Search

Electricity users are the major players of the electricity systems, and electricity consumption is growing at an extraordinary rate. The research on electricity consumption behaviors are becoming increasingly important to design and deployment of the electricity systems. However, the acquisition of data related to the electricity consumption behaviors is still a major challenge. Data synthesis is among the best approaches to solving the issue, and the key is the model that preserves the real electricity consumption behaviors. In this paper, we propose a hierarchical multi-matrices Markov (HMM) model to synthesize scalable electricity load curves that preserve the real consumption behaviors on three time scales: per day, per week, and per year. To promote the research on the electricity consumption behaviors, we use the HMM approach to modeling two distinctive raw electricity load curves. One is collected from the resident sector, and the other is collected from the non-resident sectors, including different industries such as education, finance, and manufacturing. The experiments show our model performs much better than the cluster-based Markov model. We publish two trained models online, publicly available from http://www.benchcouncil.org/electricity , and researchers are allowed to directly use these trained models to synthesize scalable electricity load curves for further research.

Big medical data poses great challenges to life scientists, clinicians, computer scientists, and engineers. In this paper, a group of life scientists, clinicians, computer scientists and engineers sit together to discuss several fundamental issues. First, what are the unique characteristics of big medical data different from those of the other domains? Second, what are the prioritized tasks in clinician research and practices utilizing big medical data? And do we have enough publicly available data sets for performing those tasks? Third, do the state-of-the-practice and state-of-the-art algorithms perform good jobs? Fourth, are there any benchmarks for measuring algorithms and systems for big medical data? Fifth, what are the performance gaps of state-of-the-practice and state-of-the-art systems handling big medical data currently or in future? Finally but not least, are we, life scientists, clinicians, computer scientists and engineers, ready for working together? We believe answering the above issues will help define and shape the landscape of big medical data., Comment: To appear in IEEE Access

Cervical spondylosis(CS), a most common orthopedic diseases, is mainly identified by the doctor’s judgment from the clinical symptoms and cervical change provided by expensive instruments in hospital. Owing to the development of the surface electromyography(sEMG) technique and artificial intelligence, we proposed a convenient non-harm CS intelligent identify method EasiCNCSII, including the sEMG data acquisition and the CS identification. For the convenience and efficiency of data acquisition with the limited testable muscles provided by the sEMG technology, we proposed a data acquisition method based on the relationship between muscle activity pattern, the tendons theory and CS etiology. It is easily performed in less than 20 minutes, even outside the hospital. Faced with the challenge of high-dimension and the weak availability, the 3-tier model EasiAI is developed to intelligently identify CS. The common features and new features are extracted from raw sEMG data in first tier. The EasiRF is proposed in second tier to further reduce the data dimension and improve the performance. With the limited and weakly available data, the gradient boosted regression tree is developed in third tier to effectively identify CS. The EasiAI achieve the best performance with 91.02% in accuracy, 97.14% in sensitivity, and 81.43% in specificity compared with 4 common machine learning classification model, validating the EasiCNCSII effectiveness.

AI benchmarking provides yardsticks for benchmarking, measuring and evaluating innovative AI algorithms, architecture, and systems. Coordinated by BenchCouncil, this paper presents our joint research and engineering efforts with several academic and industrial partners on the datacenter AI benchmarks—AIBench. The benchmarks are publicly available from http://www.benchcouncil.org/AIBench/index.html. Presently, AIBench covers 16 problem domains, including image classification, image generation, text-to-text translation, image-to-text, image-to-image, speech-to-text, face embedding, 3D face recognition, object detection, video prediction, image compression, recommendation, 3D object reconstruction, text summarization, spatial transformer, and learning to rank, and two end-to-end application AI benchmarks. Meanwhile, the AI benchmark suites for high performance computing (HPC), IoT, Edge are also released on the BenchCouncil web site. This is by far the most comprehensive AI benchmarking research and engineering effort.