著者

Yota Tsukamoto Honami Tsushima Tohru Ikeguchi

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.14, no.4, pp.677-690, 2023 (Released:2023-10-01)

参考文献数

29

---

The Izhikevich neuron model can reproduce various types of neurons, including chaotic neurons, by utilizing appropriate parameter sets. This study analyzes the responses of a periodically forced Izhikevich neuron with chaotic parameters using three measures—the diversity index, the coefficient of variation, and the local variation—to quantify interspike intervals (ISIs). The evaluation of ISIs combining these three measures clarifies the differences in neuronal activities, but evaluation using an individual measure cannot. In addition, we analyzed the change in the stability of the equilibrium points caused by a periodic input on a phase plane. The results indicate that in electrophysiologically feasible parameter sets, the stability of equilibrium points plays a crucial role in determining the critical amplitude around which irregular activities transition to regular ones. Thus, the relationship between neural behavior and the period and amplitude of the input current is contingent upon the existence and stability of equilibrium points.

著者

Zhonghao Zhang Zong Li Bin Cao Xinyu Huang Liming Wang

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Electronics Express (ISSN:13492543)

巻号頁・発行日

vol.20, no.19, pp.20230211, 2023-10-10 (Released:2023-10-10)

参考文献数

31

---

Composite insulation equipment is widely used in power systems, and the detection of internal material interface defects is an important and difficult task in power grids. Terahertz wave can help detect internal faults in equipment in a timely manner, but the analysis of large amounts of data has brought about significant labor costs. In order to improve the efficiency of Terahertz wave detection, this paper proposes a Terahertz wave defect detection method based on spectrum feature fusion and spiking neural network. By performing multiple wavelet basis transformations on terahertz wave timing waveforms, and then performing feature fusion extraction on the data through a self encoder incorporating spatial and channel attention mechanisms, the differences between different defect detection waveforms are expanded. Then, spiking neural networks are used to classify the feature fused spectra to obtain defect detection results. Compared with other typical models, this model performs better in terms of accuracy and training costs.

著者

Atsushi KOSHIBA Takahiro HIROFUCHI Ryousei TAKANO Mitaro NAMIKI

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Transactions on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E102.D, no.12, pp.2377-2388, 2019-12-01 (Released:2019-12-01)

参考文献数

25

被引用文献数

2 4

---

Non-volatile memory (NVM) is a promising technology for low-energy and high-capacity main memory of computers. The characteristics of NVM devices, however, tend to be fundamentally different from those of DRAM (i.e., the memory device currently used for main memory), because of differences in principles of memory cells. Typically, the write latency of an NVM device such as PCM and ReRAM is much higher than its read latency. The asymmetry in read/write latencies likely affects the performance of applications significantly. For analyzing behavior of applications running on NVM-based main memory, most researchers use software-based emulation tools due to the limited number of commercial NVM products. However, these existing emulation tools are too slow to emulate a large-scale, realistic workload or too simplistic to investigate the details of application behavior on NVM with asymmetric read/write latencies. This paper therefore proposes a new NVM emulation mechanism that is not only light-weight but also aware of a read/write latency gap in NVM-based main memory. We implemented the prototype of the proposed mechanism for the Intel CPU processors of the Haswell architecture. We also evaluated its accuracy and performed case studies for practical benchmarks. The results showed that our prototype accurately emulated write-latencies of NVM-based main memory: it emulated the NVM write latencies in a range from 200 ns to 1000 ns with negligible errors from 0.2% to 1.1%. We confirmed that the use of our emulator enabled us to successfully estimate performance of practical workloads for NVM-based main memory, while an existing light-weight emulation model misestimated.

著者

真次 彰平 塩川 浩昭

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

電子情報通信学会論文誌 D (ISSN:18804535)

巻号頁・発行日

vol.J106-D, no.10, pp.459-469, 2023-10-01

---

グラフ要約はグラフ中の幾つかのノード,及びエッジを一つにまとめることにより,グラフサイズを削減する技術である.グラフ要約では(1) 情報の欠損がない,(2) 圧縮率が高い,(3) 実装が容易であるという三つの要件が求められるが,従来の手法ではそれらを同時に満たすことができない.そこで本論文では,情報の欠損がなく高圧縮率なグラフ要約手法を提案する.提案手法は連結した3ノードに着目し要約を行い,それらの接続関係をビット列に変換することで.元のグラフに存在する全ての情報を高い圧縮率で要約する.本論文では実データを用いた実験を行い,従来手法と比較して高圧縮率な要約が行えることを確認した.

著者

Xiaoman LIU Yujie GAO Yuan HE Xiaohan YUE Haiyan JIANG Xibo WANG

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Electronics (ISSN:09168516)

巻号頁・発行日

vol.E106-C, no.10, pp.570-579, 2023-10-01

---

The complexity and scale of Networks-on-Chip (NoCs) are growing as more processing elements and memory devices are implemented on chips. However, under strict power budgets, it is also critical to lower the power consumption of NoCs for the sake of energy efficiency. In this paper, we therefore present three novel input unit designs for on-chip routers attempting to shrink their power consumption while still conserving the network performance. The key idea behind our designs is to organize buffers in the input units with characteristics of the network traffic in mind; as in our observations, only a small portion of the network traffic are long packets (composed of multiple flits), which means, it is fair to implement hybrid, asymmetric and reconfigurable buffers so that they are mainly targeting at short packets (only having a single flit), hence the smaller power consumption and area overhead. Evaluations show that our hybrid, asymmetric and reconfigurable input unit designs can achieve an average reduction of energy consumption per flit by 45%, 52.3% and 56.2% under 93.6% (for hybrid designs) and 66.3% (for asymmetric and reconfigurable designs) of the original router area, respectively. Meanwhile, we only observe minor degradation in network latency (ranging from 18.4% to 1.5%, on average) with our proposals.

著者

王 晨旭 川口 秀樹 渡邊 浩太

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

電子情報通信学会論文誌 C (ISSN:13452827)

巻号頁・発行日

vol.J106-C, no.10, pp.366-372, 2023-10-01

---

リコンフィギュラブルコンピューティング技術に基づくハイパフォーマンスコンピューティングの試みとして,データフローアーキテクチャ専用計算機の方法を提案し,電磁界シミュレーション,とりわけ,マイクロ波シミュレーションへの応用を検討してきた.このとりくみの次の段階として,より広範囲の電磁界をとり扱うためには,大型疎行列計算のハードウェア化が重要な課題となる.本研究では,典型的な疎行列計算スキームBiCG-Stabのハードウェア回路化に際して必須のタスクとなる倍精度浮動小数点相当の精度を有する多倍長整数型除算回路の検討を行ったので報告する.

著者

Peijian Zhang Kunfeng Zhu Wensuo Chen

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Transactions on Electronics (ISSN:09168524)

巻号頁・発行日

pp.2022ECP5059, (Released:2023-07-04)

---

In this paper, a novel trench MOS barrier Schottky contact super barrier rectifier (TMB-SSBR) is proposed by combining the advantages of vertical SSBR and conventional TMBS. The operation mechanism and simulation verification are presented. TMB-SSBR consists of MOS trenches with a vertical SSBR grid which replaces the Schottky diode in the mesa of a TMBS. Due to the presence of top p-n junction in the proposed TMB-SSBR, the image force barrier lowering effect is eliminated, the pinching off electric field effect by MOS trenches is weakened, so that the mesa surface electric field is much larger than that in conventional TMBS. Therefore, the mesa width is enlarged and the n-drift concentration is slightly increased, which results in a low specific on-resistance and a good tradeoff between reverse leakage currents and forward voltages. Compared to a conventional TMBS, simulation results show that, with the same breakdown voltage of 124 V and the same reverse leakage current at room temperature, TMB-SSBR increases the figure of merit (FOM, equates to VB2/Ron,sp) by 25.5%, and decreases the reverse leakage by 33.3% at the temperature of 423 K. Just like the development from SBD to TMBS, from TMBS to TMB-SSBR also brings obvious improvement of performance.

著者

Meng-Yuan HE Ling-Yun JIANG

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Communications (ISSN:09168516)

巻号頁・発行日

vol.E106-B, no.10, pp.881-890, 2023-10-01

---

In the current heterogeneous wireless communication system, the sharp rise in energy consumption and the emergence of new service types pose great challenges to nowadays radio access network selection algorithms which do not take care of these new trends. So the proposed energy efficiency based multi-service heterogeneous access network selection algorithm-ESRS (Energy Saving Radio access network Selection) is intended to reduce the energy consumption caused by the traffic in the mobile network system composed of Base Stations (BSs) and Access Points (APs). This algorithm models the access network selection problem as a Multiple-Attribute Decision-Making (MADM) problem. To solve this problem, lots of methods are combined, including analytic Hierarchy Process (AHP), weighted grey relational analysis (GRA), entropy theory, simple additive weight (SAW), and utility function theory. There are two main steps in this algorithm. At first, the proposed algorithm gets the result of the user QoS of each network by dealing with the related QoS parameters, in which entropy theory and AHP are used to determine the QoS comprehensive weight, and the SAW is used to get each network's QoS. In addition to user QoS, parameters including user throughput, energy consumption utility and cost utility are also calculated in this step. In the second step, the fuzzy theory is used to define the weight of decision attributes, and weighted grey relational analysis (GRA) is used to calculate the network score, which determines the final choice. Because the fuzzy weight has a preference for the low energy consumption, the energy consumption of the traffic will be saved by choosing the network with the least energy consumption as much as possible. The simulation parts compared the performance of ESRS, ABE and MSNS algorithms. The numerical results show that ESRS algorithm can select the appropriate network based on the service demands and network parameters. Besides, it can effectively reduce the system energy consumption and overall cost while still maintaining a high overall QoS value and a high system throughput, when compared with the other two algorithms.

著者

Hong LI Wenjun CAO Chen WANG Xinrui ZHU Guisheng LIAO Zhangqing HE

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences (ISSN:09168508)

巻号頁・発行日

vol.E106-A, no.10, pp.1311-1321, 2023-10-01

---

The configurable Ring oscillator Physical unclonable function (CRO PUF) is the newly proposed strong PUF based on classic RO PUF, which can generate exponential Challenge-Response Pairs (CRPs) and has good uniqueness and reliability. However, existing proposals have low hardware utilization and vulnerability to modeling attacks. In this paper, we propose a Novel Configurable Dual State (CDS) PUF with lower overhead and higher resistance to modeling attacks. This structure can be flexibly transformed into RO PUF and TERO PUF in the same topology according to the parity of the Hamming Weight (HW) of the challenge, which can achieve 100% utilization of the inverters and improve the efficiency of hardware utilization. A feedback obfuscation mechanism (FOM) is also proposed, which uses the stable count value of the ring oscillator in the PUF as the updated mask to confuse and hide the original challenge, significantly improving the effect of resisting modeling attacks. The proposed FOM-CDS PUF is analyzed by building a mathematical model and finally implemented on Xilinx Artix-7 FPGA, the test results show that the FOM-CDS PUF can effectively resist several popular modeling attack methods and the prediction accuracy is below 60%. Meanwhile it shows that the FOM-CDS PUF has good performance with uniformity, Bit Error Rate at different temperatures, Bit Error Rate at different voltages and uniqueness of 53.68%, 7.91%, 5.64% and 50.33% respectively.

著者

Wenqi Ge Xiaotong Wang Yi Xie

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Electronics Express (ISSN:13492543)

巻号頁・発行日

vol.20, no.18, pp.20230321, 2023-09-25 (Released:2023-09-25)

参考文献数

31

被引用文献数

1

---

Electromagnetic interference has always been an important assessment indicator for the inspection of power intelligent Unmanned Aerial Vehicles (UAVs). Therefore, it is necessary to carry out a structure optimization study to improve the UAV’s anti-electromagnetic interference capability. This paper analyses the flight stability of the UAV at different heights under the strong magnetic environment of the dry-type transformer, and carries out structural optimisation of the rotary-wing UAV design against the standard non-magnetic environment. After simulation and comparison, the UAV’s anti-electromagnetic interference capability is significantly enhanced after structural optimisation. The research results of this paper can further expand the application scope of inspection UAVs and provide a strong technical guarantee for promoting the development of intelligent and automated power inspection.

著者

Mustafa Sami KACAR Semih YUMUSAK Halife KODAZ

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E106-D, no.9, pp.1461-1471, 2023-09-01

被引用文献数

1

---

The use of reports in action has grown significantly in recent decades as data has become digitized. However, traditional statistical methods no longer work due to the uncontrollable expansion and complexity of raw data. Therefore, it is crucial to clean and analyze financial data using modern machine learning methods. In this study, the quarterly reports (i.e. 10Q filings) of publicly traded companies in the United States were analyzed by utilizing data mining methods. The study used 8905 quarterly reports of companies from 2019 to 2022. The proposed approach consists of two phases with a combination of three different machine learning methods. The first two methods were used to generate a dataset from the 10Q filings with extracting new features, and the last method was used for the classification problem. Doc2Vec method in Gensim framework was used to generate vectors from textual tags in 10Q filings. The generated vectors were clustered using the K-means algorithm to combine the tags according to their semantics. By this way, 94000 tags representing different financial items were reduced to 20000 clusters consisting of these tags, making the analysis more efficient and manageable. The dataset was created with the values corresponding to the tags in the clusters. In addition, PriceRank metric was added to the dataset as a class label indicating the price strength of the companies for the next financial quarter. Thus, it is aimed to determine the effect of a company's quarterly reports on the market price of the company for the next period. Finally, a Convolutional Neural Network model was utilized for the classification problem. To evaluate the results, all stages of the proposed hybrid method were compared with other machine learning techniques. This novel approach could assist investors in examining companies collectively and inferring new, significant insights. The proposed method was compared with different approaches for creating datasets by extracting new features and classification tasks, then eventually tested with different metrics. The proposed approach performed comparatively better than the other machine learning methods to predict future price strength based on past reports with an accuracy of 84% on the created 10Q filings dataset.

著者

Koichi MAEZAWA Umer FAROOQ Masayuki MORI

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Electronics (ISSN:09168516)

巻号頁・発行日

vol.E106-C, no.9, pp.486-490, 2023-09-01

---

A novel displacement sensor was proposed based on a frequency delta-sigma modulator (FDSM) employing a microwave oscillator. To demonstrate basic operation, we fabricated a stylus surface profiler using a cylindrical cavity resonator, where one end of the cavity is replaced by a thin metal diaphragm with a stylus probe tip. Good surface profile was successfully obtained with this device. A 10 nm depth trench was clearly observed together with a 10 µm trench in a single scan without gain control. This result clearly demonstrates an extremely wide dynamic range of the FDSM displacement sensors.

著者

Ryo TAKAHASHI Hidenori MATSUO Sijie XIA Qiang CHEN Fumiyuki ADACHI

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Communications (ISSN:09168516)

巻号頁・発行日

vol.E106-B, no.9, pp.748-757, 2023-09-01

---

Cell-free massive MIMO (CF-mMIMO), which cooperatively utilizes a large number of antennas deployed over a communication area, has been attracting great attention as an important technology for realizing 5G-advanced and 6G systems. Recently, to ensure system scalability and mitigate inter-user interference in CF-mMIMO, a user-centric (UC) approach was investigated. In this UC approach, user-centric antenna-sets are formed by selecting appropriate antennas for each user, and postcoding is applied to reduce the strong interference from users whose antenna-sets overlap. However, in very high user density environments, since the number of interfering users increases due to increased overlapping of antenna-sets, the achievable link capacity may degrade. In this paper, we propose a user-cluster-centric (UCC) approach, which groups neighborhood users into a user-cluster and associates the predetermined number of antennas to this user-cluster for spatial multiplexing. We derive the uplink postcoding weights and explain the effectiveness of the proposed UCC approach in terms of the computational complexity of the weight computation. We also compare the uplink user capacities achievable with UC and UCC approaches by computer simulation and clarify situations where the UCC approach is effective. Furthermore, we discuss the impact of the number of interfering users considered in the zero-forcing and minimum mean square error postcoding weight computation on the user capacity.

著者

Hiroshi FUJIWARA Masaya KAWAGUCHI Daiki TAKIZAWA Hiroaki YAMAMOTO

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences (ISSN:09168508)

巻号頁・発行日

vol.E106-A, no.9, pp.1100-1110, 2023-09-01

---

The bin packing problem is a problem of finding an assignment of a sequence of items to a minimum number of bins, each of capacity one. An online algorithm for the bin packing problem is an algorithm that irrevocably assigns each item one by one from the head of the sequence. Gutin, Jensen, and Yeo (2006) considered a version in which all items are only of two different sizes and the online algorithm knows the two possible sizes in advance, and gave an optimal online algorithm for the case when the larger size exceeds 1/2. In this paper we provide an optimal online algorithm for some of the cases when the larger size is at most 1/2, on the basis of a framework that facilitates the design and analysis of algorithms.

著者

Issei KANNO Kosuke YAMAZAKI Yoji KISHI Satoshi KONISHI

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Transactions on Communications (ISSN:09168516)

巻号頁・発行日

pp.2021MEI0001, (Released:2022-04-28)

被引用文献数

8

---

5G service has been launched in various countries, and research for the beyond 5G is already underway actively around the world. In beyond 5G, it is expected to expand the various capabilities of communication technologies to cover further wide use cases from 5G. As a candidate elemental technology, cell free massive MIMO has been widely researched and shown its potential to enhance the capabilities from various aspects. However, for deploying this technology in reality, there are still many technical issues such as a cost of distributing antenna and installing fronthaul, and also the scalability aspects. This paper surveys research trends of cell free massive MIMO, especially focusing on the deployment challenges with an introduction to our specific related research activities including some numerical examples.

著者

安川 洵 槇原 靖 八児 正次 村形 駿樹 亀田 佳一 細井 利憲 久保 雅洋 八木 康史

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

電子情報通信学会論文誌 D (ISSN:18804535)

巻号頁・発行日

vol.J106-D, no.9, pp.445-456, 2023-09-01

---

近年,我が国では脳卒中患者が増加しており,その後遺症の一つに片麻痺症状による歩行障害が挙げられる.日常生活に支障のない歩行レベルであるかの判断指標の一つにバランス能力指標Berg Balance Scale (BBS)がある.ただし約20分の評価を専門家が行い,評価者の主観が影響する点が課題であった.本研究では,属人性を排した効率的なバランス能力評価実現のために,対象者の歩行計測のみで簡便かつ自動的にBBSを推定するシステムを開発した.まず1台のRGBDセンサを用いて対象者の歩行を撮影し,見守り者がいる場合は,対象者と介助者の領域を分離する.次に歩幅,つま先向き,立脚時間,歩行速度など計23種類の特徴量を抽出する.最後にLasso回帰モデルを用いてBBSを推定する.実験では94件の脳卒中患者の歩行動画と専門家が付与したBBSのデータセットを用いた.BBSの推定は,平均絶対誤差4.97 ± 4.31点で,従来手法より誤差が小さく,臨床的に許容可能な誤差範囲内であることを確認した.処理時間は見守り無しパタン(シーケンス長515 ± 504 frame)で47 ± 52 s,見守り有りパタン(764 ± 465 frame)で62 ± 32 sであった.従来の評価時間を短縮し,提案手法の有用性を示した.

著者

Koji NAKAO Katsunari YOSHIOKA Takayuki SASAKI Rui TANABE Xuping HUANG Takeshi TAKAHASHI Akira FUJITA Jun'ichi TAKEUCHI Noboru MURATA Junji SHIKATA Kazuki IWAMOTO Kazuki TAKADA Yuki ISHIDA Masaru TAKEUCHI Naoto YANAI

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Transactions on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E106.D, no.9, pp.1302-1315, 2023-09-01 (Released:2023-09-01)

参考文献数

40

---

In this paper, we developed the latest IoT honeypots to capture IoT malware currently on the loose, analyzed IoT malware with new features such as persistent infection, developed malware removal methods to be provided to IoT device users. Furthermore, as attack behaviors using IoT devices become more diverse and sophisticated every year, we conducted research related to various factors involved in understanding the overall picture of attack behaviors from the perspective of incident responders. As the final stage of countermeasures, we also conducted research and development of IoT malware disabling technology to stop only IoT malware activities in IoT devices and IoT system disabling technology to remotely control (including stopping) IoT devices themselves.

著者

Yuya USHIODA Mineo KANEKO

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences (ISSN:09168508)

巻号頁・発行日

pp.2023VLP0020, (Released:2023-09-04)

---

Adiabatic logic circuits are regarded as one of the most attractive solutions for low-power circuit design. This study is dedicated to optimizing the design of the Two-Level Adiabatic Logic (2LAL) circuit, which boasts a relatively simple structure and superior low-power performance among many asymptotically adiabatic or quasi-adiabatic logic families, but suffers from a large number of timing buffers for “decompute”. Our focus is on the “early decompute” technique for fully pipelined 2LAL, and we propose two ILP approaches for minimizing hardware cost through optimization of early decompute. In the first approach, the problem is formulated as a kind of scheduling problem, while it is reformulated as node selection problem (stable set problem). The performance of the proposed methods are evaluated using several benchmark circuits from ISCAS-85, and the maximum 70 % hardware reduction is observed compared with an existing method.

著者

小瀬良 開光 今井 哲朗 北尾 光司郎 須山 聡

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

電子情報通信学会論文誌 B (ISSN:13444697)

巻号頁・発行日

vol.J106-B, no.9, pp.618-627, 2023-09-01

---

現在,伝搬損失推定のためのDCNN(Deep Convolutional Neural Network)モデルが検討されている.本モデルは都市構造から伝搬損失に関連する特徴量を自動抽出することで伝搬損失を推定することから,高精度かつ汎用性の高い推定モデルとして期待されている.しかし,その性能は十分に明らかになっていない.本論文では,BS距離マップ(基地局からの距離を要素とするマップ),MS距離マップ(移動局からの距離を要素とするマップ),建物高マップ(建物高を要素とするマップ)の入力に対して,BS距離マップと建物高マップがそれぞれ伝搬損失の距離特性と場所依存特性に大きく寄与していることを明らかにする.また,Grad-CAM(Gradient-weighted Class Activation Mapping)による解析により,DCNNモデルが移動局周辺の“低層建物及び建物の存在しない空間の分布”を伝搬損失推定の判断根拠にしていることを明らかにする.

著者

Ruochen LIAO Kousuke MORIWAKI Yasushi MAKIHARA Daigo MURAMATSU Noriko TAKEMURA Yasushi YAGI

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Transactions on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E104.D, no.10, pp.1678-1690, 2021-10-01 (Released:2021-10-01)

参考文献数

86

---

In this study, we propose a method to estimate body composition-related health indicators (e.g., ratio of body fat, body water, and muscle, etc.) using video-based gait analysis. This method is more efficient than individual measurement using a conventional body composition meter. Specifically, we designed a deep-learning framework with a convolutional neural network (CNN), where the input is a gait energy image (GEI) and the output consists of the health indicators. Although a vast amount of training data is typically required to train network parameters, it is unfeasible to collect sufficient ground-truth data, i.e., pairs consisting of the gait video and the health indicators measured using a body composition meter for each subject. We therefore use a two-step approach to exploit an auxiliary gait dataset that contains a large number of subjects but lacks the ground-truth health indicators. At the first step, we pre-train a backbone network using the auxiliary dataset to output gait primitives such as arm swing, stride, the degree of stoop, and the body width — considered to be relevant to the health indicators. At the second step, we add some layers to the backbone network and fine-tune the entire network to output the health indicators even with a limited number of ground-truth data points of the health indicators. Experimental results show that the proposed method outperforms the other methods when training from scratch as well as when using an auto-encoder-based pre-training and fine-tuning approach; it achieves relatively high estimation accuracy for the body composition-related health indicators except for body fat-relevant ones.