No abstract

Abstract. This paper introduces ALYSIA: Automated LYrical SongwrIting Application. ALYSIA is based on a machine learning model using Random Forests, and we discuss its success at pitch and rhythm prediction. Next, we show how ALYSIA was used to create original pop songs that were subsequently recorded and produced. Finally, we discuss our vision for the future of Automated Songwriting for both co-creative and autonomous systems.

This paper presents the results of a novel digital signal processor (DSP) based technique for signal conditioning of Linear Variable Dgferential Transformers (L VDTs).Signal conditioning is achieved through a modified DSP-based Costas receiver. This system is tested and compared with two commercially available analog signal conditioners and a second DSP-based signal conditioner. The system developed by the authors has better dynamic response than existing solutions and better noise rejection than commercially available solutions. Static testing of the system using both 4-wire and 5-wire LVDTs verifies that the conditioner meets or exceeds the linearity performance of existing signal conditioning systems over the full-scale operating range. In addition, this system requires no phase compensation network or manual tuning.

No abstract

No abstract

Abstract:Machining is one of the major manufacturing techniques where the material is removed to prepare the complete or sub-part. In general, this is also referred to as subtractive manufacturing. Due to solid-to-solid contact between the cutting tool and the work-piece, the machine dynamics get influenced by various operating parameters. This generates force and vibration, and thus noise. Over time the cutting tool reaches its end-of-life which increases the force to cut, and thus produces more vibration and noise. The noise parameter was considered in this work. A 32-element spherical microphone array acoustic camera system was used to record and analyze the sound that was emitted during the machining processes. The startup, idle, and load operating characteristics for various industrial machining equipment were monitored with the acoustic beam former microphone system. The industrial applications included a bench grinder, surface grinder, vertical band saw, lathe machine, and vertical milling machine. Analysis of the acoustic noise generated from these processes could demonstrate the similarities between the cyclical patterns of resonating sound.

We investigate a natural generalization of the classical clustering problem, considering clustering tasks in which different instances may have different weights. We conduct the first extensive theoretical analysis on the influence of weighted data on standard clustering algorithms in both the partitional and hierarchical settings, characterizing the conditions under which algorithms react to weights. Extending a recent framework for clustering algorithm selection, we propose intuitive properties that would allow users to choose between clustering algorithms in the weighted setting and classify algorithms accordingly.

No abstract