Rethinking Embedded Blocks for Machine Learning Applications

The underlying goal of FPGA architecture research is to devise flexible substrates that implement a wide variety of circuits efficiently. Contemporary FPGA architectures have been optimized to support networking, signal processing, and image processing applications through high-precision digital signal processing (DSP) blocks. The recent emergence of machine learning has created a new set of demands characterized by: (1) higher computational density and (2) low precision arithmetic requirements. With the goal of exploring this new design space in a methodical manner, we first propose a problem formulation involving computing nested loops over multiply-accumulate (MAC) operations, which covers many basic linear algebra primitives and standard deep neural network (DNN) kernels. A quantitative methodology for deriving efficient coarse-grained compute block architectures from benchmarks is then proposed together with a family of new embedded blocks, called MLBlocks. An MLBlock instance includes several multiply-accumulate units connected via a flexible routing, where each configuration performs a few parallel dot-products in a systolic array fashion. This architecture is parameterized with support for different data movements, reuse, and precisions, utilizing a columnar arrangement that is compatible with existing FPGA architectures. On synthetic benchmarks, we demonstrate that for 8-bit arithmetic, MLBlocks offer 6× improved performance over the commercial Xilinx DSP48E2 architecture with smaller area and delay; and for time-multiplexed 16-bit arithmetic, achieves 2× higher performance per area with the same area and frequency. All source codes and data, along with documents to reproduce all the results in this article, are available at http://github.com/raminrasoulinezhad/MLBlocks .

Theory-Based Problem Formulation and Ideation in mHealth Analysis and Recommendations

This article reports on an investigation into how to improve problem formulation and ideation in Design Science Research (DSR) within the mHealth domain. A Systematic Literature Review of problem formulation in published mHealth DSR papers found that problem formulation is often only weakly performed, with shortcomings in stakeholder analysis, patient-centricity, clinical input, use of kernel theory, and problem analysis. The study proposes using Coloured Cognitive Mapping for DSR (CCM4DSR) as a tool to improve problem formulation in mHealth DSR. A case study using CCM4DSR found that using CCM4DSR provided a more comprehensive problem formulation and analysis, highlighting aspects that, until CCM4DSR was used, weren’t apparent to the research team and which served as a better basis for mHealth feature ideation.

Deep Learning-based Face Super-resolution: A Survey

Face super-resolution (FSR), also known as face hallucination, which is aimed at enhancing the resolution of low-resolution (LR) face images to generate high-resolution face images, is a domain-specific image super-resolution problem. Recently, FSR has received considerable attention and witnessed dazzling advances with the development of deep learning techniques. To date, few summaries of the studies on the deep learning-based FSR are available. In this survey, we present a comprehensive review of deep learning-based FSR methods in a systematic manner. First, we summarize the problem formulation of FSR and introduce popular assessment metrics and loss functions. Second, we elaborate on the facial characteristics and popular datasets used in FSR. Third, we roughly categorize existing methods according to the utilization of facial characteristics. In each category, we start with a general description of design principles, present an overview of representative approaches, and then discuss the pros and cons among them. Fourth, we evaluate the performance of some state-of-the-art methods. Fifth, joint FSR and other tasks, and FSR-related applications are roughly introduced. Finally, we envision the prospects of further technological advancement in this field.

Evolutionary Machine Learning: A Survey

Evolutionary Computation (EC) approaches are inspired by nature and solve optimization problems in a stochastic manner. They can offer a reliable and effective approach to address complex problems in real-world applications. EC algorithms have recently been used to improve the performance of Machine Learning (ML) models and the quality of their results. Evolutionary approaches can be used in all three parts of ML: preprocessing (e.g., feature selection and resampling), learning (e.g., parameter setting, membership functions, and neural network topology), and postprocessing (e.g., rule optimization, decision tree/support vectors pruning, and ensemble learning). This article investigates the role of EC algorithms in solving different ML challenges. We do not provide a comprehensive review of evolutionary ML approaches here; instead, we discuss how EC algorithms can contribute to ML by addressing conventional challenges of the artificial intelligence and ML communities. We look at the contributions of EC to ML in nine sub-fields: feature selection, resampling, classifiers, neural networks, reinforcement learning, clustering, association rule mining, and ensemble methods. For each category, we discuss evolutionary machine learning in terms of three aspects: problem formulation, search mechanisms, and fitness value computation. We also consider open issues and challenges that should be addressed in future work.

Systems dynamic modeling on sustainable apples agriculture

History shows the long process of apple plants originating from subtropical regions adapting to Indonesia's tropical climate until its popularity is increasingly marginalized and replaced with other commodities, as evidenced by the decreasing land area, especially in Batu City. Indonesia. In developing and analyzing solutions based on the principles of sustainable development, an integrated and holistic approach is required. To understand problems and find solutions, we can use Systems dynamics. The purpose of this study is to obtain a policy scenario that encourages sustainable apple farming. Data is collected from the local government and BPS City or Province so that the selected variables follow the specific location. The system approach is used to identify needs, problem formulation, preparation of input-output diagrams, cause-effect diagrams and stock-flow diagrams. A series of scenarios is created and tested through simulation to understand the system's dynamic behavior better and obtain the desired output. The best scenario was chosen, namely by replanting 10% of old plant each year, using integrated agriculture with 3 female and 1 male brooders, reduction of land change with 50% success, Local economic development by integrating tourist ticket and hotels with 0,75 kg apple fruits also increasing health support for students

Optimal Control for Cleaner Hybrid Vehicles: A Backward Approach

This work presents an application of the optimal control theory to find trade offs between fuel consumption and pollutant emissions (CO, HC, NOx) of sustaining hybrid vehicles. Both cold start and normal operations are considered. The problem formulation includes two state variables: battery state of energy and catalyst temperature; and three control variables: torque repartition between engine and motor, spark advance, and equivalence ratio. Optimal results were obtained by delaying the first engine crank after the urban part of the mission. The results show that a quick catalyst light off is performed. Once the catalyst is primed, special control parameters values are adopted to operate the engine.

GENDER INEQUALITY BEFORE THE LAWS AS SEEN IN ON THE BASIS OF SEX FILM BY MIMI LEDER

In this study, researcher analyzes an inequality film written by Daniel Stiepleman and directed by Mimi Leder. This Film tells the strory about inequality dan women struggle. Therefore the researcher entitled this research with “Gender Inequality before the Laws as seen in On the Basis Of Sex film by Mimi Leder”, This study aimed to discuss; 1) injustice between a man and a woman before the law, 2) how women try to resist the laws. Design of this research was qualitative descriptive research. The researcher applied the theory of human rights and feminist legal theory by Universal Decralation of human right and Judith and remer to answer the research question problem formulation. Sociological approach also used in this research. In collecting the data, the researcher used technique of documentation. The technique used in analyzing data in this study was a descriptive technique. The results of this research are; 1) there are four gender inequalities depicted in the film on the basis of sex; (a) inequality in economic right (b) inequality in education right (c) inequality in social right (d) inequality in civil right 2) women's efforts to fight the law are three ways (a) Speak Out the Own Experiences (b) support other campaigners (c) exspressing rational opinions.

Determination of confiscation of evidence of data in cyber crime

The social order in the digital era is increasingly diverse through interaction and communication using high-tech devices. However, this often causes violations and disturbances to public order and harms others (cyber crime). Based on the background above, there is problem formulation in this research, namely what is the legal basis for determining data confiscation in cyber crime and what the mechanism for data confiscation in cybercrime is. The type of research used is normative, namely seeing and analyzing from the point of view of legislation and applicable norms, especially those related to the problems in this research. The result of discussion is that the legal basis for data confiscation in cyber crime is referring to Law no. 11 of 2008 concerning Information and Electronic Transactions (ITE). This law contains regulations regarding the management of information and electronic transactions at the national level, with the aim that information technology development can be carried out optimally, evenly, and spread to all levels of society in order to educate the nation's life, while the mechanism for confiscation of data in cyber crime begins with electronic data in the form of writing, images and sound or all three are intangible and cannot be seen/heard.

PERLINDUNGAN HUKUM BAGI PEKERJA PENYANDANG DISABILITAS DITINJAU DARI UNDANG-UNDANG NOMOR 13 TAHUN 2013

ABSTRACTThis study aims to determine the form of legal protection against disabled workers with disabilities. This study uses normative research methods with data collection techniques used to solve the problem formulation is by library data obtained based on legislation and literature - literature or official books. Data analysis used is qualitative approach to primary data and secondary data. The result of the research can be concluded that the form of legal protection for workers with disabilities who are harmed by employers by viewing or reviewing Law No.13 Year 2103, in the law has regulated the legal protection for workers with disabilities. Therefore, the need for legal protection is preventive and repressive, by increasing the supervision of the relevant agencies so that the disability workers are not harmed by the employer. And if there has been a dispute then it can be a repressive legal protection, which prioritizes the form of bipartite negotiations, in deliberation and tripartite, mediated by the facilitator. If in such endeavors remain unreachable, either party may make a lawsuit by enclosing minutes of negotiations and being registered with the industrial relations court at the local district court. ABSTRAKPenelitian ini bertujuan untuk mengetahui bentuk perlindungan hukum terhadap pekerja penyandang disabilitas yang dirugikan. Penelitian ini menggunakan metode penelitian normatif dengan teknik pengumpulan data yang digunakan untuk memecahkan rumusan masalah yaitu dengan data kepustakaan yang diperoleh berdasarkan dari perundang – undangan dan literaturr - literatur atau buku - buku resmi. Analisis data yang dipergunakan adalah pendekatan kualitatif terhadap data primer maupun data sekunder. Hasil penelitian dapat disimpulkan bahwa bentuk perlindungan hukum bagi pekerja penyandang disabilitas yang dirugikan oleh pemberi kerja / pengusaha dengan melihat atau meninjau Undang-Undang No.13 Tahun 2103, di undang-undang tersebut sudah mengatur tentang perlindungan hukum bagi pekerja penyandang disabilitas tersebut. Untuk itu perlunya perlindungan hukum secara preventif dan represif, dengan lebih meningkatkan pengawasan dari dinas terkait agar pekerja disabilitas ini tidak dirugikan oleh pemberi kerja. Dan jika telah terjadi perselisihan maka dapat dilakukan perlindungan hukum secara represif, yang lebih mengutamakan ke bentuk perundingan secara bipartit, secara musyawarah dan tripartit, dengan ditengahi oleh fasiliator. Jika dalam upaya tersebut tetap tidak mencapai kesepakatan, maka salah satu pihak dapat membuat gugatan dengan melampirkan risalah hasil perundingan dan didaftarkan ke pengadilan hubungan industrial di pengadilan negeri setempat.