Internet of Things (IoTs) are set to revolutionize our lives and are widely being adopted nowadays. The IoT devices have a range of applications including smart homes, smart industrial networks and healthcare. Since these devices are responsible for generating and handling large amounts of sensitive data, the security of the IoT devices always poses a challenge. It is observed that a security breach could effect individuals and eventually the world at large. Artificial intelligence (AI), on the other hand, has found many applications and is widely being explored in providing security specifically for IoT devices. Malicious insider attack is the biggest security challenge associated with the IoT devices. Although, most of the research in IoT security has pondered on the means of preventing illegal and unauthorized access to systems and information; unfortunately, the most destructive malicious insider attacks that are usually a consequence of internal exploitation within an IoT network remains unaddressed. Therefore, the focus of this research is to detect malicious insider attacks in the IoT environment using AI. This research presents a lightweight approach for detecting insider attacks and has the capability of detecting anomalies originating from incoming data sensors in resource constrained IoT environments. The results and comparison show that the proposed approach achieves better accuracy as compared to the state of the art in terms of: a) improved attack detection accuracy; b) minimizing false positives; and c) reducing the computational overhead.

Various topic modeling methods provide a means of understanding and analyzing content available on social media platforms like Twitter and Facebook in an unsupervised manner. However, despite several existing conventional techniques, they have had limited success when applied directly for filtering and quick comprehension of short-text contents due to text sparseness and noise. Thus, it always has been a challenging problem to discover reliable latent topics from online discussion texts that prevailed with low words co-occurrence and availability of large size social media benchmark datasets even for resource-rich languages. The existing literature lacks such work for Urdu text to unveil niche topics even with conventional topic models mainly due to lack of benchmark datasets, limited availability of pre-processing tools/ algorithms, and time and compute limitations on large size datasets. This work presents experiments with multiple approaches of topic modeling like Latent Semantic Analysis (LSA), Probabilistic Latent Semantic Analysis (PLSA), Latent Dirichlet Allocation (LDA), and Non-negative Matrix Factorization (NMF) on 0.8 million Urdu tweets. These tweets are collected through Twitter API by giving various hashtags as a query to avoid dominance of single topic in the dataset. In addition, we have pre-processed the text of the tweets, prepared the three variants of the collected dataset, and extracted multiple features to represent documents on different n-grams. Furthermore, all these techniques are compared and evaluated on the dataset variants using both qualitative and quantitative measures. We have also demonstrated the results of these approaches through visualization methods, graphs depicting tweets size per topic, word clouds, and hashtags analysis giving insights about algorithms performances on finalized topics. Observed results reveal that NMF outperformed aa the techniques with TF-IDF feature vectors on Urdu tweets text while LDA performed best with merging shorttext strategy into long pseudo documents.

Perinatal depression and anxiety are defined to be the mental health problems a woman faces during pregnancy, around childbirth, and after child delivery. While this often occurs in women and affects all family members including the infant, it can easily go undetected and underdiagnosed. The prevalence rates of antenatal depression and anxiety worldwide, especially in low-income countries, are extremely high. The wide majority suffers from mild to moderate depression with the risk of leading to impaired child–mother relationship and infant health, few women end up taking their own lives. Owing to high costs and non-availability of resources, it is almost impossible to diagnose every pregnant woman for depression/anxiety whereas under-detection can have a lasting impact on mother and child’s health. This work proposes a multi-layer perceptron based neural network (MLP-NN) classifier to predict the risk of depression and anxiety in pregnant women. We trained and evaluated our proposed system on a Pakistani dataset of 500 women in their antenatal period. ReliefF was used for feature selection before classifier training. Evaluation metrics such as accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver operating characteristic curve were used to evaluate the performance of the trained model. Multilayer perceptron and support vector classifier achieved an area under the receiving operating characteristic curve of 88% and 80% for antenatal depression and 85% and 77% for antenatal anxiety, respectively. The system can be used as a facilitator for screening women during their routine visits in the hospital’s gynecology and obstetrics departments.

Arm fatigue is an important factor affecting user experience in Virtual Reality (VR). In this work, we have proposed ProxyHand and StickHand, virtual hand techniques to address this issue. Using ProxyHand or StickHand, users can flexibly adjust the 3D-spatial offset between the physical hand and its virtual representation. This will allow users to keep their arms in a comfortable posture (vertically down) even when they have to manipulate objects in locations that require lifting of arms using the default interaction method. Proposed ProxyHand and StickHand have a similar Underlying concept that is to introduce a 3D-spatial offset between the physical hand and its virtual representation in VR. However, they respond differently to the user’s hand movements because of different working mechanisms. Question arises whether the 3D-spatial offset will negatively impact the hand control ability as the directness of interaction is being violated. To investigate this, we conducted user studies where users were asked to perform object translation, rotation and hybrid tasks. ProxyHand and StickHand are used in combination in some scenarios to maximize positive impact on the user experience in VR. This raises the question to find the best possible combination of these virtual hands to reduce arm fatigue. Firstly, for this purpose, we combined both virtual hands by manually allowing users to switch between ProxyHand and StickHand. Secondly, we used machine learning to automatically switch between both the virtual hands. Results showed that introduction of a 3D-spatial offset largely reduced the arm fatigue while offering equal performance to the default interaction method for all these tasks; translation, rotation and hybrid task. Users preferred using ProxyHand and StickHand to interact in the VR environment for longer periods of time.

Edge computing is a distributed architecture that features decentralized processing of data near the source/devices, where data are being generated. These devices are known as Internet of Things (IoT) devices or edge devices. As we continue to rely on IoT devices, the amount of data generated by the IoT devices have increased significantly due to which it has become infeasible to transfer all the data over to the Cloud for processing. Since these devices contain insufficient storage and processing power, it gives rise to the edge computing paradigm. In edge computing data are processed by edge devices and only the required data are sent to the Cloud to increase robustness and decrease overall network overhead. IoT edge devices are inherently suffering from various security risks and attacks causing a lack of trust between devices. To reduce this malicious behavior, a lightweight trust management model is proposed that maintains the trust of a device and manages the service level trust along with quality of service (QoS). The model calculates the overall trust of the devices by using QoS parameters to evaluate the trust of devices through assigned weights. Trust management models using QoS parameters show improved results that can be helpful in identifying malicious edge nodes in edge computing networks and can be used for industrial purposes.

With the innovation of embedded devices, the concept of smart marketplace came into existence. A smart marketplace is a platform on which participants can trade multiple resources, such as water, energy, bandwidth. Trust is an important factor in the trading platform, as the participants would prefer to trade with those peers who have a high trust rating. Most of the existing trust management models for smart marketplace only provide a single aggregated trust score for a participant. However, they lack the mechanism to gauge the level of commitment shown by a participant while trading a particular resource. This work aims to provide a fine-grained trust score for a participant with respect to each resource that it trades. Several parameters, such as resource availability, success rate, and turnaround time are used to gauge the participant’s level of commitment, specific to the resource being traded. Moreover, the effectiveness of the proposed model is validated through security analysis against ballot-stuffing and bad-mouthing attacks, along with simulationbased analysis and a comparison in terms of accuracy, false positive, false negative, computational cost and latency. The results indicate that the proposed trust model has 7% better accuracy, 30.13% lower computational cost and 31.74% less latency compared to the existing benchmark model.