecified by the 802.11 standards, yet critical to the system performance by exploiting the multi-rate capability at the physical layer.I n this paper, we conduct a systematic and experimental study on rate adaptation over 802.11 wireless networks. Our main contributions are two-fold. First, we critique five design guidelines adopted by most existing algorithms. Our study reveals that these seemingly correct guidelines can be misleading in practice, thus incur significant performance penalty in certain scenarios. The fundamental challenge is that rate adaptation must accurately estimate the channel condition despite the presence of various dynamics caused by fading, mobility and hidden terminals. Second, we design and implement a new Robust Rate Adaptation Algorithm (RRAA)that addresses the above challenge. RRAA uses short-term loss ratio to opportunistically guide its rate change decisions, and an adaptive RTS filter to prevent collision losses from triggering rate decrease. Our extensive experiments have shown that RRAA outperforms three well-known rate adaptation solutions (ARF, AARF, and SampleRate) in all tested scenarios, with throughput improvement up to 143%.

http://nms.lcs.mit.edu/6829-papers/rraa.pdf

Robust rate adaptation for 802.11 wireless networks

Recently, many e-commerce websites have encouraged their users to rate shopping items and write review texts. This review information has been very useful for understanding user preferences and item properties, as well as enhancing the capability to make personalized recommendations of these websites. In this paper, we propose to model user preferences and item properties using convolutional neural networks (CNNs) with dual local and global attention, motivated by the superiority of CNNs to extract complex features. By using aggregated review texts from a user and aggregated review text for an item, our model can learn the unique features (embedding) of each user and each item. These features are then used to predict ratings. We train these user and item networks jointly which enable the interaction between users and items in a similar way as matrix factorization. The local attention provides us insight on a user's preferences or an item's properties. The global attention helps CNNs focus on the semantic meaning of the whole review text. Thus, the combined local and global attentions enable an interpretable and better-learned representation of users and items. We validate the proposed models by testing on popular review datasets in Yelp and Amazon and compare the results with matrix factorization (MF), the hidden factor and topical (HFT) model, and the recently proposed convolutional matrix factorization (ConvMF+). Our proposed CNNs with dual attention model outperforms HFT and ConvMF+ in terms of mean square errors (MSE). In addition, we compare the user/item embeddings learned from these models for classification and recommendation. These results also confirm the superior quality of user/item embeddings learned from our model.

https://dl.acm.org/doi/pdf/10.1145/3109859.3109890

Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction

Learning node representations in graphs is important for many applications such as link prediction, node classification, and community detection. Existing graph representation learning methods primarily target static graphs while many real-world graphs evolve over time. Complex time-varying graph structures make it challenging to learn informative node representations over time. We present Dynamic Self-Attention Network (DySAT), a novel neural architecture that learns node representations to capture dynamic graph structural evolution. Specifically, DySAT computes node representations through joint self-attention along the two dimensions of structural neighborhood and temporal dynamics. Compared with state-of-the-art recurrent methods modeling graph evolution, dynamic self-attention is efficient, while achieving consistently superior performance. We conduct link prediction experiments on two graph types: communication networks and bipartite rating networks. Experimental results demonstrate significant performance gains for DySAT over several state-of-the-art graph embedding baselines, in both single and multi-step link prediction tasks. Furthermore, our ablation study validates the effectiveness of jointly modeling structural and temporal self-attention.

DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks

Smartphones have recently become increasingly popular because they provide "all-in-one" convenience by integrating traditional mobile phones with handheld computing devices. However, the flexibility of running third-party softwares also leaves the smartphones open to malicious viruses. In fact, hundreds of smartphone viruses have emerged in the past two years, which can quickly spread through various means such as SMS/MMS, Bluetooth and traditional IP-based applications. Our own implementations of two proof-of-concept viruses on Windows Mobile have confirmed the vulnerability of this popular smartphone platform.In this paper, we present SmartSiren, a collaborative virusdetection and alert system for smartphones. In order to detect viruses, SmartSiren collects the communication activity information from the smartphones, and performs joint analysis to detect both single-device and system-wide abnormal behaviors. We use a proxy-based architecture to offload the processing burden from resource-constrained smartphones and simplify the collaboration among smartphones. When a potential virus is detected, the proxy quarantines the out-break by sending targeted alerts to those immediately threatened smartphones. We have demonstrated the feasibility of SmartSiren through implementations on a Dopod 577w smartphone, and evaluated its effectiveness using simulations driven by 3-week SMS traces from a national cellular carrier. Our results show that SmartSiren can effectively prevent wide-area virus outbreaks with affordable overhead.

/pdf/smartsiren-virus-detection-and-alert-for-smartphones-2fmfr7olmf.pdf

Hao Yang

Papers

Security in mobile ad hoc networks: challenges and solutions

Robust rate adaptation for 802.11 wireless networks

Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction

DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks

SmartSiren: virus detection and alert for smartphones