Simultaneous Coalition Structure Generation and Assignment (SCSGA) is an important research problem in multi-agent systems. Given n agents and m tasks, the aim of SCSGA is to form m disjoint coalitions of n agents such that between the coalitions and tasks there is a one-to-one mapping, which ensures each coalition is capable of accomplishing the assigned task. SCSGA with Multi-dimensional Features (SCSGA-MF) extends the problem by introducing a d-dimensional vector for each agent and task. We propose a heuristic algorithm called Multiple Distance Metric (MDM) approach to solve SCSGA-MF. Experimental results confirm that MDM produces near optimal solutions, while being feasible for large-scale inputs within a reasonable time frame.

Facial expressions have been considered a metric reflecting a person’s engagement with a task. While the evolution of expression detection methods is consequential, the foundation remains mostly on image processing techniques that suffer from occlusion, ambient light, and privacy concerns. In this paper, we propose ExpresSense, a lightweight application for standalone smartphones that relies on near-ultrasound acoustic signals for detecting users’ facial expressions. ExpresSense has been tested on different users in lab-scaled and large-scale studies for both posed as well as natural expressions. By achieving a classification accuracy of over various basic expressions, we discuss the potential of a standalone smartphone to sense expressions through acoustic sensing.

In this work, we introduce an edge intelligence layer into the traditional Safety-as-a-Service (Safe-aaS) platform for Social Internet of Vehicles (SIoV) networks, to minimize the network latency incurred in delivery of decisions. The prior announcement of safety-related information in social IoV environment, minimizes the rate of accidents to a significant extent. Safe-aaS provides customized safety-related decisions dynamically to the end-users. On the other hand, the timely delivery of accurate decisions to the end-users in a social IoV network is a challenging task. We introduce the concept of edge servers in the edge layer of Safe-aaS, such that the bandwidth required for uploading data is minimized, and the problems associated with processing, storage, and complex analysis of data are eliminated. We apply Artificial Neural Network (ANN) at the edge nodes to select the appropriate edge server and fuzzy logic at the edge server side for the generation of a decision. Here social entities are not humans rather vehicles, distributed edge servers and cloud servers all are acting as intelligent objects. Extensive simulation of our proposed architecture demonstrates that the computing density of edge servers is normally distributed. Additionally, we analyze the classification of the edge servers using training data obtained from the edge nodes and network is tested with the test dataset. We apply fuzzified decision is generated method at the edge sever. Extensive simulation results demonstrate that the delay incurred in delivery of decision is reduced by 90:58%, after introduction of edge intelligence layer.

The success of self-supervised learning (SSL) has mostly been attributed to the availability of unlabeled yet large-scale datasets. However, in a specialized domain such as medical imaging which is a lot different from natural images, the assumption of data availability is unrealistic and impractical, as the data itself is scanty and found in small databases, collected for specific prognosis tasks. To this end, we seek to investigate the applicability of self-supervised learning algorithms on small-scale medical imaging datasets. In particular, we evaluate 4 state-of-the-art SSL methods on three publicly accessible small medical imaging datasets. Our investigation reveals that in-domain low-resource SSL pre-training can yield competitive performance to transfer learning from large-scale datasets (such as ImageNet). Furthermore, we extensively analyse our empirical findings to provide valuable insights that can motivate for further research towards circumventing the need for pre-training on a large image corpus. To the best of our knowledge, this is the first attempt to holistically explore self-supervision on low-resource medical datasets. Source codes are available at: https://github.com/soumitri2001/SmallDataSSL

The 5th Generation (5G) New Radio (NR) and beyond technologies will support enhanced mobile broadband, very low latency communications, and huge numbers of mobile devices. Therefore, for very high speed users, seamless mobility needs to be maintained during the migration from one cell to another in the handover. Due to the presence of a massive number of mobile devices, the management of the high mobility of a dense network becomes crucial. Moreover, a dynamic adaptation is required for the Time-to-Trigger (TTT) and hysteresis margin, which significantly impact the handover latency and overall throughput. Therefore, in this paper, we propose an online learning-based mechanism, known asLearning-basedIntelligentMobilityManagement (LIM2), for mobility management in 5G and beyond, with an intelligent adaptation of the TTT and hysteresis values. LIM2 uses a Kalman filter to predict the future signal quality of the serving and neighbor cells, selects the target cell for the handover usingstate-action-reward-state-action (SARSA)-based reinforcement learning, and adapts the TTT and hysteresis using the$\epsilon$-greedypolicy. We implement a prototype of the LIM2 in NS-3 and extensively analyze its performance, where it is observed that the LIM2 algorithm can significantly improve the handover operation in very high speed mobility scenarios.

Contextualised word representations (e.g., ELMo and BERT) have been shown to outperform static representations (e.g., Word2vec, Fasttext, and GloVe) for many NLP tasks. In this paper, we investigate the use of contextualised embeddings for code search and classification, an area receiving less attention. We construct CodeELMo by training ELMo from scratch and fine tuning CodeBERT embeddings using masked language modeling based on natural language (NL) texts related to software development concepts and programming language (PL) texts consisting of method comment pairs from open source code bases. The dimensionality of the Finetuned Code BERT embeddings is reduced using linear transformations and augmented with a CodeELMo representation to develop CodeELBE – a lowdimensional contextualised software code representation. Results for binary classification and retrieval tasks show that CodeELBE1considerably improves retrieval performance on standard deep code search datasets compared to CodeBERT and baseline BERT models.

The profuse popularity of video conferencing has led to a simultaneous rise in the opportunity for the participants to multitask. Productive multitasking, such as taking notes, browsing for relevant information, etc., can help promote the cognitive attentiveness of participants. However, existing approaches of tagging inattentive participants solely based on their visual concentration on the meeting app fail to work in such instances. This paper proposes EmotiConf -- a novel real-time framework to monitor participants' attentiveness and a non-real-time framework for visual multitask detection without explicitly relying on their visual concentration. EmotiConf utilizes an unconventional observation where the emotional states of attentive participants, captured through their facial expressions, correlate and also correspond to the vocal expression of the speaker and the intent of the speech. Accordingly, EmotiConf develops a software wrapper to tag the inattentive participants while also characterizing visual multitasking instances performed by them. A thorough evaluation of EmotiConf confirms its usability with a high score of >80.

Smartphones are ubiquitous nowadays, be it for setting a reminder, quick messaging, or an email reply, which requires typing through a soft-keyboard. However, people with medical issues like dactylitis, sarcopenia, joint pains might feel difficulty in typing, using the conventional approach. Existing gaze or voice-based approaches do not work well without commercial trackers or in noisy environments. In this paper, we develop a novel technique called Nosype, a contact-free text entry system for such users. Nosype’s core functionality lies in nose-tip tracking and projection and allows the users to draw alphanumeric characters in the air for constructing a text. With 11 users with different clinical conditions, on a lab-scale, we observe that Nosype can help in typing with an average typing error rate of 6.9% and a typing-speed of 6.31 words/minute. A large-scale usability study with 60 participants, including 10 participants having clinical disabilities, shows an average usability score of 77.708.

Dynamic bandwidth operation in IEEE 802.11ac helps wireless access points to tune channel widths based on carrier sensing and bandwidth requirements of associated wireless stations. However, wide channels result in a reduction in the carrier sensing range, which leads to the problem of channel sensing asymmetry. As a consequence, access points face hidden channel interference that may lead to as high as 60% reduction in the throughput under certain scenarios of dense deployments of access points. Existing approaches handle this problem by detecting the hidden channels once they occur and affect the channel access performance. In a different direction, in this paper, we develop a method for avoiding hidden channels by meticulously predicting the channel width that can reduce interference as well as can improve the average communication capacity. The core of our approach is a deep probabilistic machinery based on point process modeling over the evolution of channel width selection process. The proposed approach, SmartBond, has been implemented and deployed over a testbed with 8 commercial wireless access points. The experiments show that the proposed model can significantly improve the channel access performance although it is lightweight and does not incur much overhead during the decision making process.

The rapid proliferation of Massive Open Online Courses (MOOC) has resulted in many-fold increase in sharing the global classrooms through customized online platforms, where a student can participate in the classes through her personal devices, such as personal computers, smartphones, tablets, etc. However, in the absence of direct interactions with the students during the delivery of the lectures, it becomes difficult to judge their involvements in the classroom. In academics, the degree of student's attention can indicate whether a course is efficacious in terms of clarity and information. An automated feedback can hence be generated to enhance the utility of the course. The precision of discernment in the context of human attention is a subject of surveillance. However, visual patterns indicating the magnitude of concentration can be deciphered by analyzing the visual emphasis and the way an individual visually gesticulates, while contemplating the object of interest. In this paper, we develop a methodology called Gestsatten which captures the learner's attentiveness from his visual gesture patterns. In this approach, the learner's visual gestures are tracked along with the region of focus. We consider two aspects in this approach -- first, we do not transfer learner's video outside her device, so we apply in-device computing to protect her privacy; second, considering the fact that a majority of the learners use handheld devices like smartphones to observe the MOOC videos, we develop a lightweight approach for in-device computation. A three level estimation of learner's attention is performed based on these information. We have implemented and tested Gestatten over 48 participants from different age groups, and we observe that the proposed technique can capture the attention level of a learner with high accuracy (average absolute error rate is 8.68%), which meets her ability to learn a topic as measured through a set of cognitive tests.

IEEE 802.11ac high throughput extension for wireless local area network comes with a large number of link layer configuration parameters, such as 4 different channel bonding levels, 10 different modulation and coding schemes, frame aggregation setup etc. However, the optimal combination of link configuration parameters, which maximizes the link layer performance, depends on the perceived channel quality based on the signal strength, channel noise and external interference. Considering the highly dynamic, nonlinear and time-varying nature of wireless channel quality, a dynamic adaptation of link configuration parameters gives a stable and optimized link layer performance. Nevertheless, the existing literature fails to design a robust mechanism for handling all the parameters simultaneously. In this article, we develop a control theoretic approach governed by a deep probabilistic machinery to design a robust and scalable dynamic link parameter adaptation mechanism. We apply deep neural network based Gaussian process regression to predict the link layer throughput and model predictive control based approach to find out the link configuration parameter that optimizes the overall link layer performance. The proposed mechanism is implemented and tested over a testbed setup, and we observe that it can significantly boost up the link layer performance compared to various baseline mechanisms.

With the ever increasing adoption rate of Internet-enabled devices [also known as Internet of Things (IoT) devices] in applications such as smart home, smart city, smart grid, and healthcare applications, we need to ensure the security and privacy of data and communications among these IoT devices and the underlying infrastructure. For example, an adversary can easily tamper with the information transmitted over a public channel, in the sense of modification, deletion, and fabrication of data-in-transit and data-in-storage. Time-critical IoT applications such as healthcare may demand the capability to support external parties (users) to securely access IoT data and services in real-time. This necessitates the design of a secure user authentication mechanism, which should also allow the user to achieve security and functionality features such as anonymity and un-traceability. In this paper, we propose a new lightweight anonymous user authenticated session key agreement scheme in the IoT environment. The proposed scheme uses three-factor authentication, namely a user's smart card, password, and personal biometric information. The proposed scheme does not require the storing of user specific information at the gateway node. We then demonstrate the proposed scheme's security using the broadly accepted real-or-random (ROR) model, Burrows-Abadi-Needham (BAN) logic, and automated validation of Internet security protocols and applications (AVISPAs) software simulation tool, as well as presenting an informal security analysis to demonstrate its other features. In addition, through our simulations, we demonstrate that the proposed scheme outperforms existing related user authentication schemes, in terms of its security and functionality features, and computation costs.

Mobile cloud computing (MCC) allows mobile users to have on-demand access to cloud services. A mobile cloud model helps in analyzing the information regarding the patients' records and also in extracting recommendations in healthcare applications. In MCC, a fine-grained level access control of multiserver cloud data is a prerequisite for successful execution of end-users applications. In this paper, we propose a new scheme that provides a combined approach of fine-grained access control over cloud-based multiserver data along with a provably secure mobile user authentication mechanism for the Healthcare Industry 4.0. To the best of our knowledge, the proposed scheme is the first to pursue fine-grained data access control over multiple cloud servers in a MCC environment. The proposed scheme has been validated extensively in different heterogeneous environment where its performance was found good in comparison to other existing schemes.

IEEE 802.11ax high-throughput wireless access networks support multi-user multiple-input multiple-output (MU-MIMO)-based communication, where a set of spatially apart wireless stations forms a user group and uses different spatial streams for simultaneous transmission and reception. In this architecture, dynamic user group selection is an important aspect for maintaining high-throughput fair channel access. In addition, the physical and media access control parameters, like channel bonding levels, modulation, and coding schemes need to be tuned based on the selected user group to utilize the maximum available capacity. In this paper, we design an online learning-based approach over a centralized logical control architecture, called intelligent MU-MIMO user selection with link adaptation (IMMULA), where a central controller collects the performance statistics under various configuration space and applies a reinforcement learning strategy to select the best-suited configurations dynamically at periodic intervals. The performance of IMMULA is analyzed over a testbed consisting of 6 IEEE 802.11ac access points and 20 wireless stations. The results show that IMMULA improves network performances significantly compared to other baseline mechanisms.

The recent proliferation of mobile devices, such as smartphones and wearable devices has given rise to crowdsourcing Internet of Things (IoT) applications. E-healthcare service is one of the important services for the crowdsourcing IoT applications that facilitates remote access or storage of medical server data to the authorized users (for example, doctors, patients, and nurses) via wireless communication. As wireless communication is susceptible to various kinds of threats and attacks, remote user authentication is highly essential for a hazard-free use of these services. In this paper, we aim to propose a new secure three-factor user remote user authentication protocol based on the extended chaotic maps. The three factors involved in the proposed scheme are: 1) smart card; 2) password; and 3) personal biometrics. As the proposed scheme avoids computationally expensive elliptic curve point multiplication or modular exponentiation operation, it is lightweight and efficient. The formal security verification using the widely-accepted verification tool, called the ProVerif 1.93, shows that the presented scheme is secure. In addition, we present the formal security analysis using the both widely accepted real-or-random model and Burrows-Abadi-Needham logic. With the combination of high security and appreciably low communication and computational overheads, our scheme is very much practical for battery limited devices for the healthcare applications as compared to other existing related schemes.

Multi-server environment is the most common scenario for a large number of enterprise class applications. In this environment, user registration at each server is not recommended. Using multi-server authentication architecture, user can manage authentication to various servers using single identity and password. We introduce a new authentication scheme for multi-server environments using Chebyshev chaotic map. In our scheme, we use the Chebyshev chaotic map and biometric verification along with password verification for authorization and access to various application servers. The proposed scheme is light-weight compared to other related schemes. We only use the Chebyshev chaotic map, cryptographic hash function and symmetric key encryption-decryption in the proposed scheme. Our scheme provides strong authentication, and also supports biometrics & password change phase by a legitimate user at any time locally, and dynamic server addition phase. We perform the formal security verification using the broadly-accepted Automated Validation of Internet Security Protocols and Applications (AVISPA) tool to show that the presented scheme is secure. In addition, we use the formal security analysis using the Burrows-Abadi-Needham (BAN) logic along with random oracle models and prove that our scheme is secure against different known attacks. High security and significantly low computation and communication costs make our scheme is very suitable for multi-server environments as compared to other existing related schemes.

IEEE 802.11ac supports Dynamic Bandwidth Channel Access (DBCA), where a wireless station dynamically selects the channel bandwidth based on the availability of the secondary channels. Although DBCA reduces the possibility of starvation due to non-availability of secondary channels, however, to the best of our knowledge, no existing works look into the performance benefits of IEEE 802.11ac DBCA based on theoretical modeling. In this paper, we develop a two dimensional Markov chain approach to model the performance of DBCA under various channel bonding conditions. We validate the proposed model based on a real testbed implementation. From the thorough analysis of the numerical results obtained from the model, we show that although DBCA improves channel utilization for secondary channels, it requires proper channel allocations and bonding level distributions across the wireless channels for reducing unfairness in the network. We observe that under certain circumstances, the secondary channel users can affect the throughput of primary channel users, which may introduce a short-term unfairness and a significant performance drop in the network.

Wi-Fi enabled hand-held devices have quickly occupied the consumer market as a result of the remarkable customer acceptance of IEEE 802.11 standard. In this regard, the demand of high throughput introduces high throughput standards such as IEEE 802.11ac. It supports Dynamic Bandwidth Channel Access (DBCA), where a wireless station selects channel bandwidth dynamically based on the availability of the secondary channels. But the widely-used contention based medium access mechanism provides an opportunistic access of secondary channels and affects the performance of DBCA. Consequently, unfairness in channel access is increased in DBCA, which further reduces average throughput of stations. In this paper, we develop a hybrid adaptive resource reservation mechanism, Hybrid Adaptive DBCA (HA-DBCA), for supporting fair channel access in DBCA. In HA-DBCA, a polling based online learning mechanism is designed to avoid starvation of primary channel users. Through IEEE 802.11ac testbed implementation, we show that HA-DBCA improves throughput fairness in DBCA significantly along with other performance parameters.

High fluctuation of signal strength is evident in wireless channel under mobile environment. IEEE 802.11n and IEEE 802.11ac based wireless technologies experience a challenge for selecting link configuration parameters, like number of spatial streams, channel bonding, advanced modulation and coding schemes, frame aggregation etc., dynamically under mobility. Selection of the best possible data rate by tuning link parameters is a challenging issue due to the channel asymmetry in mobile environment. In this paper, we propose an adaptive learning mechanism, HT-MobiRate, for high throughput dynamic link adaptation under mobile scenario. HT-MobiRate is based on Thompson sampling and inspired from multi-armed bandit approach. To the best of our knowledge, this invention is first in the direction of link adaptation for IEEE 802.11ac under mobile environment. We analyze the performance of HT-MobiRate with a practical high throughput wireless testbed built over 6 IEEE 802.11ac supported access points and 20 IEEE 802.11ac clients (both client boards as well as smart-phones). We recognize that it performs considerably better than other competing schemes proposed in the literature for link adaptation in static environment.

Internet access via wireless hotspots is an ever increasing demand with the inception of smart cities, where most of the users connect the Internet with their WiFi enabled devices. A set of wireless devices forms a basic service set (BSS) connected to an access point (AP). However, large number of APs are deployed in the form of extended service set (ESS) to balance the traffic load and to provide seamless data connectivity. Recent studies show that in a public WiFi hotspot, a mobile device remains in the overlapping region of multiple APs. Due to geographically sparse distributions of mobile devices, an AP may need to keep its interfaces on to serve only a few devices which otherwise can be shifted to another active AP. In this paper, we develop CrowdAP, an energy balancing AP coordination mechanism; where the minimum number of APs are computed such that the underlying mobile devices can be served without any degradation in performance, while the rest of the APs can go to the sleep state to save power. We analyze the performance of CrowdAP through simulation as well as from testbed, and show that it is able to save significant energy in the network.

High throughput wireless access networks based on IEEE 802.11ac show a significant challenge in dynamically selecting the link configuration parameters based on channel conditions due to large pool of design set, like number of spatial streams, channel bonding, guard intervals, frame aggregation and different modulation and coding schemes. In this paper, we develop a learning based approach for link adaptation motivated by the multi-armed bandit based distributed learning algorithm. The proposed link adaptation algorithm, BanditLink, explores different possible configuration options based on observing their impact over the network performance at various channel conditions. We analyze the performance of BanditLink from simulation results, and observe that it performs significantly better compared to other competing mechanisms proposed in the literature.

Abstract To ensure the secure transmission of data, cryptography is treated as the most effective solution. Cryptographic key is an important entity in this process. In general, randomly generated cryptographic key (of 256 bits) is difficult to remember. However, such a key needs to be stored in a protected place or transported through a shared communication line which, in fact, poses another threat to security. As an alternative to this, researchers advocate the generation of cryptographic key using the biometric traits of both sender and receiver during the sessions of communication, thus avoiding key storing and at the same time without compromising the strength in security. Nevertheless, the biometric-based cryptographic key generation has some difficulties: privacy of biometrics, sharing of biometric data between both communicating parties (i.e., sender and receiver), and generating revocable key from irrevocable biometric. This work addresses the above-mentioned concerns. We propose an approach to generate cryptographic key from cancelable fingerprint template of both communicating parties. Cancelable fingerprint templates of both sender and receiver are securely transmitted to each other using a key-based steganography. Both templates are combined with concatenation based feature level fusion technique and generate a combined template. Elements of combined template are shuffled using shuffle key and hash of the shuffled template generates a unique session key. In this approach, revocable key for symmetric cryptography is generated from irrevocable fingerprint and privacy of the fingerprints is protected by the cancelable transformation of fingerprint template. Our experimental results show that minimum, average, and maximum Hamming distances between genuine key and impostor’s key are 80, 128, and 168 bits, respectively, with 256-bit cryptographic key. This fingerprint-based cryptographic key can be applied in symmetric cryptography where session based unique key is required.

We consider the problem of energy efficient broadcasting in wireless ad hoc network where nodes have limited energy resources. We investigate the scope of using directional antennas for energy efficient broadcast routing in stationary networks and consider the case where wireless nodes can dynamically adjust their transmission power for each broadcast session. Minimum spanning tree (MST) has an interesting property that the longest edge in the tree is the shortest among all the spanning trees. We construct a broadcast tree using minimum spanning tree and show that use of directional antennas, with fixed orientation and fixed beamwidth, for broadcasting data over this broadcast tree strikes a balance in the energy consumption rate among nodes in the network and hence improves overall lifetime of the network.