Nowadays, an Internet of Things (IoT) device consists of algorithms, datasets, and models. Due to good performance of deep learning methods, many devices integrated well-trained models in them. IoT empowers users to communicate and control physical devices to achieve vital information. However, these models are vulnerable to adversarial attacks, which largely bring potential risks to the normal application of deep learning methods. For instance, very little changes even one point in the IoT time-series data could lead to unreliable or wrong decisions. Moreover, these changes could be deliberately generated by following an adversarial attack strategy. We propose a robust IoT data classification model based on an encode-decode joint training model. Furthermore, thermometer encoding is taken as a nonlinear transformation to the original training examples that are used to reconstruct original time series examples through the encode-decode model. The trained ResNet model based on reconstruction examples is more robust to the adversarial attack. Experiments show that the trained model can successfully resist to fast gradient sign method attack to some extent and improve the security of the time series data classification model.

Anomaly detection algorithms (ADA) have been widely used as services in many maintenance monitoring platforms. However, there are numerous algorithms that could be applied to these fast changing stream data. Furthermore, in IoT stream data due to its dynamic nature, the phenomena of conception drift happened. Therefore, it is a challenging task to choose a suitable anomaly detection service (ADS) in real time. For accurate online anomalous data detection, this paper developed a service selection method to select and configure ADS at run-time. Initially, a time-series feature extractor (Tsfresh) and a genetic algorithm-based feature selection method are applied to swiftly extract dominant features which act as representation for the stream data patterns. Additionally, stream data and various efficient algorithms are collected as our historical data. A fast classification model based on XGBoost is trained to record stream data features to detect appropriate ADS dynamically at run-time. These methods help to choose suitable service and their respective configuration based on the patterns of stream data. The features used to describe and reflect time-series data’s intrinsic characteristics are the main success factor in our framework. Consequently, experiments are conducted to evaluate the effectiveness of features closed by genetic algorithm. Experimentations on both artificial and real datasets demonstrate that the accuracy of our proposed method outperforms various advanced approaches and can choose appropriate service in different scenarios efficiently.

Digital divide means unequal access to the people for information and communication technology (ICT) facilities. The developed countries are comparatively less digitally divided as compared to developing countries. This study focuses on District Chitral considering its geographical conditions and high mountainous topography which plays a significant role in its isolation. Aside from the digital divide, the situation in Chitral is even more severe in terms of the absence of basic ICT infrastructure and electricity in the schools. To address this issue, especially in female secondary and higher secondary schools, we designed a project to bridge the digital divide via Wireless Local Area Network on Raspberry Pi3 for balancing the ICT facilities in the targeted area. The Wi‐Fi‐Based Content Distributors (Wi‐Fi‐BCDs) were provided to bridge the digital divide in rural area schools of Chitral. The Wi‐Fi‐BCD is a solar‐based system that is used to deliver quality educational contents directly to classroom, library, or other learning environments without electricity connection and Internet wire as these facilities are available by default in it. The close‐ended questionnaire was adopted to collect data from the students, teachers, and headmistresses of girl secondary and higher secondary schools in Chitral. The procedure of validity, reliability, regression, correlation, and exploratory factor analysis was used to analyze the obtained data. The technology acceptance model (TAM) was modified and adopted to examine the effects of Wi‐Fi‐BCD for bridging the digital divide. The relationship of the modified TAM model was examined through regression and correlation to verify the model fitness according to the data obtained. The result analysis of this study shows that the relationship of the modified TAM model with its variables is positively significant, while the analysis of path relationship between model variables and outcomes from the questionnaire shows that it motivates learners to use Wi‐Fi‐BCD.

A challenged network is one where traditional hypotheses such as reduced data transfer error rates, end‐to‐end connectivity, or short transmissions have not gained much significance. A wide range of application scenarios are associated with such networks. Delay tolerant networking (DTN) is an approach that pursues to report the problems which reduce communication in disrupted networks. DTN works on store‐carry and forward mechanism in such a way that a message may be stored by a node for a comparatively large amount of time and carry it until a proper forwarding opportunity appears. To store a message for long delays, a proper buffer management scheme is required to select a message for dropping upon buffer overflow. Every time dropping messages lead towards the wastage of valuable resources which the message has already consumed. The proposed solution is a size‐based policy which determines an inception size for the selection of message for deletion as buffer becomes overflow. The basic theme behind this scheme is that by determining the exact buffer space requirement, one can easily select a message of an appropriate size to be discarded. By doing so, it can overcome unnecessary message drop and ignores biasness just before selection of specific sized message. The proposed scheme Spontaneous Size Drop (SS‐Drop) implies a simple but intelligent mechanism to determine the inception size to drop a message upon overflow of the buffer. After simulation in ONE (Opportunistic Network Environment) simulator, the SS‐Drop outperforms the opponent drop policies in terms of high delivery ratio by giving 66.3% delivery probability value and minimizes the overhead ratio up to 41.25%. SS‐Drop also showed a prominent reduction in dropping of messages and buffer time average.