3rd International Workshop on Artificial Intelligence Applications in Internet of Things

Session AI2OT


3:15 PM — 5:15 PM GMT
Dec 13 Mon, 10:15 AM — 12:15 PM EST

Examining and Evaluating Dimension Reduction Algorithms for Classifying Alzheimer’s Diseases using Gene Expression Data

Shunbao Li, Po Yang, Vitaveska Lanfranchi (University of Sheffield, UK), Alzheimer’s Disease Neuroimaging Initiative

Alzheimer's disease (AD) is a neurodegenerative disease. Its condition is irreversible and ultimately fatal. Researchers have been studying approaches to support early diagnosis of Alzheimer disease and further delay the patient's condition and improve AD patient's quality of life. Gene expression data is a mature technology. It has many advantages such as high throughput, less-invasiveness, and affordability. It has great potential to help people diagnose Alzheimer's disease in early stage. However, because the amount of information is too large compared to the number of samples in the Alzheimer's database, researchers are facing "curse of dimensionality " when using gene expression data. In this work we are interested in the task of dimensionality reduction of gene expression data in Alzheimer??s Disease Neuroimaging Initiative (ADNI) database. We investigated six dimensionality redu

LSTM for Periodic Broadcasting in Green IoT Applications over Energy Harvesting Enabled Wireless Networks: Case Study on ADAPCAST

Mustapha Khiati (USTHB, Algeria), Djamel Djenouri (University of the West of England - UWE Bristol, UK), Jianguo Ding (University of Skovde, Sweden), Youcef Djenouri (SINTEF Digital, Norway)

The present paper considers emerging Internet of Things (IoT) applications and proposes a Long Short Term Memory (LSTM) based neural network for predicting the end of the broadcasting period under slotted CSMA (Carrier Sense Multiple Access) based MAC protocol and Energy Harvesting enabled Wireless Networks (EHWNs). The goal is to explore LSTM for minimizing the number of missed nodes and the number of broadcasting time-slots required to reach all the nodes under periodic broadcast operations. The proposed LSTM model predicts the end of the current broadcast period relying on the Root Mean Square Error (RMSE) values generated by its output, which (the RMSE) is used as an indicator for the divergence of the model. As a case study, we enhance our already developed broadcast policy, ADAPCAST by applying the proposed LSTM. This allows to dynamically adjust the end of the broadcast periods, instead of statically fixing it beforehand. An artificial data-set of the historical data is used to feed the proposed LSTM with information about the amounts of incoming, consumed, and effective energy per time-slot, and the radio activity besides the average number of missed nodes per frame. The obtained results prove the efficiency of the proposed LSTM model in terms of minimizing both the number of missed nodes and the number of time-slots required for completing broadcast operations.

MsfNet: a Novel Small Object Detection based on Multi-Scale Feature Fusion

Ziying Song (Hebei University of Science and Technology, China), Peiliang Wu (Yanshan University, China), Kuihe Yang, Yu Zhang, Yi Liu (Hebei University of Science and Technology, China)

This paper proposes a small object detection algorithm based on multi-scale feature fusion. By learning shallow features at the shallow level and deep features at the deep level, the proposed multi-scale feature learning scheme focuses on the fusion of concrete features and abstract features. It constructs object detector (MsfNet) based on multi-scale deep feature learning network and considers the relationship between a single object and local environment. Combining global information with local information, the feature pyramid is constructed by fusing different depth feature layers in the network. In addition, this paper also proposes a new feature extraction network (CourNet), through the way of feature visualization compared with the mainstream backbone network, the network can better express the small object feature information. The proposed algorithm is evaluated on MS COCO dataset and achieves the leading performance. This study shows that the combination of global information and local information is helpful to detect the expression of small objects in different illumination. MsfNet uses CourNet as the backbone network, which has high efficiency and a good balance between accuracy and speed.

Under-Determined Blind Speech Separation via the Convolutive Transfer Function and Lp Regularization

Liu Yang (Guangzhou University, China), Yang Junjie (Guangdong University ot Technology, China), Yi Guo (Western Sydney University, Australia)

Blind speech separation (BSS) aims at recovering speech sources from the recorded mixture signals. The conventional methods that dealt with audio speech separation problem mainly based on a linear system model in time-frequency (TF) domain. However, this model is sensitive to the length of room impulse response coefficients (RIRs). For example, a long length of RIRs (a strongly reverberant environment) can result in the overlapping of sources and consequently a degenerated performance. Moreover, the source reconstruction is problematic when the system is underdetermined, i.e., the number of sources is larger than the number of microphones. To tackle these problems, a Lp (0 < p ≤ 1) regularization is provided to reconstruct the sparsity of sources in the TF domain. The proposed approach is based on a convolutive transfer functions (CTFs) approximation. The experiment results demonstrate that the proposed method is more robust to the room reverberation than the conventional methods under various speech separation cases.

Session Chair

Xuan Liu (Hunan University, Changsha, China) Yanchao Zhao (Nanjing University of Aeronautics and Astronautics Nanjing, China)

Made with in Toronto · Privacy Policy · © 2022 Duetone Corp.