This article uses Deep Learning technologies to safeguard DNA sequencing against Bio-Cyber attacks. We consider a hybrid attack scenario where the payload is encoded into a DNA sequence to activate a Trojan malware implanted in a software tool used in the sequencing pipeline in order to allow the perpetrators to gain control over the resources used in that pipeline during sequence analysis. The scenario considered in the paper is based on perpetrators submitting synthetically engineered DNA samples that contain digitally encoded IP address and port number of the perpetrator’s machine in the DNA. Genetic analysis of the sample’s DNA will decode the address that is used by the software Trojan malware to activate and trigger a remote connection. This approach can open up to multiple perpetrators to create connections to hijack the DNA sequencing pipeline. As a way of hiding the data, the perpetrators can avoid detection by encoding the address to maximise similarity with genuine DNAs, which we showed previously. However, in this paper we show how Deep Learning can be used to successfully detect and identify the trigger encoded data, in order to protect a DNA sequencing pipeline from Trojan attacks. The result shows nearly up to 100% accuracy in detection in such a novel Trojan attack scenario even after applying fragmentation encryption and steganography on the encoded trigger data. In addition, feasibility of designing and synthesizing encoded DNA for such Trojan payloads is validated by a wet lab experiment.

The strategic allocation of pasture grazing area to dairy cows is essential for optimal management and increased outputs. Rising plate meters are frequently used to estimate pasture herbage mass, i.e. dry matter yield per hectare, by employing simple regression equations that relate compressed sward height to herbage mass. However, to improve the accuracy and precision of these equations, so that inherent variation of grasslands is captured, there is a need to incorporate differences in grass types and seasonal growth. Using a total of 308 grass plots, the variation of growth for both perennial ryegrass and hybrid ryegrass was recorded over the seven-month growing season, i.e. March–September. From these data three dynamic equations were derived. The models showed reduced levels of error in comparison to most other conventional equations. As such, the derived models represent a considerable advance for predictive assessment of herbage mass and will support more efficient grassland utilisation by farmers. Although all equations were found to be highly accurate and precise, only a single equation was considered the most effective (R2 = 0.7; RMSE = 248.05), allowing herbage mass to be predicted reliably from compressed sward height data in relation to ryegrass type and calendar month. Although further research will be required, the results presented allow farm operators to calculate herbage mass, as well as support the development of decision support tools to improve on-farm grassland management, particularly at the local paddock rather than national level.

Intensive pasture-based farming systems rely on precise and frequent allocations of grass to animals. Virtual fence (VF) systems have been successfully used to contain animals within predefined boundaries. Accordingly, utilisation of a VF system to enhance automated allocation of correct forage areas to animals would represent a major advancement for grazing management strategies. Traditional VF systems rely on a perimeter cable to establish the boundary line, and this then needs to be deployed and physically moved to alter the parameters of the boundary. In our study, wearable GPS technology was used to implement a VF system without the need for such cabling. To accomplish this, we designed and developed a VF system comprised of a wearable collar with associated on-farm communication infrastructure. Moreover, we attempted to train dairy cows to associate an audio warning stimulus with boundary encroachment. Overall, the operating capacity of the cow-collar and the communications network were found to be robust. However, although dairy cows rapidly associated visual cues with VF boundary lines, and quickly developed a cue-consequence association between the audio warning and corrective stimulus, the number of boundary challenges made by cows increased upon removal of all visual cues. In addition, we observed a reduction in time spent grazing and ruminating during the training period, which suggested cows had become stressed within the designated inclusion zone. Nevertheless, our results are preliminary and further experimental work is required to truly assess best implementation protocols for virtual fencing without visual cues.

The article focuses on the information security risks that arise from the use of dubious software as part of a DNA-sequencing pipeline. We show how the perpetrator can use a biologically engineered sample that contains the remote machine's IP address and port number to trigger Trojan spyware previously dormant, and create a connection to the remote machine. The spyware is then used to either steal sensitive data processed by the pipeline (e.g. DNA-sample of crime suspect) or manipulate its control-flow (e.g. via opening a backdoor). To avoid detection the spyware can accept and expect required payload in fragments, which are also hidden inside the sample in a distributed manner. We show how the adversary can use cryptographic tools such as encryption and steganography to make such detection even harder while limiting the footprint that either identifies the attacker or makes the trigger-sample substantially different from its biological species. Therefore, we prove the viability of the attack and further stress the need to account for attacks being launched from the physical, rather than cyber-world. Furthermore, DNA sequencing error can hinder the successful delivery of a payload, hence the success of such attacks. We estimate the success rates for different sequencing error rates, where the calculated results are also verified with corresponding results from simulations.

In this article, we present a fog computing technique for real-time activity recognition and localization on-board wearable Internet of Things(IoT) devices. Our technique makes joint use of two light-weight analytic methods—Iterative Edge Mining(IEM) and Cooperative Activity Sequence-based Map Matching(CASMM). IEM is a decision-tree classifier that uses acceleration data to estimate the activity state. The sequence of activities generated by IEM is analyzed by the CASMM method for identifying the location. The CASMM method uses cooperation between devices to improve accuracy of classification and then performs map matching to identify the location. We evaluate the performance of our approach for activity recognition and localization of animals. The evaluation is performed using real-world acceleration data of cows collected during a pilot study at a Dairygold-sponsored farm in Kilworth, Ireland. The analysis shows that our approach can achieve a localization accuracy of up to 99%. In addition, we exploit the location-awareness of devices and present an event-driven communication approach to transmit data from the IoT devices to the cloud. The delay-tolerant communication facilitates context-aware sensing and significantly improves energy profile of the devices. Furthermore, an array-based implementation of IEM is discussed, and resource assessment is performed to verify its suitability for device-based implementation.

We present the work towards strengthening the security of DNA-sequencing functionality of future bioinformatics systems against bio-computing attacks. Recent research has shown how using common tools, a perpetrator can synthesize biological material, which upon DNA-analysis opens a cyber-backdoor for the perpetrator to hijack control of a computational resource from the DNA-sequencing pipeline. As DNA analysis finds its way into practical everyday applications, the threat of bio-hacking increases. Our wetlab experiments establish that malicious DNA can be synthesized and inserted into E. coli, a common contaminant. Based on that, we propose a new attack, where a hacker to reach the target hides the DNA with malicious code on common surfaces (e.g., lab coat, bench, rubber glove). We demonstrated that the threat of bio-hacking can be mitigated using dedicated input control techniques similar to those used to counter conventional injection attacks. This article proposes to use genetic similarity of biological samples to identify material that has been generated for bio-hacking. We considered freely available genetic data from 506 mammary, lymphocyte and erythrocyte samples that have a bio-hacking code inserted. During the evaluation we were able to detect up to 95% of malicious DNAs confirming suitability of our method.

Globally, the Rising Plate Meter (RPM) is a device used to measure compressed sward height, to enable estimation of herbage mass. Despite improved farm management practices aided by a variety of technological advances, the standard design of a RPM has remained relatively unchanged. Recently, however, a RPM utilising a micro-sonic sensor, with digital data capture capability via a Bluetooth communications link to a smart device application, has been developed. Here, we assess the comparable ability of both a standard cumulative ratchet counter RPM and the micro-sonic sensor RPM, to accurately and precisely measure fixed heights. Moreover, as correct allocation of grazing area requires accurate geolocation positioning, we assess the associated GPS technology. The micro-sonic sensor RPM was significantly more accurate for height capture than the cumulative ratchet counter RPM. Overall, across all heights, the cumulative ratchet counter RPM underestimated height by 7.68 ± 0.06 mm (mean ± SE). Alternatively, the micro-sonic sensor RPM overestimated height by 0.18 ± 0.08 mm. In relation to a practical applications, these discrepancies can result in an under- and overestimation of dry matter yield by 13.71% and 0.32% kilograms per hectare, respectively. The performance of the on-board GPS did not significantly differ from that of a tertiary device. Overall, the wireless technology, integrated mapping, and decision support tools offered by the innovative micro-sonic sensor RPM provides for a highly efficacious grassland management tool.

The progress of molecular communication (MC) is tightly connected to the progress of nanomachine design. State-of-the-art states that nanomachines can be built either from novel nanomaterials by the help of nanotechnology or they can be built from living cells which are modified to function as intended by synthetic biology. With the growing need of the biomedical applications of MC, we focus on developing bio-compatible communication systems by engineering the cells to become MC nanomachines. Since this approach relies on modifying cellular functions, the improvements in the performance can only be achieved by integrating new biological properties. A previously proposed model for molecular communication is using bacteria as information carriers between transmitters and receivers, also known as bacterial nanonetworks. This approach has suggested encoding information into the plasmids inserted into the bacteria which leads to extra overhead for the receivers to decode and analyze the plasmids to obtain the encoded information. Another scheme, which is proposed in this paper, is to determine the digital information transmitted based on the quantity of bacteria emitted. While this scheme has its simplicity, the major drawback is the low-data rate resulting from the long propagation of the bacteria. To improve the performance, this paper proposes a distributed modulation scheme utilizing three bacterial properties, namely, engineering of plasmids, conjugation, and bacterial motility. In particular, genetic engineering allows us to engineer the different combinations of genes representing the different series of bits. When compared with binary density modulation and the M-ary density modulation, it is shown that the distributed modulation scheme outperforms the other two approaches in terms of bit error probability as well as the achievable rate for varying quantity of bacteria transmitted, distances, as well as time slot length.

Ambient Assisted Living (AAL) is a novel discipline that aims at improving the quality of life for all generations, especially the elderly, with the help of information and communication technologies. Behavioral tracking AAL systems necessitate the monitoring and understanding of daily activities and preferences of the user for design of customized, context-aware services and detection of behavior anomalies. Localization of the user is, therefore, key to facilitate real-time activity monitoring in AAL applications. Although several localization techniques have been proposed to date, majority of them incur a high operational cost owing to dependency on dense sensor deployments for ambient intelligence or use of expensive hardware such as GPS receivers. In this paper, we propose a low-cost Wireless Sensor Networks (WSN) system, comprising of a single wearable device and a cloud gateway, for outdoor localization in the context of AAL. With the inception of the Fog Computing paradigm, we consider the implementation of a light-weight data mining technique, Iterative Edge Mining (IEM), on the wearable device for on-board activity recognition. IEM is based on the classification of signal distributions to enable real-time mobility tracking as the user moves around an environment. Given the topology information and the activity sequence generated by the algorithm, we estimate the user location by associating the distance covered over time with the orientation values. Alerts are signaled locally upon detection of behavior anomalies and transmitted to the gateway node using a delay-tolerant communication framework. As such, IEM runs autonomously on the sensor node without interaction with external objects, thereby, improving the responsiveness as well as the operational cost of our system. We evaluate the performance of IEM in terms of localization accuracy in an outdoor environment.

The Fog Computing paradigm proposes an extension of the cloud-based computing to the network edges in the Internet of Things. It facilitates localized analysis closer to the data sources for improved responsiveness of the system as well as cloud-based learning for historical analysis. In this paper, we present our fogenabled Wireless Sensor Network (WSN) system for activity monitoring and localization in the context of Ambient Assisted Living. Our WSN architecture consists of two types of devices - a wearable sensor device and a cloud gateway node. We discuss our Edge Mining approach for real-time activity classification on the sensor device as well as the Genetic Algorithm used for cloud-based analysis. The design of our analytical framework together with the communication model addresses the challenge of sensor-cloud integration. We evaluate the performance of our system for outdoor localization of the elderly. The analysis is based on acceleration data collected using our wearable device across different activity sequences obtained from the Kasteren dataset.

The integration of precision farming techniques with the Internet of Things, cloud computing, and big data analytics is vital to increase productivity in the challenging dairy industry. At the same time, the energy-efficiency and cost-effectiveness of networking solutions that bring big data from farms to the cloud should be addressed as regards economic and environmental sustainability. This article presents an opportunistic networking paradigm for a pasture-based dairy farm in which cows voluntarily participating in robotic milking are used for mulling delay-tolerant data to a fog computing node at an Internet gateway.

The Internet of Things paradigm is creating an environment where the big data originators will be located at the edge of the Internet. Accordingly, data analytic infrastructure is also being relocated to the network edges, to fulfill the philosophy of data gravity, under the umbrella of Fog computing. The extreme edge of the hierarchical infrastructure consists of sensor devices that constitute the wireless sensor networks. The role of these devices has evolved tremendously over the past few years owing to significant improvements in their design and computational capabilities. Sensor devices, today, are not only capable of performing sense and send tasks but also certain kinds of in-network processing. As such, triple optimization of sensing, computing and communication tasks is required to facilitate the implementation of data analytics on the sensor devices. A sensor node may optimally partition a computation task, for instance, and offload sub-tasks to cooperative neighbouring nodes for parallel execution to, in turn, optimize the network resources. This approach is crucial, especially, for energy harvesting sensor devices where the energy profile and, therefore, the computation capability of each device differs depending on the node location and time of day. Accordingly, future in-network computing must capture the energy harvesting information of sensor nodes to jointly optimize the computation and communication within the network. In this paper, we present a theoretical model for computation offloading in micro-solar powered energy harvesting sensor devices. Optimum data partitioning to minimize the total energy consumption has been discussed based on the energy harvesting status of sensor nodes for different scenarios. The simulation results show that our model reduced both energy losses and waste due to energy conversion and overflows respectively compared to a data partitioning algorithm that offloads computation tasks without taking the energy harvesting status of nodes into consideration. Our approach also improves energy balance of a WSN which is an important factor for its long-term autonomous operation. (C) 2017 Elsevier Inc. All rights reserved.

Technology now offers the possibility of delivering a vast range of low-cost people-centric services to citizens. Internet of Things (IoT) supporting technologies are becoming robust, viable and cheaper. Mobile phones are increasingly more powerful and disseminated. On the other hand, social networks and virtual worlds are experiencing an exploding popularity and have millions of users. These low-cost technologies can now be used to create an Internet of People (IoP), a dynamically configurable integration platform of connected smart objects that allows enhanced, people-centric applications. As opposed to things-centric ones, IoP combines the real, sensory world with the virtual world for the benefit of people while it also enables the development of sensing applications in contexts such as e-health, sustainable mobility, social networks enhancement or fulfilling people's special needs. This paper identifies the main challenges, a possible approach, and key enabling technologies for a people-centric society based on the Internet of Things.

Despite the numerous advantages of using Wireless Sensor Networks (WSN) in precision farming, the lack of infrastructure in the remote farm locations as well as the constraints of WSN devices have limited its role, to date. In this paper, we present the design and implementation of our WSN based prototype system for intelligent data collection in the context of precision dairy farming. Due to the poor Internet connectivity in a typical farm environment, we adopt the delay-tolerant networking paradigm. However, the data collection capability of our system is restricted by the memory constraints of the constituent WSN devices. To address this issue, we propose the use of Edge Mining, a novel fog computing technique, to compress farming data within the WSN. Opposed to the conventional data compression techniques, Edge Mining not only optimizes memory usage of the sensor device, but also builds a foundation for future real-time responsiveness of the prototype system. In particular, we use L-SIP, one of the Edge Mining techniques that provides real-time event-driven feedbacks while allowing accurate reconstruction of the original sensor data, for our data compression tasks. We evaluate the performance of L-SIP in terms of Root Mean Square Error (RMSE) and memory gain using R analysis.

Monitoring and analysis of animal behavior are two of the prominent applications of Wireless Sensor Networks (WSN) in modern Dairy Farming. Behavioral information collected by sensor devices worn by the animals is expected to provide early detection of stress and onset of specific diseases. Animal mobility coupled with farm-based contextual information is expected to automate and increase efficiency of the pasture. Though some WSN solutions have been proposed for these applications, their realizations commonly depend on high availability of third-party components (e.g. cloud-environment for behavior analysis). This reduces suitability of these solutions for pasture-based dairy farms, where large scale and remote locations significantly restrict accessibility to external components (e.g. poor or no internet connectivity). Meanwhile, continuous design improvement of WSN devices has significantly increased their computational capacity. To take advantage of this, a novel Edge Mining (EM) concept has been proposed under the umbrella of Fog Computing, where to increase availability, data analysis is partially hosted by WSN. In this article, we propose an Edge Mining implementation of our WSN system for analyzing animal mobility and behavior. We develop a novel EM method that could be used for a range of animal activity and behavior analysis. Performance of the method is evaluated regarding the accuracy and suitability for WSN-based execution.

Fog Computing is a new paradigm that has been proposed by CISCO to take full advantage of the ever growing computational capacity of the near-user or edge devices (e.g., wireless gateways and sensors). The paradigm proposes an architecture that enables the devices to host functionality of various user-centric services. While the prospects of Fog Computing promise numerous advantages, development of Fog Services remains under-investigated. This article considers an opportunity of Fog implementation for Alert Services on top of Wireless Sensor Network (WSN) technology. In particular, we focus on targeted WSN-alert delivery based on spontaneous interaction between a WSN and hand-held devices of its users. For the alert delivery, we propose a Gravity Routing concept that prioritizes the areas of high user-presence within the network. Based on the concept, we develop a routing protocol, namely the Gradient Gravity Routing (GGR) that combines targeted delivery and resilience to potential sensor-load heterogeneity within the network. The protocol has been compared against a set of state-of-the-art solutions via a series of simulations. The evaluation has shown the ability of GGR to match the performance of the compared solutions in terms of alert delivery ratio, while minimizing the overall energy consumption of the network.

Edge Mining (EM), a novel Fog Computing technique, has been proposed to perform data analysis on sensor devices at the edge of Internet of Things (IoT). The approach, however, is limited to analysis conducted by each sensor node in isolation. In this paper, we propose Collaborative Edge Mining (CEM), an extension of the EM technique, wherein multiple sensor devices participate together in on-site data analysis and prediction. Our model detects contextually relevant events by integrating and analysing data arising from different sources and, thereby, lays the foundation of a sensor-based implementation of Apache Storm like framework. We have evaluated our approach with respect to the Linear Spanish Inquisition Protocol for a precision farming application. We illustrate CEM for the estimation of Temperature Humidity Index, an important metric to predict Heat Stress in dairy cattle, and compare its performance to EM. CEM performs well in most cases, especially, latency-sensitive scenarios.

This material is based on work in progress. Over the last decade, precision agriculture has grown in importance in order to meet the increasing food demand and ensure sustainability of farming. Today, advances in the Internet of Things (IoT) paradigm have promoted the use of Wireless Sensor Networks (WSN) for precision farming. However, recent technological developments suggest that use of Nanotechnology has immense potential to further improve the farming productivity. In this paper, we present some use-cases for the application of Internet of Nano Things (IoNT) in dairy farming. Although the use of IoNT involves several challenges, we envisage a multitude of benefits associated with its implementation.

The role of wireless sensor networks (WSNs) in agriculture has become prominent as part of the precision farming initiative. In the future, multiple WSN systems will be deployed on every farm. Accurate and timely analyses of the data collected by these systems will become paramount for increasing efficiency and sustainability of farming. Conventionally, analyzing monitoring data is considered to be beyond WSN capabilities, and, therefore, carried out remotely. Meanwhile, in recent years, complexity of the tasks performed by WSNs has been constantly increasing. Modern wireless sensors possess computational capacity sufficient for certain data-analytics functionality. This article overviews modern WSN functionality that incorporates a certain level of intelligence, while the authors explore challenges and potential benefits of WSN-based analytics in the scope of precision farming.