Water is a precious resource that should be managed carefully. However, due to leakages in Water Distributed Networks (WDNs), a large amount of water is lost each year that suggests the need for reliable and robust leak detection and localization system. This paper attempts to review the current technologies for leakage detection in WDN as well as several proposed intelligent methodologies (such as support vector machine, neural network and convolution neural network) over the past few years. The current methodologies and their limitations are discussed. Uncertainties involved in the implementation of WDN leakage detection are also discussed and several suggestions to overcome such uncertainties are provided for future implementations.

Human factors are the primary catalyst for traffic accidents. Among different factors, fatigue, distraction, drunkenness, and/or recklessness are the most common types of abnormal driving behavior that leads to an accident. With technological advances, modern smartphones have the capabilities for driving behavior analysis. There has not yet been a comprehensive review on methodologies utilizing only a smartphone for drowsiness detection and abnormal driver behavior detection. In this paper, different methodologies proposed by different authors are discussed. It includes the sensing schemes, detection algorithms, and their corresponding accuracy and limitations. Challenges and possible solutions such as integration of the smartphone behavior classification system with the concept of context-aware, mobile crowdsensing, and active steering control are analyzed. The issue of model training and updating on the smartphone and cloud environment is also included.

With the concept of Internet-of-Things, autonomous vehicles can provide higher driving efficiency, traffic safety, and freedom for the driver to perform other tasks. This paper first covers enabling technology involving a vehicle moving out of parking, traveling on the road, and parking at the destination. The development of autonomous vehicles relies on the data collected for deployment in actual road conditions. Research gaps and recommendations for autonomous intelligent vehicles are included. For example, a sudden obstacle while the autonomous vehicle executes the parking trajectory on the road is discussed. Several aspects of social problems, such as the liability of an accident affecting the autonomous vehicle, are described. A smart device to detect abnormal driving behaviors to prevent possible accidents is briefly discussed.

The lack of strongly labeled data can limit the potential of a Sound Event Detection (SED) system trained using deep learning approaches. To address this issue, this paper proposes a novel method to approximate strong labels for the weakly labeled data using Nonnegative Matrix Factorization (NMF) in a supervised manner. Using a combinative transfer learning and semi-supervised learning framework, two different Convolutional Neural Networks (CNN) are trained using synthetic data, approximated strongly labeled data, and unlabeled data where one model will produce the audio tags. In contrast, the other will produce the frame-level prediction. The proposed methodology is then evaluated on three different subsets of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 dataset: validation dataset, challenge evaluation dataset, and public YouTube evaluation dataset. Based on the results, our proposed methodology outperforms the baseline system by a minimum of 7% across these three different data subsets. In addition, our proposed method also outperforms the top 3 submissions from the DCASE 2019 challenge task 4 on the validation and public YouTube evaluation datasets. Our system performance is also competitive against the top submission in DCASE 2020 challenge task 4 on the challenge evaluation data. A post-challenge analysis was also performed using the validation dataset, which revealed the causes of the performance difference between our system and the top submission of the DCASE 2020 challenge task 4. The leading causes that we observed are 1) detection threshold tuning method and 2) augmentation techniques used. We observed that our system could perform better than the first place submission by 1.5% by changing our detection threshold tuning method. In addition, the post-challenge analysis also revealed that our system is more robust than the top submission in DCASE 2020 challenge task 4 on long-duration audio clips, where we outperformed them by 37%.

Sound Event Detection remains a challenging task due to the lack of strongly labeled data. While the use of weakly labeled and unlabeled data can alleviate this issue, most states of the art utilized the Mean Teacher approach, which requires training two identical models in a semi-supervised manner. Such methodology can have two critical limitations. Firstly, it can be computationally expensive if a very deep model is designed. Secondly, a model designed might only be optimal for either audio tagging or frame-level prediction but not both. Thus, using the Mean-Teacher approach may only allow a model to perform at its maximum potential for one of the tasks. However, the aforementioned issues can be circumvented by designing two different models where the less complex model provides the frame-level prediction while the more complex model provides the audio tags. To increase the accuracy of the models, we propose the use of Squeeze and Excite, meta-ACON, an improved Transformer encoding layer, a triple instance-level pooling approach (i.e., multi-branch pooling), and an improved cyclic learning scheme. Based on such a framework, the best system can achieve an event-based F1-score of 48.5%. By ensembling the top 5 models, the event-based F1-score increases to 50.4%. The proposed framework can achieve a minimum margin of over 12% against the baseline system while being competitive to the other state of the arts.