Plant leaf disease classification using EfficientNet deep learning model

Dense convolutional neural networks based multiclass plant disease detection and classification using leaf images

COVID-19 has disrupted normal life and has enforced a substantial change in the policies, priorities and activities of individuals, organisations and governments. These changes are proving to be a catalyst for technology and innovation. In this paper, we discuss the pandemic’s potential impact on the adoption of the Internet of Things (IoT) in various broad sectors, namely healthcare, smart homes, smart buildings, smart cities, transportation and industrial IoT. Our perspective and forecast of this impact on IoT adoption is based on a thorough research literature review, a careful examination of reports from leading consulting firms and interactions with several industry experts. For each of these sectors, we also provide the details of notable IoT initiatives taken in the wake of COVID-19. We also highlight the challenges that need to be addressed and important research directions that will facilitate accelerated IoT adoption.

Impact of COVID-19 on IoT Adoption in Healthcare, Smart Homes, Smart Buildings, Smart Cities, Transportation and Industrial IoT.

Determining how to structure vehicular network environments can be done in various ways. Here, we highlight vehicle networks' evolution from vehicular ad-hoc networks (VANET) to the internet of vehicles (IoVs), listing their benefits and limitations. We also highlight the reasons in adopting wireless technologies, in particular, IEEE 802.11p and 5G vehicle-to-everything, as well as the use of paradigms able to store and analyze a vast amount of data to produce intelligence and their applications in vehicular environments. We also correlate the use of each of these paradigms with the desire to meet existing intelligent transportation systems' requirements. The presentation of each paradigm is given from a historical and logical standpoint. In particular, vehicular fog computing improves on the deficiences of vehicular cloud computing, so both are not exclusive from the application point of view. We also emphasize some security issues that are linked to the characteristics of these paradigms and vehicular networks, showing that they complement each other and share problems and limitations. As these networks still have many opportunities to grow in both concept and application, we finally discuss concepts and technologies that we believe are beneficial. Throughout this work, we emphasize the crucial role of these concepts for the well-being of humanity.

Computing Paradigms in Emerging Vehicular Environments: A Review

The monitoring and control of crops in precision agriculture sometimes requires a high collection frequency of information (e.g., temperature, humidity, and salinity) due to the variability in crops. Data acquisition and transmission are generally achieved thanks to wireless sensor networks. However, sensor nodes have limited resources. Thus, it is necessary to adapt the increase in sampling frequency for different crops, under application constraints (reliability, packet delay, and lifetime duration). In this paper, we propose to properly tune IEEE 802.15.4 MAC parameters ( macMinBE and macMaxCSMABackoffs ) and the sampling frequency of deployed sensor nodes. An analytical model of network performance is derived and used to perform the tuning of these tradeoff parameters. Simulation analysis shows that our scheme provides an efficient increase of sampling frequency of sensor nodes while satisfying application requirements.

Performance Management of IEEE 802.15.4 Wireless Sensor Network for Precision Agriculture

Daily conversations contain rich emotional information, and identifying this emotional information has become a hot task in the field of natural language processing. The traditional dialogue sentiment analysis method studies one-to-one dialogues and cannot be effectively applied to multi-speaker dialogues. This paper focuses on the relationship between participants in a multi-speaker conversation and analyzes the influence of each speaker on the emotion of the whole conversation. We summarize the challenges of emotion recognition work in multi-speaker dialogue, focusing on the context-topic switching problem caused by multi-speaker dialogue due to its free flow of topics. For this challenge, this paper proposes a graph network that combines syntactic structure and topic information. A syntax module is designed to convert sentences into graphs, using edges to represent dependencies between words, solving the colloquial problem of daily conversations. We use graph convolutional networks to extract the implicit meaning of discourse. In addition, we focus on the impact of topic information on sentiment, so we design a topic module to optimize the topic extraction and classification of sentences by VAE. Then, we use the combination of attention mechanism and syntactic structure to strengthen the model’s ability to analyze sentences. In addition, the topic segmentation technology is adopted to solve the long-term dependencies problem, and a heterogeneous graph is used to model the dialogue. The nodes of the graph combine speaker information and utterance information. Aiming at the interaction relationship between the subject and the object of the dialogue, different edge types are used to represent different interaction relationships, and different weights are assigned to them. The experimental results of our work on multiple public datasets show that the new model outperforms several other alternative methods in sentiment label classification results. In the multi-person dialogue dataset, the classification accuracy is increased by more than 4%, which verifies the effectiveness of constructing heterogeneous dialogue graphs.

/pdf/joint-syntax-enhanced-and-topic-driven-graph-networks-for-20aatdt6.pdf

Joint Syntax-Enhanced and Topic-Driven Graph Networks for Emotion Recognition in Multi-Speaker Conversations

Emergencies can happen at anytime and anywhere. Governments around the world try to ensure public and private organizations’ preparedness for all types of potential emergencies. They usually rely on implementing autonomous systems to deal with unpredictable emergency scenarios. This paper proposes an adaptive emergency evacuation approach based on a wireless sensor network integrated with cloud. The proposed approach maximizes the safety of the obtained paths by adapting to the characteristics of the hazard, evacuees’ behavior, and environmental conditions. It also employs an on-demand cloudification algorithm that improves the evacuation accuracy and efficiency for critical cases. It mainly handles the important evacuation issue when people are blocked in a safe, dead-end area of a building. Simulation results show an improved safety and evacuation efficiency by an average of 98% over the existing time-based and single-metric emergency evacuation approaches.

Emergency Navigation Approach Using Wireless Sensor Networks and Cloud Computing

Building a human-computer conversational system that can communicate with humans is a research hotspot in the field of artificial intelligence. Traditional dialogue systems tend to produce irrelevant and non-information responses, which reduce people’s interest in engaging in a conversation. This often leads to boring conversations. To alleviate this problem, many researchers use external knowledge to assist conversation generation. The accuracy of knowledge selection is the prerequisite to ensure the quality of knowledge conversation. This approach has worked positively to a certain extent, but generally only searches knowledge information based on entity words themselves, without considering the specific conversation context. Therefore, if irrelevant knowledge is retrieved, the quality of conversation generation will be reduced. Motivated by this, we propose a novel neural knowledge-based conversation generation model, named Siamese Network based Posterior Knowledge Selection Model for Knowledge Driven Conversation Generation (SPK-CG). We have designed a novel knowledge selection mechanism to obtain knowledge information that is highly relevant to the context of the conversation. Specifically, the posterior knowledge distribution is used as a soft label to make the prior distribution consistent with the posterior distribution in the training process. At the same time, in order to narrow the gap between prior and posterior distributions and improve the accuracy of knowledge selection, we leverage siamese network and design multi-granularity matching module for knowledge selection. Compared with previous knowledge-based models, our method can select more appropriate knowledge and use the selected knowledge to generate responses that are more relevant to the conversation context. Extensive automatic and human evaluations demonstrate that our model has advantages over previous baselines.

SPK-CG: Siamese Network based Posterior Knowledge Selection Model for Knowledge Driven Conversation Generation

With the development of multimodal sentiment analysis tasks, target-level/aspect-level multimodal sentiment analysis has received more attention, aiming to intelligently judge the sentiment orientation of target words using visual and textual information. Most existing methods mainly rely on combining the whole image and text while ignoring the implicit affective regions in the image. We introduce a novel affective region recognition and fusion network (ARFN) for target-level multimodal sentiment classification, which focuses more on the alignment of multimodal fusion of visual and textual. First, to produce a visual representation with sentiment elements, ARFN employs the Yolov5 algorithm to extract the object region of the image and selects the emotional area according to the strategy. Next, this method learns target-sensitive visual representations and text semantic representations through a multi-head attention mechanism and pre-trained models BERT, respectively. Moreover, ARFN fuses textual and visual representations through a multimodal interaction method to perform target-level multimodal sentiment classification tasks. We achieve state-of-the-art performance on two available multimodal Twitter datasets, and experimental results show the effectiveness of our approach. 

Affective Region Recognition and Fusion Network for Target-Level Multimodal Sentiment Classification

Diagnosability is an important characteristic indicator to determine whether the system is stable and reliable. In this paper, the general architecture of event-state-combination diagnosability is investigated. The contributions are threefold. First, the notion of event-state-combination diagnosability is formalized. Roughly speaking, an event-state-combination diagnosable system means that not only each combined fault can be detected, but also the system can determine whether it will work permanently in the failure states after the combined fault occurs. Then, an automaton with new information structure, called event-state-combination verifier, is constructed, which can be used for the verification of the event-state-combination diagnosability. Finally, the necessary and sufficient conditions for verifying whether the system is event-state-combination diagnosable is presented, that is, the event-state-combination verifier does not have any failure confused cycle.

Najla Al-Nabhan

Papers

Joint Syntax-Enhanced and Topic-Driven Graph Networks for Emotion Recognition in Multi-Speaker Conversations

Emergency Navigation Approach Using Wireless Sensor Networks and Cloud Computing

SPK-CG: Siamese Network based Posterior Knowledge Selection Model for Knowledge Driven Conversation Generation

Affective Region Recognition and Fusion Network for Target-Level Multimodal Sentiment Classification

Fault diagnosis of discrete-event systems under a general architecture