Rapid advances in hardware-based technologies during the past decades have opened up new possibilities for life scientists to gather multimodal data in various application domains, such as omics, bioimaging, medical imaging, and (brain/body)-machine interfaces. These have generated novel opportunities for development of dedicated data-intensive machine learning techniques. In particular, recent research in deep learning (DL), reinforcement learning (RL), and their combination (deep RL) promise to revolutionize the future of artificial intelligence. The growth in computational power accompanied by faster and increased data storage, and declining computing costs have already allowed scientists in various fields to apply these techniques on data sets that were previously intractable owing to their size and complexity. This paper provides a comprehensive survey on the application of DL, RL, and deep RL techniques in mining biological data. In addition, we compare the performances of DL techniques when applied to different data sets across various application domains. Finally, we outline open issues in this challenging research area and discuss future development perspectives.

Automatically recognizing human emotions from spontaneous and non-prototypical real-life data is currently one of the most challenging tasks in the field of affective computing. This article presents our recent advances in assessing dimensional representations of emotion, such as arousal, expectation, power, and valence, in an audiovisual human-computer interaction scenario. Building on previous studies which demonstrate that long-range context modeling tends to increase accuracies of emotion recognition, we propose a fully automatic audiovisual recognition approach based on Long Short-Term Memory (LSTM) modeling of word-level audio and video features. LSTM networks are able to incorporate knowledge about how emotions typically evolve over time so that the inferred emotion estimates are produced under consideration of an optimal amount of context. Extensive evaluations on the Audiovisual Sub-Challenge of the 2011 Audio/Visual Emotion Challenge show how acoustic, linguistic, and visual features contribute to the recognition of different affective dimensions as annotated in the SEMAINE database. We apply the same acoustic features as used in the challenge baseline system whereas visual features are computed via a novel facial movement feature extractor. Comparing our results with the recognition scores of all Audiovisual Sub-Challenge participants, we find that the proposed LSTM-based technique leads to the best average recognition performance that has been reported for this task so far.

Recent technological advancements in data acquisition tools allowed life scientists to acquire multimodal data from different biological application domains. Categorized in three broad types (i.e. images, signals, and sequences), these data are huge in amount and complex in nature. Mining such enormous amount of data for pattern recognition is a big challenge and requires sophisticated data-intensive machine learning techniques. Artificial neural network-based learning systems are well known for their pattern recognition capabilities, and lately their deep architectures—known as deep learning (DL)—have been successfully applied to solve many complex pattern recognition problems. To investigate how DL—especially its different architectures—has contributed and been utilized in the mining of biological data pertaining to those three types, a meta-analysis has been performed and the resulting resources have been critically analysed. Focusing on the use of DL to analyse patterns in data from diverse biological domains, this work investigates different DL architectures’ applications to these data. This is followed by an exploration of available open access data sources pertaining to the three data types along with popular open-source DL tools applicable to these data. Also, comparative investigations of these tools from qualitative, quantitative, and benchmarking perspectives are provided. Finally, some open research challenges in using DL to mine biological data are outlined and a number of possible future perspectives are put forward.

Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders—focusing on Alzheimer’s disease, Parkinson’s disease and schizophrenia—from MRI data acquired using different modalities including functional and structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.

Rapid developments in the fields of information and communication technology and microelectronics allowed seamless interconnection among various devices letting them to communicate with each other. This technological integration opened up new possibilities in many disciplines including healthcare and well-being. With the aim of reducing healthcare costs and providing improved and reliable services, several healthcare frameworks based on Internet of Healthcare Things (IoHT) have been developed. However, due to the critical and heterogeneous nature of healthcare data, maintaining high quality of service (QoS) -in terms of faster responsiveness and data-specific complex analytics -has always been the main challenge in designing such systems. Addressing these issues, this paper proposes a five-layered heterogeneous mist, fog, and cloud based IoHT framework capable of efficiently handling and routing (near-)real-time as well as offline/batch mode data. Also, by employing software defined networking and link adaptation based load balancing, the framework ensures optimal resource allocation and efficient resource utilization. The results, obtained by simulating the framework, indicate that the designed network via its various components can achieve high QoS, with reduced end-to-end latency and packet drop rate, which is essential for developing next generation e-healthcare systems.

Rapid popularity of Internet of Things (IoT) and cloud computing permits neuroscientists to collect multilevel and multichannel brain data to better understand brain functions, diagnose diseases, and devise treatments. To ensure secure and reliable data communication between end-to-end (E2E) devices supported by current IoT and cloud infrastructure, trust management is needed at the IoT and user ends. This paper introduces a Neuro-Fuzzy based Brain-inspired trust management model (TMM) to secure IoT devices and relay nodes, and to ensure data reliability. The proposed TMM utilizes node behavioral trust and data trust estimated using Adaptive Neuro-Fuzzy Inference System and weighted-additive methods respectively to assess the nodes trustworthiness. In contrast to the existing fuzzy based TMMs, the NS2 simulation results confirm the robustness and accuracy of the proposed TMM in identifying malicious nodes in the communication network. With the growing usage of cloud based IoT frameworks in Neuroscience research, integrating the proposed TMM into the existing infrastructure will assure secure and reliable data communication among the E2E devices.

No abstract

Abstract-The recent expansion of pervasive computing technology has contributed with novel means to pursue human activities in urban space. The urban dynamics unveiled by these means generate an enormous amount of data. These data are mainly endowed by portable and radio-frequency devices, transportation systems, video surveillance, satellites, unmanned aerial vehicles, and social networking services. This has opened a new avenue of opportunities, to understand and predict urban dynamics in detail, and plan various real-time services and applications in response to that. Over the last decade, certain aspects of the crowd, e.g. mobility, sentimental, size estimation and behavioral, have been analyzed in detail and the outcomes have been reported. This article mainly conducted an extensive survey on various data sources used for different urban applications, the state-of-the-art on urban data generation techniques and associated processing methods in order to demonstrate their merits and capabilities. Then, a possible crowd event detection framework is discussed which fuses data from all the available pervasive technology sources. In addition, available open-access crowd datasets for urban event detection are provided along with relevant Application Programming Interfaces, and finally, some open challenges and promising research directions are outlined.Index Terms-Urban sensing, pervasive technology, crowd mobility and management, information fusion, decision support system, benchmark datasets.