In this century, most of the companies use the electricity from the fossils fuels such as oil, gas and coal. This method will give negative impact to the environment and the fossils fuel will be run out. This project ...
In this century, most of the companies use the electricity from the fossils fuels such as oil, gas and coal. This method will give negative impact to the environment and the fossils fuel will be run out. This project is to develop a microbial fuels cell that can produce electricity. There are several types of the microbial fuel cell, which are a single chamber, double chamber and continuous. In this paper, the double chamber microbial fuel cell was selected to investigate the effect of suspended sludge into the double chamber microbial fuels cell. The salt bridge will construct between both chambers of the double chamber microbial fuels cell. Carbon graphite rod is selected as an electrode at the cathode and anode to transfer the electron from the anode to the cathode. Electricity is generated from the anaerobic oxidation of organic matter by bacteria. At the end of this project, the microbial fuels cell was successful in generating electricity that can be used for a specific application.
Customer churn prediction has been used widely in various kind of domain especially subscription-basis industries. With the rapid growth of telecommunication industry over the last decade, this industry not only focus...
Customer churn prediction has been used widely in various kind of domain especially subscription-basis industries. With the rapid growth of telecommunication industry over the last decade, this industry not only focuses on providing numerous products, but also satisfying the customers as it is one of the key solutions to remain competitive. This research proposed MultiLayer Perceptron Method for churn prediction. The evaluation is compared with three classifiers which includes are Support Vector Machine, Naïve Bayes and Decision Tree in term of several aspects. In preprocessing phase, we employed Principal Component Analysis and normalization to find the correlation among all the variables. For the postprocessing, InfoGainAttribute is used to identify the highest factor attribute that leads to customer retention. It is found that MultiLayer Perceptron outperforms other classifiers and international plan plays important role to retain customer from leaving organization.
Energy is essential for human existence, and its high consumption is a growing concern in today's technology-driven society. Global initiatives aim to reduce energy consumption and pollution by developing and depl...
详细信息
Energy is essential for human existence, and its high consumption is a growing concern in today's technology-driven society. Global initiatives aim to reduce energy consumption and pollution by developing and deploying energy-efficient sensing technologies for long-term monitoring, control, automation, security, and interactions. Wireless Body Area Networks (WBANs) benefit a lot from the continuous monitoring capabilities of these sensing devices, which include medical sensors worn on or implanted in the human body for healthcare monitoring. Despite significant advancements, achieving energy efficiency in WBANs remains a significant challenge. A deep understanding of the WBAN architecture is essential to identify the causes of its energy inefficiency and develop novel energy-efficient solutions. We investigate energy efficiency issues specific to WBANs. We discuss the transformative impact that artificial intelligence and Machine Learning (ML) can have on achieving the energy efficiency of WBANs. Additionally, we explore the potential of emerging technologies such as quantum computing, nano-technology, biocompatible energy harvesting, and Simultaneous Wireless Information and Power Transfer (SWIPT) in enabling energy efficiency in WBANs. We focus on WBANs' architecture, hardware, and software components to identify key factors responsible for energy consumption in the WBAN environment. Based on our comprehensive review, we introduce an innovative, energy-efficient three-tier architecture for WBANs that employs ML and edge computing to overcome the limitations inherent in existing energy-efficient solutions. Finally, we summarize the lessons learned and highlight future research directions that will enable the development of energy-efficient solutions for WBANs.
Adopting new tools and technologies on a development process can be a risky endeavor. Will the project accept the new technology? What will be the impact? Far too often the project is forced to adopt the new technolog...
详细信息
Traditionally, digital hardware designs are written in the Verilog hardware description language (HDL) and debugged manually by engineers. This can be time-consuming and error-prone for complex designs. Large Language...
详细信息
Traditionally, digital hardware designs are written in the Verilog hardware description language (HDL) and debugged manually by engineers. This can be time-consuming and error-prone for complex designs. Large Language Models (LLMs) are emerging as a potential tool to help generate fully functioning HDL code, but most works have focused on generation in the single-shot capacity: i.e., run and evaluate, a process that does not leverage debugging and, as such, does not adequately reflect a realistic development process. In this work, we evaluate the ability of LLMs to leverage feedback from electronic design automation (EDA) tools to fix mistakes in their own generated Verilog. To accomplish this, we present an open-source, highly customizable framework, AutoChip, which combines conversational LLMs with the output from Verilog compilers and simulations to iteratively generate and repair Verilog. To determine the success of these LLMs we leverage the VerilogEval benchmark set. We evaluate four state-of-the-art conversational LLMs, focusing on readily accessible commercial models. EDA tool feedback proved to be consistently more effective than zero-shot prompting only with GPT-4o, the most computationally complex model we evaluated. In the best case, we observed a 5.8% increase in the number of successful designs with a 34.2% decrease in cost over the best zero-shot results. Mixing smaller models with this larger model at the end of the feedback iterations resulted in equally as much success as with GPT-4o using feedback, but incurred 41.9% lower cost (corresponding to an overall decrease in cost over zero-shot by 89.6%).
According to the site layout of cigarette industry and the requirement of AGV soft time window for waste tobacco recycling, the change of demand for waste tobacco recycling based on soft time window ant colony algorit...
According to the site layout of cigarette industry and the requirement of AGV soft time window for waste tobacco recycling, the change of demand for waste tobacco recycling based on soft time window ant colony algorithm is proposed. The method is based on the waste smoke recovery centered on the unit station, Considering the influence of the actual production rhythm of complex Workshop on the recovery demand time, the membership function of the time when AGV arrives at the waste smoke recovery station is used to characterize the satisfaction of the unit station to the timeliness of the waste smoke recovery business. Therefore, with the average satisfaction of AGV arrival time as the constraint condition and the minimum cost of recycling time as the objective, an optimization model of smoke recycling path with fuzzy soft time window is established, and the model is solved by ant colony algorithm. The validity and robustness of the path optimization model are verified by an example.
The paper deals with the issues of data collection in the dynamic Internet of Things network. An approach proposed is based on the models and methods of social networks analysis along with clustering methods commonly ...
The paper deals with the issues of data collection in the dynamic Internet of Things network. An approach proposed is based on the models and methods of social networks analysis along with clustering methods commonly used in this case. The developed hybrid model tracks contacts between nodes of the network thus creating 'social relationships' for each node and estimates the number and the frequency of 'social contacts' characterizing the degree of 'friendships'. After fixing the contacts between nodes the model takes into consideration only the nodes connected by 'friendship' relation. Data collection based on 'social structure' provides higher security level and shows the enhancement as regards energy saving and delays of data transfer.
In this paper, we briefly summarize the first competition on resource-limited infrared small target detection (namely, LimitIRSTD). This competition has two tracks, including weakly-supervised infrared small target de...
With the rapid development of the information technologies in the financial field, extracting meaningful information from a massive amount of data is hugely significant for efficient business decision making. The reco...
With the rapid development of the information technologies in the financial field, extracting meaningful information from a massive amount of data is hugely significant for efficient business decision making. The recommendation system is an intelligent system that applies historical knowledge of users to infer their preferences and make a personalized recommendation. However, it suffers from the problem of time effect of user's behaviour, which means a user's interests may change over time. To overcome this problem, we propose a time effect based collaborative filtering approach to adaptively statistics the change of user preferences. Firstly, Item-based collaborative filtering is used to calculate rating similarity between items. Since an Item-based collaborative filtering algorithm doesn't consider the time effect; next, the time decay function is proposed to statistics the change of user interests. Experimental results show that the proposed scheme retained higher accuracy compare to traditional collaborative filtering method.
暂无评论